Face Recognition Rate Research Articles

Face recognition algorithm based on Gabor wavelet and locality preserving projections

In order to solve the effects of illumination changes and differences of personal features on the face recognition rate, this paper presents a new face recognition algorithm based on Gabor wavelet and Locality Preserving Projections (LPP). The problem of the Gabor filter banks with high dimensions was solved effectively, and also the shortcoming of the LPP on the light illumination changes was overcome. Firstly, the features of global image information were achieved, which used the good spatial locality and orientation selectivity of Gabor wavelet filters. Then the dimensions were reduced by utilizing the LPP, which well-preserved the local information of the image. The experimental results shown that this algorithm can effectively extract the features relating to facial expressions, attitude and other information. Besides, it can reduce influence of the illumination changes and the differences in personal features effectively, which improves the face recognition rate to 99.2%.

Face Recognition and Human Tracking Using GMM, HOG and SVM in Surveillance Videos

Tracking of human and recognition in public places using surveillance cameras is the topic of research in the area computer vision. Recognition of human and then tracking completes the video surveillance system. A novel algorithm for face recognition and human tracking is presented in this article. Human is tracked using Gaussian mixture model. To track the human in specific, template of GMM is divided into four regions which are placed one above the other and tracked simultaneously. For recognizing the human, the histogram of oriented gradients features of the face region are given to the support vector machine classifier. Three experiments are conducted in taking the training faces. Every $$10{\mathrm{th}}$$ frame, every $$5{\mathrm{th}}$$ frame and every $$3{\mathrm{rd}}$$ frame of the first 100 frames are considered. The other frames in the video are considered for testing using SVM classifier. Three datasets namely AITAM1 (simple), AITAM2 (moderate) and AITAM3 (complex) are used in this work. The experimental results show that as the complexity of dataset increases the performance metrics are getting decreased. The more the number of training faces in preparing a classifier, the better is the face recognition rate. This is experimented for all types of datasets. The Performance results show that the combination of the tracking algorithm and the face recognition algorithm not only tracks the person but also recognizes the person. This unique property of both tracking and recognition makes it best suit for video surveillance applications.

A novel deep learning algorithm for incomplete face recognition: Low-rank-recovery network

There have been a lot of methods to address the recognition of complete face images. However, in real applications, the images to be recognized are usually incomplete, and it is more difficult to realize such a recognition. In this paper, a novel convolution neural network frame, named a low-rank-recovery network (LRRNet), is proposed to conquer the difficulty effectively inspired by matrix completion and deep learning techniques. The proposed LRRNet first recovers the incomplete face images via an approach of matrix completion with the truncated nuclear norm regularization solution, and then extracts some low-rank parts of the recovered images as the filters. With these filters, some important features are obtained by means of the binaryzation and histogram algorithms. Finally, these features are classified with the classical support vector machines (SVMs). The proposed LRRNet method has high face recognition rate for the heavily corrupted images, especially for the images in the large databases. The proposed LRRNet performs well and efficiently for the images with heavily corrupted, especially in the case of large databases. Extensive experiments on several benchmark databases demonstrate that the proposed LRRNet performs better than some other excellent robust face recognition methods.

Analyses of Face Recognition Rate Using Holistic Methods

Abstract The paper focuses on the analysis of holistic facial recognition rates obtained by changing the parameters related to the number of components and the number of images for the same subject in the training set. It has been observed that, regardless of the method used, choosing a small number of samples for the training set does not lead to acceptable results. The recognition rate for using the PCA algorithm is directly influenced by the number of samples and by the size of the feature vector. Thus, if all the features were retained and the number of images in the training set was high, 95% rates were obtained. Similarly, in the case of the extraction of vectors of variable dimensions with DCT and the use of a neural network for classification, the obtained rates were not satisfactory for a small number of samples in the training set.

Impact of Facial Expressions and Posture Variations in Face Recognition Rate on Different Image Databases

Impact of Facial Expressions and Posture Variations in Face Recognition Rate on Different Image Databases

포즈 추정 기반 얼굴 인식 시스템 설계 : 포즈 추정 알고리즘 비교 연구

This paper is concerned with the design methodology of face recognition system based on pose estimation. In 2-dimensional face recognition, the variations of facial pose cause the deterioration of recognition performance because object recognition is carried out by using brightness of each pixel on image. To alleviate such problem, the proposed face recognition system deals with Learning Vector Quantizatioin(LVQ) or K-Nearest Neighbor(K-NN) to estimate facial pose on image and then the images obtained from LVQ or K-NN are used as the inputs of networks such as Convolution Neural Networks(CNNs) and Radial Basis Function Neural Networks(RBFNNs). The effectiveness and efficiency of the post estimation using LVQ and K-NN as well as face recognition rate using CNNs and RBFNNs are discussed through experiments carried out by using ICPR and CMU PIE databases.

