2D Pose-Invariant Face Recognition Using Single Frontal-View Face Database

2020 ◽  
Author(s):  
Chayanut Petpairote ◽  
Suthep Madarasmi ◽  
Kosin Chamnongthai
Keyword(s):  
Face Recognition ◽  
Frontal View ◽  
Face Database

scholarly journals Face Recognition Using the SR-CNN Model

Sensors ◽  
2018 ◽  
Vol 18 (12) ◽  
pp. 4237 ◽  
Author(s):  
Yu-Xin Yang ◽  
Chang Wen ◽  
Kai Xie ◽  
Fang-Qing Wen ◽  
Guan-Qun Sheng ◽  
...  
Keyword(s):  
Face Recognition ◽  
Target Position ◽  
Operation Time ◽  
True Positive Rate ◽  
Processing Unit ◽  
True Positive ◽  
Face Database ◽  
Acceleration Ratio ◽  
Computational Performance ◽  
Positive Rate

In order to solve the problem of face recognition in complex environments being vulnerable to illumination change, object rotation, occlusion, and so on, which leads to the imprecision of target position, a face recognition algorithm with multi-feature fusion is proposed. This study presents a new robust face-matching method named SR-CNN, combining the rotation-invariant texture feature (RITF) vector, the scale-invariant feature transform (SIFT) vector, and the convolution neural network (CNN). Furthermore, a graphics processing unit (GPU) is used to parallelize the model for an optimal computational performance. The Labeled Faces in the Wild (LFW) database and self-collection face database were selected for experiments. It turns out that the true positive rate is improved by 10.97–13.24% and the acceleration ratio (the ratio between central processing unit (CPU) operation time and GPU time) is 5–6 times for the LFW face database. For the self-collection, the true positive rate increased by 12.65–15.31%, and the acceleration ratio improved by a factor of 6–7.

scholarly journals A Novel Approach of Low-Light Image Denoising for Face Recognition

2014 ◽  
Vol 6 ◽  
pp. 256790
Author(s):  
Yimei Kang ◽  
Wang Pan
Keyword(s):  
Face Recognition ◽  
Image Denoising ◽  
Recognition Rate ◽  
Low Frequency ◽  
Frequency Noise ◽  
Low Frequency Noise ◽  
Face Database ◽  
Low Light ◽  
Very Low Frequency ◽  
Light Image

Illumination variation makes automatic face recognition a challenging task, especially in low light environments. A very simple and efficient novel low-light image denoising of low frequency noise (DeLFN) is proposed. The noise frequency distribution of low-light images is presented based on massive experimental results. The low and very low frequency noise are dominant in low light conditions. DeLFN is a three-level image denoising method. The first level denoises mixed noises by histogram equalization (HE) to improve overall contrast. The second level denoises low frequency noise by logarithmic transformation (LOG) to enhance the image detail. The third level denoises residual very low frequency noise by high-pass filtering to recover more features of the true images. The PCA (Principal Component Analysis) recognition method is applied to test recognition rate of the preprocessed face images with DeLFN. DeLFN are compared with several representative illumination preprocessing methods on the Yale Face Database B, the Extended Yale face database B, and the CMU PIE face database, respectively. DeLFN not only outperformed other algorithms in improving visual quality and face recognition rate, but also is simpler and computationally efficient for real time applications.

Bayesian Robust Coding Face Recognition Algorithm Based on New Dictionary

2014 ◽  
Vol 644-650 ◽  
pp. 4080-4083
Author(s):  
Ye Cai Guo ◽  
Ling Hua Zhang
Keyword(s):  
Face Recognition ◽  
Recognition Rate ◽  
Recognition Algorithm ◽  
Binary Image ◽  
Test Image ◽  
Face Database ◽  
Robust Coding ◽  
The Face ◽  
Isolated Points ◽  
Rate Comparison

In order to overcome the defects that the face recognition rate can be greatly reduced in the existing uncontrolled environments, Bayesian robust coding for face recognition based on new dictionary was proposed. In this proposed algorithm, firstly a binary image is gained by gray threshold transformation and a more clear image without some isolated points can be obtained via smoothing, secondly a new dictionary can be reconstructed via fusing the binary image with the original training dictionary, finally the test image can be classified as the existing class via Bayesian robust coding. The experimental results based on AR face database show that the proposed algorithm has higher face recognition rate comparison with RRC and RSC algorithm.

