Zhan-Li Sun

Face recognition with multi-resolution spectral feature images

The one-sample-per-person problem has become an active research topic for face recognition in recent years because of its challenges and significance for real-world applications. However, achieving relatively higher recognition accuracy is still a difficult problem due to, usually, too few training samples being available and variations of illumination and expression. To alleviate the negative effects caused by these unfavorable factors, in this paper we propose a more accurate spectral feature image-based 2DLDA (two-dimensional linear discriminant analysis) ensemble algorithm for face recognition, with one sample image per person. In our algorithm, multi-resolution spectral feature images are constructed to represent the face images; this can greatly enlarge the training set. The proposed method is inspired by our finding that, among these spectral feature images, features extracted from some orientations and scales using 2DLDA are not sensitive to variations of illumination and expression. In order to maintain the positive characteristics of these filters and to make correct category assignments, the strategy of classifier committee learning (CCL) is designed to combine the results obtained from different spectral feature images. Using the above strategies, the negative effects caused by those unfavorable factors can be alleviated efficiently in face recognition. Experimental results on the standard databases demonstrate the feasibility and efficiency of the proposed method.

Application of BW-ELM model on traffic sign recognition

Traffic sign recognition is an important and active research topic of intelligent transport system. With a constant increasing of the training database size, not only the recognition accuracy, but also the computation complexity should be considered in designing a feasible recognition approach. In this paper, an effective and efficient algorithm based on a relatively new artificial neural network, extreme learning machine (ELM), is proposed for traffic sign recognition. In the proposed algorithm, the locally normalized histograms of the oriented gradient (HOG) descriptors, which are extracted from the traffic sign images, are used as the features and the inputs of the ELM classification model. Moreover, the ratio of features between-category to within-category sums of squares (BW) is designed as a feature selection criterion to improve the recognition accuracy and to decrease the computation burden. Application on a well known database, German traffic sign recognition benchmark (GTSRB) dataset, demonstrates the feasibility and efficiency of the proposed BW-ELM model.

Depth Estimation of Face Images Using the Nonlinear Least-Squares Model

In this paper, we propose an efficient algorithm to reconstruct the 3D structure of a human face from one or more of its 2D images with different poses. In our algorithm, the nonlinear least-squares model is first employed to estimate the depth values of facial feature points and the pose of the 2D face image concerned by means of the similarity transform. Furthermore, different optimization schemes are presented with regard to the accuracy levels and the training time required. Our algorithm also embeds the symmetrical property of the human face into the optimization procedure, in order to alleviate the sensitivities arising from changes in pose. In addition, the regularization term, based on linear correlation, is added in the objective function to improve the estimation accuracy of the 3D structure. Further, a model-integration method is proposed to improve the depth-estimation accuracy when multiple nonfrontal-view face images are available. Experimental results on the 2D and 3D databases demonstrate the feasibility and efficiency of the proposed methods.

Depth Estimation of Face Images Based on the Constrained ICA Model

In this paper, we propose a novel and efficient algorithm to reconstruct the 3-D structure of a human face from one or a number of its 2-D images with different poses. In our proposed algorithm, the rotation and translation process from a frontal-view face image to a nonfrontal-view face image is at first formulated as a constrained independent component analysis (cICA) model. Then, the overcomplete ICA problem is converted into a normal ICA problem by incorporating a prior from the CANDIDE 3-D face model. Furthermore, the CANDIDE model is employed to construct a reference signal that is used in both the initialization and the objective function of the cICA model. Moreover, a model-integration method is proposed to improve the depth-estimation accuracy when multiple nonfrontal-view face images are available. An important advantage of the proposed algorithm is that no frontal-view face image is required for the estimation of the corresponding 3-D face structure. Experimental results on a real 3-D face image database demonstrate the feasibility and efficiency of the proposed method.

Directionlet-based denoising of SAR images using a Cauchy model

A new denoising algorithm based on directionlet transform using a Cauchy probability density function (PDF) is proposed to remove speckle noise. First, an anisotropic directionlet transform is taken on the logarithmically transformed SAR images. The directionlet transform coefficients of reflectance image are modeled as a zero-location Cauchy PDF, while the distribution of speckle noise is modeled as an additive Gaussian distribution with zero-mean. Then a maximum a posteriori (MAP) estimator is designed using the assumed priori models. And a regression-based method is proposed to estimate the parameters from the noisy observations. Finally, the performance of the proposed algorithm is compared with those of existing despeckling methods applied on both synthetic speckled images and actual SAR images. Experimental results show that the proposed scheme efficiently removes speckle noise from SAR images. Graphical abstractDisplay Omitted Highlights? Directionlet transform based on lattice is used to represent the SAR image. ? Cauchy distribution with one parameter is employed to fit the detail coefficients. ? Parameter is estimated in frequency domain instead of spatial domain. ? Edge preservation and ratio image are used as evaluation indexes of despeckling.

