scholarly journals Occluded Face Recognition Based on Double Layers Module Sparsity Difference

2014 ◽  
Vol 2014 ◽  
pp. 1-6 ◽  
Author(s):  
Shuhuan Zhao ◽  
Zheng-ping Hu
Keyword(s):  
Pattern Recognition ◽  
Face Recognition ◽  
Sparse Representation ◽  
Image Recognition ◽  
Double Layers ◽  
Four Blocks

Image recognition with occlusion is one of the popular problems in pattern recognition. This paper partitions the images into some modules in two layers and the sparsity difference is used to evaluate the occluded modules. The final identification is processed on the unoccluded modules by sparse representation. Firstly, we partition the images into four blocks and sparse representation is performed on each block, so the sparsity of each block can be obtained; secondly, each block is partitioned again into two modules. Sparsity of each small module is calculated as the first step. Finally, the sparsity difference of small module with the corresponding block is used to detect the occluded modules; in this paper, the small modules with negative sparsity differences are considered as occluded modules. The identification is performed on the selected unoccluded modules by sparse representation. Experiments on the AR and Yale B database verify the robustness and effectiveness of the proposed method.

Double layers sparse representation for occluded face recognition

Optik ◽  
2015 ◽  
Vol 126 (21) ◽  
pp. 3016-3019 ◽  
Author(s):  
Shuhuan Zhao ◽  
Zheng-ping Hu
Keyword(s):  
Face Recognition ◽  
Sparse Representation ◽  
Double Layers

Improved combination of RPCA and MEL for sparse representation-based face recognition

2014 ◽  
Vol 12 (03) ◽  
pp. 1450031 ◽  
Author(s):  
Rokan Khaji ◽  
Hong Li ◽  
Hongfeng Li ◽  
Rabiu Haruna ◽  
Ramadhan Abdo Musleh Alsaidi
Keyword(s):  
Pattern Recognition ◽  
Face Recognition ◽  
Sparse Representation ◽  
Principal Component ◽  
Second Phase ◽  
Robust Principal Component Analysis ◽  
Practical Applications ◽  
Face Images ◽  
Two Phases ◽  
Improved Technique

Face recognition (FR) is an important and challenging task in pattern recognition and has many important practical applications. This paper presents an improved technique for Face Recognition, which consists of two phases where in each phase; a technique is employed effectively that is used extensively in computer vision and pattern recognition. Initially, the Robust Principal Component Analysis (RPCA) is used specifically in the first phase, which is employed to reduce dimensionality and to extract abstract features of faces. The framework of the second phase is sparse representation based classification (SRC) and introduced metaface learning (MFL) of face images. Experiments for face recognition have been performed on ORL and AR face database. It is shown that the proposed method can perform much best than other methods. And with the proposed method, we can obtain a best understanding of data.

Sparse Representation Frontal Facial Recognition Algorithm Based on Eigenface

2013 ◽  
Vol 347-350 ◽  
pp. 3629-3633
Author(s):  
Bo Yang Ding ◽  
Yuan Yan Tang ◽  
Zhen Chao Zhang ◽  
Xue Wei Wang ◽  
Chi Fang
Keyword(s):  
Computer Vision ◽  
Pattern Recognition ◽  
Face Recognition ◽  
Compressed Sensing ◽  
Sparse Representation ◽  
Facial Recognition ◽  
Recognition Algorithm ◽  
New Technique ◽  
Great Performance ◽  
A New Technique

Face recognition continues to be a hot topic in pattern recognition and computer vision recent years. Meantime, sparse representation is a new technique utilizing compressed sensing method applied in pattern recognition research recent years. This paper comparison with PCA and SP for face recognition, makes some improvement on great performance eigenface algorithm, using sparse representation with eigenface space to achieved better result. Finally, the proposed algorithm based on eigenface sparse recognition shows that of better result.

Occluded Face Recognition Based on Block-Label and Residual

2016 ◽  
Vol 25 (03) ◽  
pp. 1650019 ◽  
Author(s):  
Shu-Huan Zhao ◽  
Zheng-Ping Hu
Keyword(s):  
Face Recognition ◽  
Sparse Representation ◽  
Normal Distribution ◽  
Image Recognition ◽  
Collaborative Representation ◽  
Human Face ◽  
Query Image ◽  
Human Face Recognition ◽  
Block Based ◽  
Selection Of

We consider the problem of automatically human face recognition from frontal views with occlusion and disguise. Since the occlusion can make the query image deviated from the normal distribution, most prior block-based methods focus on reducing the occlusion influence on the global-based representation. Our method is also block-based, but the blocks are non-uniform. Each block contains a certain face component such as eyes, cheek, and forehead, which makes the block more physically meaningful. Recently, sparse representation-based classification (SRC) and Collaborative representation-based classification (CRC) are applied to image recognition successfully, so we classify each block by SRC or CRC respectively. Then the occlusion pixels can be estimated by residuals. Besides, based on the distribution of block labels and the corresponding residual, we propose a new rule for the selection of block and the coefficients for the reconstruction. The final identification is performed on the un-occluded part of each image. Experiments on the AR, extended Yale B and CMU-PIE database verify the robustness and effectiveness of our method.

A novel sparse representation method based on virtual samples for face recognition

2012 ◽  
Vol 24 (3-4) ◽  
pp. 513-519 ◽  
Author(s):  
Deyan Tang ◽  
Ningbo Zhu ◽  
Fu Yu ◽  
Wei Chen ◽  
Ting Tang
Keyword(s):  
Face Recognition ◽  
Sparse Representation ◽  
Virtual Samples ◽  
Representation Method

Integrating Sparse and Collaborative Representation Classifications for Image Classification

2017 ◽  
Vol 17 (02) ◽  
pp. 1750007 ◽  
Author(s):  
Chunwei Tian ◽  
Guanglu Sun ◽  
Qi Zhang ◽  
Weibing Wang ◽  
Teng Chen ◽  
...  
Keyword(s):  
Sparse Representation ◽  
Image Classification ◽  
Linear Combination ◽  
Image Recognition ◽  
Test Sample ◽  
Collaborative Representation ◽  
Training Samples ◽  
Sparse Representation Classification ◽  
The Difference ◽  
Representation Method

Collaborative representation classification (CRC) is an important sparse method, which is easy to carry out and uses a linear combination of training samples to represent a test sample. CRC method utilizes the offset between representation result of each class and the test sample to implement classification. However, the offset usually cannot well express the difference between every class and the test sample. In this paper, we propose a novel representation method for image recognition to address the above problem. This method not only fuses sparse representation and CRC method to improve the accuracy of image recognition, but also has novel fusion mechanism to classify images. The implementations of the proposed method have the following steps. First of all, it produces collaborative representation of the test sample. That is, a linear combination of all the training samples is first determined to represent the test sample. Then, it gets the sparse representation classification (SRC) of the test sample. Finally, the proposed method respectively uses CRC and SRC representations to obtain two kinds of scores of the test sample and fuses them to recognize the image. The experiments of face recognition show that the combination of CRC and SRC has satisfactory performance for image classification.

Sign in / Sign up

Export Citation Format

Share Document