一种高效目标搜索方法及其在图象分析中的应用

An Efficient Object Exploring Strategy and Its Application in the Image Analysis

针对自然环境中（自然光照和复杂背景条件下）的特定目标模式搜索，利用视觉神经生理学和认知心理学实验结果，归纳出一种仿生目标搜索策略——ＢＯＥＳ（Ｂｉｏｎｉｃ ＯｂｊｅｃｔＥｘｐｌｏｒｉｎｇ Ｓｔｒａｔｅｇｙ）策略。该策略应用在车牌识别系统中，设计出简捷实用的高效模式搜索算法，解决了快速准确定位车牌的难题。

Pattern recognition is derived from the will to imitate the sense of the creatures, object searching in an image aims at imitating the human's visual ability. In this paper, utilizing the results of the vision neurophysiology and the psychology of cognizance, and aiming at the specific pattern location in the natural environment, we put forward a Bionic Object Exploring Strategy——BOES. In a license plate recognition system, an algorithm of succinctness and practicality on this strategy has developed to solve the difficulty of locating license plates rapidly and precisely. In our algorithm, to deal with the complex, uncontrollable background of the natural environment and the variability of the color, brightness and size, we extract the license plate pattern's most permanent characters, design a set of filters to mask the background, organize the image data in a series of steps by spatial and frequencial filtering, and divide the task into several layers. This system can locate the license plate in an image of complex environment within 0 5 second on a Pentium Ⅱ 300Hz machine, and the rate of success is over 95%.