Thinning algorithms based on quadtree and octree representations

Thinning is a critical pre-processing step to obtain skeletons for pattern analysis. Quadtree and octree are hierarchical data representations in image processing and computer graphics. In this paper, we present new 2-D area-based and 3-D surface-based thinning algorithms for directly converting quadtree and octree representations to skeletons. The computational complexity of our thinning algorithm for a 2-D or a 3-D image with each length N is respectively O(N²) or O(N³), which is more efficient than the existing algorithms of O(N³) or O(N⁴). Furthermore, our thinning algorithms can lessen boundary noise spurs and are suited for parallel implementation.     

Efficient region segmentation on compressed gray images using quadtree and shading representation

Image segmentation, which partitions the image into homogeneous regions, is a fundamental operation in image processing. Suppose the input gray image with size N×N has been compressed into the compressed image via quadtree and shading representation. Assume that the number of blocks in the representation is B, commonly B<N² due to the compression effect. This paper first derives some closed forms for computing the mean/variance of any block and for calculating the two statistical measures of any merged region in O(1) time. It then presents an efficient O(Bα(B))-time algorithm for performing region segmentation on the compressed image directly where α(B) is the inverse of the Ackerman's function and is a very slowly growing function. With the same time complexity, our results extend the pioneering results by Dillencourt and Samet from the map image to the gray image. In addition, with four real images, experimental results show that our proposed algorithm has about 55.4% execution time improvement ratio when compared to the previous fastest region-segmentation algorithm by Fiorio and Gustedt whose O(N²)-time algorithm is run on the original N×N gray image.     

New progressive image transmission based on quadtree and shading approach with resolution control

Employing the quadtree and Gouraud shading approach, this paper first presents a modified image compression method called the QSC. Then, based on the proposed compression method, a new progressive image transmission (PIT) scheme is presented. In the proposed PIT scheme, the encoding algorithm partitions all the quadtree nodes into several disjoint subsets such that the resolution of nodes in each subset must be in the specified interval. The decoding algorithm reconstructs the partitioned quadtree from coarse to the required quality stage by stage. Experimental results reveal that under the similar peak signal to noise ratio (PSNR) and bits per pixel (bpp), the proposed PIT scheme has a better feature-preserving capability when compared to the reduced-difference pyramid PIT scheme [Optic. Eng. 28 (7) (1989) 708] and the progressive JPEG [JPEB: Still Image Data Compression Standard, New York, 1993].     

A universal texture segmentation and representation scheme based on ant colony optimization for iris image processing

This paper proposes a novel scheme for texture segmentation and representation based on Ant Colony Optimization (ACO). Texture segmentation and texture characteristic expression are two important areas in image pattern recognition. Nevertheless, until now, how to find an effective way for accomplishing these tasks is still a major challenge in practical applications such as iris image processing. We propose a framework for ACO based image processing methods. Considering the specific characteristics of various tasks, such a framework possesses the flexibility of only defining different criteria for ant behavior correspondingly. By defining different kinds of direction probability and movement difficulty for artificial ants, an ACO based image segmentation algorithm and a texture representation method are then presented for automatic iris image processing. Experimental results demonstrated that the ACO based image processing methods are competitive and quite promising, with excellent effectiveness and practicability especially for images with complex local texture situations.     

A geographic information system using quadtrees

We describe the current status of an ongoing research effort to develop a geographic information system based on quadtrees. Quadtree encodings were constructed for area, point and line features for a small area in Northern California. The encoding used was a variant of the linear quadtree. The implementation used a B-tree to organize the list of leaves and allow management of trees too large to fit in core memory. Several database query functions have been implemented, including set operations, region property computations, map editing functions and map subset and windowing functions. A user of the system may access the database via an English-like query language.     

Region oriented compression of color images using fuzzy inference and fast merging

A new region based lossy compression scheme for color images is proposed. The segmentation method belongs to the split and merge category. Splitting is carried out using the watershed transform. In the merging stage, a fuzzy color preserving rule-based system and a novel one-dimensional graph structure are introduced to provide accurate results with reduced computational complexity. The compression part is based on the Shape Adaptive DCT with ΔDC correction method. The quantization matrices used have been designed according to the properties of the employed transform. Promising perceptual results for the low bit rate range compared to previously reported compression methods have also been reported.     