Face Illumination Processing Using Wavelet Transform and Gradientfaces

In view of the problem of illumination, a new approach based on wavelet transform and gradientfaces for illumination processing is presented. Firstly, the method calculates wavelet transform and multilevel wavelet decomposition in logarithm domain. The low frequency coefficient is discarded partially. After reconstructed, the high frequency component of the face image is enhanced using gradientfaces. Secondly, the face invariant feature is extracted by Principal Component Analysis (PCA), the nearest neighborhood classifier using cosine distance is adopted for face classification. The experiment result on Yale B frontal face database demonstrates that the presented algorithm could recognize all of the test samples and the face recognition rate is 100%. Thus, this technique can overcome the effect of different degree of illumination efficiently.

Collaborative Random Faces-Guided Encoders for Pose-Invariant Face Representation Learning.

Learning discriminant face representation for pose-invariant face recognition has been identified as a critical issue in visual learning systems. The challenge lies in the drastic changes of facial appearances between the test face and the registered face. To that end, we propose a high-level feature learning framework called "collaborative random faces (RFs)-guided encoders" toward this problem. The contributions of this paper are three fold. First, we propose a novel supervised autoencoder that is able to capture the high-level identity feature despite of pose variations. Second, we enrich the identity features by replacing the target values of conventional autoencoders with random signals (RFs in this paper), which are unique for each subject under different poses. Third, we further improve the performance of the framework by incorporating deep convolutional neural network facial descriptors and linking discriminative identity features from different RFs for the augmented identity features. Finally, we conduct face identification experiments on Multi-PIE database, and face verification experiments on labeled faces in the wild and YouTube Face databases, where face recognition rate and verification accuracy with Receiver Operating Characteristic curves are rendered. In addition, discussions of model parameters and connections with the existing methods are provided. These experiments demonstrate that our learning system works fairly well on handling pose variations.

FACE RECOGNITION BASED ON LOCAL DERIVATIVE TETRA PATTERN

This paper proposes a new face recognition algorithm called local derivative tetra pattern (LDTrP). The new technique LDTrP is used to alleviate the face recognition rate under real-time challenges. Local derivative pattern (LDP) is a directional feature extraction method to encode directional pattern features based on local derivative variations. The nth -order LDP is proposed to encode the first (n-1)th order local derivative direction variations. The LDP templates extract high-order local information by encoding various distinctive spatial relationships contained in a given local region. The local tetra pattern (LTrP) encodes the relationship between the reference pixel and its neighbours by using the first-order derivatives in vertical and horizontal directions. LTrP extracts values which are based on the distribution of edges which are coded using four directions. The LDTrP combines the higher order directional feature from both LDP and LTrP. Experimental results on ORL and JAFFE database show that the performance of LDTrP is consistently better than LBP, LTP and LDP for face identification under various conditions. The performance of the proposed method is measured in terms of recognition rate.

Face recognition based on the fusion of wavelet packet sub-images and fisher linear discriminant

With the improvement of security requirements of individuals, businesses and countries, the identity authentication system based on face recognition technology is applied widely. The identity methods based on single theory, due to a variety of factors, have their own inherent limitations. In order to improve the efficiency and accuracy of face recognition, based on fusion of wavelet packet sub-images, a face recognition algorithm named FW-FLD is proposed in this paper by combining PCA (Principal Component Analysis) and FLD(Fisher Linear Discriminant). Firstly, the training samples are decomposed using wavelet packet. The fusion weights of the decomposed sub-images are calculated according to their energy distribution and the weighted fusion images are obtained, which reserve the images characteristic in the frequency. Then the features of the fused images are extracted using PCA, and the optimized Fisher space is constructed using FLD. Finally, face images are classified by measuring the projection coefficients of optimized training samples and testing samples in Fisher space. Experimental results on CMU PIE, JAFFE and AR face databases show that the proposed algorithm is robust, and can adapt to face recognition with various illumination, facial expressions and gestures. Compared with other algorithms, it not only improves the face recognition rate, but also has a higher time efficiency.

Retinex Algorithm Based on Mean-Shift Applied in Face Recognition

In order to improve the face recognition rate with complex illumination conditions changing, a Retinex algorithm based on Mean-Shift smoothing filtering was proposed and applied to illumination pretreatment of face recognition. The original image was enhanced by this method with local nonlinear contrast enhancement, illumination was evaluated by Mean-Shift smoothing filtering instead of Gaussian filter in traditional Retinex and the problem that halo formation couldn't be removed by Retinex algorithm was solved. The result of experiment in CAS_PEAL face library shows that, the algorithm has better illumination pretreatment effect than tradition algorithms, and also can improve the face recognition rate.

