Efficient Face Recognition Method Research Articles

An efficient method for multi-view sheep face recognition

Sheep face recognition is an efficient and non-contact identification technology; however, it has not been widely adopted due to the time-consuming and labor-intensive nature of traditional methods for collecting sheep face images. To address these issues, we developed a multi-view sheep face image acquisition device. A total of 50 experimental sheep were used in this study to construct a multi-view sheep face dataset. Moreover, a high-precision sheep face recognition model called T2T-ViT-SFR was developed in this study. T2T-ViT-SFR combines multiple optimization strategies to improve the performance of the model. Specifically, we introduced the Squeeze-and-Excitation (SE) attention mechanism into the backbone to enhance the model's ability to learn useful information while suppressing non-essential information. The LayerScale module was embedded in the transformer of the backbone to prevent model collapse as the network depth increased. Meanwhile, the Additive Angular Margin Loss (ArcFace) was integrated at the head to address the challenge posed by the high similarity among sheep faces. Experiments on the multi-view sheep face dataset showed that T2T-ViT-SFR achieved the best recognition performance after pre-training, with an accuracy of 95.9% and an F1-score of 95.5%, significantly superior to the sheep face recognition models proposed in previous studies. Compared to T2T-ViT-24, the accuracy and F1-score of T2T-ViT-SFR increased by 2.6% and 2.1%, respectively, demonstrating the effectiveness of the optimization strategies proposed in this study. This study provides a feasible new strategy for actual sheep identity recognition, achieving a complete recognition process from image acquisition to recognition result output.

ULN: An efficient face recognition method for person wearing a mask.

Although the face recognition has advanced by leaps and bounds in recent years, recognizing faces with large occlusion, e.g., masks, is still a challenging problem. In the context of the COVID-19 outbreak, wearing masks becomes mandatory, which fails numerous face attendance and surveillance systems. Therefore, a robust face recognition algorithm that can deal with facial masks is urgently needed. To build a mask-robust face recognition algorithm, we first generate numerous facial images with masks based on public face datasets, which obviously alleviates the problem of the training data shortage. Second, we propose a novel network architecture called Upper-Lower Network (ULN) to recognize the faces with masks efficiently. The upper branch of ULN with the mask-free images as input is pretrained that provides supervisory information for the training of the lower branch. Considering that the occlusion areas of masks usually appear in the lower parts of faces, we further divide the high-order semantic features into upper and lower parts. The designed loss function force the learned features of the lower branch similar to those of the upper branch with the same mask-free image inputs, but only the upper part of features similar to the mask counterparts. Extensive experiments demonstrate that the proposed method is effective for recognizing persons with masks and outperforms other state-of-the-art face recognition methods.

Interest point based face recognition using adaptive neuro fuzzy inference system

In this paper, an efficient face recognition method using AGA and ANFIS-ABC has been proposed. At first stage, the face images gathered from the database are preprocessed. At Second stage, an interest point which is used to improve the detection rate consequently. The parameters used in the interest point determination are optimized using the Adaptive Genetic Algorithm. Finally using ANFIS, face images are classified by using extracted features. During the training process, the parameters of ANFIS are optimized using Artificial Bee Colony Algorithm (ABC) in order to improve the accuracy. The performance of the proposed ANFIS-ABC technique is evaluated using an ORL database with 400 images of 40 individuals, YALE-B database with 165 images of 15 individuals and finally with real time video the detection rate and false alarm rate is compared with proposed and existing methods to prove the system efficiency.

Generalized Robust Regression for Jointly Sparse Subspace Learning

Ridge regression is widely used in multiple variable data analysis. However, in very high-dimensional cases such as image feature extraction and recognition, conventional ridge regression or its extensions have the small-class problem, that is, the number of the projections obtained by ridge regression is limited by the number of the classes. In this paper, we proposed a novel method called generalized robust regression (GRR) for jointly sparse subspace learning which can address the problem. GRR not only imposes $L_{2,1} $ -norm penalty on both loss function and regularization term to guarantee the joint sparsity and the robustness to outliers for effective feature selection, but also utilizes $L_{2,1} $ -norm as the measurement to take the intrinsic local geometric structure of the data into consideration to improve the performance. Moreover, by incorporating the elastic factor on the loss function, GRR can enhance the robustness to obtain more projections for feature selection or classification. To obtain the optimal solution of GRR, an iterative algorithm was proposed and the convergence was also proved. Experiments on six well-known data sets demonstrate the merits of the proposed method. The result indicates that GRR is a robust and efficient regression method for face recognition.

