Partition-based weighted sum filters for image restoration

We develop the concept of partitioning the observation space to build a general class of filters referred to as partition-based weighted sum (PWS) filters. In the general framework, each observation vector is mapped to one of M partitions comprising the observation space, and each partition has an associated filtering function. We focus on partitioning the observation space utilizing vector quantization and restrict the filtering function within each partition to be linear. In this formulation, a weighted sum of the observation samples forms the estimate, where the weights are allowed to be unique within each partition. The partitions are selected and weights tuned by training on a representative set of data. It is shown that the proposed data adaptive processing allows for greater detail preservation when encountering nonstationarities in the data and yields superior results compared to several previously defined filters. Optimization of the PWS filters is addressed and experimental results are provided illustrating the performance of PWS filters in the restoration of images corrupted by Gaussian noise.     

Maximum minimal distance partitioning of the /spl Zopf//sup 2/ lattice

We study the problem of dividing the /spl Zopf//sup 2/ lattice into partitions so that minimal intra-partition distance between the points is maximized. We show that this problem is analogous to the problem of sphere packing. An upper bound on the achievable intra-partition distances for a given number of partitions follows naturally from this observation, since the optimal sphere packing in two dimensions is achieved by the hexagonal lattice. Specific instances of this problem, when the number of partitions is 2/sup m/, were treated in trellis-coded modulation (TCM) code design by Ungerboeck (1982) and others. It is seen that methods previously used for set partitioning in TCM code design are asymptotically suboptimal as the number of partitions increases. We propose an algorithm for solving the /spl Zopf//sup 2/ lattice partitioning problem for an arbitrary number of partitions.     

Synthesis and Time Partitioning for Reconfigurable Systems

This paper aims to introduce a time partitioning algorithm which is an important step during the design process for fully reconfigurable systems. This algorithm is used to solve the time partitioning problem. It divides the input task graph model to an optimal number of partitions and puts each task in the appropriate partition so that the latency of the input task graph is optimal. Also a part of this paper is consecrated for implementation of some examples on a fully reconfigurable architecture following our approach.     

Temporal Partitioning Data Flow Graphs for Dynamically Reconfigurable Computing

FPGA-based configurable computing machines are evolving rapidly in large signal processing applications due to flexibility and high performance. In this paper, given a reconfigurable processing unit (RPU) with a logic capacity of A_RPU and a computational task represented by a data flow graph G = (V, E, W), we propose a network flow-based multiway task partitioning algorithm to minimize communication costs for temporal partitioning. The proposed algorithm obtains an optimal solution with minimum interconnection under area constraints. The optimal solution is a cut set. In our approach, two techniques are applied. In the initial partition, any feasible min-cut is produced by the proposed network flow-based algorithm, so a set of feasible min-cuts is obtained. From the feasible solutions, the scheduling technique selects an optimal global solution.     

Region-based image coding using polynomial intensity functions

The vast majority of coded images are real-world images. These images consist of distinct objects within a scene, where each object has its own reflective, textural and lighting characteristics. Region-based image coding encodes these images by partitioning the scene into objects, and then describing each object's characteristics using a set of parameters. The paper uses orthonormal polynomial functions to describe the lighting and reflective characteristics of each object. The coefficients of these polynomials are coded with linear quantisers that have their decision boundaries spaced according to rate-distortion considerations. The textural component of each object is coded using vector quantisation of the autocorrelation coefficients of the residual. The partitioning of the image into distinct objects is achieved with a segmentation algorithm which attempts to maximise the rate-distortion performance of the encoding procedure as a whole. In doing so, the segmentation algorithm partitions the image into distinct objects as well as providing estimates for the optimal bit allocations among the polynomial coefficients. Results generated by this method show reconstructions with quality superior to other region-based methods, both objectively and subjectively     