关于多种分割方法的综合集成的研究

图像分割是图像处理的一个重要领域,本文尝试从一个新的角度来理解与研究图像分割的方法,提出将多种分割方法加以综合集成的思路。它包含了三个方面的内容：将图像作合理区域划分;区域分割算法的优选;区域间分割结果的平滑过渡。     

A multisecret sharing scheme for color images based on cellular automata

In this work a new multisecret sharing scheme for secret color images among a set of users is proposed. The protocol allows that each participant in the scheme to share a secret color image with the rest of participants in such a way that all of them can recover all the secret color images only if the whole set of participants pools their shadows. The proposed scheme is based on the use of bidimensional reversible cellular automata with memory. The security of the scheme is studied and it is proved that the protocol is ideal and perfect and that it resists the most important statistical attacks.     

Efficient embedded wavelet codec based on list structure

A new efficient image codec called embedded wavelet coding based on list structure (EWCBL) is proposed in this paper. By combining the techniques of morphological representation and quadtree partitioning, EWCBL effectively exploits both within-subband clustering and cross-subband similarity of wavelet coefficients. Based on the list structure, a fine fractional bit-plane coding is employed to achieve excellent rate-distortion performance. The patterned morphological dilation is introduced to greatly reduce the redundant test operations. Experimental results show that the proposed EWCBL outperforms state-of-the-art embedded codecs for both lossy and lossless compression. Moreover, the good performance and features of embeddedness and scalability are achieved with relatively low complexity.     

A novel image-hiding scheme based on block difference

To transmit a secret-image securely by embedding it into a cover-image without drawing the unintended observer's attention, a novel image-hiding scheme is proposed. By exploring the block correlation between the cover-image and the secret-image, the stego-image quality can be greatly improved. Experimental results demonstrate that the stego-image has a high peak signal-to-noise ratio and the stego-image is almost the same as the cover-image.     

基于边缘信息的分开合并图象分割方法

图象分割是目标识别和图象理解的关键的第一步处理。分开合并方法是一种有效的、实用的图象分割方法。本文提出了基于边缘信息实现分开合并方法，它利用边缘信息解决了自适应确定最佳初始层和在分开、合并过程中度量图象块属性一致性的问题。基于边缘信息的分开合并方法改进了图象分割质量，缩短了处理时间，分割复杂图象的实验结果是令人满意的。     

一个可视化集成图象处理环境

提出了图象处理的一个可视化集成环境，提供了图象和图象分析的可视化以及图象处理算法的集成。在此基础上研究图象处理算法或构造图象理解系统将大大提高工作效率。     

A collaborative representation based projections method for feature extraction

In graph embedding based methods, we usually need to manually choose the nearest neighbors and then compute the edge weights using the nearest neighbors via L2 norm (e.g. LLE). It is difficult and unstable to manually choose the nearest neighbors in high dimensional space. So how to automatically construct a graph is very important. In this paper, first, we give a L2-graph like L1-graph. L2-graph calculates the edge weights using the total samples, avoiding manually choosing the nearest neighbors; second, a L2-graph based feature extraction method is presented, called collaborative representation based projections (CRP). Like SPP, CRP aims to preserve the collaborative representation based reconstruction relationship of data. CRP utilizes a L2 norm graph to characterize the local compactness information. CRP maximizes the ratio between the total separability information and the local compactness information to seek the optimal projection matrix. CRP is much faster than SPP since CRP calculates the objective function with L2 norm while SPP calculate the objective function with L1 norm. Experimental results on FERET, AR, Yale face databases and the PolyU finger-knuckle-print database demonstrate that CRP works well in feature extraction and leads to a good recognition performance.     

Finding rotational symmetries by cyclic string matching

Symmetry is an important shape feature. In this paper, a simple and fast method to detect perfect and distorted rotational symmetries of 2D objects is described. The boundary of a shape is polygonally approximated and represented as a string. Rotational symmetries are found by cyclic string matching between two identical copies of the shape string. The set of minimum cost edit sequences that transform the shape string to a cyclically shifted version of itself define the rotational symmetry and its order. Finally, a modification of the algorithm is proposed to detect reflectional symmetries. Some experimental results are presented to show the reliability of the proposed algorithm.     

