智能系统学报Issue(4)：333-338,6.DOI:10.3969/j.issn.1673-4785.2011.04.009
基于Tent映射CPSO和车牌纹理特征的车牌定位
License plate location based on texture features and tent chaotic particle swarm optimization
摘要
Abstract
Considering the problems of the low precision ratio and slow arithmetic speed of license plate location, an accurate license plate location method based on tent chaotic particle swarm optimization (TCPSO) was proposed by combining the texture features. First, binarization was adopted to segment the license plate image by the OTSU method, which is based on a 2-D histogram oblique. Then the texture feature vector was obtained by three one-dimensional filters. With the rapid and accurate searching ability, the best location parameters of license plate area were found by constructing the fitness function with the texture feature vector when introducing the texture coherence into the judgment. At last, the proposed method was compared with a genetic algorithm (GA) and BPSO. The experimental results show that the proposed method has stronger adaptability, better location effect, and shorter running time.关键词
车牌纹理特征/Tent映射/混沌/粒子群优化/车牌定位Key words
texture feature/ tent map/ chaotic/ particle swarm optimization/ license plate location分类
信息技术与安全科学引用本文复制引用
吴加明,吴一全..基于Tent映射CPSO和车牌纹理特征的车牌定位[J].智能系统学报,2011,(4):333-338,6.基金项目
国家自然科学基金资助项目(60872065). （60872065）
