Learning deep forest for face anti-spoofing: An alternative to the neural network against adversarial attacks

Rizhao Cai; Liepiao Zhang; Changsheng Chen; Yongjian Hu; Alex Kot; Rizhao Cai; Liepiao Zhang; Changsheng Chen; Yongjian Hu; Alex Kot

doi:10.3934/era.2024259

Electronic Research Archive

2024, Volume 32, Issue 10: 5592-5614. doi: 10.3934/era.2024259

Previous Article Next Article

Research article

Learning deep forest for face anti-spoofing: An alternative to the neural network against adversarial attacks

1.
School of Electrical and Electronic Engineering, Nanyang Technological University, 639798, Singapore
2.
GRGTally-vision I.T. Co., Ltd., Guangzhou 510663, China
3.
College of Electronics and Information Engineering, Shenzhen University, Shenzhen 518061, China
4.
School of Electronic and Information Engineering, South China University of Technology, Guangzhou 510641, China

Received: 20 May 2024 Revised: 31 August 2024 Accepted: 09 September 2024 Published: 11 October 2024

Face anti-spoofing (FAS) is significant for the security of face recognition systems. neural networks (NNs), including convolutional neural network (CNN) and vision transformer (ViT), have been dominating the field of the FAS. However, NN-based methods are vulnerable to adversarial attacks. Attackers could insert adversarial noise into spoofing examples to circumvent an NN-based face-liveness detector. Our experiments show that the CNN or ViT models could have at least an 8% equal error rate (EER) increment when encountering adversarial examples. Thus, developing methods other than NNs is worth exploring to improve security at the system level. In this paper, we have proposed a novel solution for FAS against adversarial attacks, leveraging a deep forest model. Our approach introduces a multi-scale texture representation based on local binary patterns (LBP) as the model input, replacing the grained-scanning mechanism (GSM) used in the traditional deep forest model. Unlike GSM, which scans raw pixels and lacks discriminative power, our LBP-based scheme is specifically designed to capture texture features relevant to spoofing detection. Additionally, transforming the input from the RGB space to the LBP space enhances robustness against adversarial noise. Our method achieved competitive results. When testing with adversarial examples, the increment of EER was less than 3%, more robust than CNN and ViT. On the benchmark database IDIAP REPLAY-ATTACK, a 0% EER was achieved. This work provides a competitive option in a fusing scheme for improving system-level security and offers important ideas to those who want to explore methods besides CNNs. To the best of our knowledge, this is the first attempt at exploiting the deep forest model in the problem of FAS, with the consideration of adversarial attacks.

Keywords:

Citation: Rizhao Cai, Liepiao Zhang, Changsheng Chen, Yongjian Hu, Alex Kot. Learning deep forest for face anti-spoofing: An alternative to the neural network against adversarial attacks[J]. Electronic Research Archive, 2024, 32(10): 5592-5614. doi: 10.3934/era.2024259

Related Papers:

[1]	Muajebah Hidan, Abbas Kareem Wanas, Faiz Chaseb Khudher, Gangadharan Murugusundaramoorthy, Mohamed Abdalla . Coefficient bounds for certain families of bi-Bazilevič and bi-Ozaki-close-to-convex functions. AIMS Mathematics, 2024, 9(4): 8134-8147. doi: 10.3934/math.2024395
[2]	Abdulmtalb Hussen, Mohammed S. A. Madi, Abobaker M. M. Abominjil . Bounding coefficients for certain subclasses of bi-univalent functions related to Lucas-Balancing polynomials. AIMS Mathematics, 2024, 9(7): 18034-18047. doi: 10.3934/math.2024879
[3]	Tariq Al-Hawary, Ala Amourah, Abdullah Alsoboh, Osama Ogilat, Irianto Harny, Maslina Darus . Applications of $q-$ Ultraspherical polynomials to bi-univalent functions defined by $q-$ Saigo's fractional integral operators. AIMS Mathematics, 2024, 9(7): 17063-17075. doi: 10.3934/math.2024828
[4]	Abeer O. Badghaish, Abdel Moneim Y. Lashin, Amani Z. Bajamal, Fayzah A. Alshehri . A new subclass of analytic and bi-univalent functions associated with Legendre polynomials. AIMS Mathematics, 2023, 8(10): 23534-23547. doi: 10.3934/math.20231196
[5]	Bilal Khan, H. M. Srivastava, Muhammad Tahir, Maslina Darus, Qazi Zahoor Ahmad, Nazar Khan . Applications of a certain $q$ -integral operator to the subclasses of analytic and bi-univalent functions. AIMS Mathematics, 2021, 6(1): 1024-1039. doi: 10.3934/math.2021061
[6]	Sheza. M. El-Deeb, Gangadharan Murugusundaramoorthy, Kaliyappan Vijaya, Alhanouf Alburaikan . Certain class of bi-univalent functions defined by quantum calculus operator associated with Faber polynomial. AIMS Mathematics, 2022, 7(2): 2989-3005. doi: 10.3934/math.2022165
[7]	Luminiţa-Ioana Cotîrlǎ . New classes of analytic and bi-univalent functions. AIMS Mathematics, 2021, 6(10): 10642-10651. doi: 10.3934/math.2021618
[8]	F. Müge Sakar, Arzu Akgül . Based on a family of bi-univalent functions introduced through the Faber polynomial expansions and Noor integral operator. AIMS Mathematics, 2022, 7(4): 5146-5155. doi: 10.3934/math.2022287
[9]	Norah Saud Almutairi, Adarey Saud Almutairi, Awatef Shahen, Hanan Darwish . Estimates of coefficients for bi-univalent Ma-Minda-type functions associated with $\mathfrak{q}$ -Srivastava-Attiya operator. AIMS Mathematics, 2025, 10(3): 7269-7289. doi: 10.3934/math.2025333
[10]	Tingting Du, Zhengang Wu . Some identities involving the bi-periodic Fibonacci and Lucas polynomials. AIMS Mathematics, 2023, 8(3): 5838-5846. doi: 10.3934/math.2023294

Abstract

1. Introduction and preliminaries

Let $\mathcal{A}$ indicate an analytic functions family, which is normalized under the condition $f$ $(0) =$ $f^{\prime}(0)-1 = 0$ in $\mathbb{U} = \{z:z\in \mathbb{C}$ and $\left \vert z \ \right \vert < 1\}$ and given by the following Taylor-Maclaurin series:

$\begin{equation} f \ (z) = z+\sum \limits_{n = 2}^{\infty}a_{n}z^{n}\ .\ \ \ \ \ \end{equation}$

(1.1)

Further, by $\mathcal{S}$ we shall denote the class of all functions in $\mathcal{A}$ which are univalent in $\mathbb{U}$ .

