Search Advanced

Mathematical Biosciences and Engineering

2023, Volume 20, Issue 2: 1820-1840. doi: 10.3934/mbe.2023083
Previous Article Next Article
Research article Special Issues

PrivacyMask: Real-world privacy protection in face ID systems

  • 1.
    Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China
  • 2.
    Network and Information Technology Center, Beijing University of Technology, Beijing 100124, China
  • 3.
    Medical Engineering Division, Beijing Friendship Hospital, Beijing 100050, China

  • Academic Editor: Simon James Fong

  • Recent works have illustrated that many facial privacy protection methods are effective in specific face recognition algorithms. However, the COVID-19 pandemic has promoted the rapid innovation of face recognition algorithms for face occlusion, especially for the face wearing a mask. It is tricky to avoid being tracked by artificial intelligence only through ordinary props because many facial feature extractors can determine the ID only through a tiny local feature. Therefore, the ubiquitous high-precision camera makes privacy protection worrying. In this paper, we establish an attack method directed against liveness detection. A mask printed with a textured pattern is proposed, which can resist the face extractor optimized for face occlusion. We focus on studying the attack efficiency in adversarial patches mapping from two-dimensional to three-dimensional space. Specifically, we investigate a projection network for the mask structure. It can convert the patches to fit perfectly on the mask. Even if it is deformed, rotated and the lighting changes, it will reduce the recognition ability of the face extractor. The experimental results show that the proposed method can integrate multiple types of face recognition algorithms without significantly reducing the training performance. If we combine it with the static protection method, people can prevent face data from being collected.

    Citation: Guangmin Sun, Hao Wang, Yu Bai, Kun Zheng, Yanjun Zhang, Xiaoyong Li, Jie Liu. PrivacyMask: Real-world privacy protection in face ID systems[J]. Mathematical Biosciences and Engineering, 2023, 20(2): 1820-1840. doi: 10.3934/mbe.2023083

    Related Papers:

    [1] Yaning Li, Mengjun Wang . Well-posedness and blow-up results for a time-space fractional diffusion-wave equation. Electronic Research Archive, 2024, 32(5): 3522-3542. doi: 10.3934/era.2024162
    [2] Shaoqiang Shang, Yunan Cui . Weak approximative compactness of hyperplane and Asplund property in Musielak-Orlicz-Bochner function spaces. Electronic Research Archive, 2020, 28(1): 327-346. doi: 10.3934/era.2020019
    [3] Eteri Gordadze, Alexander Meskhi, Maria Alessandra Ragusa . On some extrapolation in generalized grand Morrey spaces with applications to PDEs. Electronic Research Archive, 2024, 32(1): 551-564. doi: 10.3934/era.2024027
    [4] Yangrong Li, Shuang Yang, Qiangheng Zhang . Odd random attractors for stochastic non-autonomous Kuramoto-Sivashinsky equations without dissipation. Electronic Research Archive, 2020, 28(4): 1529-1544. doi: 10.3934/era.2020080
    [5] Huali Wang, Ping Li . Fractional integral associated with the Schrödinger operators on variable exponent space. Electronic Research Archive, 2023, 31(11): 6833-6843. doi: 10.3934/era.2023345
    [6] Peng Gao, Pengyu Chen . Blowup and MLUH stability of time-space fractional reaction-diffusion equations. Electronic Research Archive, 2022, 30(9): 3351-3361. doi: 10.3934/era.2022170
    [7] Ling-Xiong Han, Wen-Hui Li, Feng Qi . Approximation by multivariate Baskakov–Kantorovich operators in Orlicz spaces. Electronic Research Archive, 2020, 28(2): 721-738. doi: 10.3934/era.2020037
    [8] Shuguan Ji, Yanshuo Li . Quasi-periodic solutions for the incompressible Navier-Stokes equations with nonlocal diffusion. Electronic Research Archive, 2023, 31(12): 7182-7194. doi: 10.3934/era.2023363
    [9] Kun Cheng, Yong Zeng . On regularity criteria for MHD system in anisotropic Lebesgue spaces. Electronic Research Archive, 2023, 31(8): 4669-4682. doi: 10.3934/era.2023239
    [10] Francisco Javier García-Pacheco, María de los Ángeles Moreno-Frías, Marina Murillo-Arcila . On absolutely invertibles. Electronic Research Archive, 2024, 32(12): 6578-6592. doi: 10.3934/era.2024307

  • Recent works have illustrated that many facial privacy protection methods are effective in specific face recognition algorithms. However, the COVID-19 pandemic has promoted the rapid innovation of face recognition algorithms for face occlusion, especially for the face wearing a mask. It is tricky to avoid being tracked by artificial intelligence only through ordinary props because many facial feature extractors can determine the ID only through a tiny local feature. Therefore, the ubiquitous high-precision camera makes privacy protection worrying. In this paper, we establish an attack method directed against liveness detection. A mask printed with a textured pattern is proposed, which can resist the face extractor optimized for face occlusion. We focus on studying the attack efficiency in adversarial patches mapping from two-dimensional to three-dimensional space. Specifically, we investigate a projection network for the mask structure. It can convert the patches to fit perfectly on the mask. Even if it is deformed, rotated and the lighting changes, it will reduce the recognition ability of the face extractor. The experimental results show that the proposed method can integrate multiple types of face recognition algorithms without significantly reducing the training performance. If we combine it with the static protection method, people can prevent face data from being collected.


    1.   Introduction

    Organic agriculture is considered the most sustainable alternative to industrial agriculture due to the many positive externalities associated with implementing innovative production processes [1]. This particular production farming system [2] includes, for example: restoration and protection of biodiversity [3,4,5,6]; maintenance of soil fertility [7,8,9] and higher water holding capacity [10]; reduction of greenhouse gas emissions [11,12,13]; human health protection [1,14]. The positive effects of organic farming on the environment, especially concerning the level of agroecosystem services provided by functional biodiversity [15], are amplified by a greater territorial concentration of production activities, which makes particularly significant actions aimed at the dissemination of this production model in a given area [16,17].

    On the other hand, the quality of organic food is particularly appreciated by postmodern consumers, who are demonstrating growing attention to the healthy dimension of food [18,19], whose demand has steadily increased in recent years, especially (but not only) in the most developed countries, rising from 15.1 billion in 2000 to 96.7 in 2018, with annual growth rates that show no sign of slowing down [20].

    The success of this type of agriculture also depends on the support received at a regulatory and political level. In Europe, for example, since the 1990s, organic farming has been supported by the Common Agricultural Policy [21] and, subsequently, by the Rural Development Regulations approved over the years. More recently, in the framework of the European Green Deal, the Farm to Fork strategy [22], among the various actions to achieve the goal of a resilient and sustainable food system in an environmental, social and economic sense, sets the goal of at least 25% of the agricultural area of the EU invested in organic farming to be reached by 2030. This recognition of the potential of these models [23] is important, but it requires the identification of factors that can facilitate the transition from industrial to organic farming.

