Robust face recognition based on sparse representation in 2D Fisherface space

Sparse representation is being proved to be effective for many tasks in the field of face recognition. In this paper, we will propose an efficient face recognition algorithm via sparse representation in 2D Fisherface space. We firstly transformed the 2D image into 2D Fisherface in preprocessing, and classify the testing image via sparse representation in the 2D Fisherface space. Then we extend the proposed method using some supplementary matrices to deal with random pixels corruption. For face image with contiguous occlusion, we partition each image into some blocks, and define a new rule combining sparsity and reconstruction residual to discard the occluded blocks, the final result is aggregated by voting the classification result of the valid individual block. The experimental results have shown that the proposed algorithm achieves a satisfying performance in both accuracy and robustness.     

Pedestrian detection from thermal images: A sparse representation based approach

Pedestrian detection, a key technology in computer vision, plays a paramount role in the applications of advanced driver assistant systems (ADASs) and autonomous vehicles. The objective of pedestrian detection is to identify and locate people in a dynamic environment so that accidents can be avoided. With significant variations introduced by illumination, occlusion, articulated pose, and complex background, pedestrian detection is a challenging task for visual perception. Different from visible images, thermal images are captured and presented with intensity maps based objects’ emissivity, and thus have an enhanced spectral range to make human beings perceptible from the cool background. In this study, a sparse representation based approach is proposed for pedestrian detection from thermal images. We first adopted the histogram of sparse code to represent image features and then detect pedestrian with the extracted features in an unimodal and a multimodal framework respectively. In the unimodal framework, two types of dictionaries, i.e. joint dictionary and individual dictionary, are built by learning from prepared training samples. In the multimodal framework, a weighted fusion scheme is proposed to further highlight the contributions from features with higher separability. To validate the proposed approach, experiments were conducted to compare with three widely used features: Haar wavelets (HWs), histogram of oriented gradients (HOG), and histogram of phase congruency (HPC) as well as two classification methods, i.e. AdaBoost and support vector machine (SVM). Experimental results on a publicly available data set demonstrate the superiority of the proposed approach.     

A palmprint recognition method based on multi-step representation

Sparse representation uses all training samples to represent a test sample only once, which can be regarded as a one step representation. However, in palmprint recognition, the appearances of palms are highly correlated which means the information provided by all the training samples are redundant while using the representation-based methods. Hence, how to obtain suitable samples for representation deserves exploring. In this paper, we devise a multi-step representation manner to extract the most representative samples for representation and recognition. In addition, the proposed sample selection strategy is based on contributions of the classes, not merely the effort of a single sample. Compared with some other appearance-based methods, the proposed method obtained a competitive result on PolyU multispectral palmprint database.     

An occlusion-adaptive tracker based on sparse representation using alternating direction method of multipliers

Recently, sparse representation has been applied to visual tracking with satisfactory performance. However, partial occlusion and computational complexity are two main obstructions in developing sparse-based tracking. In this paper, a simple yet robust tracker based on patch-based sparse representation is proposed. An adaptive motion model, including adaptive sampling regions and adaptive particle numbers, is proposed to improve the sampling efficiency. A self-adjustable segmentation approach is proposed to segment the target into local patches. A patch-based observation model, which is occlusion-adaptive, is constructed by solving a set of L1-regularized least squares problems. The L1-regularized least squares problem is solved using the alternating direction method of multipliers (ADMM). Both quantitative and qualitative experiments are conducted on several challenging image sequences and the comparisons with several state-of-the-art trackers demonstrate the effectiveness and efficiency of our tracker.     

