摘要
提出用图像复数矩与其它特征结合进行商标图像检索的方法,并给出了检索算法.实验结果证明,这是一种较好的方法,基本不会出现漏检索.
The key and challenging problem of image retrieving is feature extraction and description of im ges.Among many features are very important moments.Complex moment is used to extract features and describe trademark images for the first time;also algorithm is proposed.According to the results of retrieving experiment,the method is practical. $$$$Abstract:The key and challenging problem of image retrieving is feature extraction and description of im ges.Among many features are very important moments.Complex moment is used to extract features and describe trademark images for the first time;also algorithm is proposed.According to the results of retrieving experiment,the method is practical. Abstract:The key and challenging problem of image retrieving is feature extraction and description of im ges.Among many features are very important moments.Complex moment is used to extract features and describe trademark images for the first time;also algorithm is proposed.According to the results of retrieving experiment,the method is practical. :The key and challenging problem of image retrieving is feature extraction and description of im ges.Among many features are very important moments.Complex moment is used to extract features and describe trademark images for the first time;also algorithm is proposed.According to the results of retrieving experiment,the method is practical.
出处
《云南大学学报(自然科学版)》
CAS
CSCD
1999年第5期380-382,385,共4页
Journal of Yunnan University(Natural Sciences Edition)
基金
云南省教委自然科学基金
关键词
复数矩
商标图像
检索
最近邻分类
特征向量
complex moment
retrieving
trademarks
nearest neighbor classification
correlation coefficient
eigenvector