结合裁剪技术的颜色特征匹配搜索  

Color Feature Matching Search with Clipping Technique

作　　者：赵佳[1] 刘克剑[1] 李晨跃 宋景平 

机构地区：[1]西华大学计算机与软件工程学院,四川成都610039 [2]西藏飞跃智能科技有限公司,西藏拉萨850000

出　　处：《宜宾学院学报》2016年第6期27-31,共5页Journal of Yibin University

基　　金：国家科技支撑计划项目"西藏自然科学博物馆数字馆关键技术研究及集成示范"(2011BAH26B01);国家自然科学基金项目(61271413;61472329;61532009);数字空间安全保障四川省高校重点实验室开放基金课题(szjj2015-055);四川省教育厅重点项目(16ZA0165);西华大学校重点项目(Z1222625)

摘　　要：剖析了单以颜色直方图作为图像特征会丢失图片空间信息以及单以感知哈希串作为图像特征受均值影响较大的缺点,提出将图片切割方法应用到颜色直方图与感知哈希算法上作为提取图像特征的一种方案.方案分别提取颜色直方图特征以及感知哈希串特征,对这两种特征进行大量的训练后得到比较满意的权重分配,按该权重分配重组为新特征再进行相似图片检索.由于图片存在部分相似,故在检索过程中引入了有限次图片剪切,目的是提取图片的相似部分.实验结果证明:在数据集较小时,两种方式差别不大,但对于比较庞大的数据,采用新检索算法能提高检索效率.An image feature extraction scheme that compiled image incision with color histogram and perception hash al- gorithm was proposed considering the two defects： if using color histogram as image feature alone, a lot of spatial informa- tion may be lost; if using perception hash string as image feature alone, the mean value would have a great effect on the re- search result. By extracting features of color histogram and perception hash string and doing a lot of training on them, a satisfactory weight allocation was obtained. Similar image retrieval was done based on the new character of this recombi- nant weight allocation. Due to the partial similarity of images, restricting image cut was introduced in retrieval to draw similarities of images. The experiment results prove that when the data set is small, there is no difference between the two ways, but to relatively large data, the new retrieval works with higher efficiency compared with the one-way retrieval search.

关 键 词：图像检索 图片切割 颜色直方图 感知哈希算法 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]