A general framework for image fusion based on multi-scale transform and sparse representation

In image fusion literature, multi-scale transform (MST) and sparse representation (SR) are two most widely used signal/image representation theories. This paper presents a general image fusion framework by combining MST and SR to simultaneously overcome the inherent defects of both the MST- and SR-based fusion methods. In our fusion framework, the MST is firstly performed on each of the pre-registered source images to obtain their low-pass and high-pass coefficients. Then, the low-pass bands are merged with a SR-based fusion approach while the high-pass bands are fused using the absolute values of coefficients as activity level measurement. The fused image is finally obtained by performing the inverse MST on the merged coefficients. The advantages of the proposed fusion framework over individual MST- or SR-based method are first exhibited in detail from a theoretical point of view, and then experimentally verified with multi-focus, visible-infrared and medical image fusion. In particular, six popular multi-scale transforms, which are Laplacian pyramid (LP), ratio of low-pass pyramid (RP), discrete wavelet transform (DWT), dual-tree complex wavelet transform (DTCWT), curvelet transform (CVT) and nonsubsampled contourlet transform (NSCT), with different decomposition levels ranging from one to four are tested in our experiments. By comparing the fused results subjectively and objectively, we give the best-performed fusion method under the proposed framework for each category of image fusion. The effect of the sliding window’s step length is also investigated. Furthermore, experimental results demonstrate that the proposed fusion framework can obtain state-of-the-art performance, especially for the fusion of multimodal images.     

图像归一化与伪Zernike矩的鲁棒水印算法研究*

以基于矩的图像归一化技术及伪Zernike矩相关知识为基础,提出一种可有效抵抗几何攻击的数字水印新算法。算法首先利用归一化技术将原始图像映射到几何不变空间内;然后结合不变质心理论提取出归一化图像的重要区域;最后通过量化调制伪Zernike矩幅值将水印嵌入到重要区域中。仿真实验表明,该算法不仅具有较好的透明性,而且对常规信号处理(滤波、锐化、加噪和JPEG压缩等)和几何攻击(全局仿射变换、局部失真等)均具有较好的鲁棒性。     

A random grid-based cyclic access structure VSS scheme for multiple secret images

Visual secret sharing (VSS) schemes based on visual cryptography (VC) or random grids (RGs) have been proposed in the past decade with the advantages of easy implementation, efficiency secret recovering and perfect security. As the concept of multiple secret images has gained more and more attention in academia, the novel concept of VC-based VSS with cyclic access structure has been discussed recently, which is a special case of multiple VSS, allowing participants to reconstruct the secret with the one next or last to him/her in a cyclic order. To obtain the benefit of RG-based VSS compared with VC-based VSS, this paper proposes the new VSS scheme with cyclic access structure for multiple secret images by random grids. The experimental results and theoretical security analysis demonstrate the feasibility.     

A novel image watermarking scheme based on amplitude attack

This paper presents a novel image watermark scheme based on the characteristics of amplitude attacks. First of all, the analysis of amplitude attacks is performed. Then the amplitude attacks are categorized into three types: positive attack, negative attack and random attack. Finally, based on these attack types, we design three corresponding detectors. The detectors remove the unreliable discrete cosine transform (DCT) coefficients in the attacked image so that only reliable coefficients are used for the extraction of the watermark embedded. The experimental results indicate that the proposed technique improves robustness significantly without sacrificing the false alarm rate.     

High-capacity image hiding scheme based on vector quantization

A novel grayscale image hiding scheme that is capable of hiding multiple secret images into a host image of the same size is proposed in this paper. The secret images to be hidden are first compressed by vector quantization with additional index compression process. Then, the compressed secret images are encrypted and embedded into the least-significant bits of the host pixels. To provide good image quality of the stego-image, the modulus function and the image property are employed to hide the secret bits into the host pixels and determine the number of hidden bits in each host pixel, respectively. According to the results, the proposed scheme provides a higher hiding capacity and a higher degree of security than that of the virtual image cryptosystem.