標題: STATE-SPACE SEARCH FOR HIGH-LEVEL CONTROL OF MACHINE VISION
作者: HWANG, SY
交大名義發表
資訊工程學系
National Chiao Tung University
Department of Computer Science
關鍵字: COMPUTER VISION;IMAGE PROCESSING;STATE-SPACE SEARCH;VISION ALGORITHM SYNTHESIS
公開日期: 1-Jun-1992
摘要: Computer vision is a task of information processing that can be modeled as a sequence of subtasks. A complete vision process can be constructed by synthesizing individual operators performing the subtasks. Previous work in computer vision has emphasized the development of individual operators for a specific subtask. However, the lack of knowledge about other levels of processing, while developing the operators for a specific level, makes the development of a robust operator and thus a robust system unlikely. To obtain vision problem-solving methods that are robust in the face of variations in image lighting, arrangements of objects, viewing parameters, etc., we can simply incorporate all possible sequences of image-processing operators, each of which deals with a specific situation of input images; then an adaptive control mechanism such as a state-space search procedure can be built into the methods. Such a procedure dynamically determines an optimal sequence of image-processing operators to classify an image or to put its parts into correspondence with a model or set of models. One critical problem in solving vision problems with a state-space search model is how to decide the costs of paths. This paper details the state-space search model of computer vision as well as the design of cost functions in terms of information distortions. A vision system, VISTAS, has been constructed under the state-space search model and its parallel version has been simulated.
URI: http://dx.doi.org/10.1117/12.56186
http://hdl.handle.net/11536/3411
ISSN: 0091-3286
DOI: 10.1117/12.56186
期刊: OPTICAL ENGINEERING
Volume: 31
Issue: 6
起始頁: 1264
結束頁: 1276
Appears in Collections:Articles


Files in This Item:

  1. A1992HY19200015.pdf