Xinge You

Segmentation of retinal blood vessels using the radial projection and semi-supervised approach

Automatic segmentation of retinal blood vessels has become a necessary diagnostic procedure in ophthalmology. The blood vessels consist of two types of vessels, i.e., thin vessels and wide vessels. Therefore, a segmentation method may require two different processes to treat different vessels. However, traditional segmentation algorithms hardly draw a distinction between thin and wide vessels, but deal with them together. The major problems of these methods are as follows: (1) If more emphasis is placed on the extraction of thin vessels, the wide vessels tend to be over detected; and more artificial vessels are generated, too. (2) If more attention is paid on the wide vessels, the thin and low contrast vessels are likely to be missing. To overcome these problems, a novel scheme of extracting the retinal vessels based on the radial projection and semi-supervised method is presented in this paper. The radial projection method is used to locate the vessel centerlines which include the low-contrast and narrow vessels. Further, we modify the steerable complex wavelet to provide better capability of enhancing vessels under different scales, and construct the vector feature to represent the vessel pixel by line strength. Then, semi-supervised self-training is used for extraction of the major structures of vessels. The final segmentation is obtained by the union of the two types of vessels. Our approach is tested on two publicly available databases. Experiment results show that the method can achieve improved detection of thin vessels and decrease false detection of vessels in pathological regions compared to rival solutions.

Shape matching and classification using height functions

We propose a novel shape descriptor for matching and recognizing 2D object silhouettes. The contour of each object is represented by a fixed number of sample points. For each sample point, a height function is defined based on the distances of the other sample points to its tangent line. One compact and robust shape descriptor is obtained by smoothing the height functions. The proposed descriptor is not only invariant to geometric transformations such as translation, rotation and scaling but also insensitive to nonlinear deformations due to noise and occlusion. In the matching stage, the Dynamic Programming (DP) algorithm is employed to find out the optimal correspondence between sample points of every two shapes. The height function provides an excellent discriminative power, which is demonstrated by excellent retrieval performances on several popular shape benchmarks, including MPEG-7 data set, Kimias data set and ETH-80 data set.

Skeletonization of Ribbon-like shapes based on a new wavelet function

A wavelet-based scheme to extract skeleton of Ribbon-like shape is proposed in this paper, where a novel wavelet function plays a key role in this scheme, which possesses three significant characteristics, namely, 1) the position of the local maximum moduli of the wavelet transform with respect to the Ribbon-like shape is independent of the gray-levels of the image. 2) When the appropriate scale of the wavelet transform is selected, the local maximum moduli of the wavelet transform of the Ribbon-like shape produce two new parallel contours, which are located symmetrically at two sides of the original one and have the same topological and geometric properties as that of the original shape. 3) The distance between these two parallel contours equals to the scale of the wavelet transform, which is independent of the width of the shape. This new scheme consists of two phases: 1) Generation of wavelet skeleton-based on the desirable properties of the new wavelet function, symmetry analyses of the maximum moduli of the wavelet transform is described. Midpoints of all pairs of contour elements can be connected to generate a skeleton of the shape, which is defined as wavelet skeleton. 2) Modification of the wavelet skeleton. Thereafter, a set of techniques are utilized for modifying the artifacts of the primary wavelet skeleton. The corresponding algorithm is also developed in this paper. Experimental results show that the proposed scheme is capable of extracting exactly the skeleton of the Ribbon-like shape with different width as well as different gray-levels. The skeleton representation is robust against noise and affine transformation.

Writer identification of Chinese handwriting documents using hidden Markov tree model

Handwriting-based writer identification, a branch of biometrics, is an active research topic in pattern recognition. Since most existing methods and models aim to on-line and/or text-dependent writer identification, it is necessary to propose new methods for off-line, text-independent writer identification. At present, two-dimensional Gabor model is widely acknowledged as an effective and classic method for off-line, text-independent handwriting identification, while it still suffers from some inherent shortcomings, such as the excessive calculational cost. In this paper, we present a novel method based on hidden Markov tree (HMT) model in wavelet domain for off-line, text-independent writer identification of Chinese handwriting documents. Our experiments show this HMT method, compared with two-dimensional Gabor model, not only achieves better identification results but also greatly reduces the elapsed time on computation.

A Blind Watermarking Scheme Using New Nontensor Product Wavelet Filter Banks

As an effective method for copyright protection of digital products against illegal usage, watermarking in wavelet domain has recently received considerable attention due to the desirable multiresolution property of wavelet transform. In general, images can be represented with different resolutions by the wavelet decomposition, analogous to the human visual system (HVS). Usually, human eyes are insensitive to image singularities revealed by different high frequency subbands of wavelet decomposed images. Hence, adding watermarks into these singularities will improve the imperceptibility that is a desired property of a watermarking scheme. That is, the capability for revealing singularities of images plays a key role in designing wavelet-based watermarking algorithms. Unfortunately, the existing wavelets have a limited ability in revealing singularities in different directions. This motivates us to construct new wavelet filter banks that can reveal singularities in all directions. In this paper, we utilize special symmetric matrices to construct the new nontensor product wavelet filter banks, which can capture the singularities in all directions. Empirical studies will show their advantages of revealing singularities in comparison with the existing wavelets. Based upon these new wavelet filter banks, we, therefore, propose a modified significant difference watermarking algorithm. Experimental results show its promising results.