Wavelet-based space-frequency compression of ultrasound images

This paper describes the compression of grayscale medical ultrasound images using a recent compression technique, i.e., space-frequency segmentation (SITS). This method finds the rate-distortion optimal representation of an image from a large set of possible space-frequency partitions and quantizer combinations and is especially effective when the images to code are statistically inhomogeneous, which is the case for medical ultrasound images. We implemented a compression application based on this method and tested the algorithm on representative ultrasound images. The result is an effective technique that performs better than a leading wavelet-transform coding algorithm, i.e., set partitioning in hierarchical trees (SPIHT), using standard objective distortion measures. To determine the subjective qualitative performance, an expert viewer study was run by presenting ultrasound radiologists with images compressed using both SFS and SPIHT. The results confirmed the objective performance rankings. Finally, the performance sensitivity of the space-frequency codec is shown with respect to several parameters, and the characteristic space-frequency partitions found for ultrasound images are discussed     

Clustering source output bits and equalizing bit error sensitivity to improve the quality and robustness of transmitted images over wireless channels

A joint design of source coding and channel coding is proposed to transmit images over error-prone wireless channels. First, the importance of each source output bit is quantified in bit error sensitivity (BES). Next, clustered set partitioning in hierarchical trees (C-SPIHT) is adopted to cluster SPIHT output bits so that the resultant bit-clusters have distinct BES. Then, we prove that equalizing the mean BES of bit-clusters provides the optimal assignment of channel coding rates for the unequal error protection. Besides, to achieve the best PSNR performance under a transmission rate, we use a heuristic method to allocate the source coding rate and channel coding rate. Simulation results show that, under different channel bit error rates, our design not only improves the mean PSNR performance, but also reduces the variations of PSNR performance, i.e. the robustness of PSNR to the channel noise interference is improved.     

Predicting group partitions in mobile ad hoc networks

Group mobility is prevalent in many mobile ad hoc network applications such as disaster recovery, military actions, etc., and group partitions are unavoidable in such kinds of dynamic networks. Group partition may occur when mobile nodes move in diverse mobility patterns and causes the network to be partitioned into disconnected components. It may result in severe link disconnections, which then interrupt intergroup communications. By examining the group mobility pattern, we can predict the possibility of network partitions, and thus minimize the amount of communication disruptions. In this paper, we introduce a system for predicting potential group partitions in mobile ad hoc networks. On the basis of historical group mobility information, a quadratic regression model is formulated to predict the direction and speed of a group's movement. A group's micromovement is ignored and is replaced by significant linear displacement to measure its mobility to improve the prediction accuracy. We also discuss the notion of safe distance between adjacent groups, based on which the time duration before the occurrence of group partitioning can be measured. Experimental results show that our proposed prediction method demonstrates its effectiveness and efficiency in group partition predictions such that remedial actions can be taken in advance to avoid network disconnection. Copyright © 2011 John Wiley & Sons, Ltd.     

Alphabet Partitioning Techniques for Semiadaptive Huffman Coding of Large Alphabets

Practical applications that employ entropy coding for large alphabets often partition the alphabet set into two or more layers, and encode each symbol by using some suitable prefix coding for each layer. In this paper, we formulate the problem of finding an alphabet partitioning for the design of a two-layer semiadaptive code as an optimization problem, and give a solution based on dynamic programming. However, the complexity of the dynamic programming approach can be quite prohibitive for a long sequence and a very large alphabet size. Hence, we also give a simple greedy heuristic algorithm whose running time is linear in the length of the input sequence, irrespective of the underlying alphabet size. Although our dynamic programming and greedy algorithms do not provide a globally optimal solution for the alphabet partitioning problem, experimental results demonstrate that superior prefix coding schemes for large alphabets can be designed using our new approach     

结合图像局部信息和Hausdorff距离的活动轮廓模型医学图像分割算法

本文提出了一种新的基于距离局部信息的活动轮廓摸型。该模型的能量函数将区域可扩展能量项(region scalable fitting, RSF)和Hausdorff距离项结合,其中RSF项在目标边缘附近起主导作用,用来吸引水平集函数曲线到达目标边界;而Hausdorff距离由于包含了局部区域的相似信息,可以提高分割方法的稳定性。在保证分割精度的情况下,相对于区域可伸缩拟合及局部巴氏距离的活动轮廓模型RSFB方法,本文方法具有更快的收敛速度和更好的参数选择鲁棒性,对于解决图像分割中的边界模糊和噪声问题效果显著。实验结果显示本文提出的方法在超声图像和不均匀图像的分割中都有非常好的效果,且计算量较小。      

