检索结果-内蒙古大学图书馆

ieee International symposium on Circuits and Systems (ISCAS)

作者： H.Q. Cao W. Li Department of Electrical Engineering and Computer Science Lehigh University Bethlehem PA USA

A new multilevel codebook searching (MCS) algorithm for vector quantization is presented. Although it belongs to the category of the fast nearest neighbor searching (FNNS) algorithms for vector quantization, the new MCS algorithm is not a variation of any existing FNNS algorithms (such as k-d tree searching algorithm, partial distance searching algorithm, triangle inequality searching algorithm...). The searching strategy involves several search levels. Each level stores a certain size codebook. Searching starts from the stage containing the smallest size (lowest bitrate) codebook to the level containing largest size (highest bitrate) codebook. The searching paths between any two adjacent levels are built by using training sets. The simulation result of applying MCS algorithm to image VQ shows that the MCS algorithm can reduce searching complexity to less than 3% of an exhaustive searching VQ (ESVQ) (codebook size of 4096) while introducing negligible error (0.064 db degradation from ESVQ). A comparison between the MCS algorithm and several k-d binary tree searching algorithms is presented too. The MCS algorithm fits very well into multilevel codebook VQ in the vector transform and vector sub-band domains.

关键词： Vector quantization signal processing algorithms Decision trees Bit rate Binary trees computational complexity Algorithm design and analysis Statistical distributions Partitioning algorithms Electronic mail

来源：评论

学校读者我要写书评

暂无评论

OPTIMAL DECOMPOSITION OF CONVEX MORPHOLOGICAL STRUCTURING ELEMENTS FOR 4-CONNECTED PARALLEL ARRAY PROCESSORS

引用

ieee TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE intelligence 1994年第3期16卷 304-313页

作者： PARK, H CHIN, RT UNIV WISCONSIN DEPT ELECT & COMP ENGNMADISONWI 53706

A morphological operation using a large structuring element can be decomposed equivalently into a sequence of recursive operations, each using a smaller structuring element. However, an optimal decomposition of arbitrarily shaped structuring elements is yet to be found. In this paper, we have derived an optimal decomposition of a specific class of structuring elements-convex sets-for a specific type of machine-4-connected parallel array processors. The cost of morphological operation on 4-connected parallel array processors is the total number of 4-connected shifts required by the set of structuring elements. First, the original structuring element is decomposed into a set of prime factors, and then their locations are determined while minimizing the cost function. Proofs are presented to show the optimality of the decomposition. Examples of optimal decomposition are given and compared to an existing decomposition reported by Xu.

关键词： Morphological operations image analysis image processing computational efficiency Cost function Morphology Object recognition image edge detection Shape image coding INSPEC: Controlled Indexing array signal processing image reconstruction mathematical morphology optimisation parallel processing INSPEC: Non-Controlled Indexing cost function minimization optimal decomposition convex morphological structuring elements 4-connected parallel array processors recursive operation sequence

来源：评论

学校读者我要写书评

暂无评论

FUZZY FILTERING FOR MIXED NOISE REMOVAL DURING image processing

FUZZY FILTERING FOR MIXED NOISE REMOVAL DURING IMAGE PROCESS...

引用

3rd ieee Conference on Fuzzy Systems/ieee World Congress on computational intelligence

作者： PENG, SM LUCKE, L UNIV MINNESOTA DEPT ELECT ENGNMINNEAPOLISMN 55455

ISBN: (纸本)0780318978

In this paper we present a new nonlinear fuzzy filter for image processing in a mixed noise environment, where both additive Gaussian noise and non-additive impulsive noise may be present. Averaging filters can effectively remove the Gaussian noise and order statistics filters or median filters can effectively remove the impulsive noise. However, it is difficult to combine these filters to remove mixed noise in an imaging processing environment without blurring the image details or edges. Trying to distinguish between noise and edge information in the image is an inherently ambiguous problem and naturally leads to the development of a fuzzy filter. We use local statistics to train the membership function of a fuzzy filter for image processing to remove both Gaussian noise and impulsive noise while preserving edges. We show that such a fuzzy filter gives superior results compared to averaging filters, median filters, and other fuzzy filters. We also demonstrate the robustness of this filtering technique.

关键词： signal filtering and prediction

来源：评论

学校读者我要写书评

暂无评论

SLIDE - SUBSPACE-BASED LINE DETECTION

引用

ieee TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE intelligence 1994年第11期16卷 1057-1073页

作者： AGHAJAN, HK KAILATH, T Dept. of Electr. Eng. Stanford Univ. CA USA

An analogy is made between each straight line in an image and a planar propagating wavefront impinging on an array of sensors so as to obtain a mathematical model exploited in recent high resolution methods for direction-of-arrival estimation in sensor array processing. The new so-called SLIDE (Subspace-Based Line Detection) algorithm then exploits the spatial coherence between the contributions of each line in different rows of the image to enhance and distinguish a signal subspace that is defined by the desired line parameters. SLIDE yields closed-form and high resolution estimates for line parameters, and its computational complexity and storage requirements are far less than those of the standard method of the Hough transform. If unknown a priori, the number of lines is also estimated in the proposed technique. The signal representation employed in this formulation is also generalized to handle grey-scale images as well. The technique has also been generalized to fitting planes in 3-D images. Potential application areas of the proposed technique include road tracking in robotic vision, mask-wafer alignment and linewidth measurement in semiconductor manufacturing, aerial image analysis, text alignment in document analysis, particle tracking in hubble chambers, and similar applications.

