摘要
以图像位平面原理为基础,结合噪声攻击特点(对高位平面影响较小),提出了一种基于重要位平面的鲁棒图像检索新算法。该算法首先从原始图像中提取重要位平面;然后选取重要位平面图像的颜色直方图作为颜色特征,选取重要位平面图像的颜色标准偏差作为空间特征;再综合利用上述颜色、空间两个特征计算图像间内容的相似度,并进行图像检索。仿真实验结果表明,本文算法能够准确和高效地查找出用户所需内容的彩色图像,并且具有较好的查准率和查全率。特别地,该算法对光照、锐化、模糊等噪声攻击均具有较好的鲁棒性。
According to the noise attack characteristic, a new robust color image retrieval based on significant bit-plane is proposed. Firstly, the significant bit-planes are extracted from the color image based on bit-plane theory and the noise attack characteristics. Secondly, the color histograms are extracted from the significant bit-planes as color feature, and the standard deviation of color for every significant bit-plane is computed as spatial feature. Finally, the similarity between color images is computed by using a combined index based on color feature and spatial feature. Experimental results show that the proposed image retrieval is more accurate and efficient in retrieving the user-interested images. Especially, it can retrieve the noise（including fuzzy, sharpen, and illumination, etc） image effectively.
出处
《中国图象图形学报》
CSCD
北大核心
2007年第9期1647-1652,共6页
Journal of Image and Graphics
基金
辽宁省自然科学基金项目(20032100)
视觉与听觉信息处理国家重点实验室(北京大学)开放基金项目(0503)
"图像处理与图像通信"江苏省重点实验室(南京邮电大学)开放基金项目(ZK205014)
江苏省计算机信息处理技术重点实验室(苏州大学)开放课题基金项目(KJS0602)
关键词
图像检索
鲁棒性
重要位平面
颜色直方图
标准偏差
image retrieval, robustness, significant bit-plane, color histogram, standard deviation