With a view to recalling the principle of subordination between analytic functions, let the functions $f$ and $g$ be analytic in $\mathbb{U}$ . Then we say that the function $f$ is subordinate to $g$ if there exists a Schwarz function $w\left(z\right)$ , analytic in $\mathbb{U}$ with

$\begin{equation*} \omega \left( 0\right) = 0, \ \left\vert \omega (z)\right\vert < 1, \ \left( z\in \mathbb{U}\right) \end{equation*}$

such that

$\begin{equation*} f \ \left( z\right) = g \ (\omega \left( z\right) ). \end{equation*}$

We denote this subordination by

$\begin{equation*} f\prec g\text{ or}\ f \ (z)\prec g \ (z). \end{equation*}$

In particular, if the function $g$ is univalent in $\mathbb{U}$ , the above subordination is equivalent to

$\begin{equation*} f \ (0) = g \ (0), \ f \ (\mathbb{U})\subset g \ ( \mathbb{U}). \end{equation*}$

The Koebe-One Quarter Theorem ^[11] asserts that image of $\mathbb{U}$ under every univalent function $f\in \mathcal{A}$ contains a disc of radius $\frac{1}{4}.\$ thus every univalent function $f$ has an inverse $\ f^{-1}\$ satisfying $\ f^{-1}(f(z)) = z$ and $f$ $(\ f^{-1}$ $(w)) = w$ $(\left\vert w\right\vert < r$ $_{0}(f$ $), r$ $_{0}(f$ $)$ $> \frac{ 1}{4}$ $)$ , where

$\begin{equation} \ f^{-1}(w) = w-a_{2}w^{2}+(2a_{2}^{2}-a_{3})w^{3}-(5a_{2}^{3}-5a_{2}a_{3}+a_{4})w^{4}+\cdots . \end{equation}$

(1.2)

A function $f\in \mathcal{A}$ is said to be bi-univalent functions in $\mathbb{U}$ if both $f$ and $\ f^{-1}$ are univalent in $\mathbb{U}$ . A function $f\in \mathcal{S}$ is said to be bi-univalent in $\mathbb{U}$ if there exists a function $g\in \mathcal{S}$ such that $g(z)$ is an univalent extension of $f^{-1}$ to $\mathbb{U}$ . Let $\Lambda$ denote the class of bi-univalent functions in $\mathbb{U}$ . The functions $\frac{z}{ 1-z}$ , $-\log (1-z)$ , $\frac{1}{2}\log \left(\frac{1+z}{1-z}\right)$ are in the class $\Lambda$ (see details in ^[20]). However, the familiar Koebe function is not bi-univalent. Lewin ^[17] investigated the class of bi-univalent functions $\Lambda$ and obtained a bound $|a_{2}|\leq 1.51$ . Motivated by the work of Lewin ^[17], Brannan and Clunie ^[9] conjectured that $|a_{2}|\leq \sqrt{2}.$ The coefficient estimate problem for $|a_{n}|\, \, \, \, (n\in \mathbb{N}, \, \, \, \, n\geq 3)$ is still open (^[20]). Brannan and Taha ^[10] also worked on certain subclasses of the bi-univalent function class $\Lambda$ and obtained estimates for their initial coefficients. Various classes of bi-univalent functions were introduced and studied in recent times, the study of bi-univalent functions gained momentum mainly due to the work of Srivastava et al. ^[20]. Motivated by this, many researchers ^[1], ^[4,5,6,7,8], ^[13,14,15], ^[20], ^[21], and ^[27,28,29], also the references cited there in) recently investigated several interesting subclasses of the class $\Lambda$ and found non-sharp estimates on the first two Taylor-Maclaurin coefficients. Recently, many researchers have been exploring bi-univalent functions, few to mention Fibonacci polynomials, Lucas polynomials, Chebyshev polynomials, Pell polynomials, Lucas–Lehmer polynomials, orthogonal polynomials and the other special polynomials and their generalizations are of great importance in a variety of branches such as physics, engineering, architecture, nature, art, number theory, combinatorics and numerical analysis. These polynomials have been studied in several papers from a theoretical point of view (see, for example, ^{[23,24,25,26,27,28,29,30]} also see references therein).

We recall the following results relevant for our study as stated in ^[3].

Let $p(x)$ and $q(x)$ be polynomials with real coefficients. The $(p, q)-$ Lucas polynomials $\mathcal{L}_{p, q, n}(x)$ are defined by the recurrence relation

$\begin{equation*} \mathcal{L}_{p, q, n}(x) = p(x)\mathcal{L}_{p, q, n-1}(x)+q(x)\mathcal{L} _{p, q, n-2}(x)\quad (n\geq 2), \end{equation*}$

from which the first few Lucas polynomials can be found as

$\begin{eqnarray} \mathcal{L}_{p, q, 0}(x) & = &2, \\ \mathcal{L}_{p, q, 1}(x) & = &p(x), \\ \mathcal{L}_{p, q, 2}(x) & = &p^{2}(x)+2q(x), \\ \mathcal{L}_{p, q, 3}(x) & = &p^{3}(x)+3p(x)q(x), ...\text{.} \end{eqnarray}$

(1.3)

For the special cases of $p(x)$ and $q(x),$ we can get the polynomials given $\mathcal{L}_{x, 1, n}(x)\equiv \mathcal{L}_{n}(x)$ Lucas polynomials, $\mathcal{L}_{2x, 1, n}(x)\equiv \mathcal{D}_{n}(x)$ Pell–Lucas polynomials, $\mathcal{L}_{1, 2x, n}(x)\equiv j_{n}(x)$ Jacobsthal–Lucas polynomials, $\mathcal{L}_{3x, -2, n}(x)\equiv F_{n}(x)$ Fermat–Lucas polynomials, $\mathcal{L}_{2x, -1, n}(x)\equiv T_{n}(x)$ Chebyshev polynomials first kind.

Lemma 1.1. ^[16] Let $G\{ \mathcal{L}(x)\}(z)$ be the generating function of the $(p, q)-$ Lucas polynomial sequence $\mathcal{L}_{p, q, n}(x).$ Then,

$\begin{equation*} G\{ \mathcal{L}(x)\}(z) = \sum\limits_{n = 0}^{\infty }\mathcal{L}_{p, q, n}(x)z^{n} = \frac{2-p(x)z}{1-p(x)z-q(x)z^{2}} \end{equation*}$

and

$\begin{equation*} \mathcal{G}_{\{ \mathcal{L}(x)\}}(z) = G\{ \mathcal{L}(x)\}(z)-1 = 1+ \sum\limits_{n = 1}^{\infty }\mathcal{L}_{p, q, n}(x)z^{n} = \frac{1+q(x)z^{2}}{ 1-p(x)z-q(x)z^{2}}. \end{equation*}$

Definition 1.2. ^[22] For $\vartheta \geq 0,$ $\delta \in \mathbb{R},$ $\vartheta +i\delta \neq 0$ and $f\in \mathcal{A}$ , let $\mathcal{B} (\vartheta, \delta)$ denote the class of Bazilevič function if and only if

$\begin{equation*} Re\left[ {\left( {\frac{{z{f^\prime }(z)}}{{f(z)}}} \right){{\left( {\frac{{f(z)}}{z}} \right)}^{\vartheta + i\delta }}} \right] > 0\;. \end{equation*}$

Several authors have researched different subfamilies of the well-known Bazilevič functions of type $\vartheta$ from various viewpoints (see ^[3] and ^[19]). For Bazilevič functions of order $\vartheta +i\delta$ , there is no much work associated with Lucas polynomials in the literature. Initiating an exploration of properties of Lucas polynomials associated with Bazilevič functions of order $\vartheta +i\delta$ is the main goal of this paper. To do so, we take into account the following definitions. In this paper motivated by the very recent work of Altinkaya and Yalcin ^[3] (also see ^[18]) we define a new class $\mathcal{B}(\vartheta, \delta)$ , bi-Bazilevič function of $\Lambda$ based on $(p, q)-$ Lucas polynomials as below:

Definition 1.3. For $f\in \Lambda$ , $\vartheta \geq0,$ $\delta \in \mathbb{R},$ $\vartheta+i\delta \neq0$ and let $\mathcal{B}(\vartheta, \delta)$ denote the class of Bi-Bazilevič functions of order $t\ \$ and type $\vartheta+i\delta$ if only if

$\begin{equation} \left[ \left( \frac{zf^{\prime}(z)}{f(z)}\right) \left( \frac{f(z)}{z} \right) ^{\vartheta+i\delta}\right] \prec \mathcal{G}_{\{ \mathcal{L} (x)\}}(z)\quad (z\in \mathbb{U}) \end{equation}$

(1.4)

and

$\begin{equation} \left[ \left( \frac{zg^{\prime}(w)}{g(w)}\right) \left( \frac{g(w)}{w}% \right) ^{\vartheta+i\delta}\right] \prec \mathcal{G}_{\{ \mathcal{L}% (x)\}}(w)\quad (w\in \mathbb{U}), \label{ieq4} \end{equation}$

(1.5)

where $\mathcal{G}_{\mathcal{L}_{p, q, n}} (z) \in \Phi$ and the function $g$ is described as $g(w) = f^{-1}(w).$

Remark 1.4. We note that for $\delta = 0$ the class $R(\vartheta, 0) = R(\vartheta)$ is defined by Altinkaya and Yalcin ^[2].