关键词： LINE FITTING EDGE DETECTION SUBSPACE FITTING ARRAY processing OBJECT RECOGNITION PROJECTION HOUGH TRANSFORM

来源：评论

学校读者我要写书评

暂无评论

HYBRID computational ARCHITECTURES FOR image SEGMENTATION

HYBRID COMPUTATIONAL ARCHITECTURES FOR IMAGE SEGMENTATION

引用

1994 ieee International Conference on image processing (ICIP-94)

作者： DAIDA, JM UNIV MICHIGAN ARTIFICIAL INTELLIGENCE LABANN ARBORMI 48109

ISBN: (纸本)0818669527

The article describes a generalizable method for creating hybrid computational architectures. This method, based on a metaphor of biological symbiosis, provides a systematic approach to combining attributes of disparate algorithms. It illustrates the approach by creating a series of hybrid architectures from a single hierarchical segmentation algorithm. Typical results from these hybrids are given. The results show that for this particular application, it is possible to leverage high-level image processing tasks with low-level algorithms. The results also demonstrate how changes in the hybrid architecture can introduce nuances in the segmentation output. © 1994 ieee.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Training genetically evolving cellular automata for image processing

Training genetically evolving cellular automata for image pr...

引用

1994 International symposium on Speech, image processing and Neural Networks, ISSIPNN 1994

作者： Sahota, P. Daemi, M.F. Elliman, D.G. Recognition Engineering Group Machine Intelligence Group Department of Computer Science University of Nottingham United Kingdom

ISBN: (纸本)078031865X

The paper describes the use of a genetically controlled automaton model to tackle image processing problems. A generalised system is set up that attempts to discover the precise cellular automaton functions required to solve a given problem. Functions are located with the help of a genetic algorithm, and once trained the system is able to process unseen images. The results have shown that the system correctly solves the task of image edge detection, and that the same procedure may be used for any image processing task. © 1994 ieee.

关键词： image processing

来源：评论

学校读者我要写书评

暂无评论

Segment-oriented coding of textured images based on successive approximation

Segment-oriented coding of textured images based on successi...

引用

1994 International symposium on Speech, image processing and Neural Networks, ISSIPNN 1994

作者： Kaup, A. Aach, T. Aachen52056 Germany

ISBN: (纸本)078031865X

The paper reports a region-based coding scheme for segmented textured images. The proposed approach uses basic principles of transform image coding which are generalized for the case of arbitrarily shaped image segments. The texture inside each region is described by successive approximation through a set of shape independent basis functions while the image partition is coded employing generalized chain codes. In contrast to other approaches aimed at segment-oriented image coding, the proposed concept does not couple texture description and contour coding. The computational load is kept low, especially for the decoding process. © 1994 ieee.

关键词： image coding

来源：评论

学校读者我要写书评

暂无评论

A heterogeneous processing (HP) framework for multimedia query processing

A heterogeneous processing (HP) framework for multimedia que...

引用

1995 Heterogeneous Computing Workshop, HCW 1994

作者： Khokhar, Ashfaq Ghafoor, Arif Distributed Multimedia Systems Lab. School of Electrical Engineering Purdue University West LafayetteIN47907 United States

ISBN: (纸本)0818655925

In this paper, we define a novel system based on a hierarchical computational and data abstraction model to handle multimedia queries involving face recognition, scene matching, and speech recognition. For this purpose, the system integrates the state of the art research in diverse areas in computational sciences, including parallel processing, computer vision and image processing, artificial intelligence, multimedia databases, and speech and signal processing. This system uses a heterogeneous processing framework consisting state of the art image understanding and signal processing algorithms in addition to content-based retrieval techniques. These algorithms comprise of parallel coarse grained (MIMD) symbolic and fine grained (SIMD) numeric algorithms at various levels of this hierarchical model. © 1994 ieee.

关键词： Content based retrieval

来源：评论

学校读者我要写书评

暂无评论

Current status and prospects of speech processing technology in Korea

Current status and prospects of speech processing technology...

引用

1994 International symposium on Speech, image processing and Neural Networks, ISSIPNN 1994

作者： Ann, S. Department of Electronic Engineering Seoul Nat. Univ. Seoul151-742 Korea Republic of

ISBN: (纸本)078031865X

We introduce the speech processing technology being studied and developed in Korea as well as its current status, problems, and future prospects. Time-varying and nonlinear methods will play important roles in the future, and considering that speech analysis is the basis of speech signal processing, this area will be studied more intensively in the future. In speech synthesis, we have already achieved comparatively good speech intelligibility, but there is room for the improvement of speech naturalness. Continuous speech recognizers which are not affected by the environment or the speakers will be constructed using HMM and ANN. For speech coding, speech coders with lower bit rate will be developed. In this area, many researchers in Korea are concentrating on the reduction of the computational burden and processing delay. © 1994 ieee.

关键词： Speech intelligibility

来源：评论

学校读者我要写书评

暂无评论

An algorithm for single-pixel detection and tracking

An algorithm for single-pixel detection and tracking

引用

1994 International symposium on Speech, image processing and Neural Networks, ISSIPNN 1994

作者： Xiong, Yan Peng, Jia-Xiong Li, Qiang Inst. of Image Recognition and Artificial Intelligence Huazhong Univ. of Sci. and Technol. Wuhan China

ISBN: (纸本)078031865X

The paper presents a new method for detection and tracking of pixel-sized moving targets from a time sequence. It uses the pipeline continuity filter for preprocessing, and then tracks the target trajectories in the two projection planes x-t and y-t by a tree-searching algorithm. Experiments show the advantage of this method for the detection and tracking of arbitrary target trajectories in high noise environments without some constraints that most other algorithms require for similar tasks. © 1994 ieee.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：