A sparse representation method based on kernel and virtual samples for face recognition

To improve the classification accuracy of face recognition, a sparse representation method based on kernel and virtual samples is proposed in this paper. The proposed method has the following basic idea: first, it extends the training samples by copying the left side of the original training samples to the right side to form virtual training samples. Then the virtual training samples and the original training samples make up a new training set and we use a kernel-induced distance to determine M nearest neighbors of the test sample from the new training set. Second, it expresses the test sample as a linear combination of the selected M nearest training samples and finally exploits the determined linear combination to perform classification of the test sample. A large number of face recognition experiments on different face databases illustrate that the error ratios obtained by our method are always lower more or less than face recognition methods including the method mentioned in Xu and Zhu [21], the method proposed in Xu and Zhu [39], sparse representation method based on virtual samples (SRMVS), collaborative representation based classification with regularized least square (CRC_RLS), two-phase test sample sparse representation (TPTSSR), and the feature space-based representation method.     

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

A limited training set usually limits the performance of face recognition in practice. Even sparse representation-based methods which outperform in face recognition cannot avoid such situation. In order to effectively improve recognition accuracy of sparse representation-based methods on a limited training set, a novel virtual samples-based sparse representation (VSSR) method for face recognition is proposed in this paper. In the proposed method, virtual training samples are constructed to enrich the size and diversity of a training set and a sparse representation-based method is used to classify test samples. Extensive experiments on different face databases confirm that VSSR is robust to illumination variations and works better than many representative representation-based face recognition methods.     

Infrared moving object detection based on local saliency and sparse representation

The key issue of infrared object detection is to locate moving object in image sequence. In order to improve detection precision, an infrared object detection method based on local saliency and sparse representation is proposed in this paper. Motion information, such as velocity, acceleration components are added into the eigenvectors to build local saliency model. And the approximate position of the infrared target is located based on the local saliency. To accurately extract the infrared object, sparse representation is used to capture complete edge of the object. Experiments show that the proposed method can accurately detect infrared moving objects, and has good robustness to external disturbances and dynamic background.     

A novel method for recognizing face with partial occlusion via sparse representation

In this paper, we propose a novel method to recognize the partially occluded face images based on sparse representation. Generally, occlusions, such as glasses and scarf, fall on some random patch of image's pixels of test images, but which is known to be connected. In our method, all images are divided into several blocks and then an indicator based on linear regression technique is presented to determine whether a block is occluded. We utilize those uncontaminated blocks as the new feature of an image. Finally, the sparse representation-based classification (SRC) method serves as the classifier to recognize unknown faces. In the original work of SRC, the extended SRC (eSRC) scheme is presented to deal with occlusions, which has very heavy computational cost. The experimental results show that our method can achieve good recognition accuracy and has much lower computational cost than eSRC.     

Effect of sparse basis selection on ultrasonic signal representation

Recently, adaptive sparse representations of ultrasonic signals have been utilized to improve the performance of scanning acoustic microscopy (SAM), a common nondestructive tool for failure analysis of microelectronic packages. The adaptive sparse representation of an ultrasonic signal is generated by decomposing it in a learned overcomplete dictionary using a sparse basis selection algorithm. Detection and location of ultrasonic echoes are then performed on the basis of the resulting redundant representation. This paper investigates the effect of sparse basis selection algorithms on ultrasonic signal representation. The overcomplete independent component analysis, focal underdetermined system solver (FOCUSS), and sparse Bayesian learning algorithms are examined. Numerical simulations are performed to quantitatively analyze the efficiency of ultrasonic signal representations. Experiments with ultrasonic A-scans acquired from flip-chip packages are also carried out in the study. The efficiency of ultrasonic signal representations are evaluated in terms of the different criteria that can be used to measure its performance for different SAM applications, such as waveform estimation, echo detection, echo location and C-scan imaging. The results show that the FOCUSS algorithm performs best overall.     