    Several studies [24,25,26,27,28] highlight that the adoption of this innovation is conditioned by multiple, sometimes interconnected, elements, including the personal characteristics of the farmer and his family (the psycho-behavioural, psychosocial factors and ethical reasons), the level of skills of the entrepreneur and the supportive factors (for example, training, information acquisition or membership of association) essential for reorganising productive and commercial activities, and the farming factors and perception of the economic and political/regulatory environment.

    Our study will contribute to this strand of the literature, assessing the impact of decisive factors on organic farmers' intentions to convert to organic farming in the Marche region and, more specifically, in the province of Pesaro-Urbino.

    The Marche region represents an interesting case because it is a 'zipper region', with a central position between Northern and Southern Italy, both in geographical terms and in terms of general economic and social conditions [29]. At the same time, it is one of the Italian regions with the greatest share of agricultural surface destined for organic farming (22.2%, in 2019). The Pesaro-Urbino province, where about 25% of farms with certified organic crops and livestock of the regional total are located (https://siar.regione.marche.it/web/public/ConsultazioneAlboBio.aspx), is characterised by the presence of pioneer farms and some supply chain in organic production. This territory is therefore configured as an area particularly suitable for the creation of programs aimed at strengthening organic agriculture, such as organic districts [30] or Area Agri-environmental Agreements1 [31].

    1 These Agreements, financed by PSR of Marche region, have the purpose of aggregating and coordinating a set of public and private subjects of a particular territory, in order to face a specific environmental problem, for example water protection, through the undertaking of specific commitments especially by organic farmers.

    To support this process, we aim to investigate the factors that may encourage (or discourage) farmers' choice of the organic farming system. The study was developed through a participatory approach, organising focus groups with experts, policymakers, and local stakeholders, to collect data and discuss the results obtained.

    Through a farmers' survey and the econometric analysis of survey data, we analysed the relationships between the farmer's choice to adopt or not to adopt organic farming and a set of personal, professional and contextual factors.

    The paper is structured as follows. Section 1 presents the main conceptual arguments proposed in the literature to explain the conversion process to organic farming. Section 2 illustrates the quantitative investigation adopted, particularly the choice and definition of the statistical analysis model and data collection. The results of the estimation procedures are reported and discussed in Section 3, whereas Section 4 presents some implications of the analysis carried out for stakeholders and policy makers and, at the same time, provides some directions for further research.

    2.   Conversion to organic farming: Drivers and obstacles

    Since the early 1990s, the organic sector has steadily grown worldwide, both in surface area and the number of producers, from 11 million hectares certified as organic in 1999 to 71.5 million hectares in 2018, and reached almost 2.8 million producers [20,32]. Europe, in particular, is one of the continents with the largest share of agricultural land devoted to organic (8.5%, in 2019, with a growth rate of 38% over the last 10 years) [33]. The positive supply trend is certainly driven by the growth in demand and exports, especially to developed countries [34], where there is a strong increase in organic food consumers [35]. In fact, in recent years, the increasing attention towards the issue of environmental protection and food safety [26,36] has led to greater demands for organic foods, which are considered healthier, tastier, and obtained through more sustainable production processes than conventional foods [18,37,38].

    In addition to excellent market prospects, several other factors may influence the choice of agricultural entrepreneurs to convert to the organic method, as highlighted by a vast body of literature.

    In general, in the initial phase of the development of this sector, entrepreneurs were driven by ethical motivations rather than economic reasons [32]: organic farming, in fact, was considered a valid alternative to intensive production systems, able to ensure the preservation of the quality of natural resources and the ecosystem [26].

    Over the years, several studies have reported the importance of other variables in the choice of production method, starting from personal characteristics. These include, for example, gender, age, and educational qualifications. In some articles, the farmers most likely to convert to organic would be mainly women [39], younger age individuals [28,40,41,42] and with a medium-high education level [25,26,35,43]; in other studies, however, older and more experienced farmers have been found to have a more favourable attitude towards this production system [44,45,46,47].

    Organic certification adoption can be driven by farmers' values and lifestyle, especially in terms of environmental attention or awareness about the impact of production activities on natural resources [32,39,48,49,50,51,52] and human health [14,25,26,27].

    In addition to social motivations, farm characteristics are also relevant for switching to this production method [25], although different studies show quite differentiated results. In fact, some analyses emphasise that large companies are less likely to convert, as they usually use more intensive production methods than small to medium-sized companies [53,54,55]. Other research shows, however, that large firms are more likely to make this shift because they have greater financial resources and have the ability to overcome one of the biggest barriers to business transformation, namely access to technical assistance, contracting, and production planning services [46,56,57].

    Shifting to more sustainable models would involve radical changes [27], which are not particularly smooth for individuals, such as farmers, who are risk averse [35,51,57,58,59].

    Among the most important motivations to convert to organic farming, economic ones should certainly be considered, especially the provision of public incentives to adopt this production model [25,26,32,39,51,56]. In the European Union, for example, the development in the 1990s was supported by the definition of the regulatory framework on organic farming (starting with Regulation (EC) 2092/1991) and the introduction of incentives for low environmental impact techniques, initially with Regulation (EC) 2078/1992 and, later, with the introduction of agri-environmental payments [60].

    Subsequently, with the reform of the Common Agricultural Policy 2014–2020, new rules for agricultural entrepreneurs were defined, such as the maintenance of ecological focus areas and sustainability as fundamental requirements to meet consumer expectations and create a competitive advantage [51].

    Moreover, after switching from conventional to organic farming, farmers report higher productivity and earnings, given the higher price level [26,28,32,61].

    The problems that hinder this process must also be considered, together with the motivations that may favour a farmer's conversion to organic. These include problems related to the availability of inputs, the difficulties of switching from conventional to organic, including those related to the bureaucratic aspects and the management of the certification system [32,35,46,49], and the lack of competent technical support [62].

    An additional constraint on conversion to organic is uncertainty about the market and commercial outlets [25,32,35,46]. However, the greatest concern appears to be related to the fear of achieving lower production yields [25,35,39,48,51] and the presence of a higher workload than that required by industrial agriculture, resulting in higher production costs [25,26,35,46]. Moreover, another aspect that can hinder the conversion to organic farming is the absence of local origin labels, which is also related to ethnocentrism [63].

    In addition to the obstacles related to higher production costs, problems related to the insufficiency of public measures to support this production system are also highlighted, in terms of contributions, advertising and food education to consumers [52,64], but especially the need for greater support for the acquisition of new knowledge and technologies [25].

    3.   Material and methods

    This study's main variable of interest is the respondent's "Intention to adopt organic agriculture" on the farm. This variable is measured using a single-item scale, which results in an ordinal variable with three levels: N—I have no intention, U—I am uncertain, Y—I will adopt organic agriculture.

    The frequency of responses will allow us to evaluate the share of conventional farmers interested or considering the possibility of starting the conversion process to become organic farmers.

    Through the literature analysis, the framework of the multiple factors that can facilitate or hinder the transition from conventional to organic agriculture has been defined. These factors are essentially related to drivers, obstacles, farm characteristics, and personal characteristics of the farmers.

    The different types of drivers can be broken down into economic, socio-cultural, and environmental, while the obstacles can be divided into economic-organisational, and socio-cultural.