The class $\mathcal{B}(0, 0) = \mathcal{S}_\Lambda^*$ is defined as follows:

Definition 1.5. A function $f\in \Lambda$ is said to be in the class $\mathcal{S }_\Lambda^*$ , if the following subordinations hold

$\begin{equation*} \frac{zf^{\prime}(z)}{f(z)}\prec \mathcal{G}_{\{ \mathcal{L}(x)\}}(z)(z\in \mathbb{U}) \end{equation*}$

and

$\begin{equation*} \frac{wg^{\prime }(w)}{g(w)}\prec \mathcal{G}_{\{ \mathcal{L}(x)\}}(w)(w\in \mathbb{U}) \end{equation*}$

where $g(w) = f^{-1}(w).$

We begin this section by finding the estimates of the coefficients $|a_{2}|$ and $|a_{3}|$ for functions in the class $\mathcal{B}(\vartheta, \delta)$ .

2. Coefficient bounds for the function class $\mathcal{B}(\vartheta, \delta)$

Theorem 2.1. Let the function $f(z)$ given by 1.1 be in the class $\mathcal{B}(\vartheta, \delta)$ . Then

$\begin{equation*} \left \vert a_{2}\right \vert \leq \frac{p(x)\sqrt {2p(x)}}{ \sqrt{\vert \{ \left( \left( \vartheta +i\delta \right) ^{2}+3\left( \vartheta +i\delta \right) +2\right)-2\left( \vartheta +i\delta +1\right) ^{2}\}p^2(x)-4q(x)\left( \vartheta +i\delta +1\right) ^{2} \vert }}. \end{equation*}$

and

$\begin{equation*} \left \vert a_{3}\right \vert \leq \frac{p^{2}(x)}{(\vartheta +1)^2+ \delta^2 } +\frac{p(x)}{\sqrt {(\vartheta +2)^2+ \delta^2} } . \end{equation*}$

Proof. Let $f\in \mathcal{B}(\vartheta, \delta, x)$ there exist two analytic functions $u, v:\mathbb{U}\rightarrow \mathbb{U}$ with $u(0) = 0 = v(0)$ , such that $|u(z)| < 1$ , $|v(w)| < 1,$ we can write from (1.4) and (1.5), we have

$\begin{equation} \left[ \left( \frac{zf^{\prime }(z)}{f(z)}\right) \left( \frac{f(z)}{z} \right) ^{\vartheta +i\delta }\right] = \mathcal{G}_{\{ \mathcal{L} (x)\}}(z)\quad (z\in \mathbb{U}) \quad \end{equation}$

(2.1)

and

$\begin{equation} \left[ \left( \frac{zg^{\prime}(w)}{g(w)}\right) \left( \frac{g(w)}{w} \right) ^{\vartheta+i\delta}\right] = \mathcal{G}_{\{ \mathcal{L} (x)\}}(w)\quad (w\in \mathbb{U}), \end{equation}$

(2.2)

It is fairly well known that if

$\begin{equation*} |u(z)| = |u_{1}z+u_{2}z^{2}+\cdots | < 1 \end{equation*}$

and

$\begin{equation*} |v(w)| = |v_{1}w+v_{2}w^{2}+\cdots | < 1. \end{equation*}$

then

$\begin{equation*} |u_{k}|\leq 1\qquad and\qquad |v_{k}|\leq 1\quad (k\in \mathbb{N}) \end{equation*}$

It follows that, so we have

$\begin{eqnarray} \mathcal{G}_{\{ \mathcal{L}(x)\}}(u(z)) & = &1+\mathcal{L}_{p, q, 1}(x)u(z)+ \mathcal{L}_{p, q, 2}(x)u^{2}(z)+\ldots \\ & = &1+\mathcal{L}_{p, q, 1}(x)u_{1}z+[\mathcal{L}_{p, q, 1}(x)u_{2}+\mathcal{L} _{p, q, 2}(x)u_{1}^{2}]z^{2}+\ldots \end{eqnarray}$

(2.3)

and

$\begin{eqnarray} \mathcal{G}_{\{ \mathcal{L}(x)\}}(v(w)) & = &1+\mathcal{L}_{p, q, 1}(x)v(w)+ \mathcal{L}_{p, q, 2}(x)v^{2}(w)+\ldots \\ & = &1+\mathcal{L}_{p, q, 1}(x)v_{1}w+[\mathcal{L}_{p, q, 1}(x)v_{2}+\mathcal{L} _{p, q, 2}(x)v_{1}^{2}]w^{2}+\ldots \end{eqnarray}$

(2.4)

From the equalities (2.1) and (2.2), we obtain that

$\begin{equation} \left[ \left( \frac{zf^{\prime }(z)}{f(z)}\right) \left( \frac{f(z)}{z} \right) ^{\vartheta +i\delta }\right] = 1+\mathcal{L}_{p, q, 1}(x)u_{1}z+[ \mathcal{L}_{p, q, 1}(x)u_{2}+\mathcal{L}_{p, q, 2}(x)u_{1}^{2}]z^{2}+\ldots, \end{equation}$

(2.5)

and

$\begin{equation} \left[ \left( \frac{zg^{\prime}(w)}{g(w)}\right) \left( \frac{g(w)}{w} \right) ^{\vartheta+i\delta}\right] = 1+\mathcal{L}_{p, q, 1}(x)v_{1}w+[ \mathcal{L}_{p, q, 1}(x)v_{2}+\mathcal{L}_{p, q, 2}(x)v_{1}^{2}]w^{2}+\ldots, \end{equation}$

(2.6)

It follows from (2.5) and (2.6) that

$\begin{equation} \left( \vartheta +i\delta +1\right) a_{2} = \mathcal{L}_{p, q, 1}(x)u_1, , \end{equation}$

(2.7)

$\begin{equation} \frac{\left( \vartheta +i\delta -1\right) \left( \vartheta +i\delta +2\right) }{2}a_{2}^{2}-\left( \vartheta +i\delta +2\right) a_3 = \mathcal{L} _{p, q, 1}(x)u_2+\mathcal{L}_{p, q, 2}(x)u_1^2, \end{equation}$

(2.8)

and

$\begin{equation} -\left( \vartheta+i\delta+1\right) a_{2} = \mathcal{L}_{p, q, 1}(x)v_1, \end{equation}$

(2.9)

$\begin{equation} \frac{\left( \vartheta+i\delta+2\right) \left( \vartheta+i\delta+3\right) }{2 }a_{2}^{2}+\left( \vartheta+i\delta+2\right) a_3 = \mathcal{L}_{p, q, 1}(x)v_2+ \mathcal{L}_{p, q, 2}(x)v_1^2, \end{equation}$

(2.10)

From (2.7) and (2.9)