Vector coding for partial response channels

A linear technique for combining equalization and coset codes on partial response channels with additive white Gaussian noise is developed. The technique, vector coding, uses a set of transmit filters or `vectors' to partition the channel into an independent set of parallel intersymbol interference (ISI)-free channels for any given finite (or infinite) block length. The optimal transmit vectors for such channel partitioning are shown to be the eigenvectors of the channel covariance matrix for the specified block length, and the gains of the individual channels are the eigenvalues. An optimal bit allocation and energy distribution, are derived for the set of parallel channels, under an accurate extension of the continuous approximation for power in optimal multidimensional signal sets for constellations with unequal signal spacing in different dimensions. Examples are presented that demonstrate performance advantages with respect to zero-forcing decision feedback methods that use the same coset code on the same partial response channel. Only resampling the channel at an optimal rate and assuming no errors in the feedback path will bring the performance of the decision feedback methods up to the level of the vector coded system     

Automated seeded lesion segmentation on digital mammograms

Segmenting lesions is a vital step in many computerized mass-detection schemes for digital (or digitized) mammograms. The authors have developed two novel lesion segmentation techniques-one based on a single feature called the radial gradient index (RGI) and one based on simple probabilistic models to segment mass lesions, or other similar nodular structures, from surrounding background. In both methods a series of image partitions is created using gray-level information as well as prior knowledge of the shape of typical mass lesions. With the former method the partition that maximizes the RGI is selected. In the latter method, probability distributions for gray-levels inside and outside the partitions are estimated, and subsequently used to determine the probability that the image occurred for each given partition. The partition that maximizes this probability is selected as the final lesion partition (contour). The authors tested these methods against a conventional region growing algorithm using a database of biopsy-proven, malignant lesions and found that the new lesion segmentation algorithms more closely match radiologists' outlines of these lesions. At an overlap threshold of 0.30, gray level region growing correctly delineates 62% of the lesions in the authors' database while the RGI and probabilistic segmentation algorithms correctly segment 92% and 96% of the lesions, respectively     

Asymptotic Bayesian decision feedback equalizer using a set of hyperplanes

We present a signal space partitioning technique for realizing the optimal Bayesian decision feedback equalizer (DFE). It is known that when the signal-to-noise ratio (SNR) tends to infinity, the decision boundary of the Bayesian DFE is asymptotically piecewise linear and consists of several hyperplanes. The proposed technique determines these hyperplanes explicitly and uses them to partition the observation signal space. The resulting equalizer is made up of a set of parallel linear discriminant functions and a Boolean mapper. Unlike the existing signal space partitioning technique of Kim and Moon (1998), which involves complex combinatorial search and optimization in design, our design procedure is simple and straightforward, and guarantees to achieve the asymptotic Bayesian DFE.     

Reconstruction of coarse depth estimates using hierarchical image partitions

This paper presents a novel depth map enhancement method which takes as inputs a single view and an associated coarse depth estimate. The depth estimate is reconstructed according to the region boundaries proposed within a set of image partitions of the associated view. Image partitions are determined through a color-based region merging procedure and organized within a hierarchy. Novel depth estimates are computed according to plane-fitting procedures using the proposed regions as support and selected coarse depth estimates. The use of partition hierarchies provides an efficient mechanism for evaluating plane-fitting results over various scales and, in this way, reduce the dependency of the results on the quality of a single color-based segmentation. Experimental results on publicly available test sequences illustrate the potential of the algorithm in significantly improving low quality depth estimates.     