Robust face recognition via occlusion dictionary learning

Sparse representation based classification (SRC) has recently been proposed for robust face recognition. To deal with occlusion, SRC introduces an identity matrix as an occlusion dictionary on the assumption that the occlusion has sparse representation in this dictionary. However, the results show that SRCs use of this occlusion dictionary is not nearly as robust to large occlusion as it is to random pixel corruption. In addition, the identity matrix renders the expanded dictionary large, which results in expensive computation. In this paper, we present a novel method, namely structured sparse representation based classification (SSRC), for face recognition with occlusion. A novel structured dictionary learning method is proposed to learn an occlusion dictionary from the data instead of an identity matrix. Specifically, a mutual incoherence of dictionaries regularization term is incorporated into the dictionary learning objective function which encourages the occlusion dictionary to be as independent as possible of the training sample dictionary. So that the occlusion can then be sparsely represented by the linear combination of the atoms from the learned occlusion dictionary and effectively separated from the occluded face image. The classification can thus be efficiently carried out on the recovered non-occluded face images and the size of the expanded dictionary is also much smaller than that used in SRC. The extensive experiments demonstrate that the proposed method achieves better results than the existing sparse representation based face recognition methods, especially in dealing with large region contiguous occlusion and severe illumination variation, while the computational cost is much lower.

Group Sparse Multiview Patch Alignment Framework With View Consistency for Image Classification

No single feature can satisfactorily characterize the semantic concepts of an image. Multiview learning aims to unify different kinds of features to produce a consensual and efficient representation. This paper redefines part optimization in the patch alignment framework (PAF) and develops a group sparse multiview patch alignment framework (GSM-PAF). The new part optimization considers not only the complementary properties of different views, but also view consistency. In particular, view consistency models the correlations between all possible combinations of any two kinds of view. In contrast to conventional dimensionality reduction algorithms that perform feature extraction and feature selection independently, GSM-PAF enjoys joint feature extraction and feature selection by exploiting l2-norm on the projection matrix to achieve row sparsity, which leads to the simultaneous selection of relevant features and learning transformation, and thus makes the algorithm more discriminative. Experiments on two real-world image data sets demonstrate the effectiveness of GSM-PAF for image classification.

Texture image retrieval based on non-tensor product wavelet filter banks

In this paper, we present a novel method, which uses non-separable wavelet filter banks, to extract the features of texture images for texture image retrieval. Compared to traditional tensor product wavelets (such as db wavelets), our new method can capture more direction and edge information of texture images, which is highly valuable to reflect the essential properties of the texture images. Experiments show that the proposed method is satisfactory and can achieve better retrieval accuracies than db wavelets.

Super-resolution Person re-identification with semi-coupled low-rank discriminant dictionary learning

Person re-identification has been widely studied due to its importance in surveillance and forensics applications. In practice, gallery images are high-resolution (HR) while probe images are usually low-resolution (LR) in the identification scenarios with large variation of illumination, weather or quality of cameras. Person re-identification in this kind of scenarios, which we call super-resolution (SR) person re-identification, has not been well studied. In this paper, we propose a semi-coupled low-rank discriminant dictionary learning (SLD2L) approach for SR person re-identification. For the given training image set which consists of HR gallery and LR probe images, we aim to convert the features of LR images into discriminating HR features. Specifically, our approach learns a pair of HR and LR dictionaries and a mapping from the features of HR gallery images and LR probe images. To ensure that the converted features using the learned dictionaries and mapping have favorable discriminative capability, we design a discriminant term which requires the converted HR features of LR probe images should be close to the features of HR gallery images from the same person, but far away from the features of HR gallery images from different persons. In addition, we apply low-rank regularization in dictionary learning procedure such that the learned dictionaries can well characterize intrinsic feature space of HR and LR images. Experimental results on public datasets demonstrate the effectiveness of SLD2L.

Wavelet-Based Approach to Character Skeleton

Character skeleton plays a significant role in character recognition. The strokes of a character may consist of two regions, i.e., singular and regular regions. The intersections and junctions of the strokes belong to singular region, while the straight and smooth parts of the strokes are categorized to regular region. Therefore, a skeletonization method requires two different processes to treat the skeletons in theses two different regions. All traditional skeletonization algorithms are based on the symmetry analysis technique. The major problems of these methods are as follows. 1) The computation of the primary skeleton in the regular region is indirect, so that its implementation is sophisticated and costly. 2) The extracted skeleton cannot be exactly located on the central line of the stroke. 3) The captured skeleton in the singular region may be distorted by artifacts and branches. To overcome these problems, a novel scheme of extracting the skeleton of character based on wavelet transform is presented in this paper. This scheme consists of two main steps, namely: a) extraction of primary skeleton in the regular region and b) amendment processing of the primary skeletons and connection of them in the singular region. A direct technique is used in the first step, where a new wavelet-based symmetry analysis is developed for finding the central line of the stroke directly. A novel method called smooth interpolation is designed in the second step, where a smooth operation is applied to the primary skeleton, and, thereafter, the interpolation compensation technique is proposed to link the primary skeleton, so that the skeleton in the singular region can be produced. Experiments are conducted and positive results are achieved, which show that the proposed skeletonization scheme is applicable to not only binary image but also gray-level image, and the skeleton is robust against noise and affine transform