    In addition to these, we consider the characteristics of the company and the level of satisfaction with the farm management results obtained. Finally, the personal characteristics of the farmer, such as gender, age, educational qualification, role on the farm, time spent on the farm, the municipality in which the farm is located.

    In order to confirm or reject the relevance of these factors in orienting the behavior of entrepreneurs in the territory under consideration, we carried out a multivariate regression analysis. Given the nature of the dependent variable, the ordered logit regression approach was adopted [65]. This approach allows modeling the probability of an ordinal set of outcomes Pr(Zi) based on the values of the predictors X, as in the equation (1).

    Pr(Zi)=exp(X′β)[1+exp(X′β)] (1)

    This analysis makes it possible to relate, with a normal distribution of errors, the polychotomous ordinal dependent variable, which in the specific case is represented by the possible choices of the entrepreneur with respect to conversion to organic farming (No, Undecided, Yes) to the various independent variables: ⅰ) drivers (Driv); ⅱ) obstacles (Obst); ⅲ) farm characteristics (AgriB); ⅳ) personal characteristics (Prof).

    Pr(Intention=No|Driv,Obst,AgriB,Prof)=exp(X′β)[1+exp(X′β)]
    Pr(Intention=Undecided|Driv,Obst,AgriB,Prof)=exp(X′β)[1+exp(X′β)]
    Pr(Intention=Yes|Driv,Obst,AgriB,Prof)=exp(X′β)[1+exp(X′β)] (2)

    Where:

    X′β=Σj=1kDrivβj+Σp=1qObstβp+Σi=1nAgriBβi+Σm=1dProfβm

    Data collection is carried out through the administration of a questionnaire. This questionnaire has been defined based on the examined literature and of a series of comparisons with different privileged witnesses, among which professors of the Department of agri-food sciences and technologies of the Alma Mater Studiorum University of Bologna and the Department of Economics, Society, Politics of the University of Urbino Carlo Bo, agricultural entrepreneurs, business consultants and managers of some producers' organisations.

    The questionnaire is divided into four sections, aimed at collecting a wide range of qualitative and quantitative information about drivers, obstacles, farm characteristics and personal characteristics of the entrepreneur interviewed. The key question was the propensity to undertake or not to undertake the process of farm conversion to organic agriculture. The drives we identified are the most often cited as key aspects for conversion in the literature [25,26,27,32,39]. Variables such as the company's small size, the lack of professionalism within the company for bureaucratic management, the higher costs linked to the certification process are the most commonly found obstacles to conversion [25,32,35]. Other aspects emerging from the literature have been included in the questionnaire, such as age and education since younger farmers with higher education levels are more inclined to convert [25,28,35].

    Initially, the questionnaire was tested with a pre-test on 50 companies, above all, to verify the comprehensibility of the questions.

    The variables obtained from the questionnaire are reported in Table 1.

    Table 1.  Independent variables (drivers, obstacles, farm characteristics and respondent profile).
    Drivers
    DRIV_01 Organic crops allow for a higher income
    DRIV_02 Organic allows you to receive more public incentives
    DRIV_03 Organic is a tool to differentiate productions from competitors
    DRIV_04 Organic farming reflects my philosophy of life
    DRIV_05 Applying organic farming requires resourcefulness
    DRIV_06 Organic is a production method highly respectful of the environment and animals
    DRIV_07 Organic farming provides consumers with safer, healthier foods
    DRIV_08 The application of the organic method protects my health and that of other agricultural operators
    DRIV_09 Organic farming allows for better products
    DRIV_10 My area is suitable for organic farming
    DRIV_11 My family members are in favour of adopting organic farming
    DRIV_12 The presence of an organic certification mark valid throughout Europe offers high guarantees
    DRIV_13 The demand for organic products is continuously growing
    DRIV_14 Organic products can be more easily placed on the market than conventional ones
    DRIV_15 In the organic sector, there are opportunities arising from the creation of forms of integration (cooperatives, consortia, supply chains)
    Obstacles
    OBST_01 Organic production costs are too high
    OBST_02 The training required for organic is excessive
    OBST_03 The organic sector needs to be sustained with more public funding
    OBST_04 Costs (also of transport) of organic fertilisers are too expensive
    OBST_05 Finding organic raw materials (such as seeds) is very difficult
    OBST_06 My financial resources are not sufficient to undertake organic farming
    OBST_07 The administrative requirements needed to undertake organic farming are difficult to manage
    OBST_08 The technical-agronomic application of organic regulations is difficult
    OBST_09 Controls for organic certification are too strict
    OBST_10 I do not have the technical facilities and farm size to undertake organic farming
    OBST_11 It is possible to efficiently adopt the organic regime only if neighbouring farmers also adhere to it
    OBST_12 In the organic sector, it is difficult to create partnerships with other producers
    OBST_13 Selling prices of organic products are excessively high
    OBST_14 The organic system does not allow a sufficiently wide range of products to be offered
    OBST_15 The commercial channels able to enhance the value of organic products are too limited
    OBST_16 In the organic sector, the lack of a national brand is strongly perceived
    OBST_17 In the organic sector, the lack of a regional brand is strongly perceived
    OBST_18 My fellow farmers make negative comments about organic farming
    OBST_19 Organic conditions will worsen in the future
    Farm characteristics
    AGRIB_01 Farm size (ha divided in classes: " > 100"; "50-99, 99"; "20-49, 99"; "10-19, 99"; "5-9, 99"; "2-4, 99"; "1-1, 99"; " < 1")
    Respondent profile
    PROF_01 Gender (Man or Woman)
    PROF_02 Age (Years)
    PROF_07 Educational Qualification (UD = University Degree; HSD = High School Diploma; SS = Secondary School; ES = Elementary School)
    Source: Survey questionnaire.
     | Show Table
    DownLoad: CSV

    For the drivers and obstacles variables, a 5-point Likert scale was used, in which the response was coded with 1 = Totally Disagree, 2 = Partially Disagree, 3 = Neither, 4 = Partially Agree, and 5 = Totally Agree.

    Before reaching the definition and estimation of the final model, monovariate analysis was performed to describe the individual variables considered. In order to understand the influence of these variables on the dependent, for purely exploratory purposes, a bivariate analysis was carried out among all the variables belonging to the four categories considered and the outcome variable Intention. After that, for the variables belonging to the Drivers and Obstacles categories, an Explanatory Factor Analysis was carried out in order to aggregate the variables that express a common concept. A correlation analysis with the Kendall method was carried out for personal characteristics variables. This aggregation will be conducted, within the identified categories, with arithmetic mean in cases with a reduced number of variables, and with the Principal Components Analysis (PCA) technique, in those with a high number of variables.

    The R software [66] and the packages 'polycor' [67], 'MASS' [68], 'readxl' [69], 'psych' [70] and 'catspec' [71] were used to process and analyse the data.

    Data collection was carried out through interviews with farmers who run conventional farms and are active in the territory of the Province of Pesaro-Urbino, selected through a non-probabilistic sampling procedure. Convenience sampling was carried out by inviting farmers belonging to the main producer organisations active in the territory (Confederazione Italiana Agricoltori and Coldiretti) to face-to-face interviews at their headquarters or on their farms, or participants in public events (seminars, conferences) held in various municipalities of the province. In order to reduce the unreliability of inference concerning quantitative information, especially regarding the response on the intention to convert to organic farming, entrepreneurs were informed that the interviews were carried out as part of a research project of the Department of Economics, Society, Politics of the University of Urbino, without specifying the objective.

