• Journal of KIISE
• /
• v.44 no.3
• /
• pp.295-305
• /
• 2017

Facial appearance is greatly influenced by illumination conditions, and therefore illumination variation is one of the factors that degrades performance of face recognition systems. In this paper, we propose a robust method for face representation under varying illumination conditions, combining non-alpha Weberface (non-alpha WF) and histogram equalization. We propose a two-step method: (1) for a given face image, non-alpha WF, which is not applied a parameter for adjusting the intensity difference between neighboring pixels in WF, is computed; (2) histogram equalization is performed to non-alpha WF, to make a uniform histogram distribution globally and to enhance the contrast. $(2D)^2PCA$ is applied to extract low-dimensional discriminating features from the preprocessed face image. Experimental results on the extended Yale B face database and the CMU PIE face database show that the proposed method yielded better recognition rates than several illumination processing methods as well as the conventional WF, achieving average recognition rates of 93.31% and 97.25%, respectively.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.1
• /
• pp.91-96
• /
• 2015

In this study, we introduce robust face recognition system with illumination variation realized with the aid of CT preprocessing method. As preprocessing algorithm, Census Transform(CT) algorithm is used to extract locally facial features under unilluminated condition. The dimension reduction of the preprocessed data is carried out by using $(2D)^2$PCA which is the extended type of PCA. Feature data extracted through dimension algorithm is used as the inputs of proposed radial basis function neural networks. The hidden layer of the radial basis function neural networks(RBFNN) is built up by fuzzy c-means(FCM) clustering algorithm and the connection weights of the networks are described as the coefficients of linear polynomial function. The essential design parameters (including the number of inputs and fuzzification coefficient) of the proposed networks are optimized by means of artificial bee colony(ABC) algorithm. This study is experimented with both Yale Face database B and CMU PIE database to evaluate the performance of the proposed system.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.3
• /
• pp.123-134
• /
• 2008

In this paper, we propose a real-tin e face recognition system that is robust under various lighting conditions. Th Modified Census Transform algorithm that is insensitive to illumination variations is employed to extract local structure features. In a practical face recognition system, acquired images through a camera are likely to be blurred and some of them could be side face images, resulting that unacceptable performance could be obtained. To improve stability of a practical face recognition system, we propose a real-time algorithm that rejects unnecessary facial picture and makes use of recognition consistency between successive frames. Experimental results on the Yale database with large illumination variations show that the proposed approach is approximately 20% better than conventional appearance-based approaches. We also found that the proposed real-time method is more stable than existing methods that produces recognition result for each frame.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.7
• /
• pp.2667-2682
• /
• 2015

Due to the wide application of face recognition (FR) in information security, surveillance, access control and others, it has received significantly increased attention from both the academic and industrial communities during the past several decades. However, partial face occlusion is one of the most challenging problems in face recognition issue. In this paper, a novel method based on linear regression-based classification (LRC) algorithm is proposed to address this problem. After all images are downsampled and divided into several blocks, we exploit the evaluator of each block to determine the clear blocks of the test face image by using linear regression technique. Then, the remained uncontaminated blocks are utilized to partial occluded face recognition issue. Furthermore, an improved Distance-based Evidence Fusion approach is proposed to decide in favor of the class with average value of corresponding minimum distance. Since this occlusion removing process uses a simple linear regression approach, the completely computational cost approximately equals to LRC and much lower than sparse representation-based classification (SRC) and extended-SRC (eSRC). Based on the experimental results on both AR face database and extended Yale B face database, it demonstrates the effectiveness of the proposed method on issue of partial occluded face recognition and the performance is satisfactory. Through the comparison with the conventional methods (eigenface+NN, fisherfaces+NN) and the state-of-the-art methods (LRC, SRC and eSRC), the proposed method shows better performance and robustness.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.8 no.2
• /
• pp.31-40
• /
• 2012

Face recognition refers to the process of identifying individuals based on their facial features. It has recently become one of the most popular research areas in the fields of computer vision, machine learning, and pattern recognition because it spans numerous consumer applications, such as access control, surveillance, security, credit-card verification, and criminal identification. However, illumination variation on face generally cause performance degradation of face recognition systems under practical environments. Thus, this paper proposes an novel face recognition system using a fusion approach based on local binary pattern and two-dimensional principal component analysis. To minimize illumination effects, the face image undergoes the local binary pattern operation, and the resultant image are divided into two sub-images. Then, two-dimensional principal component analysis algorithm is separately applied to each sub-images. The individual scores obtained from two sub-images are integrated using a weighted-summation rule, and the fused-score is utilized to classify the unknown user. The performance evaluation of the proposed system was performed using the Yale B database and CMU-PIE database, and the proposed method shows the better recognition results in comparison with existing face recognition techniques.