Face recognition based on improved BP neural network

In order to improve the recognition rate of face recognition, face recognition algorithm based on histogram equalization, PCA and BP neural network is proposed. First, the face image is preprocessed by histogram equalization. Then, the classical PCA algorithm is used to extract the features of the histogram equalization image, and extract the principal component of the image. And then train the BP neural network using the trained training samples. This improved BP neural network weight adjustment method is used to train the network because the conventional BP algorithm has the disadvantages of slow convergence, easy to fall into local minima and training process. Finally, the BP neural network with the test sample input is trained to classify and identify the face images, and the recognition rate is obtained. Through the use of ORL database face image simulation experiment, the analysis results show that the improved BP neural network face recognition method can effectively improve the recognition rate of face recognition.

Unconstrained face recognition in surveillance videos using moment invariants

Video-based face recognition is a challenging research area. In the unconstrained surveillance videos, recognition of faces with arbitrary poses, illumination, expressions, noise and blurriness is highly difficult task. In this paper, an efficient moment invariant face descriptor (MFD) is proposed. The geometric feature points of eyes, nose and mouth are extracted using face block filtering. These descriptors consist of 33 moment invariant features (11 from each). In these 11 moment invariant features, three of them are geometric moments and the remaining eight are central moments. It provides robustness against variability due to changes in localised regions of the faces. A public unconstrained video data set with three cameras is used. The proposed algorithm is compared with LBP, LPQ, HOG and moment invariant feature descriptors against different classifiers such as J48, random forest and multilayer perceptron. Experimental results show that the proposed algorithm using random forest classifier improves face recognition rate.

Improved immune computation for high-precision face recognition

Dangerous persons can be monitored accurately and quickly using the high-precision recognition of the relative facial images via the image sensors. To increase the recognition rate of face recognition by improving the immune algorithm, the immune computation was redesigned for better face recognition to decrease the facial disturbances of the pose, illumination and expression (PIE), in this paper. The clonal selection algorithm was improved with the modification of the affinity and the algorithm workflow. The improved clonal selection algorithm searches the most similar antibody sample against the antigen of an unknown facial image, according to the affinity between the antigen and the antibody. The unknown facial images were recognized with this improved affinity and the uncertainty-based reasoning, so the affinity matching of the antibody with the unknown antigen was also improved. Experimental results show that this immune algorithm outperforms some state-of-the-art algorithms in the face recognition accuracy tests with such facial image databases as AR, Yale and CMU-PIE. So the proposed immune algorithm is useful and effective to improve the performance of face recognition in the image sensor network.

Novel Method for Face Recognition using Laplacian of Gaussian Mask with Local Contour Pattern

We propose a face recognition method that utilizes the LCP face descriptor. The proposed method applies a LoG mask to extract a face contour response, and employs the LCP algorithm to produce a binary pattern representation that ensures high recognition performance even under the changes in illumination, noise, and aging. The proposed LCP algorithm produces excellent noise reduction and efficiency in removing unnecessary information from the face by extracting a face contour response using the LoG mask, whose behavior is similar to the human eye. Majority of reported algorithms search for face contour response information. On the other hand, our proposed LCP algorithm produces results expressing major facial information by applying the threshold to the search area with only 8 bits. However, the LCP algorithm produces results that express major facial information with only 8-bits by applying a threshold value to the search area. Therefore, compared to previous approaches, the LCP algorithm maintains a consistent accuracy under varying circumstances, and produces a high face recognition rate with a relatively small feature vector. The test results indicate that the LCP algorithm produces a higher facial recognition rate than the rate of human visuals recognition capability, and outperforms the existing methods.

A Novel Face Recognition Algorithm Based on Improved Retinex and Sparse Representation

In recent years, face recognition technology has been widely used as a kind of important modern biological recognition technology. As one of the main factors that affect the recognition rate, the illumination variation has attracted the attention of many researchers. In order to improve the face recognition under illumination variation condition, a novel face recognition algorithm based on improved Retinex and sparse representation is proposed in this paper. Retinex algorithm can be used to solve the problem of face illumination variation in face recognition, but it is easy to produce ‘halo’ phenomenon. In order to improve the face recognition rate under the change of illumination condition. In this paper, firstly, in order to eliminate the interference of illumination on face recognition, we apply the Retinex that is improved by partial differential equations to face image processing. Then, sparse representation is used to extract face feature vector, and the voting method is used to realize the face recognition. Finally, the performance of the algorithm is tested by 3 standard face databases. The results show that the proposed algorithm can improve the face recognition rate under different illumination conditions, and has good robustness to illumination.