Deep Learning on Binary Patterns for Face Recognition

In this paper an efficient and robust method for real-time face recognition is proposed. As a part of pre-processing to remove noise and unwanted features, a filter is applied to the images of standard datasets. Subsequently binary patterns are extracted from these images which are further fed into multilayer perceptron to classify images. The proposed method is tested on four benchmark datasets namely FACES94, FACES95, FACES96 and Grimace which pose challenges in illumination, pose, expression, head scale and rotation. This method delivers accuracies in the neighbourhood of 91% when tested on these datasets. Our methodology was further extended to embedded systems like Raspberry Pi 3 to give it more real-time and practical scenario. This test gave promising results and proved the model to be efficient and useful in day to day scenarios for face recognition.

An efficient face recognition method using contourlet and curvelet transform

In the paper we propose a novel method for face recognition using contourlet transform (CNT) and curvelet transform (CLT) which improves rate of face recognition under different challenges. We obtain smooth contour information along different directions by applying CNT on the face image while CLT having multiscale, multidirectional and anisotropic properties has been employed to represent the edges more prominently. Pre-processed training images are decomposed up to fourth level using CNT and coefficients of directional subbands are analysed to obtain the features from the images. In another approach CLT has been applied on the pre-processed face images and considering scale of four and angle eight, different statistical features are extracted from the detail subbands. Finally, we integrate the features obtained from two approaches. High dimensionality of feature space has been reduced by selecting important features depending on the entropy of the transform coefficients. Selected features are applied to recognize the face images using support vector machine (SVM) classifier. Experimental results show that the proposed feature extraction method improves recognition accuracy compare to other methods and efficiently handle the effect of Gaussian noise as tested on JAFFE, ORL and FERET database.

On the selection of 2D Krawtchouk moments for face recognition

Sparse representation of images using orthogonal two-dimensional Krawtchouk moments (2D KCMs) for face recognition is motivated by their ability to capture region-based higher-order hidden nonlinear structures from discrete coordinates of finitely supported images and the invariance of affine transformations of these moments to common geometric distortions. This paper presents the effectiveness of selecting the discriminatory set of KCMs as the global and local face features as opposed to traditional features obtained from heuristic choice of fixed-order moments or projection of the moments for recognizing an identity. The selection of significantly sparse 2D KCM-based features according to the proposed approach results in highly efficient face recognition method as compared to the other methods that use orthogonal moments such as the 2D Zernike, 2D Tchebichef or 2D Gaussian-Hermite. Experiments on challenging databases (viz., FRGC and CK-AUC) and comparisons with the well established projection, texture, and moment-based methods indicate superior recognition performance in terms of mean accuracy and robustness of the proposed holistic- or hybrid-type discriminative KCM-based method, especially when sample sizes are small and the intraclass faces have significant variations due to expressions.

Robust face recognition technique using Gabor phase pattern and phase only correlation

A robust and efficient method for face recognition using phase only correlation (POC) is proposed in this paper. To achieve efficient recognition rate, it uses the concept of histogram of Gabor phase pattern (HGPP) supplemented by POC technique. In HGPP, the quadrant-bit codes are first extracted from faces, and in order to encode the phase variations, global Gabor phase pattern (GGPP) and local Gabor phase pattern (LGPP) are derived. GGPP and LGPP are then split into the non-overlapping rectangular regions. From the above regions, spatial histograms are extracted and concatenated into an extended histogram feature to represent the original image. The recognition is carried out with the nearest-neighbor classifier, using the histogram intersection as the similarity measurement. Finally, face patterns are verified with POC based matching technique to improve the accuracy of the system. This method improves the result both distribution wise and content wise. Experiments are done on the large scale ORL, YALE, FERET and DCSKU databases. Experimental results show that the proposed method is promising and is comparable with the advanced face recognition algorithms reported in the literature.