    The administration took place during the period October 2018–January 2019. A total of 202 entrepreneurs were interviewed, representing 2.4% of the reference population [72], whose company location falls in 40 municipalities out of 54 in the Province of Pesaro-Urbino. In the assumption of a random sample, this sample size would imply a power of 7.1% considering a binomial variable at a 33% expected proportion and a confidence level (α) of 0.05.

    4.   Results and discussion

    4.1.   The propensity of entrepreneurs to convert to organic farming

    The survey data allowed us to analyse the four categories of variables that explain the farmer's decision.

    The descriptive statistics of the single independent variables were highlighted with the monovariate analysis. The results are reported in Supplementary Tables 1–4.

    The data collected are in line with the demographic characteristics of the European and Italian agricultural production structure [33,73], especially concerning the low presence of young entrepreneurs (10%), with a median age of our sample equal to 54 years (i.e. under 40 years of age, according to the indications of ISTAT and the Agricultural Accounting Information Network).

    In terms of educational level, 40% of respondents have a university degree (82 respondents), 8% have a high school diploma (17 respondents), 9% have a middle school diploma (18 respondents), and the remaining 42% have a primary school diploma (85 respondents). The majority of farmers, about 77%, work full-time in agriculture. In addition, in 54% of cases, it was found that at least one other member of the household works on the same farm. In other words, there is a clear prevalence of family management. Finally, most farmers are men (90%), and women represent only 10% of the sample.

    "Intention" is an ordinal dependent variable, measuring the propensity to adopt the organic production system, with three levels (NO, UNDECIDED, and YES). Figure 1 shows the number of responses in the sample.

    Figure 1.  Intention to convert to organic agriculture.
    DownLoad: Full-Size Img PowerPoint

    An ordered logistic regression model (Ordered Logit) was estimated to identify the factors that most influence the propensity to convert to organic farming. In equation (3), reformulating (2), the predictors (i.e., the independent variables) are fifteen different motivations and nineteen issues that may or may not have driven farmers to convert, one farm characteristic (farm size), and three personal respondent's characteristics (gender, age, and education level).

    Pr(Intention=No|Drivj,Obstp,AgriBi,Profm)=exp(X′β)[1+exp(X′β)]
    Pr(Intention=Undecided|Drivj,Obstp,AgriBi,Profm)=exp(X′β)[1+exp(X′β)]
    Pr(Intention=Yes|Drivj,Obstp,AgriBi,Profm)=exp(X′β)[1+exp(X′β)] (3)

    Where:

    X′β=β0+Σj=115βjDrivj+Σp=119βpObstp+βi=1AgriBi+Σm=13βmProfm

    Factor analysis, specifically PCA, which allows the extraction of a small number of independent, interpretable factors from a high-dimensional observed dataset with complex structure [74], was used to summarise the variables from the drivers and obstacles reported in Table 2.

    Table 2.  Synthesis variables.
    Synthesis variables Original variables
    Social and environmental sustainability—SocEnvSust Farmer's philosophy of life (DRIV_04)-Respect for the environment and animal welfare (DRIV_06)-Food safety (DRIV_07)-Health protection (DRIV_08)-Quality of organic products (DRIV_09)-Family members are favourable (DRIV_11)
    Technical and bureaucratic requirements—TecBurReq Bureaucratic compliance (OBST_07)-Technical implementation of legislation (OBST_08)
    Inadequate corporate assets—InadCorpAs Financial resources of the farmer (OBST_06)-Available technical facilities (OBST_10)-Controls for organic certification are too strict (OBST_09)
    Local Visibility—LocVis Absence of national label (OBST_16)-Absence of regional label (OBST_17)
    Personal Characteristics—PersChar Age (PROF_02)-Education qualification (PROF_07)
    Source: Analysis of the survey data.
     | Show Table
    DownLoad: CSV

    Drivers reflecting a positive attitude towards organic farming were aggregated into a single factor (SocEnvSust-Social and environmental sustainability), which had a factor loading greater than 0.6 (see Figure 2). These drivers were related to the farmer's philosophy of life (DRIV_04), the resourcefulness of farmers (DRIV_05), the respect for the environment and animal welfare (DRIV_06), food safety (DRIV_07), health protection (DRIV_08), higher quality of organic products (DRIV_09) and the favour of family members towards this production method (DRIV_11).

    Figure 2.  Factor analysis for drivers.
    DownLoad: Full-Size Img PowerPoint

    Regarding the obstacles, the variables with a factor loading greater than 0.6 (see Figure 3) were aggregated into three summarising factors by averaging them: the perceived difficulties in the management of bureaucratic requirements (OBST_07) and the technical-agronomic application of the organic regulations necessary to undertake organic farming (OBST_08) were aggregated in the factor TecBurReq-Technical and bureaucratic requirements; the second factor InadCorpAs-Inadequate corporate assets aggregates the variables on the perceived lack of financial availability possessed by the farmer (OBST_06), absence of technical facilities and adequate company size (OBST_10) and difficulty of complying with the controls for organic certification considered too strict (OBST_09); finally, the lack of a national organic brand (OBST_17) and a regional organic brand (OBST_16), were aggregated in the factor LocVis-Local Visibility.

    Figure 3.  Factor analysis for obstacles.
    DownLoad: Full-Size Img PowerPoint

    Regarding the characteristics of the respondent's profile, a "Kendall correlation"2 analysis was carried out between the identified variables to understand the correlation level, and the results are shown in Table 3.

    2 Values with a correlation greater than 20% are considered statistically significant, although those just above this value will be weakly correlated while those above 40-50% will be more so.

    Table 3.  Correlation between personal characteristics variables.
    PROF_01_l Age PROF_07_l
    PROF_01_l 1.00 0.11 0.00
    Age 0.11 1.00 −0.29
    PROF_07_l 0.00 −0.29 1.00
    Source: Analysis of the survey data, Kendall's correlation coefficients.
     | Show Table
    DownLoad: CSV

    Among the variables of the respondent's personal characteristics, it can be seen that those relating to age (Age) and the educational qualification of farmers (PROF_07) are negatively correlated with a coefficient of −29%. Those belonging to the youngest age groups are, on average, also the most educated and, for this reason, the two variables have been merged, with mean, into a single synthesis variable PersChar-Personal Characteristics.

    In the final multivariate order logit regression model, the new summary variables, SocEnvSust, TecBurReq, LocVis, InadCorpAs, PersChar, have been included.

    The variable company size was not included as the bivariate analysis with Intention did not show it to be statistically significant.