A Theoretical Approach on Face Recognition with Single Sample Per Class using CS-LBP and Gabor Magnitude and Phase

Objectives: To develop a theoretical model in order to understand how to recognize acquainted faces and the relationship between face processing acknowledgement with other aspects in face. Greater Performance is achieved in face recognition by local appearance based methods. Methods: The Centre Symmetric local binary pattern with gabor magnitude phase have been proposed in this paper to provide an expression, illumination and pose invariant in a single sample problem for face recognition approach with local spatial, scale and directional discriminate and low dimensional face representation based on features. The proposed methodology was compared with PCA and LBP. Findings: Gabor magnitude and Gabor phase tracks the texture boundaries of textured regions accurately. The evaluated Face features from CS-LBP and gabor magnitude phase has better performance. The Photometric descriptors are used in recent years, proven successful for computing regions which are in interest. In this approach the strength of SIFT descriptors are used in combination with LBP texture operator collectively called CS-LBP descriptor. This nullified illumination changes, strengthening flat image areas, and proficiency in computation. Improvements: For images with severe illumination variations SIFT descriptor is outperformed by CSLBP descriptor this was proved experimentally. The face recognition rate is increased by selective local texture feature Gabor Magnitude and Phase CS-LBP when compared with LBP method and Gabor filter.

Score Fusion of 3DLBP and ACDN+P for 3D Face Recognition

Many situations of our everyday life require our identification. Biometrics-based methods, besides allowing such identification, can help to prevent frauds. Among several biometrics features, face is one of the most popular due to its intrinsic and important properties, such as universality, acceptability, lowcosts, and covert identification. On the other hand, the traditional automatic face recognition methods based on 2D features can not properly deal with some very frequent challenges, such as occlusion, illumination and pose variations. In this paper we propose a new method for face recognition based on the fusion of 3D low-level local features, ACDN+P and 3DLBP, using depth images captured by cheap Kinect V1 sensors. In order to improve the low quality of the point cloud provided by such devices, Symmetric Filling, Iterative Closest Point, and Savitzky-Golay Filter are used in the preprocessing stage of the proposed method. Experimental results obtained on EURECOM Kinect dataset showed that the proposed method can improve the face recognition rates.

Facial Recognition using Unsupervised Mode in Artificial Neural Network by Self-Organizing Map using MATLAB

The main aim of this paper is to label a Self-Organizing Map (SOM) to measure image similarity. To achieve this, we input Facial images linked to the regions of interest into the neural network. Every single neural unit is tuned to a particular Facial image prototype at the end of the learning step. Probabilistic decision rule then performs facial recognition. This method gives accurate results for face identification taking into consideration various factors such as illumination variation and facial poses and expressions. The current research reveals a promising Self-Organizing Map (SOM) for face recognition. The Self-Organizing Map (SOM) technique is trained on images from one database. The novelty of this research comes from the integration of Images from input database, Training and Mapping. Face Recognition using unsupervised mode in neural network by Self-Organizing Map. Out of the all the architectures and algorithms suggested for artificial neural network, the SOM has an advantageous property of effectively creating a spatially organized `internal representation’ of various features of input signals and their abstractions. After the weight vectors have been finely tuned, the SOM technique has been promisingly accurate in various pattern recognition tasks involving very noisy signal. One develops realistic cortical structures when given approximations of visual environment as input, and is effective way to model the development of face recognition capability. In this study Kohonen self-organizing map (SOM) based retrieval system has been used to develop and illustrate a recognition system for human faces. It is due to topological ordering that Self-organizing map possess a better and precise feature recognizing and extracting property. Factoring in the Facial Analysis solutions for over 400 images used from the AT&T database we can say safely say that the facial recognition rate using one of the neural network algorithm SOM is 92.40% for 40 persons.

RANCANG BANGUN SISTEM PENGENALAN WAJAH DENGAN METODE PRINCIPAL COMPONENT ANALYSIS

The face is one of the easiest physiological measures and is often used to distinguish individual identities from one another. This facial recognition process uses raw information from pixel images generated through a camera which is then represented in the Principal Components Analysis method. The Principal Components Analysis method works by calculating the average flatvector pixel of images that have been stored in a database, from the average flatvector will get the value of each image eigenface and then the nearest eigenface value of the image will be found and then the nearest eigenface value of the image will be found the image of the face you want to recognize. The test results showed an overall success rate of face recognition of 82.27% with face data of 130 images.