基于特征点匹配和哈希法的图像检索方法

提出一种基于点特征匹配和几何型哈希法的图像检索方法。利用小波变换提取图像的突变点，以点为辜心划定一小块区域，将图像划分成图像块。提取块的低层次特征矢量，将两幅图像之间的匹配转换成图像块之间的匹配。并采用几何型哈希索引方法实现图像的快速检索。实验证明，这种方法能够取得较高的检索精度，且对图像形变以及局部遮挡等都有较好的适应能力。

Image Retrieval Using SalientPoints and Geometric Hashing

This paper presents a content-based image retrieval technique based on salient points matching and geometric hashing. We extract salient points using wavelet transform. A small region around the salient point is located as an image patch. Then low-level features such as color are extracted to describe each image patch. To provide geometric invariant image matching, we index the image patches into a 2-D hash table by geometric hashing technique. Thus, the matching is invariant to global and local geometric transforms. We performed a series of experiments to confirm the effectiveness of our method, as compared to the global feature approaches. And experimental results indicate satisfactory retrieval in the case of partial matching and geometric transformation.