• Journal of KIISE:Software and Applications
• /
• v.36 no.10
• /
• pp.816-824
• /
• 2009

In the face space, face images due to illumination and pose variations have a nonlinear distribution. Active Appearance Models (AAM) based on the linear model have limits to the nonlinear distribution of face images. In this paper, we assume that a few clusters of face images are given; we build local AAMs according to the clusters of face images, and then select a proper AAM model during the fitting phase. To solve the problem of updating fitting parameters among the models due to the model changing, we propose to build in advance relationships among the clusters in the parameter space from the training images. In addition, we suggest a gradual model changing to reduce improper model selections due to serious fitting failures. In our experiment, we apply the proposed model to Yale Face Database B and compare it with the previous method. The proposed method demonstrated successful fitting results with strongly illuminated face images of deep shadows.

• Journal of Advanced Navigation Technology
• /
• v.17 no.6
• /
• pp.726-735
• /
• 2013

This paper proposed face recognition methods about performance improvement of the face recognition using the properties of wavelet transform. Using discrete wavelet transform is Daubechies D4 filter that is similar to mother wavelet transform. For discrete wavelet transform method, In this case, by using LL subband only we can reduce processing time and amount of memory in recognition processing. To improve recognition ratio without further loss of 2 dimensional data changing, We applies 2D LDA. We perform SVM training algorithm to the feature vector obtained by 2D LDA. Experiment is performed using ORL database set and Yale database set by Matlab program. Test result shows that proposed method is superior to existence methods in recognition rate and performance time.

• Journal of the Korean Society of Industry Convergence
• /
• v.8 no.4
• /
• pp.221-226
• /
• 2005

This paper presents a hybrid method for recognizing the faces by using zero mean and principal component analysis. Zero mean is applied to reduce the 1st order statistics to data nonlinearities. PCA is also used to derive an orthonormal basis which directly leads to dimensionality reduction, and possibly to feature extraction of face image. The proposed method has been applied to the problems for recognizing the 20 face images(10 persons * 2 scenes) of 324*243 pixels from Yale face database. 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 method has a superior recognition performances(speed, rate). The negative angle has been relatively achieved more an accurate similarity than city-block or Euclidean.

• Journal of the Korean Society of Industry Convergence
• /
• v.8 no.3
• /
• pp.143-148
• /
• 2005

This paper presents a hybrid method for recognizing the faces by using principal component analysis(PCA) and fixed-point independent component analysis(FP-ICA). PCA is used to whiten the data, which reduces the effects of second-order statistics to the nonlinearities. FP-ICA is applied to extract the statistically independent features of face image. The proposed method has been applied to the problems for recognizing the 20 face images(10 persons * 2 scenes) of 324*243 pixels from Yale face database. 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 method has a superior recognition performances(speed, rate). The negative angle has been relatively achieved more an accurate similarity than city-block or Euclidean.

• Journal of KIISE:Software and Applications
• /
• v.34 no.7
• /
• pp.681-687
• /
• 2007

Face recognition technique is very popular for a personal information security and user identification in recent years. However, the face recognition system is very hard to be implemented due to the difficulty where change in illumination, pose and facial expression. In this paper, we consider that an illumination change causing the variety of face appearance, virtual image data is generated and added to the D-LDA which was selected as the most suitable feature extractor. A less sensitive recognition system in illumination is represented in this paper. This way that consider nature of several illumination directions generate the virtual training image data that considered an illumination effect of the directions and the change of illumination density. As result of experiences, D-LDA has a less sensitive property in an illumination through ORL, Yale University and Pohang University face database.