$\begin{equation} u_{1} = -v_{1} \end{equation}$

(2.11)

and

$\begin{equation} 2\left( \vartheta+i\delta+1\right) ^{2}a_{2}^{2} = \mathcal{L} _{p, q, 1}^{2}(x)(u_{1}^{2}+v_{1}^{2})., \end{equation}$

(2.12)

by adding (2.8) to (2.10), we get

$\begin{equation} \left( \left( \vartheta +i\delta \right) ^{2}+3\left( \vartheta +i\delta \right) +2\right) a_{2}^{2} = \mathcal{L}_{p, q, 1}(x)(u_{2}+v_{2})+\mathcal{L} _{p, q, 2}(x)(u_{1}^{2}+v_{1}^{2}), \end{equation}$

(2.13)

by using (2.12) in equality (2.13), we have

$\begin{eqnarray} \left[ \left( \left( \vartheta +i\delta \right) ^{2}+3\left( \vartheta +i\delta \right) +2\right) -\frac{2\mathcal{L}_{p, q, 2}(x)\left( \vartheta +i\delta +1\right) ^{2}}{\mathcal{L}^{2}_{p, q, 1}(x)}\right] a_{2}^{2}& = & \mathcal{L}_{p, q, 1}(x)(u_{2}+v_{2}), \end{eqnarray}$

$\begin{eqnarray} a_{2}^{2}& = &\frac{\mathcal{L}^3_{p, q, 1}(x)(u_{2}+v_{2})} {\left[ \left( \left( \vartheta +i\delta \right) ^{2}+3\left( \vartheta +i\delta \right) +2\right)\mathcal{L}^{2}_{p, q, 1}(x)-2\mathcal{L}_{p, q, 2}(x)\left( \vartheta +i\delta +1\right) ^{2}\right]}. \end{eqnarray}$

(2.14)

Thus, from (1.3) and (2.14) we get

$\begin{equation*} \left \vert a_{2}\right \vert \leq \frac{p(x)\sqrt {2p(x)}}{\sqrt{\vert \{ \left( \left( \vartheta +i\delta \right) ^{2}+3\left( \vartheta +i\delta \right) +2\right)-2\left( \vartheta +i\delta +1\right) ^{2}\}p^2(x)-4q(x)\left( \vartheta +i\delta +1\right) ^{2} \vert }}. \end{equation*}$

Next, in order to find the bound on $|a_{3}|$ , by subtracting (2.10) from (2.8), we obtain

$\begin{eqnarray} 2\left( \vartheta +i\delta +2\right) a_{3}-2\left( \vartheta +i\delta +2\right) a_{2}^{2}& = &\mathcal{L}_{p, q, 1}(x)(u_{2}-v_{2})+\mathcal{L} _{p, q, 2}(x)(u_{1}^{2}-v_{1}^{2}) \\ 2\left( \vartheta +i\delta +2\right) a_{3}& = &\mathcal{L} _{p, q, 1}(x)(u_{2}-v_{2})+2\left( \vartheta +i\delta +2\right) a_{2}^{2} \\ a_{3}& = &\frac{\mathcal{L}_{p, q, 1}(x)(u_{2}-v_{2})}{2\left( \vartheta +i\delta +2\right)}+a_{2}^{2} \end{eqnarray}$

(2.15)

Then, in view of (2.11) and (2.12), we have from (2.15)

$\begin{equation*} a_{3} = \frac{\mathcal{L}_{p, q, 1}^{2}(x)}{2\left( \vartheta +i\delta +2\right) ^{2}}(u_{1}^{2}+v_{1}^{2})+\frac{\mathcal{L}_{p, q, 1}(x)}{2\left( \vartheta +i\delta +2\right) }(u_{2}-v_{2}). \end{equation*}$

$\begin{eqnarray*} |a_{3}|&\leq&\frac{p^{2}(x)}{\left|\vartheta +i\delta +1\right| ^{2}}+\frac{ p(x)}{|\vartheta +i\delta +2| } \notag \\ & = &\frac{p^{2}(x)}{(\vartheta +1)^2+ \delta^2 } +\frac{p(x)}{\sqrt { (\vartheta +2)^2+ \delta^2} } \end{eqnarray*}$

This completes the proof.

Taking $\delta = 0,$ in Theorem 2.1, we get the following corollary.

Corollary 2.2. Let the function $f(z)$ given by (1.1) be in the class $\mathcal{B} (\vartheta)$ . Then

$\begin{equation*} \left \vert a_{2}\right \vert \leq \frac{p(x)\sqrt {2p(x)}}{\sqrt{\vert \{ \left( \vartheta ^{2}+3\vartheta +2\right)-2\left( \vartheta+1\right) ^{2}\}p^2(x)-4q(x)\left( \vartheta +1\right) ^{2} \vert }} \end{equation*}$

and

$\begin{equation*} \left \vert a_{3}\right \vert \leq \frac{p^{2}(x)}{(\vartheta +2)^2} +\frac{ p(x)}{\vartheta +2} \end{equation*}$

Also, taking $\vartheta = 0$ and $\delta = 0,$ in Theorem 2.1, we get the results given in ^[18].

3. Fekete-Szegö inequality for the class $\mathcal{B}(\vartheta, \delta)$

Fekete-Szegö inequality is one of the famous problems related to coefficients of univalent analytic functions. It was first given by ^[12], the classical Fekete-Szegö inequality for the coefficients of $f\in \mathcal{S}$ is

$\begin{equation*} \left \vert a_{3}-\mu a_{2}^{2}\right \vert \leq1+2\exp \left( -2\mu /(1-\mu)\right) \text{ for }\mu \in \left[ 0, 1\right) . \end{equation*}$

As ${\mu} \rightarrow1^{-}$ , we have the elementary inequality $\left \vert a_{3}-a_{2}^{2}\right \vert \leq1$ . Moreover, the coefficient functional

$\begin{equation*} \varsigma_{\mu}(f) = a_{3}-\mu a_{2}^{2} \end{equation*}$

on the normalized analytic functions $f$ in the unit disk $\mathbb{U}$ plays an important role in function theory. The problem of maximizing the absolute value of the functional $\varsigma {\mu} (f)$ is called the Fekete-Szegö problem.

In this section, we are ready to find the sharp bounds of Fekete-Szegö functional $\varsigma _{\mu }(f)$ defined for $f\in \mathcal{B}(\vartheta, \delta)$ given by (1.1).

Theorem 3.1. Let f given by (1.1) be in the class $\mathcal{B} (\vartheta, \delta)$ and ${\mu} \in \mathbb{R}$ . Then

$\begin{equation*} \left \vert a_{3}- {\mu} a_{2}^{2}\right \vert \leq \left \{ \begin{array}{c} \frac{p(x)}{\sqrt{(\vartheta+2)^{2}+\delta ^{2}}}, \ \ \ \ \ \ \ \ 0\leq \left \vert h(\mu )\right \vert \leq \frac{1}{2\sqrt{ (\vartheta+2)^{2}+\delta ^{2}}} \\ 2p(x)\left \vert h(\mu )\right \vert , \ \ \ \ \ \ \ \ \ \ \ \ \ \left \vert h(\mu )\right \vert \geq \frac{1}{2\sqrt{(\vartheta+2)^{2}+ \delta ^{2}}} \end{array} \right. \end{equation*}$

where

$\begin{equation*} h(\mu) = \frac{\mathcal{L}^2_{p, q, 1}(x)(1-\mu)}{\left( \left( \vartheta +i\delta \right) ^{2}+3\left( \vartheta +i\delta \right) +2\right)\mathcal{L} ^{2}_{p, q, 1}(x)-2\mathcal{L}_{p, q, 2}(x)\left( \vartheta +i\delta +1\right) ^{2}}. \end{equation*}$