    Pr(Intention=No|SocEnvSust,TecBurReq,LocVis,InadCorpAs,PersChar)=exp(X′β)[1+exp(X′β)]
    Pr(Intention=Undecided|SocEnvSust,TecBurReq,LocVis,InadCorpAs,PersChar)=exp(X′β)[1+exp(X′β)]
    Pr(Intention=Yes|SocEnvSust,TecBurReq,LocVis,InadCorpAs,PersChar)=exp(X′β)[1+exp(X′β)] (4)

    Where:

    X′β=β0+β1SocEnvSust+β2TecBurReq+β3LocVis+β4InadCorpAs+β5PersChar

    To assess the significance of the synthesis variables in the final regression model, we used the Residual Deviance, the Akaike Information Criterion (AIC) and the t-value3 and the signs of the coefficients of the value, allow us to interpret the effect, positive or negative, that each has on the probability of adopting the organic model.

    3 Statistically significant variable when the t-value, in absolute value, is greater than or equal to 1.96 with 95% probability.

    4.2.   Discussion of the results

    In the estimated model, two variables (SocEnvSust and LocVis) assume a positive coefficient sign, showing an effect in favour of conversion to organic farming (Table 4).

    Table 4.  Multivariate regression results.
    Value Std.
    Error    		 t-value
    SocEnvSust 0.73537 0.1625 4.5264
    PersChar −0.35665 0.1400 −2.5471
    TecBurReq −0.18323 0.1444 −1.2688
    LocVis 0.02692 0.1399 0.1924
    InadCorpAs −0.18547 0.1433 −1.2942
    Source: Analysis of the survey data.
     | Show Table
    DownLoad: CSV

    Social and environmental sustainability is the variable that most influences the likelihood of adopting organic farming. In particular, the greater the farmer's degree of attention to the social and environmental benefits achievable through organic farming, the greater the likelihood that he or she will be inclined to undertake the conversion process to organic farming.

    This result, which appears consistent with those reported in other studies [25,26,27,32,39], is essentially attributable to ethical and environmental motivation, considered to be the most significant driver in orienting the choices of the first generation of organic farmers. In the province of Pesaro-Urbino, in particular, the high significance of this variable can also be explained by the widespread knowledge of the successful experiences of many organic agri-food companies that, for several decades, have successfully combined environmental sustainability with the achievement of high levels of competitiveness at a national and international level [75]. The variable that seems to have a lower level of influence is inherent to local visibility.

    Vice versa, the other three variables (Personal characteristics, Technical and bureaucratic requirements and Inadequate farm assets) have a negative coefficient, highlighting the farmer's tendency to maintain, with greater probability, the conventional production system. In particular, when the variable 'Personal characteristics' (which is highly influential) takes on a higher value, i.e. when the farmer's age increases or when the level of education decreases, the probability that the individual adopts organic farming tends to decrease. For example, when considering two farmers with perfectly equal holdings, the older or less educated farmer is less likely to convert to organic farming than a younger, more educated farmer.

    These results are in line with the evidence from the literature review, which points to a higher propensity to convert to organic farming among younger and highly educated farmers [25,28,35]. According to [25,32,35], these aspects, such as the small size of the company, the lack of professionalism within the company for bureaucratic management, the higher costs related also to the certification process are the most marked obstacles to conversion.

    5.   Conclusions

    To satisfy the growing demand for organic food, a substantial increase in the area devoted to this farming system is necessary [76]. Internationally, the value of organic retail sales has grown from 15 billion euros in 2000 to 106 billion euros in 2019, and, in the same period, Europe has gone from 7 billion euros to 45 billion euros, of which 4 billion in Italy [20]. Apparently, the possibility of obtaining more remunerative and less volatile prices, in the face of production costs that are not necessarily higher and of yields that are not always lower than those of industrial agriculture [77,78,79], are not enough to incentivise conversion to organic farming [16].

    This work analysed the motivations and possible obstacles for the conversion process in a specific territory, providing information that could help policymakers identify appropriate support measures [80]. The effectiveness of policy measures is closely related to the knowledge of the factors that influence the propensity of agricultural entrepreneurs to convert to organic farming. Our study confirms that propensity is strongly related to the individual's characteristics and needs.

    Although in areas like the Province of Pesaro-Urbino, organic farming penetration is already quite high compared to other areas and the objectives of Farm to Fork [22], this penetration is not sufficient to reach the territorial scale needed to fully deploy the positive environmental effects of organic farming [2,17]. For companies operating in the local food supply chains, it would be necessary to promote economically sustainable production, distribution, and consumption projects, also favouring consumers' involvement [81,82].

    More structured technical assistance could remove some of the identified obstacles in the case we examined. For instance, providing knowledge to young entrepreneurs and technical-organisational support to farmers worried about the bureaucratic burden through innovation transfer agencies or supporting integration and cooperation to improve the farms' quality management systems. These measures would facilitate the transition towards more sustainable production models [35,49] in environmental, social and economic terms, offering development opportunities to small and medium-sized enterprises and the most marginal rural areas.

    An open question is whether these conclusions are valid in a context in which the penetration of organic farming is lower or inexistent. It may be reasonable to assume that farmers' attitudes about organic farming may be affected by the information they receive from their peers. Therefore, if the community does not include organic farmers or they are very few, a lack of trust in the information about the potential benefits of this farming system is to be expected. Subjective norms and the surrounding environment is positively correlated with the probability of converting to organic farming for less developed countries in Europe where this production model is still in its early stages [83]. This issue represents a limitation of this research, implying the need to analyse the predictors of organic farming adoption in a low penetration context.

    Acknowledgments

    We thank the Regione Marche for financing the PhD fellowship of S.R. (POR Marche FSE 2014/2020, Progetto "Dottorato Innovativo").

    Elena Viganò also acknowledges funding from the PRIN 2017 project 20177J2LS9 004 ”Innovation for global challenges in a connected world: the role of local resources and socio-economic conditions”.

    We would like to thank all the stakeholders who help us with the design of the questionnaire and its implementation as prof. Gianluca Vitali (University of Bologna), the Operational Units of the Province of Pesaro-Urbino of CIA and Coldiretti, Fondazione Girolomoni (Silvia Cavinato and Maria Girolomoni), Cooperativa Gino Girolomoni (Giovanni Battista Girolomoni and Pierfrancesco Fattori), Consorzio Marche Biologiche (Francesco Torriani), and the President of Province of Pesaro-Urbino, Giuseppe Paolini.

    We also thank the reviewers whose comments and suggestions allowed our work to be improved.

    Conflict of interest

    The authors declare no conflict of interest.

    Author contributions

    Conceptualisation E.V., M.C. and S.R.; Literature review F.G., M.C. and S.R.; Qualitative Analysis and Data collection F.G. and S.R.; Methodology M.C. and S.R.; Software M.C. and S.R.; Validation E.V., M.C., F.G. and S.R.; Wrote the paper E.V., M.C. and S.R. All authors contributed to the manuscript revision, read, and approved the submitted and final version.