Tumor Classification Using Eigengene-Based Classifier Committee Learning Algorithm

Eigengene extracted by independent component analysis (ICA) is one kind of effective feature for tumor classification. In this letter, a novel tumor classification approach is proposed by using eigengene and support vector machine (SVM) based classifier committee learning (CCL) algorithm. In this method, a strategy of random feature subspace division is designed to improve the diversity of weaker classifiers. Gene expression data constructed by different feature subspaces are modeled by ICA, respectively. And the corresponding eigengene sets extracted by the ICA algorithm are used as the inputs of the weaker SVM classifiers. Moreover, a strategy of Bayesian sum rule (BSR) is designed to integrate the outputs of the weaker SVM classifiers, and used to provide a final decision for the tumor category. Experimental results on three DNA microarray datasets demonstrate that the proposed method is effective and feasible for tumor classification.

A local spectral feature based face recognition approach for the one-sample-per-person problem

Abstract Face recognition for the one-sample-per-person problem has received increasing attention owing to its wide range of potential applications. However, since only one training image is available for each person, and the face images may have large appearance variations, how to achieve a high recognition accuracy is still a challenging work. In this paper, we propose a more accurate local spectral feature based face recognition approach for the one-sample-per-person problem. In the proposed algorithm, multi-resolution local spectral features are first extracted to represent the face images to enlarge the training set. A weaker classifier is then constructed based on the spectral features of each local region. Since a good diversity is observed for the outputs of the weaker classifiers, a strategy of classifier committee learning is adopted to combine the results obtained from different local spectral features. Moreover, inspired by the fact that the iterations are completely independent of each other, a scheme of multiple worker based parallel computing is designed to improve the loop speed by distributing iterations to the MATLAB workers simultaneously. Experimental results on the standard databases demonstrate the feasibility and effectiveness of the proposed method.

Modified sparse representation based image super-resolution reconstruction method

To improve the geometric structure and texture features of reconstructed images, a novel image super-resolution reconstruction (ISR) method based on modified sparse representation, here denoted by MSR_ISR, is discussed in this paper. In this algorithm, edge and texture features of images are synchronously considered, and the over-complete sparse dictionaries of high resolution (HR) and low resolution (LR) image patches, behaving clearer structure features, are learned by feature classification based fast sparse coding (FSC) algorithm. A LR image is first preprocessed by contourlet transform method to denoise unknown noise. Furthermore, four gradient feature images of the LR image preprocessed are extracted. For HR image patches, the edge features are extracted by Canny operator. Then using these edge pixel values as the benchmark to determine whether each image patchs center value is equal to one of edge pixel values, then the edge and texture image patches can be marked out. For gradient image patches, they are first classified by the extreme learning machine (ELM) classifier, thus, corresponding to the class label sequence of LR image patches, the HR image features can also be classified. Furthermore, using FSC algorithm based on the k-means singular value decomposition (K-SVD) model, the edge and texture feature classification dictionaries of HR and LR image patches can be trained. Utilized HR and LR dictionaries trained, a LR image can be reconstructed well. In test, the artificial LR images, namely degraded natural images, are used to testify our ISR method proposed. Utilized the signal noise ratio (SNR) criterion to estimate the quality of reconstructed images and compared with other algorithms of the common K-SVD, FSC and FSC based K-SVD without considering feature classification technique, simulation results show that our method has clear improvement in visual effect and can retain well image edge and texture features.

An eigen decomposition based rank parameter selection approach for the NRSFM algorithm

Non-rigid structure from motion (NRSFM) with an affine structure from motion (aSFM) kernel (NRSFM-aSFM) is a relative novel and robust 3D shape recovery algorithm to the abrupt deformations. Nevertheless, the estimated 3D shapes generally fluctuate with the variation of rank parameter, i.e., the number of shape bases. Therefore, it is necessary to develop an effective method to select the rank parameter. In this paper, we propose an eigen decomposition based rank parameter selection approach, which can automatically select the optimal or an approximately optimal rank parameter for the NRSFM-aSFM algorithm. In the proposed method, a symmetric matrix is first constructed to simplify the singular value estimation. Further, the QR decomposition based iterations are carried out to compute the eigenvalues of the observation matrix. Finally, the rank parameter is estimated according to the cumulative sum of eigenvalues by setting a referred threshold value. The experimental results on several widely used sequences demonstrate the effectiveness and feasibility of the proposed method.

Low-rank and eigenface based sparse representation for face recognition.

In this paper, based on low-rank representation and eigenface extraction, we present an improvement to the well known Sparse Representation based Classification (SRC). Firstly, the low-rank images of the face images of each individual in training subset are extracted by the Robust Principal Component Analysis (Robust PCA) to alleviate the influence of noises (e.g., illumination difference and occlusions). Secondly, Singular Value Decomposition (SVD) is applied to extract the eigenfaces from these low-rank and approximate images. Finally, we utilize these eigenfaces to construct a compact and discriminative dictionary for sparse representation. We evaluate our method on five popular databases. Experimental results demonstrate the effectiveness and robustness of our method.