Proof. From (2.14) and (2.15), we conclude that

$\begin{eqnarray*} a_{3}- {\mu} a_{2}^{2}& = &(1-\mu )\frac{\mathcal{L}^3_{p, q, 1}(x)(u_{2}+v_{2})} {\left[ \left( \left( \vartheta +i\delta \right) ^{2}+3\left( \vartheta +i\delta \right) +2\right)\mathcal{L}^{2}_{p, q, 1}(x)-2\mathcal{L}_{p, q, 2}(x)\left( \vartheta +i\delta +1\right) ^{2}\right]} \\ &+&\frac{\mathcal{L}_{p, q, 1}(x)}{2\left( \vartheta +i\delta +2\right) } (u_{2}-v_{2}) \end{eqnarray*}$

$\begin{eqnarray*} = \mathcal{L}_{p, q, 1}(x)\left[ \left( h(\mu )+\frac{1}{2(\vartheta +i\delta +2)}\right) u_{2}+\left( h(\mu )-\frac{1}{2(\vartheta +i\delta +2)}\right) v_{2}\right] \end{eqnarray*}$

where

Then, in view of (1.3), we obtain

We end this section with some corollaries.

Taking ${\mu} = 1$ in Theorem 3.1, we get the following corollary.

Corollary 3.2. If $f\in \mathcal{B}(\vartheta, \delta)$ , then

$\begin{equation*} \left \vert a_{3}-a_{2}^{2}\right \vert \leq \frac{p(x)}{\sqrt{ (\vartheta+2)^{2}+\delta ^{2}}}. \end{equation*}$

Taking $\delta = 0$ in Theorem 3.1, we get the following corollary.

Corollary 3.3. Let $f$ given by (1.1) be in the class $\mathcal{B}(\vartheta, 0)$ . Then

$\begin{equation*} \left \vert a_{3}- {\mu} a_{2}^{2}\right \vert \leq \left \{ \begin{array}{c} \frac{p(x)}{\vartheta+2}, \ \ \ \ \ \ \ \ 0\leq \left \vert h(\mu )\right \vert \leq \frac{1}{2(\vartheta+2)} \\ 2p(x)\left \vert h(\mu )\right \vert , \ \ \ \ \ \ \ \ \ \ \ \ \ \left \vert h(\mu )\right \vert \geq \frac{1}{2(\vartheta+2)} \end{array} \right. \end{equation*}$

Also, taking $\vartheta = 0,$ $\delta = 0$ and ${\mu} = 1$ in Theorem 3.1, we get the following corollary.

Corollary 3.4. Let $f$ given by (1.1) be in the class $\mathcal{B}$ . Then

$\begin{equation*} \left| {{a_3} - a_2^2} \right| \le \frac{{p(x)}}{2}. \end{equation*}$

Conflict of interest

All authors declare no conflicts of interest in this paper.