基于双向稀疏表示的鲁棒目标跟踪算法

目前,基于稀疏表示的目标跟踪通常为在目标模板集上重构候选样本的正向模型或者在候选样本集上描述目标模板的反向模型.两个模型的共同点是均需计算候选样本与模板集合之间的稀疏相关系数矩阵.基于此,建立了一个双向联合稀疏表示的跟踪模型,该模型通过L2范数约束正反向稀疏相关系数矩阵达到一致收敛.与之前的单向稀疏表示模型相比,双向稀疏表示跟踪模型在正反向联合求解框架下可以更加充分地挖掘所有候选样本与模板集之间的稀疏映射关系,并将稀疏映射表上对正负模板区分度最好的候选样本作为目标.基于加速逼近梯度(accelerated proximal gradient)快速算法,以矩阵形式推导了双向稀疏表示模型的求解框架,使得候选样本集和目标模板集均以矩阵方式并行求解,在一定程度上提高了计算效率.实验数据表明所提出的算法优于传统的单向稀疏表示目标跟踪算法.     

A face recognition algorithm based on collaborative representation

In this paper, we propose a face recognition algorithm by incorporating a neighbor matrix into the objective function of sparse coding. We first calculate the neighbor matrix between the test sample and each training sample by using the revised reconstruction error of each class. Specifically, the revised reconstruction error (RRE) of each class is the division of the l₂-norm of reconstruction error to the l₂-norm of reconstruction coefficients, which can be used to increase the discrimination information for classification. Then we use the neighbor matrix and all the training samples to linearly represent the test sample. Thus, our algorithm can preserve locality and similarity information of sparse coding. The experimental results show that our algorithm achieves better performance than four previous algorithms on three face databases.     

The infrared and visible image fusion algorithm based on target separation and sparse representation

Although the fused image of the infrared and visible image takes advantage of their complementary, the artifact of infrared targets and vague edges seriously interfere the fusion effect. To solve these problems, a fusion method based on infrared target extraction and sparse representation is proposed. Firstly, the infrared target is detected and separated from the background rely on the regional statistical properties. Secondly, DENCLUE (the kernel density estimation clustering method) is used to classify the source images into the target region and the background region, and the infrared target region is accurately located in the infrared image. Then the background regions of the source images are trained by Kernel Singular Value Decomposition (KSVD) dictionary to get their sparse representation, the details information is retained and the background noise is suppressed. Finally, fusion rules are built to select the fusion coefficients of two regions and coefficients are reconstructed to get the fused image. The fused image based on the proposed method not only contains a clear outline of the infrared target, but also has rich detail information.     

Automatic segmentation of brain MRI in high-dimensional local and non-local feature space based on sparse representation

Automatic extraction of the varying regions of magnetic resonance images is required as a prior step in a diagnostic intelligent system. The sparsest representation and high-dimensional feature are provided based on learned dictionary. The classification is done by employing the technique that computes the reconstruction error locally and non-locally of each pixel. The acquired results from the real and simulated images are superior to the best MRI segmentation method with regard to the stability advantages. In addition, it is segmented exactly through a formula taken from the distance and sparse factors. Also, it is done automatically taking sparse factor in unsupervised clustering methods whose results have been improved.     

Infrared small target tracking based on sample constrained particle filtering and sparse representation

Infrared search and track technology for small target plays an important role in infrared warning and guidance. In view of the tacking randomness and uncertainty caused by background clutter and noise interference, a robust tracking method for infrared small target based on sample constrained particle filtering and sparse representation is proposed in this paper. Firstly, to distinguish the normal region and interference region in target sub-blocks, we introduce a binary support vector, and combine it with the target sparse representation model, after which a particle filtering observation model based on sparse reconstruction error differences between sample targets is developed. Secondly, we utilize saliency extraction to obtain the high frequency area in infrared image, and make it as a priori knowledge of the transition probability model to limit the particle filtering sampling process. Lastly, the tracking result is brought about via target state estimation and the Bayesian posteriori probability calculation. Theoretical analyses and experimental results show that our method can enhance the state estimation ability of stochastic particles, improve the sparse representation adaptabilities for infrared small targets, and optimize the tracking accuracy for infrared small moving targets.     