Efficient face recognition using wavelet-based generalized neural network

This paper presents an efficient face recognition method where enhanced local Gabor binary pattern histogram sequence has been used for efficient face feature extraction and generalized neural network with wavelet as activation function is being used for classification. In this method the face is first decomposed into multiresolution Gabor wavelets the magnitude responses of which are applied to enhanced local binary patterns. The efficiency has been significantly improved by combining two efficient local appearance descriptors named Gabor wavelet and enhanced local binary pattern with generalized neural network. Generalized neural network is a proven technique for pattern recognition and is insensitive to small changes in input data. The proposed method is robust-to-slight variation of imaging conditions and pose variations. Performance comparison with other existing techniques shows that the proposed technique provides better results in terms of false acceptance rate, false rejection rate, equal error rate and time complexity.

New Robust Face Recognition Methods Based on Linear Regression

Nearest subspace (NS) classification based on linear regression technique is a very straightforward and efficient method for face recognition. A recently developed NS method, namely the linear regression-based classification (LRC), uses downsampled face images as features to perform face recognition. The basic assumption behind this kind method is that samples from a certain class lie on their own class-specific subspace. Since there are only few training samples for each individual class, which will cause the small sample size (SSS) problem, this problem gives rise to misclassification of previous NS methods. In this paper, we propose two novel LRC methods using the idea that every class-specific subspace has its unique basis vectors. Thus, we consider that each class-specific subspace is spanned by two kinds of basis vectors which are the common basis vectors shared by many classes and the class-specific basis vectors owned by one class only. Based on this concept, two classification methods, namely robust LRC 1 and 2 (RLRC 1 and 2), are given to achieve more robust face recognition. Unlike some previous methods which need to extract class-specific basis vectors, the proposed methods are developed merely based on the existence of the class-specific basis vectors but without actually calculating them. Experiments on three well known face databases demonstrate very good performance of the new methods compared with other state-of-the-art methods.

New Method using Feature Level Image Fusion and Entropy Component Analysis for Multimodal Human Face Recognition

Visual and infrared cameras have complementary properties and using them together may increase the performance of human face recognition. This study presents a new efficient method for face recognition which fusing the complementary information from both domains. The fused image is obtained by a new image fusion method based on region segmentation and PCNN for the first step. In the second step, features of the fused images are extracted by ECA and 2DECA according to the entropy contribution. The method has been tested on OTCBVS database. Comparison of the experimental results shows that the proposed approach performs significantly well in face recognition.

Illumination invariant feature extraction and mutual-information-based local matching for face recognition under illumination variation and occlusion

An efficient method for face recognition which is robust under illumination variations is proposed. The proposed method achieves the illumination invariants based on the illumination-reflection model employing local matching for best classification. Different filters have been tested to achieve the reflectance part of the image, which is illumination invariant, and maximum filter is suggested as the best method for this purpose. A set of adaptively weighted classifiers vote on different sub-images of each input image and a decision is made based on their votes. Image entropy and mutual information are used as weight factors. The proposed method does not need any prior information about the face shape or illumination and can be applied on each image separately. Unlike most available methods, our method does not need multiple images in training stage to get the illumination invariants. Support vector machines and k-nearest neighbors methods are used as classifier. Several experiments are performed on Yale B, Extended Yale B and CMU-PIE databases. Recognition results show that the proposed method is suitable for efficient face recognition under illumination variations.

An Efficient Method for Face Feature Extraction and Recognition based on Contourlet Transform and Principal Component Analysis using Neural Network

this paper, an efficient face recognition method based on discrete Contourlet transform using PCA and Neural Network classifier is proposed. Each face from the Face Dataset is decomposed using the Discrete Contourlet transform. The Contourlet coefficients of low frequency & high frequency in different scales & various angles are obtained. The frequency coefficients are used as a feature vector for further process. The PCA (Principal component analysis) is used to reduce the dimensionality of the feature vector. The reduced feature vector is used for learning phase of Neural Network classifier. The test databases are projected on Contourlet-PCA subspace to retrieve reduced coefficients. These coefficients are used to match the feature vector coefficients of training dataset using Neural Network Classifier and the results are compared with Euclidean Distance Classifier. The experiments are carried out using Face94 and IIT_Kanpur database.