References

[1]	K. Patel, H. Han, A. K. Jain, Secure face unlock: Spoof detection on smartphones, IEEE Trans. Inf. Forensics Secur., 11 (2016), 2268–2283. https://doi.org/10.1109/TIFS.2016.2578288 doi: 10.1109/TIFS.2016.2578288
[2]	A. Krizhevsky, I. Sutskever, G. E. Hinton, ImageNet classification with deep convolutional neural networks, Commun. ACM, 60 (2017), 84–90. https://doi.org/10.1145/3065386 doi: 10.1145/3065386
[3]	Y. Sun, Y. Chen, X. Wang, X. Tang, Deep learning face representation by joint identification-verification, in Proceedings of the 27th International Conference on Neural Information Processing Systems, 2 (2014), 1988–1996.
[4]	A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, et al., An image is worth 16 $\times$ 16 words: Transformers for image recognition at scale, preprint, arXiv: 2010.11929.
[5]	Z. Liu, Y. Lin, Y. Cao, H. Hu, Y. Wei, Z. Zhang, et al., Swin transformer: Hierarchical vision transformer using shifted windows, in 2021 IEEE/CVF International Conference on Computer Vision (ICCV), (2021), 9992–10002. https://doi.org/10.1109/ICCV48922.2021.00986
[6]	J. Yang, Z. Lei, S. Z. Li, Learn convolutional neural network for face anti-spoofing, preprint, arXiv: 1408.5601.
[7]	Z. Xu, S. Li, W. Deng, Learning temporal features using LSTM-CNN architecture for face anti-spoofing, in 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR), (2016), 141–145. https://doi.org/10.1109/ACPR.2015.7486482
[8]	Z. Yu, C. Zhao, Z. Wang, Y. Qin, Z. Su, X. Li, et al., Searching central difference convolutional networks for face anti-spoofing, in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2020), 5294–5304. https://doi.org/10.1109/CVPR42600.2020.00534
[9]	R. Cai, Z. Li, R. Wan, H. Li, Y. Hu, A. C. Kot, Learning meta pattern for face anti-spoofing, IEEE Trans. Inf. Forensics Secur., 17 (2022), 1201–1213. https://doi.org/10.1109/TIFS.2022.3158551 doi: 10.1109/TIFS.2022.3158551
[10]	R. Cai, Z. Yu, C. Kong, H. Li, C. Chen, Y. Hu, et al., S-adapter: Generalizing vision transformer for face anti-spoofing with statistical tokens, IEEE Trans. Inf. Forensics Secur., 19 (2024), 8385–8397. https://doi.org/10.1109/TIFS.2024.3420699 doi: 10.1109/TIFS.2024.3420699
[11]	R. Cai, Y. Cui, Z. Li, Z. Yu, H. Li, Y. Hu, et al., Rehearsal-free domain continual face anti-spoofing: Generalize more and forget less, in 2023 IEEE/CVF International Conference on Computer Vision (ICCV), (2023), 8003–8014. https://doi.org/10.1109/ICCV51070.2023.00738
[12]	A. Liu, Z. Tan, Z. Yu, C. Zhao, J. Wan, Y. Liang, et al., FM-ViT: Flexible modal vision transformers for face anti-spoofing, IEEE Trans. Inf. Forensics Secur., 18 (2023), 4775–4786. https://doi.org/10.1109/TIFS.2023.3296330 doi: 10.1109/TIFS.2023.3296330
[13]	C. Szegedy, W. Zaremba, I. Sutskever, J. Bruna, D. Erhan, I. J. Goodfellow, et al., Intriguing properties of neural networks, preprint, arXiv: 1312.6199.
[14]	A. Aldahdooh, W. Hamidouche, O. Deforges, Reveal of vision transformers robustness against adversarial attacks, preprint, arXiv: 2106.03734.
[15]	A. Kurakin, I. J. Goodfellow, S. Bengio, Adversarial examples in the physical world, preprint, arXiv: 1607.02533.
[16]	K. Eykholt, I. Evtimov, E. Fernandes, B. Li, A. Rahmati, C. Xiao, et al., Robust physical-world attacks on deep learning visual classification, in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2018), 1625–1634. https://doi.org/10.1109/CVPR.2018.00175
[17]	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
[18]	Y. Liu, X. Chen, C. Liu, D. Song, Delving into transferable adversarial examples and black-box attacks, preprint, arXiv: 1611.02770.
[19]	W. Ma, Y. Li, X. Jia, W. Xu, Transferable adversarial attack for both vision transformers and convolutional networks via momentum integrated gradients, in 2023 IEEE/CVF International Conference on Computer Vision (ICCV), (2023), 4607–4616. https://doi.org/10.1109/ICCV51070.2023.00427
[20]	P. Russu, A. Demontis, B. Biggio, G. Fumera, F. Roli, Secure kernel machines against evasion attacks, in Proceedings of the 2016 ACM workshop on artificial intelligence and security, (2016), 59–69. https://doi.org/10.1145/2996758.2996771
[21]	F. Tramèr, N. Papernot, I. Goodfellow, D. Boneh, P. McDaniel, The space of transferable adversarial examples, preprint, arXiv: 1704.03453.
[22]	F. Yang, Z. Chen, Using randomness to improve robustness of machine-learning models against evasion attacks, preprint, arXiv: 1808.03601.
[23]	Z. Zhou, J. Feng, Deep forest: Towards an alternative to deep neural networks, in Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, (2017), 3553–3559. https://doi.org/10.24963/ijcai.2017/497
[24]	J. Maatta, A. Hadid, M. Pietikäinen, Face spoofing detection from single images using micro-texture analysis, in 2011 International Joint Conference on Biometrics (IJCB), (2011), 1–7. https://doi.org/10.1109/IJCB.2011.6117510
[25]	J. Yang, Z. Lei, S. Liao, S. Z. Li, Face liveness detection with component dependent descriptor, in 2013 International Conference on Biometrics (ICB), (2013), 1–6. https://doi.org/10.1109/ICB.2013.6612955
[26]	R. Nosaka, Y. Ohkawa, K. Fukui, Feature extraction based on co-occurrence of adjacent local binary patterns, in Advances in Image and Video Technology, 7088 (2011), 82–91. https://doi.org/10.1007/978-3-642-25346-1_8
[27]	I. Chingovska, A. Anjos, S. Marcel, On the effectiveness of local binary patterns in face anti-spoofing, in 2012 BIOSIG-Proceedings of the International Conference of Biometrics Special Interest Group (BIOSIG), (2012), 1–7.
[28]	Y. Atoum, Y. Liu, A. Jourabloo, X. Liu, Face anti-spoofing using patch and depth-based CNNs, in 2017 IEEE International Joint Conference on Biometrics (IJCB), (2017), 319–328. https://doi.org/10.1109/BTAS.2017.8272713
[29]	X. Tan, Y. Li, J. Liu, L. Jiang, Face liveness detection from a single image with sparse low rank bilinear discriminative model, in Computer Vision-ECCV 2010, 6316 (2010), 504–517. https://doi.org/10.1007/978-3-642-15567-3_37
[30]	D. Gragnaniello, G. Poggi, C. Sansone, L. Verdoliva, An investigation of local descriptors for biometric spoofing detection, IEEE Trans. Inf. Forensics Secur., 10 (2015), 849–863. https://doi.org/10.1109/TIFS.2015.2404294 doi: 10.1109/TIFS.2015.2404294
[31]	Z. Boulkenafet, J. Komulainen, A. Hadid, Face antispoofing using speeded-up robust features and fisher vector encoding, IEEE Signal Process. Lett., 24 (2017), 141–145. https://doi.org/10.1109/LSP.2016.2630740 doi: 10.1109/LSP.2016.2630740
[32]	T. D. F. Pereira, A. Anjos, J. M. D. Martino, S. Marcel, LBP-TOP based countermeasure against face spoofing attacks, in Computer Vision-ACCV 2012 Workshops, 7728 (2012), 121–132. https://doi.org/10.1007/978-3-642-37410-4_11
[33]	S. R. Arashloo, J. Kittler, W. Christmas, Face spoofing detection based on multiple descriptor fusion using multiscale dynamic binarized statistical image features, IEEE Trans. Inf. Forensics Secur., 10 (2015), 2396–2407. https://doi.org/10.1109/TIFS.2015.2458700 doi: 10.1109/TIFS.2015.2458700
[34]	Z. Boulkenafet, J. Komulainen, A. Hadid, Face spoofing detection using colour texture analysis, IEEE Trans. Inf. Forensics Secur., 11 (2016), 1818–1830. https://doi.org/10.1109/TIFS.2016.2555286 doi: 10.1109/TIFS.2016.2555286
[35]	D. Menotti, G. Chiachia, A. Pinto, W. R. Schwartz, H. Pedrini, A. X. Falcão, et al., Deep representations for iris, face, and fingerprint spoofing detection, IEEE Trans. Inf. Forensics Secur., 10 (2015), 864–879. https://doi.org/10.1109/TIFS.2015.2398817 doi: 10.1109/TIFS.2015.2398817
[36]	H. Li, P. He, S. Wang, A. Rocha, X. Jiang, A. C. Kot, Learning generalized deep feature representation for face anti-spoofing, IEEE Trans. Inf. Forensics Secur., 13 (2018), 2639–2652. https://doi.org/10.1109/TIFS.2018.2825949 doi: 10.1109/TIFS.2018.2825949
[37]	R. Cai, H. Li, S. Wang, C. Chen, A. C. Kot, DRL-FAS: A novel framework based on deep reinforcement learning for face anti-spoofing, IEEE Trans. Inf. Forensics Secur., 16 (2020), 937–951. https://doi.org/10.1109/TIFS.2020.3026553 doi: 10.1109/TIFS.2020.3026553
