摘要
提出了一种基于特征块匹配的图像检索算法。首先,利用小波变换的多尺度特性检测出图像的特征点,特征点比较全面地反映了图像中的视觉兴趣点;用以特征点为中心的特征块的前三阶颜色矩来描述特征块的特征;进一步统计出两个图像中匹配的特征块数目,计算图像间的相似距离。实验表明,算法中所使用的特征块更全面、更精确地描述了图像的视觉信息,实现相似度计算的方法简单、高效。该检索算法不仅检索精度高,还具有较好的旋转、尺度及视觉角度不变性。
A novel content-based image retrieval algorithm based on salient blocks matching is presented in this paper.First,salient points in an image are detected by wavelet transform in which those wavelet coefficients can be calculated in different multi-resolutions.Next,the features of each salient block,a rectangle area includes 5×5 pixels,are described by three important color moments.Finally,the similar distance between two images are calculated based on counting the number of matched salient blocks in two pictures.The experiments indicate that the salient block in the algorithm is more comprehensive and precise as describing the visual information of a picture and the similarity measurement method is easy to realize and highly effective as comparing two pictures.Experimental results also show that this algorithm has robustness to rotation and translation because it can avoid the shortcoming of losing location information in the traditional color histogram.
出处
《计算机仿真》
CSCD
2008年第7期180-183,共4页
Computer Simulation
关键词
图像检索
小波变换
特征点
颜色矩
距离
Image retrieval
Wavelet transform
Salient point
Color moment
Distance