Fusion (2D) 2PCALDA: A new method for face recognition

This paper proposes an efficient face representation and recognition method, which combines the both information between rows and those between columns from two-directional 2DPCA on fusion face image and the optimal discriminative information from column-directional 2DLDA. Experiment results on ORL and Yale face database demonstrate the effectiveness of the proposed method.

An efficient method for face feature extraction and recognition based on contourlet transforms and principal component analysis

Abstract In this paper, an efficient face recognition method based on the discrete contourlet transform using PCA and the Euclidean distance classifier is proposed. Each face is decomposed using the contourlet transform. The contourlet coefficients of low and high frequency in different scales and various angles are obtained. The frequency coefficients are used as a feature vector for further processing. PCA (Principal Component Analysis) is then used to reduce the dimensionality of the feature vector. Finally, the reduced feature vector is adopted as the face classifier. The test databases are projected onto contourlet-PCA subspace to retrieve reduced coefficients. These coefficients are used to match the feature vector coefficients of the training dataset using a Euclidean distance classifier. Experiments are carried out using the Face94 and IIT_Kanpur databases.

Locally linear discriminant embedding: An efficient method for face recognition

In this paper an efficient feature extraction method named as locally linear discriminant embedding (LLDE) is proposed for face recognition. It is well known that a point can be linearly reconstructed by its neighbors and the reconstruction weights are under the sum-to-one constraint in the classical locally linear embedding (LLE). So the constrained weights obey an important symmetry: for any particular data point, they are invariant to rotations, rescalings and translations. The latter two are introduced to the proposed method to strengthen the classification ability of the original LLE. The data with different class labels are translated by the corresponding vectors and those belonging to the same class are translated by the same vector. In order to cluster the data with the same label closer, they are also rescaled to some extent. So after translation and rescaling, the discriminability of the data will be improved significantly. The proposed method is compared with some related feature extraction methods such as maximum margin criterion (MMC), as well as other supervised manifold learning-based approaches, for example ensemble unified LLE and linear discriminant analysis (En-ULLELDA), locally linear discriminant analysis (LLDA). Experimental results on Yale and CMU PIE face databases convince us that the proposed method provides a better representation of the class information and obtains much higher recognition accuracies.

Neighbourhood Discriminant Embedding in face recognition

Neighborhood Preserving Embedding (NPE) is a linear approximate of Locally Linear Embedding with local geometry preserving property. An efficient face recognition method requires a mapping to separate within-class structure from between-class structure. But, NPE is not in the case since it is unsupervised. Hence, we improved NPE- utilizing the neighbor and class relations of face data. The proposed technique, Neighborhood Discriminant Embedding (NDE), takes into account the local neighboring and the between-class neighboring information. NDE seeks a projection in such that the projected samples of different classes are far apart. Experimental results show that NDE achieves superior results to NPE in face authentication with error reduction at least 20%.

Pose-Encoded Spherical Harmonics for Face Recognition and Synthesis Using a Single Image

Face recognition under varying pose is a challenging problem, especially when illumination variations are also present. In this paper, we propose to address one of the most challenging scenarios in face recognition. That is, to identify a subject from a test image that is acquired under dierent pose and illumination condition from only one training sample (also known as a gallery image) of this subject in the database. For example, the test image could be semifrontal and illuminated by multiple lighting sources while the corresponding training image is frontal under a single lighting source. Under the assumption of Lambertian reflectance, the spherical harmonics representation has proved to be effective in modeling illumination variations for a fixed pose. In this paper, we extend the spherical harmonics representation to encode pose information. More specifically, we utilize the fact that 2D harmonic basis images at different poses are related by close-form linear transformations, and give a more convenient transformation matrix to be directly used for basis images. An immediate application is that we can easily synthesize a different view of a subject under arbitrary lighting conditions by changing the coefficients of the spherical harmonics representation. A more important result is an efficient face recognition method, based on the orthonormality of the linear transformations, for solving the above-mentioned challenging scenario. Thus, we directly project a nonfrontal view test image onto the space of frontal view harmonic basis images. The impact of some empirical factors due to the projection is embedded in a sparse warping matrix; for most cases, we show that the recognition performance does not deteriorate after warping the test image to the frontal view. Very good recognition results are obtained using this method for both synthetic and challenging real images.