    Supplementary

    Table Supplementary 1.  Descriptive analysis of independent variables: drivers.
    Variable label Description Totally disagree Partially disagree Neutral Partially agree Totally
    agree
    DRIV_01 Organic crops allow to obtain a higher income 27 40 24 83 28
    DRIV_02 Organic allows you to receive more public incentives 3 6 10 56 127
    DRIV_034 Organic is a tool to differentiate productions from competitors 9 17 20 76 79
    DRIV_04 Organic farming reflects my philosophy of life 17 19 53 43 70
    DRIV_05 Applying organic farming requires resourcefulness 16 15 44 56 71
    DRIV_06 Organic is a production method highly respectful of the environment and animals 4 13 8 46 131
    DRIV_07 Organic farming provides consumers with safer, healthier foods 7 18 6 60 111
    DRIV_08 The application of the organic method protects my health and that of other agricultural operators 5 14 6 45 132
    DRIV_09 Organic farming allows to make better products 16 23 32 72 59
    DRIV_10 My area is suitable for organic farming 16 20 25 51 90
    DRIV_11 My family members are in favour of adopting organic farming 22 18 42 51 69
    DRIV_12 The presence of an organic certification mark valid throughout Europe offers high guarantees 16 29 43 55 59
    DRIV_13 The demand of organic products is steadily growing 4 5 12 60 121
    DRIV_14 Organic products can be more easily placed on the market than conventional ones 9 25 28 72 68
    DRIV_15 In the organic sector, there are opportunities arising from the creation of forms of integration (cooperatives, consortia, supply chains) 6 11 61 68 56
     | Show Table
    DownLoad: CSV

    4 One omitted variable.

    Table Supplementary 2.  Descriptive analysis of independent variables: obstacles.
    Variable label Description Totally disagree Partially disagree Neutral Partially agree Totally agree
    OBST_01 Organic production costs are too high 26 43 22 64 47
    OBST_02 The training required for organic is excessive 24 40 56 45 37
    OBST_03 Organic sector needs to be sustained with more public funding 18 21 15 57 91
    OBST_04 Costs (also of transport) of organic fertilizers are too expensive 16 17 53 49 67
    OBST_05 Finding organic raw materials (such as seeds) is very difficult 24 28 43 63 44
    OBST_06 My financial resources are not sufficient to undertake organic farming 63 35 45 32 27
    OBST_07 The administrative requirements needed to undertake organic farming are difficult to manage 12 11 19 49 111
    OBST_08 The technical-agronomic application of organic regulations is difficult 16 8 44 78 56
    OBST_09 Controls for organic certification are too strict 50 41 47 45 19
    OBST_10 I do not have the technical facilities and farm size to undertake organic farming 84 20 42 26 30
    OBST_11 It is possible to efficiently adopt the organic regime only if neighbouring farmers also adhere to it 45 18 43 47 49
    OBST_12 In the organic sector, it is difficult to create partnerships with other producers 34 24 68 35 41
    OBST_13 Selling prices of organic products are excessively expensive 63 37 41 37 24
    OBST_14 The organic system does not allow a sufficiently wide range of products to be offered 49 34 47 38 34
    OBST_15 The commercial channels able to enhance the value of organic products are too limited 19 37 31 54 61
    OBST_16 In the organic sector, the lack of a national brand is strongly perceived 12 11 69 36 74
    OBST_17 In the organic sector, the lack of a regional brand is strongly perceived 12 13 76 50 51
    OBST_18 My fellow farmers make negative comments about organic farming 35 35 63 43 26
    OBST_19 Organic conditions will worsen in the future 72 49 46 23 12
     | Show Table
    DownLoad: CSV
    Table 3.  Descriptive analysis of independent variables: respondent profile.
    Variable label Description Basic statistics
    PROF_01 Gender (n.) Male = 180 Female = 22
    PROF_02 Age (years) Min = 20
    Max = 82    		 Median = 54
    Mean = 52.67    		 SD = 1.705099
    PROF_07 Education level5 UD = 82 HSD = 17 SS = 18 ES = 85
     | Show Table
    DownLoad: CSV

    5 UD = University Degree; HSD = High School Diploma; SS = Secondary School; SE = Elementary School.

    Table 4.  Descriptive analysis of independent variables: farm characteristics.
    Variable label Description Basic statistics
    AGRIB_01 Farm size6
    (hectares)    		 Min = 1
    Max = 8    		 Median = 6
    Mean = 5.562    		 SD = 1.705099
     | Show Table
    DownLoad: CSV