Palmprint recognition based on the representation in the feature space

In this paper, we propose a palmprint recognition method based on the representation in the feature space. The proposed method seeks to represent the test sample as a linear combination of all the training samples in the feature space and then exploits the obtained linear combination to perform palmprint recognition. We can implement the mapping from the original space to the feature space by using the kernel functions such as radial basis function (RBF). In this method, the selection of the parameter of the kernel function is important. We propose an automatic algorithm for selecting the parameter. The basic idea of the algorithm is to optimize the feature space such that the samples from the same class are well clustered while the samples from different classes are pushed far away. The proposed criterion measures the goodness of a feature space, and the optimal kernel parameter is obtained by minimizing this criterion. Experimental results on multispectral palmprint database show that the proposed method is more effective than 2DPCA, 2DLDA, AANNC, CRC_RLS, nearest neighbor method (NN) and competitive coding method in terms of the correct recognition rate.     

基于稀疏表示的核素能谱特征提取及核素识别

提出了一种基于稀疏表示的核素能谱特征提取方法,其实质是将核素能谱在区分性最好的稀疏原子上进行投影。利用稀疏分解方法对核素能谱进行稀疏分解,提取分解系数向量作为表征核素的特征向量,通过模式识别分类方法建立分类模型实现核素识别。与传统稀疏分解方法的区别在于：在能谱稀疏分解过程中按照稀疏字典中的原子排列顺序顺次进行分解;其次,分解目的在于特征提取,即最终提取到的特征对不同核素具有可区分性,并不要求核素能谱的重构精度。在²⁴¹Am, ¹³³Ba, ⁶⁰Co, ¹³⁷Cs, ¹³¹I和¹⁵²Eu共6种核素1200个能谱数据上进行了核素识别实验,7种不同分类算法的平均识别率达到91.71%,实验结果的统计分析表明,本文提出的特征提取方法识别准确率显著地高于两种传统核素能谱特征提取方法准确率。     

Palmprint recognition method based on score level fusion

Different palmprint recognition methods have different advantages. The texture- and feature-based palmprint recognition methods can well exploit the minutiae of the palmprint but are not very robust to the possible variation such as the rotation and shift of the palm. The representation-based palmprint recognition method can well take advantage of the holistic information but seems not to be able to fully exploit the minutiae of the palmprint. In this paper, we propose to fuse the competitive coding method and two-phase test sample sparse representation (TPTSR) method for palmprint recognition. As one of representation-based methods, TPTSR method takes the whole palmprint image as the input and determines the contribution of the training samples of each class in representing the test sample. TPTSR also uses the contribution to calculate the similarities between the test sample and every class. The competitive coding method is a feature-based method and is highly complementary with TPTSR. We use a weighted fusion scheme to combine the matching scores generated from TPTSR and the competitive coding method. The experimental results show that the proposed method can obtain a very high classification accuracy and outperforms both TPTSR and the competitive coding method.     

Infrared and visible image fusion method based on saliency detection in sparse domain

Infrared and visible image fusion is a key problem in the field of multi-sensor image fusion. To better preserve the significant information of the infrared and visible images in the final fused image, the saliency maps of the source images is introduced into the fusion procedure. Firstly, under the framework of the joint sparse representation (JSR) model, the global and local saliency maps of the source images are obtained based on sparse coefficients. Then, a saliency detection model is proposed, which combines the global and local saliency maps to generate an integrated saliency map. Finally, a weighted fusion algorithm based on the integrated saliency map is developed to achieve the fusion progress. The experimental results show that our method is superior to the state-of-the-art methods in terms of several universal quality evaluation indexes, as well as in the visual quality.     

基于小波分析和SVM的人脸表情识别

提出了一种能量特征与支持向量机(SVM)相结合的面部表情识别方法。首次提出了小波能量特征在表情识别中的应用。由于小波能量特征具有表现表情纹路的能力,与人脸表情识别的要求正好相符,所以把小波能量特征加入到原始图像中,再用Fisher线性判别法(FLD)进行特征提取,然后采用SVM进行识别。通过对在日本JAFFE人脸表情库中的七种表情(生气、厌恶、恐惧、高兴、中性、悲伤、惊讶)进行实验,验证了该方法的有效性。它不仅能获得高的表情识别率,而且过程简单,易于实现。