중심이동과 상호정보 추정에 의한 효과적인 얼굴인식

본 논문에서는 영상의 중심이동과 상호정보 추정에 의한 효과적인 얼굴인식 기법을 제안하였다. 여기서 중심이동은 영상의 1차 모멘트에 의해 계산된 중심좌표로 얼굴영상을 이동하는 것이며, 이는 인식에 불필요한 배경을 배제시킴으로써 인식성능을 개선시키기 위함이다. 상호정보 추정은 상관관계를 나타내는 척도로 영상간의 유사성을 효과적으로 측정하기 위함이다. 특히 영상의 상호정보 추정을 위한 확률밀도함수 계산에 동일한 량의 샘플분할을 이용한 적응분할의 추정 방법을 이용함으로써 영상 상호간의 종속성을 더욱 더 정확하게 구하였다. 제안된 기법을 64*64 픽셀의 48장(12명*4장) 얼굴영상을 대상으로 실험한 결과, 제안된 기법은 중심이동을 거치지 않는 단순히 상호정보 추정만을 이용하는 기법보다 우수한 인식성능(인식률, 인식속도)이 있음을 확인하였다. 또한 얼굴의 표정, 위치, 그리고 각도 등의 변화에도 매우 강건한 인식성능이 있음을 확인하였다. This paper presents an efficient face recognition method by using both centroid shift and mutual information estimation of images. The centroid shift is to move an image to center coordinate calculated by first moment, which is applied to improve the recognition performance by excluding the needless backgrounds in face image. The mutual information which is a measurements of correlations, is applied to efficiently measure the similarity between images. Adaptive partition mutual information(AP-MI) estimation is especially applied to find an accurate dependence information by equally partitioning the samples of input image for calculating the probability density function(PDF). The proposed method has been applied to the problem for recognizing the 48 face images(12 persons * 4 scenes) of 64*64 pixels. The experimental results show that the proposed method has a superior recognition performances(speed, rate) than a conventional method without centroid shift. The proposed method has also robust performance to changes of facial expression, position, and angle, etc. respectively.

영상의 1차 모멘트와 기저영상을 이용한 효율적인 얼굴인식

본 논문에서는 영상의 1차 모멘트와 기저영상을 이용한 효율적인 얼굴인식 방법을 제안하였다. 여기서 1차 모멘트는 입력되는 얼굴영상의 중심 좌표를 계산하여 중심 이동하는 전처리로 인식에 불필요한 배경을 배제시킴으로써 인식성능을 개선하기 위함이다. 또한 기저영상은 얼굴의 특징으로 주요성분분석과 고정점 알고리즘의 독립성분분석을 각각 이용하여 추출하였다. 이는 2차와 고차의 통계성을 각각 고려한 중복신호의 제거로 인식성능을 개선하기 위함이다. 제안된 2가지 방법을 각각 64*64 픽셀의 48개(12명*4장) 얼굴영상에 적용하여 city-block, Euclidean, 그리고 negative angle의 3가지 거리 척도를 분류척도로 이용하여 실험하였다. 실험결과, 중심이동의 제안된 방법은 전처리과정을 거치지 않는 기존방법보다 우수한 인식성능이 있음을 확인하였다. 또한 제안된 중심이동의 독립성분분석이 중심이동의 주요성분분석보다 더욱 우수한 인식성능이 있음도 확인하였다. 특히 city-block이 Euclidean이나 negative angle의 거리척도보다 상대적으로 정확하게 유사성을 측정함을 알 수 있었다. This paper presents an efficient face recognition method using both first moment of image and basis images. First moment which is a method for finding centroid of image, is applied to exclude the needless backgrounds in the face recognitions by shifting to the centroid of face image. Basis images which are the face features, are respectively extracted by principal component analysis(PCA) and fixed-point independent component analysis(FP-ICA). This is to improve the recognition performance by excluding the redundancy considering to second- and higher-order statistics of face image. The proposed methods has been applied to the problem for recognizing the 48 face images(12 persons*4 scenes) of 64*64 pixels. The 3 distances such as city-block, Euclidean, negative angle are used as measures when match the probe images to the nearest gallery images. The experimental results show that the proposed methods has a superior recognition performances(speed, rate) than conventional PCA and FP-ICA without preprocessing, the proposed FP-ICA has also better performance than the proposed PCA. The city-block has been relatively achieved more an accurate similarity than Euclidean or negative angle.