Salient Points for Image Retrieval



In image retrieval, global features related to color or texture are commonly used to describe the image content. The problem with this approach is that these global features cannot capture all parts of the image having different characteristics. Therefore, local computation of image information is necessary. By using salient points to represent local information, more discriminative features can be computed. We show that extracting color and texture information in the locations given by our salient points provides significantly improved results as compared to global feature approaches. Moreover, our salient points lead to a more complete image representation than using corners.