Classic Methods of Face Recognition

2010 ◽  
Vol 121-122 ◽  
pp. 350-353
Author(s):  
Hai Yang Zhang ◽  
Xian Wei Li
Keyword(s):  
Face Recognition ◽  
Face Database ◽  
Research Results ◽  
The Past

Over the past few years, face recognition has been actively studied. Some classic methods of face recognition are introduced in this paper. At first, we give an overview of face recognition and its applications. Then, we will present some classic techniques of face recognition. A brief overview of ORL face database which is usually used to test the performance of these methods is given. At last, we will give a summary of the research results.

3D Face Recognition Based on Regional Shape Maps

2018 ◽  
Vol 22 (1) ◽  
pp. 141-146 ◽  
Author(s):  
Xiaoni Wang ◽  
Keyword(s):  
Face Recognition ◽  
Recognition Performance ◽  
3D Face Recognition ◽  
Face Database ◽  
Registration Method ◽  
3D Face ◽  
Feature Vectors ◽  
Input Face ◽  
Point To Point ◽  
3D Face Database

This study proposes an iterative closest shape point (ICSP) registration method based on regional shape maps for 3D face recognition. A neutral expression image randomly selected from a face database is considered as the reference face. The point-to-point correspondences between the input face and the reference face are achieved by constructing the points’ regional shape maps. The distance between corresponding point pairs is then minimized by iterating through the correspondence findings and coordinate transformations. The vectors composed of the closest shape points obtained in the last iteration are regarded as the feature vectors of the input face. These 3D face feature vectors are finally used for both training and recognition using the Fisherface method. Experiments are conducted using the 3D face database maintained by the Chinese Academy of Science Institute of Automation (CASIA). The results show that the proposed method can effectively improve 3D face recognition performance.

Research on Importance of Texture Information in Face Recognition

2013 ◽  
Vol 278-280 ◽  
pp. 1193-1196 ◽  
Author(s):  
Yong Gao Jin ◽  
Cheng Zhe Xu
Keyword(s):  
Face Recognition ◽  
Face Image ◽  
Experimental Results ◽  
Face Database ◽  
Illumination Variation ◽  
Illumination Normalization ◽  
Skin Texture ◽  
Shape Information ◽  
Texture Information

This paper presents importance of skin texture information in face recognition. To this end, we perform the illumination normalization on face image in order to extract texture information unaffected by illumination variation. And then apply mask image on each illumination normalized face image to obtain the corresponding texture data, which hardly contain the shape information. Face recognition experiments are carried out by using texture data. Experimental results on Yale face database B and CMU PIE database show that the texture information has considerable ability to distinguish subjects in face recognition.

Two-Dimensional Locality Discriminant Preserving Projections for Face Recognition

2010 ◽  
Vol 121-122 ◽  
pp. 391-398 ◽  
Author(s):  
Qi Rong Zhang ◽  
Zhong Shi He
Keyword(s):  
Feature Extraction ◽  
Face Recognition ◽  
Recognition Performance ◽  
Recognition Rate ◽  
Image Feature ◽  
Two Dimensional ◽  
Face Database ◽  
Image Feature Extraction ◽  
Locality Preserving Projection ◽  
Locality Preserving

In this paper, we propose a new face recognition approach for image feature extraction named two-dimensional locality discriminant preserving projections (2DLDPP). Two-dimensional locality preserving projections (2DLPP) can direct on 2D image matrixes. So, it can make better recognition rate than locality preserving projection. We investigate its more. The 2DLDPP is to use modified maximizing margin criterion (MMMC) in 2DLPP and set the parameter optimized to maximize the between-class distance while minimize the within-class distance. Extensive experiments are performed on ORL face database and FERET face database. The 2DLDPP method achieves better face recognition performance than PCA, 2DPCA, LPP and 2DLPP.

Inverse Constrained Maximum Variance Mapping for Face Recognition

2013 ◽  
Vol 462-463 ◽  
pp. 452-457 ◽  
Author(s):  
Qi Rong Zhang ◽  
Jia Nan Gu ◽  
Ming Fu Zhang
Keyword(s):  
Pattern Recognition ◽  
Face Recognition ◽  
Mapping Method ◽  
Face Database ◽  
New Approach ◽  
Maximum Variance

Li et al. [Pattern Recognition 41 (2008) 3287 -- 329 proposed the constrained maximum variance mapping method. The CMVM is globally maximizing the distances between different manifolds. We find out that globally minimizing the distances between the same manifolds can have better recognition than CMVM method on the Yale face database, ORL face database and UMIST face database. Hence we propose to use an inverse constrained maximum variance mapping method (ICMVM) which can be seen as the inverse Laplacian Fisher discriminate criteria. Experiment results suggest that this new approach performs well.

Sign in / Sign up

Export Citation Format

Share Document