[38]	W. Sun, Y. Song, C. Chen, J. Huang, A. C. Kot, Face spoofing detection based on local ternary label supervision in fully convolutional networks, IEEE Trans. Inf. Forensics Secur., 15 (2020), 3181–3196. https://doi.org/10.1109/TIFS.2020.2985530 doi: 10.1109/TIFS.2020.2985530
[39]	A. George, S. Marcel, Deep pixel-wise binary supervision for face presentation attack detection, preprint, arXiv: 1907.04047.
[40]	Z. Yu, X. Li, J. Shi, Z. Xia, G. Zhao, Revisiting pixel-wise supervision for face anti-spoofing, IEEE Trans. Biom. Behav. Identity Sci., 3 (2021), 285–295. https://doi.org/10.1109/TBIOM.2021.3065526 doi: 10.1109/TBIOM.2021.3065526
[41]	R. Shao, X. Lan, J. Li, P. C. Yuen, Multi-adversarial discriminative deep domain generalization for face presentation attack detection, in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2019), 10015–10023. https://doi.org/10.1109/CVPR.2019.01026
[42]	Y. Qin, Z. Yu, L. Yan, Z. Wang, C. Zhao, Z. Lei, Meta-teacher for face anti-spoofing, IEEE Trans. Pattern Anal. Mach. Intell., 44 (2022), 6311–6326. https://doi.org/10.1109/TPAMI.2021.3091167 doi: 10.1109/TPAMI.2021.3091167
[43]	Z. Yu, J. Wan, Y. Qin, X. Li, S. Z. Li, G. Zhao, NAS-FAS: Static-dynamic central difference network search for face anti-spoofing, IEEE Trans. Pattern Anal. Mach. Intell., 43 (2021), 3005–3023. https://doi.org/10.1109/tpami.2020.3036338 doi: 10.1109/tpami.2020.3036338
[44]	Y. Liu, J. Stehouwer, X. Liu, On disentangling spoof trace for generic face anti-spoofing, in Computer Vision-ECCV 2020, 12363 (2020), 406–422. https://doi.org/10.1007/978-3-030-58523-5_24
[45]	K. Zhang, T. Yao, J. Zhang, Y. Tai, S. Ding, J. Li, et al., Face anti-spoofing via disentangled representation learning, in Computer Vision-ECCV 2020, 12364 (2020), 641–657. https://doi.org/10.1007/978-3-030-58529-7_38
[46]	H. Wu, D. Zeng, Y. Hu, H. Shi, T. Mei, Dual spoof disentanglement generation for face anti-spoofing with depth uncertainty learning, IEEE Trans. Circuits Syst. Video Technol., 32 (2022), 4626–4638. https://doi.org/10.1109/TCSVT.2021.3133620 doi: 10.1109/TCSVT.2021.3133620
[47]	W. Yan, Y. Zeng, H. Hu, Domain adversarial disentanglement network with cross-domain synthesis for generalized face anti-spoofing, IEEE Trans. Circuits Syst. Video Technol., 32 (2022), 7033–7046. https://doi.org/10.1109/TCSVT.2022.3178723 doi: 10.1109/TCSVT.2022.3178723
[48]	Y. Jia, J. Zhang, S. Shan, X. Chen, Single-side domain generalization for face anti-spoofing, in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2020), 8481–8490. https://doi.org/10.1109/CVPR42600.2020.00851
[49]	Z. Wang, Z. Wang, Z. Yu, W. Deng, J. Li, T. Gao, et al., Domain Generalization via Shuffled Style Assembly for Face Anti-Spoofing, in 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2022), 4113–4123. https://doi.org/10.1109/CVPR52688.2022.00409
[50]	A. Liu, C. Zhao, Z. Yu, J. Wan, A. Su, X. Liu, et al., Contrastive context-aware learning for 3D high-fidelity mask face presentation attack detection, IEEE Trans. Inf. Forensics Secur., 17 (2022), 2497–2507. https://doi.org/10.1109/TIFS.2022.3188149 doi: 10.1109/TIFS.2022.3188149
[51]	A. George, S. Marcel, Learning one class representations for face presentation attack detection using multi-channel convolutional neural networks, IEEE Trans. Inf. Forensics Secur., 16 (2020), 361–375. https://doi.org/10.1109/TIFS.2020.3013214 doi: 10.1109/TIFS.2020.3013214
[52]	H. Li, W. Li, H. Cao, S. Wang, F. Huang, A. C. Kot, Unsupervised Domain Adaptation for Face Anti-Spoofing, IEEE Trans. Inf. Forensics Secur., 13 (2018), 1794–1809. https://doi.org/10.1109/TIFS.2018.2801312 doi: 10.1109/TIFS.2018.2801312
[53]	Y. Liu, Y. Chen, W. Dai, M. Gou, C. Huang, H. Xiong, Source-free domain adaptation with contrastive domain alignment and self-supervised exploration for face anti-spoofing, in Computer Vision-ECCV 2022, 13672 (2022), 511–528. https://doi.org/10.1007/978-3-031-19775-8_30
[54]	Y. Qin, C. Zhao, X. Zhu, Z. Wang, Z. Yu, T. Fu, et al., Learning meta model for zero-and few-shot face anti-spoofing, in Proceedings of the AAAI Conference on Artificial Intelligence, 34 (2020), 11916–11923. https://doi.org/10.1609/aaai.v34i07.6866
[55]	H. Huang, D. Sun, Y. Liu, W. Chu, T. Xiao, J. Yuan, et al., Adaptive transformers for robust few-shot cross-domain face anti-spoofing, in Computer Vision-ECCV 2022, 13673 (2022), 37–54. https://doi.org/10.1007/978-3-031-19778-9_3
[56]	L. Li, X. Feng, Z. Xia, X. Jiang, A. Hadid, Face spoofing detection with local binary pattern network, J. Visual Commun. Image Representation, 54 (2018), 182–192. https://doi.org/10.1016/j.jvcir.2018.05.009 doi: 10.1016/j.jvcir.2018.05.009
[57]	A. Roohi, S. Angizi, Efficient targeted bit-flip attack against the local binary pattern network, in 2022 IEEE International Symposium on Hardware Oriented Security and Trust (HOST), (2022), 89–92. https://doi.org/10.1109/HOST54066.2022.9839959
[58]	N. Bousnina, L. Zheng, M. Mikram, S. Ghouzali, K. Minaoui, Unraveling robustness of deep face anti-spoofing models against pixel attacks, Multimedia Tools Appl., 80 (2021), 7229–7246. https://doi.org/10.1007/s11042-020-10041-1 doi: 10.1007/s11042-020-10041-1
[59]	D. Deb, X. Liu, A. K. Jain, Unified detection of digital and physical face attacks, in 2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG), (2023) 1–8. https://doi.org/10.1109/FG57933.2023.10042500
[60]	T. K. Ho, The random subspace method for constructing decision forests, IEEE Trans. Pattern Anal. Mach. Intell., 20 (1998), 832–844. https://doi.org/10.1109/34.709601 doi: 10.1109/34.709601
[61]	L. Breiman, Random forest, Mach. Learn., 45 (2001), 5–32. https://doi.org/10.1023/A: 1010933404324
[62]	F. T. Liu, M. T. Kai, Y. Yu, Z. Zhou, Spectrum of variable-random trees, J. Artif. Intell. Res., 32 (2008), 355–384.
[63]	T. Chen, C. Guestrin, XGBoost: A scalable tree boosting system, preprint, arXiv: 1603.02754.
[64]	T. Ojala, M. Pietikainen, T. Maenpaa, Multiresolution gray-scale and rotation invariant texture classification with local binary patterns, IEEE Trans. Pattern Anal. Mach. Intell., 24 (2002), 971–987. https://doi.org/10.1109/TPAMI.2002.1017623 doi: 10.1109/TPAMI.2002.1017623
[65]	Z. Zhang, J. Yan, S. Liu, Z. Lei, D. Yi, S. Z. Li, A face antispoofing database with diverse attacks, in 2012 5th IAPR International Conference on Biometrics (ICB), (2012), 26–31. https://doi.org/10.1109/ICB.2012.6199754
[66]	P. Viola, M. Jones, Rapid object detection using a casacde of simple features, in Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, (2001). https://doi.org/10.1109/CVPR.2001.990517
[67]	K. Simonyan, A. Zisserman, Very deep convolutional networks for large-scale image recognition, preprint, arXiv: 1409.1556.
[68]	K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2016), 770–778, . https://doi.org/10.1109/CVPR.2016.90
[69]	I. J. Goodfellow, J. Shlens, C. Szegedy, Explaining and harnessing adversarial examples, preprint, arXiv: 1412.6572.
[70]	Z. Sun, L. Sun, Q. Li, Investigation in spatial-temporal domain for face spoof detection, in 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), (2018), 1538–1542. https://doi.org/10.1109/ICASSP.2018.8461942
[71]	T. M. Oshiro, P. S. Perez, J. A. Baranauskas, How many trees in a random forest? in Machine Learning and Data Mining in Pattern Recognition, 7376 (2012), 154–168. https://doi.org/10.1007/978-3-642-31537-4_13
[72]	J. Lu, V. E. Liong, J. Zhou, Cost-sensitive local binary feature learning for facial age estimation, IEEE Trans. Image Process., 24 (2015), 5356–5368. https://doi.org/10.1109/TIP.2015.2481327 doi: 10.1109/TIP.2015.2481327
[73]	J. Lu, V. E. Liong, J. Zhou, Deep hashing for scalable image search, IEEE Trans. Image Process., 26 (2017), 2352–2367. https://doi.org/10.1109/TIP.2017.2678163 doi: 10.1109/TIP.2017.2678163
[74]	J. Lu, V. E. Liong, J. Zhou, Simultaneous local binary feature learning and encoding for homogeneous and heterogeneous face recognition, IEEE Trans. Pattern Anal. Mach. Intell., 40 (2018), 1979–1993. https://doi.org/10.1109/TPAMI.2017.2737538 doi: 10.1109/TPAMI.2017.2737538
[75]	Y. Duan, J. Lu, J. Feng, J. Zhou, Context-aware local binary feature learning for face recognition, IEEE Trans. Pattern Anal. Mach. Intell., 40 (2018), 1139–1153. https://doi.org/10.1109/TPAMI.2017.2710183 doi: 10.1109/TPAMI.2017.2710183