    6 One omitted variable.



    [1] M. Sharif, S. Bhagavatula, L. Bauer, M. K. Reiter, Accessorize to a crime: real and stealthy attacks on state-of-the-art face recognition, in Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security, (2016), 1528–1540. https://doi.org/10.1145/2976749.2978392
    [2] S. Komkov, A. Petiushko, Advhat: Real-world adversarial attack on ArcFace face id system, preprint, arXiv: 1908/08705
    [3] M. Pautov, G. Melnikov, E. Kaziakhmedov, K. Kireev, A. Petiushko, On adversarial patches: Real-world attack on ArcFace-100 face recognition system, in 2019 International Multi-Conference on Engineering, Computer and Information Sciences, (2019), 391–396. https://doi.org/10.1109/SIBIRCON48586.2019.8958134
    [4] S. Thys, W. Van Ranst, T. Goedemé, Fooling automated surveillance cameras: Adversarial patches to attack person detection, in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, (2019), 49–55. https://doi.org/10.1109/CVPRW.2019.00012
    [5] N. Ud Din, K. Javed, S. Bae, J. Yi, A novel GAN-based network for unmasking of masked face, IEEE Access, 8 (2020), 44276–44287. https://doi.org/10.1109/ACCESS.2020.2977386 doi: 10.1109/ACCESS.2020.2977386
    [6] S. Ge, C. Li, S. Zhao, D. Zeng, Occluded face recognition in the wild by identity-diversity inpainting, IEEE Trans. Circ. Syst. Vid., 30 (2020), 3387–3397. https://doi.org/10.1109/TCSVT.2020.2967754 doi: 10.1109/TCSVT.2020.2967754
    [7] R. Weng, J. Lu, Y. P. Tan, Robust point set matching for partial face recognition, IEEE Trans. Image Process., 25 (2016), 1163–1176. https://doi.org/10.1109/TIP.2016.2515987 doi: 10.1109/TIP.2016.2515987
    [8] W. Hariri, Efficient masked face recognition method during the COVID-19 pandemic, Signal Image Video Process., 16 (2022), 605–612. https://doi.org/10.1007/s11760-021-02050-w doi: 10.1007/s11760-021-02050-w
    [9] D. Montero, M. Nieto, P. Leskovsky, N. Aginako, Boosting masked face recognition with multi-task ArcFace, preprint, arXiv: 2104/09874
    [10] M. Sharif, S. Bhagavatula, L. Bauer, M. K. Reiter, Accessorize to a crime: Real and stealthy attacks on state-of-the-art face recognition, in Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security, (2016), 1528–1540. https://doi.org/10.1145/2976749.2978392
    [11] Y. Kim, J. Na, S. Yoon, J. Yi, Masked fake face detection using radiance measurements, J. Opt. Soc. Am. A. Opt. Image Sci. Vis., 26 (2009), 760–766, https://doi.org/10.1364/JOSAA.26.000760 doi: 10.1364/JOSAA.26.000760
    [12] N. Kose, J. L. Dugelay, Countermeasure for the protection of face recognition systems against mask attacks, in 2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG), (2013), 1–6. https://doi.org/10.1109/FG.2013.6553761
    [13] Y. Song, H. Zhang, A framework of face synthesis based on multilinear analysis, in Proceedings of the 15th ACM SIGGRAPH Conference on Virtual-Reality Continuum and Its Applications in Industry, 1 (2016), 111–114. https://doi.org/10.1145/3013971.3014026
    [14] J. Pu, N. Mangaokar, L. Kelly, P. Bhattacharya, K. Sundaram, M. Javed, et al., Deepfake videos in the wild: Analysis and detection, in Proceedings of the Web Conference 2021, (2021), 981–992. https://doi.org/10.1145/3442381.3449978
    [15] R. Sun, C. Huang, H. Zhu, L. Ma, Mask-aware photorealistic facial attribute manipulation, Comput. Visual Media, 7 (2021), 363–374. https://doi.org/10.1007/s41095-021-0219-7 doi: 10.1007/s41095-021-0219-7
    [16] J. Lei, Z. Liu, Z. Zou, T. Li, J. Xu, Z. Feng, et al., Facial expression recognition by expression-specific representation swapping, in Artificial Neural Networks and Machine Learning—ICANN 2021, Lecture Notes in Computer Science, (2021), 80–91. https://doi.org/10.1007/978-3-030-86340-1_7
    [17] H. Wang, G. Sun, K. Zheng, H. Li, J. Liu, Y. Bai, Privacy protection generalization with adversarial fusion, Math. Biosci. Eng., 19 (2022), 7314–7336. https://doi.org/10.3934/mbe.2022345 doi: 10.3934/mbe.2022345
    [18] W. Ou, X. You, D. Tao, P. Zhang, Y. Tang, Z. Zhu, Robust face recognition via occlusion dictionary learning, Pattern Recogn., 47 (2014), 1559–1572. https://doi.org/10.1016/j.patcog.2013.10.017 doi: 10.1016/j.patcog.2013.10.017
    [19] N. Alyuz, B. Gokberk, L. Akarun, 3-D Face recognition under occlusion using masked projection, IEEE Trans. Inf. Foren. Sec., 8 (2013), 789–802. https://doi.org/10.1109/TIFS.2013.2256130 doi: 10.1109/TIFS.2013.2256130
    [20] H. Drira, B. Ben Amor, A. Srivastava, M. Daoudi, R. Slama, 3D Face recognition under expressions, occlusions and pose variations, IEEE Trans. Pattern Anal. Mach. Intell., 35 (2013), 2270–2283. https://doi.org/10.1109/TPAMI.2013.48 doi: 10.1109/TPAMI.2013.48
    [21] H. Li, D. Huang, J. M. Morvan, Y. Wang, L. Chen, Towards 3D face recognition in the real: A registration-free approach using fine-grained matching of 3D keypoint descriptors, Int. J. Comput. Vis., 113 (2015), 128–142. https://doi.org/10.1007/s11263-014-0785-6 doi: 10.1007/s11263-014-0785-6
    [22] Y. Guo, J. Zhang, J. Cai, B. Jiang, J. Zheng, CNN-based real-time dense face reconstruction with inverse-rendered photo-realistic face images, IEEE Trans. Pattern Anal. Mach. Intell., 41 (2019), 1294–1307. https://doi.org/10.1109/TPAMI.2018.2837742 doi: 10.1109/TPAMI.2018.2837742
    [23] Q. Hong, Z. Wang, Z. He, N. Wang, X. Tian, T. Lu, Masked face recognition with identification association, in 2020 IEEE 32nd International Conference on Tools with Artificial Intelligence (ICTAI), (2020), 731–735. https://doi.org/10.1109/ICTAI50040.2020.00116
    [24] Y. Utomo, G. P. Kusuma, Masked face recognition: Progress, dataset and dataset generation, in 2021 3rd International Conference on Cybernetics and Intelligent System (ICORIS), (2021), 419–422. https://doi.org/10.1109/ICORIS52787.2021.9649622
    [25] J. Prinosil, O. Maly, Detecting faces with face masks, in 2021 44th International Conference on Telecommunications and Signal Processing (TSP), (2021) 259–262. https://doi.org/10.1109/TSP52935.2021.9522677
    [26] R. Tolosana, R. Vera-Rodriguez, J. Fierrez, A. Morales, J. Ortega-Garcia, Deepfakes and beyond: A survey of face manipulation and fake detection, Inf. Fusion, 64 (2020), 131–148. https://doi.org/10.1016/j.inffus.2020.06.014 doi: 10.1016/j.inffus.2020.06.014
    [27] S. Avidan, M, Butman, Blind vision, in Computer Vision–ECCV 2006, (2006), 1–13, https://doi.org/10.1007/11744078_1
    [28] G. Sun, H. Wang, Image encryption and decryption technology based on Rubik's cube and dynamic password, J. Beijing Univ. Technol., 47 (2021), 833–841. https://doi.org/10.11936/bjutxb2020120003 doi: 10.11936/bjutxb2020120003
    [29] J. Zhou, C. Pun, Personal privacy protection via irrelevant faces tracking and pixelation in video live streaming, IEEE Trans. Inf. Foren. Sec., 16 (2021), 1088–1103. https://doi.org/10.1109/TIFS.2020.3029913 doi: 10.1109/TIFS.2020.3029913
    [30] P. Climent-Pérez, F. Florez-Revuelta, Protection of visual privacy in videos acquired with RGB cameras for active and assisted living applications, Multimed. Tools Appl., 80 (2021), 23649–23664. https://doi.org/10.1007/s11042-020-10249-1 doi: 10.1007/s11042-020-10249-1
    [31] K. Zheng, J. Shen, G. Sun, H. Li, Y. Li, Shielding facial physiological information in video, Math. Biosci. Eng., 19 (2021), 5153–5168. https://doi.org/10.3934/mbe.2022241 doi: 10.3934/mbe.2022241
    [32] M. Chen, X. Liao, M. Wu, PulseEdit: Editing physiological signals in facial videos for privacy protection, IEEE Trans. Inf. Foren. Sec., 17 (2022), 457–471. https://doi.org/10.1109/TIFS.2022.3142993 doi: 10.1109/TIFS.2022.3142993
    [33] S. Shan, E. Wenger, J. Zhang, H. Li, H. Zheng, B. Y. Zhao, Fawkes: Protecting personal privacy against unauthorized deep learning models, in 29th USENIX Security Symposium (USENIX Security 20), (2020), 1589–1604
    [34] J. R. Padilla-López, A. A. Chaaraoui, F. Flórez-Revuelta, Visual privacy protection methods: A survey, Expert Syst. Appl., 42 (2015), 4177–4195. https://doi.org/10.1016/j.eswa.2015.01.041 doi: 10.1016/j.eswa.2015.01.041
    [35] S. N. Patel, J. W. Summet, K. N. Truong, BlindSpot: Creating capture-resistant spaces, in Protecting Privacy in Video Surveillance, 13 (2009), 185–201. https://doi.org/10.1007/978-1-84882-301-3_11
    [36] T. B. Brown, D. Mané, A. Roy, M. Abadi, J. Gilmer, Adversarial patch, preprint, arXiv: 1712/09665
    [37] C. He, H. Hu, Image captioning with text-based visual attention, Neural Process. Lett., 49 (2019), 177–185. https://doi.org/10.1007/s11063-018-9807-7 doi: 10.1007/s11063-018-9807-7
    [38] K. Cho, B. van Merriënboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, et al., Learning phrase representations using RNN encoder-decoder for statistical machine translation, in Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), (2014), 1724–1734. http://dx.doi.org/10.3115/v1/D14-1179
    [39] Q. Guo, J. Huang, N. Xiong, MS-Pointer network: Abstractive text summary based on multi-head self-attention, IEEE Access, 7 (2019), 138603–138613. https://doi.org/10.1109/ACCESS.2019.2941964 doi: 10.1109/ACCESS.2019.2941964
    [40] H. Li, A. Kadav, I. Durdanovic, H. Samet, H. P. Graf, Pruning filters for efficient convnets, preprint, arXiv: 1608.08710
    [41] J. Liu, B. Zhuang, Z. Zhuang, Y. Guo, J. Huang, J. Zhu, et al., Discrimination-aware network pruning for deep model compression, IEEE Trans. Pattern Anal. Mach. Intell., 44 (2022), 4035–4051. https://doi.org/10.1109/TPAMI.2021.3066410 doi: 10.1109/TPAMI.2021.3066410
    [42] H. Zou, X. Sun, 3D Face recognition based on an attention mechanism and sparse loss function, Electronics, 10 (2021), 2539. https://doi.org/10.3390/electronics10202539 doi: 10.3390/electronics10202539
    [43] J. J Koenderink, A. J. Doorn, Surface shape and curvature scales, Image Vis. Comput., 10 (1992), 557–564. https://doi.org/10.1016/0262-8856(92)90076-F doi: 10.1016/0262-8856(92)90076-F
    [44] I. G. Kang, F. C. Park, Cubic spline algorithms for orientation interpolation, Int. J. Numer. Meth. Eng., 46 (1999), 45–64. https://doi.org/10.1002/(SICI)1097-0207(19990910)46:1%3C45::AID-NME662%3E3.0.CO; 2-K doi: 10.1002/(SICI)1097-0207(19990910)46:1<45::AID-NME662>3.0.CO;2-K
    [45] P. J. Phillips, P. J. Flynn, T. Scruggs, K. W. Bowyer, J. Chang, K. Hoffman, et al., Overview of the face recognition grand challenge, in 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), 1 (2005), 947–954. https://doi.org/10.1109/CVPR.2005.268
    [46] M. Jaderberg, K. Simonyan, A. Zisserman, K. Kavukcuoglu, Spatial transformer networks, in Advances in Neural Information Processing Systems, 2 (2015), 2017–2025. Available from: https://papers.nips.cc/paper/2015/file/33ceb07bf4eeb3da587e268d663aba1a-Paper.pdf
    [47] W. Arendt, M. Warma, Dirichlet and neumann boundary conditions: What is in between?, J. Evol. Equations, 3 (2003), 119–135. https://doi.org/10.1007/978-3-0348-7924-8_6 doi: 10.1007/s000280300005
    [48] R. Carbó-Dorca, Logical kronecker delta deconstruction of the absolute value function and the treatment of absolute deviations, J. Math. Chem., 49 (2011), 619–624. https://doi.org/10.1007/s10910-010-9781-4 doi: 10.1007/s10910-010-9781-4
    [49] M. Jaderberg, K. Simonyan, A. Zisserman, K. Kavukcuoglu, Spatial transformer networks, preprint, arXiv: 1506/02025
    [50] Z. Wang, G. Wang, B. Huang, Z. Xiong, Q. Hong, H. Wu, et al., Masked face recognition dataset and application, preprint, arXiv: 2003/09093
    [51] X. Li, S. Liu, H. Chen, K. Wang, A potential information capacity index for link prediction of complex networks based on the cannikin, Entropy, 21 (2019), 863. https://doi.org/10.3390/e21090863 doi: 10.3390/e21090863
    [52] A. Athalye, L. Engstrom, A. Ilyas, K. Kwok, Synthesizing robust adversarial examples, preprint, arXiv: 1707/07397