Geometrically uniform partitions of L×MPSK constellations andrelated binary trellis codes

The theory of geometrically uniform trellis codes is applied to the case of multidimensional PSK (phase shift keying) constellations. The symmetry group of an L×MPSK (M-ary PSK) constellation is completely characterized. Conditions for rotational invariance of geometrically uniform partitions of a signal constellation are given. Through suitable algorithms, geometrically uniform partitions of L×MPSK (M=4,8,16 and L=1,2,3,4) constellations are found, which present good characteristics in terms of the set of distances at a given partition level, the maximum obtainable rotational invariance, and the isomorphism of the quotient group associated with the partition. These partitions are used as starting points in a search for good geometrically uniform trellis codes based on binary convolutional codes     

Phishing web image segmentation based on improving spectral clustering

This paper proposes a novel phishing web image segmentation algorithm which based on improving spectral clustering. Firstly, we construct a set of points which are composed of spatial lo-cation pixels and gray levels from a given image. Secondly, the data is clustered in spectral space of the similar matrix of the set points, in order to avoid the drawbacks of K-means algorithm in the con-ventional spectral clustering method that is sensitive to initial clustering centroids and convergence to local optimal solution, we introduce the clone operator, Cauthy mutation to enlarge the scale of clustering centers, quantum-inspired evolutionary algorithm to find the global optimal clustering centroids. Compared with phishing web image segmentation based on K-means, experimental results show that the segmentation performance of our method gains much improvement. Moreover, our method can convergence to global optimal solution and is better in accuracy of phishing web seg-mentation.     

一种视频编码数据分割方案

数据分割是在无线移动信道等传输视频码流时用于抵御信道误码、提高编码比特流健壮性的一种机制.在对现在流行的视频编码标准中数据分割方案进行研究的基础上,文中提出了一种视频编码中数据分割的新方案.在该方案中,运动矢量信息和头信息分割于不同部分;而且运动矢量的水平和垂直分量也可以分割到不同的部分,从而可以更好地抵御信道误码.在这种分割方案下,又提出了可以改进运动矢量编码效率的新编码方法.实验表明该方法对具有尖峰概率密度函数的情形尤为有效.采用文中数据分割方案具有抗信道误码能力强、运动矢量编码比特位数少、编码效率高等优点.     

Pessimistic quasipartitioning protocols for distributed databasesystems

A communication link failure can result in a network partitioning that fragments a distributed database system into isolated parts. If a severed high-speed link (e.g. satellite link) between the partitions can be replaced by a much slower backup link (e.g. a dial-up telephone line), the partitioning becomes a quasipartitioning. Two protocols for transaction processing in quasipartitioned databases are proposed. The protocols are pessimistic in that they permit transactions to be updated in exactly one partition. The first protocol is defined for a fully partition-replicated database in which every partition contains a copy of every data object. The second protocol is defined for a partially partition-replicated database in which some objects have no copies in some partitions. Both protocols improve their major performance measures linearly with the backup link speed but are not visibly affected by duration of the partitioning or the database size     

A partitioning technique for reducing the computational complexity of probabilistic fault detection in general combinational circuits

This paper examines the impacts of different types of circuit partitioning on reducing the computational complexity for computing the fault detection probability, which usually grows exponentially with the number of input lines in the given circuit. Partitioning a large combinational circuit into arbitrary subcircuits does not, in general, reduce the computational time complexity of the fault detection probability. In fact, partitioning a given circuit into general subcircuits is expected to increase the time complexity by the amount of time spent in the partition process itself. Nevertheless, it will be shown that decomposing a general combinational circuit into its modules (supergates) such that these modules constitute the basic elements of a tree circuit (network) considerably reduces the computational complexity of the fault detection probability problem. Toward this goal, two algorithms are developed. The first partitions a given circuit into maximal supergates whenever this is possible. Its computational complexity depends linearly on the number of edges (or lines) and nodes (or gates) of the circuit. The second computes the exact detection probabilities of single faults in the tree network and its computational complexity grows exponentially with the largest number of input lines in any of the network maximal supergates rather than the total number of inputs. The case of multi-output circuits is also discussed.