This article has been cited by:

1.	Ala Amourah, Basem Aref Frasin, Thabet Abdeljawad, Sivasubramanian Srikandan, Fekete-Szegö Inequality for Analytic and Biunivalent Functions Subordinate to Gegenbauer Polynomials, 2021, 2021, 2314-8888, 1, 10.1155/2021/5574673
2.	Mohamed Illafe, Ala Amourah, Maisarah Haji Mohd, Coefficient Estimates and Fekete–Szegö Functional Inequalities for a Certain Subclass of Analytic and Bi-Univalent Functions, 2022, 11, 2075-1680, 147, 10.3390/axioms11040147
3.	Nazmiye Yilmaz, İbrahim Aktaş, On some new subclasses of bi-univalent functions defined by generalized Bivariate Fibonacci polynomial, 2022, 33, 1012-9405, 10.1007/s13370-022-00993-y
4.	Daniel Breaz, Halit Orhan, Luminiţa-Ioana Cotîrlă, Hava Arıkan, A New Subclass of Bi-Univalent Functions Defined by a Certain Integral Operator, 2023, 12, 2075-1680, 172, 10.3390/axioms12020172
5.	Luminiţa-Ioana Cotîrlǎ, Abbas Kareem Wanas, Applications of Laguerre Polynomials for Bazilevič and θ-Pseudo-Starlike Bi-Univalent Functions Associated with Sakaguchi-Type Functions, 2023, 15, 2073-8994, 406, 10.3390/sym15020406
6.	Isra Al-Shbeil, Abbas Kareem Wanas, Afis Saliu, Adriana Cătaş, Applications of Beta Negative Binomial Distribution and Laguerre Polynomials on Ozaki Bi-Close-to-Convex Functions, 2022, 11, 2075-1680, 451, 10.3390/axioms11090451
7.	Tariq Al-Hawary, Ala Amourah, Basem Aref Frasin, Fekete–Szegö inequality for bi-univalent functions by means of Horadam polynomials, 2021, 27, 1405-213X, 10.1007/s40590-021-00385-5
8.	Abbas Kareem Wanas, Luminiţa-Ioana Cotîrlă, Applications of (M,N)-Lucas Polynomials on a Certain Family of Bi-Univalent Functions, 2022, 10, 2227-7390, 595, 10.3390/math10040595
9.	Abbas Kareem Wanas, Haeder Younis Althoby, Fekete-Szegö Problem for Certain New Family of Bi-Univalent Functions, 2022, 2581-8147, 263, 10.34198/ejms.8222.263272
10.	Arzu Akgül, F. Müge Sakar, A new characterization of (P, Q)-Lucas polynomial coefficients of the bi-univalent function class associated with q-analogue of Noor integral operator, 2022, 33, 1012-9405, 10.1007/s13370-022-01016-6
11.	Tariq Al-Hawary, Coefficient bounds and Fekete–Szegö problem for qualitative subclass of bi-univalent functions, 2022, 33, 1012-9405, 10.1007/s13370-021-00934-1
12.	Ala Amourah, Basem Aref Frasin, Tamer M. Seoudy, An Application of Miller–Ross-Type Poisson Distribution on Certain Subclasses of Bi-Univalent Functions Subordinate to Gegenbauer Polynomials, 2022, 10, 2227-7390, 2462, 10.3390/math10142462
13.	Abbas Kareem Wanas, Alina Alb Lupaş, Applications of Laguerre Polynomials on a New Family of Bi-Prestarlike Functions, 2022, 14, 2073-8994, 645, 10.3390/sym14040645
14.	Ibtisam Aldawish, Basem Frasin, Ala Amourah, Bell Distribution Series Defined on Subclasses of Bi-Univalent Functions That Are Subordinate to Horadam Polynomials, 2023, 12, 2075-1680, 362, 10.3390/axioms12040362
15.	Ala Amourah, Omar Alnajar, Maslina Darus, Ala Shdouh, Osama Ogilat, Estimates for the Coefficients of Subclasses Defined by the Bell Distribution of Bi-Univalent Functions Subordinate to Gegenbauer Polynomials, 2023, 11, 2227-7390, 1799, 10.3390/math11081799
16.	Omar Alnajar, Maslina Darus, 2024, 3150, 0094-243X, 020005, 10.1063/5.0228336
17.	Muajebah Hidan, Abbas Kareem Wanas, Faiz Chaseb Khudher, Gangadharan Murugusundaramoorthy, Mohamed Abdalla, Coefficient bounds for certain families of bi-Bazilevič and bi-Ozaki-close-to-convex functions, 2024, 9, 2473-6988, 8134, 10.3934/math.2024395
18.	Ala Amourah, Ibtisam Aldawish, Basem Aref Frasin, Tariq Al-Hawary, Applications of Shell-like Curves Connected with Fibonacci Numbers, 2023, 12, 2075-1680, 639, 10.3390/axioms12070639
19.	Tariq Al-Hawary, Ala Amourah, Abdullah Alsoboh, Osama Ogilat, Irianto Harny, Maslina Darus, Applications of $q-$ Ultraspherical polynomials to bi-univalent functions defined by $q-$ Saigo's fractional integral operators, 2024, 9, 2473-6988, 17063, 10.3934/math.2024828
20.	İbrahim Aktaş, Derya Hamarat, Generalized bivariate Fibonacci polynomial and two new subclasses of bi-univalent functions, 2023, 16, 1793-5571, 10.1142/S1793557123501474
21.	Abbas Kareem Wanas, Fethiye Müge Sakar, Alina Alb Lupaş, Applications Laguerre Polynomials for Families of Bi-Univalent Functions Defined with (p,q)-Wanas Operator, 2023, 12, 2075-1680, 430, 10.3390/axioms12050430
22.	Ala Amourah, Zabidin Salleh, B. A. Frasin, Muhammad Ghaffar Khan, Bakhtiar Ahmad, Subclasses of bi-univalent functions subordinate to gegenbauer polynomials, 2023, 34, 1012-9405, 10.1007/s13370-023-01082-4
23.	Tariq Al-Hawary, Basem Aref Frasin, Abbas Kareem Wanas, Georgia Irina Oros, On Rabotnov fractional exponential function for bi-univalent subclasses, 2023, 16, 1793-5571, 10.1142/S1793557123502170
24.	Tariq Al-Hawary, Ala Amourah, Hasan Almutairi, Basem Frasin, Coefficient Inequalities and Fekete–Szegö-Type Problems for Family of Bi-Univalent Functions, 2023, 15, 2073-8994, 1747, 10.3390/sym15091747
25.	Omar Alnajar, Osama Ogilat, Ala Amourah, Maslina Darus, Maryam Salem Alatawi, The Miller-Ross Poisson distribution and its applications to certain classes of bi-univalent functions related to Horadam polynomials, 2024, 10, 24058440, e28302, 10.1016/j.heliyon.2024.e28302
26.	Tariq Al-Hawary, Basem Frasin, Daniel Breaz, Luminita-Ioana Cotîrlă, Inclusive Subclasses of Bi-Univalent Functions Defined by Error Functions Subordinate to Horadam Polynomials, 2025, 17, 2073-8994, 211, 10.3390/sym17020211

Reader Comments

Your name:*

Email:*
© 2024 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)