  • This article has been cited by:

    1. Aasheesh Dixit, Pinakhi Suvadarshini, Dewang Vijay Pagare, Analysis of barriers to organic farming adoption in developing countries: a grey-DEMATEL and ISM approach, 2022, 2044-0839, 10.1108/JADEE-06-2022-0111
    2. Isabell Richter, Nicolas E. Neef, Alireza Moghayedi, Folasade Mary Owoade, Kutemba Kapanji-Kakoma, Francis Sheena, Kaliyadasa Ewon, Willing to be the change: Perceived drivers and barriers to participation in urban smart farming projects, 2023, 0735-2166, 1, 10.1080/07352166.2023.2232060
    3. L. Krasilnikova, D. Balandin, E. Balandin, G. Uzakov, I. Chudov, A. Gibadullin, Z. Zalilova, Monitoring the use of mineral fertilizers in rural areas of the region, 2023, 71, 2117-4458, 01105, 10.1051/bioconf/20237101105
    4. Oksana Bialkovska, Nataliia Poprozman, Andrii Zelenskyi, Nataliia Fedorchuk, Yaroslav Huk, Prospects for the introduction of a green economy in the agricultural sector of Ukraine for the next 10 years, 2024, 27, 2709-8877, 163, 10.48077/scihor6.2024.163
    5. Marilena Gemtou, Konstantina Kakkavou, Evangelos Anastasiou, Spyros Fountas, Soren Marcus Pedersen, Gohar Isakhanyan, Kassa Tarekegn Erekalo, Serafin Pazos-Vidal, Farmers’ Transition to Climate-Smart Agriculture: A Systematic Review of the Decision-Making Factors Affecting Adoption, 2024, 16, 2071-1050, 2828, 10.3390/su16072828
    6. Francesca Monticone, Antonella Samoggia, Unveiling farmers' perspectives on urban food policies: The case of farmers' markets in Bologna (Italy), 2025, 160, 02642751, 105806, 10.1016/j.cities.2025.105806
    7. Selene Righi, Elena Viganò, Innovativeness in organic farming system: The case of the Marche region, 2025, 1126-1668, 137, 10.3280/ecag2024oa17604
  • Reader Comments
  • © 2023 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)
通讯作者: 陈斌, bchen63@163.com
  • 1. 

    沈阳化工大学材料科学与工程学院 沈阳 110142

  1. 本站搜索
  2. 百度学术搜索
  3. 万方数据库搜索
  4. CNKI搜索
Mathematical Biosciences and Engineering
3.9

Metrics

Article views(2533) PDF downloads(136) Cited by(1)

Preview PDF
Download XML
Export Citation
Article outline
Abstract
   Introduction
   Conversion to organic farming: Drivers and obstacles
   Material and methods
   Results and discussion
   Conclusions
Acknowledgments
Conflict of interest
Author contributions
Supplementary
References

Figures and Tables

Figures(17)  /  Tables(1)

Other Articles By Authors

Related pages

Tools

Copyright © AIMS Press

/

DownLoad:  Full-Size Img  PowerPoint
Return
Return

Catalog