Zhenghua Zhou

Pose and illumination variable face recognition via sparse representation and illumination dictionary

This paper addresses the problem of face recognition under pose and illumination variations, and proposes a novel algorithm inspired by the idea of sparse representation (SR). In order to make the SR early designed for the pose-invariant face recognition suitable for the case of pose variation, a multi-pose weighted sparse representation (MW-SR) algorithm is proposed to emphasize the contributions of the similar poses in the representation of the test image. Furthermore, when some illumination variations are added to the images, it is more reasonable to take advantage of the results of pose variable recognition and avoid the traditional SR method that adds all kinds of images with pose and illumination variations in the training dictionary. Here, a novel idea of the proposed algorithms is adding a general illumination dictionary to the training dictionary, and that once the illumination dictionary is designed, it is common for the other face databases. Extensive experiments illustrate that the proposed algorithms perform better than some existing methods for the face recognition under pose and illumination variations.

Recovering low-rank and sparse matrix based on the truncated nuclear norm

Recovering the low-rank, sparse components of a given matrix is a challenging problem that arises in many real applications. Existing traditional approaches aimed at solving this problem are usually recast as a general approximation problem of a low-rank matrix. These approaches are based on the nuclear norm of the matrix, and thus in practice the rank may not be well approximated. This paper presents a new approach to solve this problem that is based on a new norm of a matrix, called the truncated nuclear norm (TNN). An efficient iterative scheme developed under the linearized alternating direction method multiple framework is proposed, where two novel iterative algorithms are designed to recover the sparse and low-rank components of matrix. More importantly, the convergence of the linearized alternating direction method multiple on our matrix recovering model is discussed and proved mathematically. To validate the effectiveness of the proposed methods, a series of comparative trials are performed on a variety of synthetic data sets. More specifically, the new methods are used to deal with problems associated with background subtraction (foreground object detection), and removing shadows and peculiarities from images of faces. Our experimental results illustrate that our new frameworks are more effective and accurate when compared with other methods.

Human face recognition based on ensemble of polyharmonic extreme learning machine

This paper proposes a classifier named ensemble of polyharmonic extreme learning machine, whose part weights are randomly assigned, and it is harmonic between the feedforward neural network and polynomial. The proposed classifier provides a method for human face recognition integrating fast discrete curvelet transform (FDCT) with 2-dimension principal component analysis (2DPCA). FDCT is taken to be a feature extractor to obtain facial features, and then these features are dimensionality reduced by 2DPCA to decrease the computational complexity before they are input to the classifier. Comparison experiments of the proposed method with some other state-of-the-art approaches for human face recognition have been carried out on five well-known face databases, and the experimental results show that the proposed method can achieve higher recognition rate.

A novel approach for fault diagnosis of induction motor with invariant character vectors

This paper proposes a novel approach for the fault diagnosis of induction motors. The invariant character vectors of fault signals are first extracted from the training samples. A single-class support vector machine (SC-SVM) is then used to detect the occurrence of faults, and the obtained invariant character vectors are employed as the desired references to classify the faults associated with the nearest neighbor classifier. The new diagnosis algorithm is validated for an induction motor (Y132S-4), which has shown excellent performance.

Dynamic neural modeling of fatigue crack growth process in ductile alloys

In this paper, the dynamic neural modeling of fatigue crack growth process in ductile alloys is studied. It is shown that a fatigue crack growth process is treated as a virtual nonlinear dynamic system. A nonlinear model can then be developed with two dynamic neural networks (DNNs), designed to learn the dynamics of crack opening stress and crack length growth, respectively. The DNNs are constructed by adding the tapped-delay-line memories to both the input and the output layers of conventional single layered feed-forward neural networks (SLFNs). Since the delayed output feedback components are placed in parallel with the hidden nodes, a generalized hidden layer is formulated. The DNNs are then trained in the sense that the input weights of the DNNs are uniformly randomly selected in a range, and the generalized output weights are globally optimized with the batch learning type of least squares. The well-trained dynamic neural model is capable of capturing all dynamic characteristics of crack growth process. The excellent performance of the dynamic neural model of fatigue crack growth process is confirmed with the experimental data of 2025-T351 and 7075-T6 aluminum alloy specimens.

Leukocyte image segmentation using feed forward neural networks with random weights

As we know, segmentation is an important countermeasure in the study of automated leukocyte image recognition. This paper proposes a novel method for leukocyte image segmentation, which is based on converting the segmentation to a classification issue. First, an effective classifier called feed forward neural network with random weights is employed to classify all the pixels in a leukocyte image. Then, according to the classification results, the regions of nucleus and cytoplasm are extracted, respectively, to achieve the segmentation. The experiments show that the proposed method is more effective compared with some existing approaches, and can segment the nucleus and cytoplasm well. Meanwhile, the advantage of the proposed method in leukocyte recognition is also reviewed and analyzed.

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.

A novel segmentation algorithm for nucleus in white blood cells based on low-rank representation

White blood cells (WBCs) segmentation is a challenging problem in the study of automated morphological systems, due to both the complex nature of the cells and the uncertainty that is present in video microscopy. This paper investigates how to boost the effects of region-based nucleus segmentation in WBCs by means of optimal thresholding and low-rank representation. The main idea is firstly using optimal thresholding to obtain the possible uniform WBC regions in the input image. After that, a manifold-based low-rank representation technique is employed to infer a unified affinity matrix that implicitly encodes the segmentation of the pixels of possible WBC regions. This is achieved by separating the low-rank affinities from the feature matrix into a pair of sparse and low-rank matrices. The experiments show that the proposed method is possible to produce better segmentation results compared with existing approaches.

Super-resolution reconstruction: using non-local structure similarity and edge sharpness dictionary

Image super-resolution (SR) reconstruction, which gains high-pixel and multi-detail image from single or several low-pixel images, has attracted increasing interest in recent years. This study proposes a new SR method based on sparse representation, which made good use of the non-local (NL) structure similarity and edge sharpness dictionary. Firstly, all the training patches are classified into different clusters according to diverse edge sharpness of patches. Secondly, different dictionaries are trained for different training patches in each cluster. Thirdly, the NL structure similarity is added into the constraint of NL structure similarity model, and the suitable dictionary is selected for current patch to achieve the coefficients according to the value of edge sharpness of patch. Finally, the high-resolution (HR) image is obtained by integrating HR patches obtained by the product of HR dictionaries and coefficients. Moreover, by calculating edge sharpness, the different dictionaries which adapt to patches with different structure are obtained, and the NL similarity is well utilised and more details are added to HR patch. Compared to some classical and common methods, the proposed method possesses better reconstruction effects in numerical and visual aspects.

Diagnosis of fatigue crack growth with recursive random weight networks

Display Omitted The fatigue crack growth process is treated as a neural network system.The recursive random weight networks are developed to diagnose fatigue crack growth.The input weights of networks are uniformly randomly selected.The output weights of networks are optimized with the batch learning of least squares. Recursive random weight networks (RRWNs) have been developed to diagnose fatigue crack growth in ductile alloys under variable amplitude loading. The fatigue crack growth process is considered as a recursive network system. RRWNs are constructed by taking the current loading, crack opening stress, and the previous computed crack length as inputs of the network system. The input weights of conventional single-layer feed-forward neural networks are uniformly and randomly selected. The output weights of RRWNs are globally optimized with the batch learning type of least squares. The trained RRWNs are capable of determining the dynamics of crack development. The proposed model is validated with fatigue test data for different types of variable amplitude loading in alloys. Compared with other experimental diagnosis models, RRWNs show excellent performance in predicting crack length growth.