首页 | 本学科首页   官方微博 | 高级检索  
     

彩色照片时间戳识别
引用本文:鲍复民,李爱国,覃征. 彩色照片时间戳识别[J]. 复旦学报(自然科学版), 2004, 43(5): 914-917,922
作者姓名:鲍复民  李爱国  覃征
作者单位:西安交通大学,计算机系,西安,710049;西安科技大学,计算机系,西安,710054
基金项目:国防"十五"预研基金资助项目(806030101)
摘    要:照片的时间戳是可用于照片检索的重要信息提出一种基于粒子群优化的照片时间戳自动识别方法首先对一张照片进行粗分割,以确定时间戳所在的区域:选定4个可能包含时间戳的探测区域,并对它们的R分量和G分量分别用Sobel算子进行边缘检测,从边缘图中判定时间戳包含在哪个区域中.然后用PSO优化算法确定一组合适的参数.对包含时间戳的区域进行精细分割和模板匹配.从而完成时间戳识别,该方法不需要大量的先验知识和离线学习的过程,实验结果表明该方法识别正确率很高。

关 键 词:图像检索  文本分割  文本识别  时间戳识别  粒子群优化
文章编号:0427-7104(2004)05-0914-04

Color Photo Time-Stamp Recognition
BAO Fu-min,LI Ai-guo,QIN Zheng. Color Photo Time-Stamp Recognition[J]. Journal of Fudan University(Natural Science), 2004, 43(5): 914-917,922
Authors:BAO Fu-min  LI Ai-guo  QIN Zheng
Affiliation:BAO Fu-min~1,LI Ai-guo~2,QIN Zheng~1
Abstract:Photo time-stamp is a valuable information source for photo retrieval. An automatically photo-stamp recognizing approach is proposed. First, the photo is roughly segmented to determine which area contains the photo-stamp. Four detecting areas are chosen in this step, which probably include the photo-stamp, and then they are margin-detected using Sobel operator to see whether the photo-stamp is in. Then it uses Particle Swarm Optimization (PSO) algorithm to do fine segmenting and template matching on the determined area to complete the photo-stamp recognition. This approach needs no prior knowledge and off-line learning processes. Experimental results show that the proposed approach can achieve high recognition accuracy.
Keywords:image retrieval  text segmentation  text recognition  time-stamp Recognition  particle swarm optimization
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号