In partial-duplicate image retrieval, images are commonly represented using Bag-of-visual-Words (BoW) built from image local features, such as SIFT. Therefore, the discriminative ...
This paper presents our research in image content based indexing and retrieval, a key technology in digital image libraries. In most of the existing image content-based techniques...
We investigate the application of a new category of low-level image descriptors termed interest points to remote sensed image analysis. In particular, we compare how scale and rot...
Abstract. Bag-of-words representation with visual keypoints has recently emerged as an attractive approach for video search. In this paper, we study the degree of improvement when ...
Recently, semantic image retrieval has attracted large amount of interest due to the rapid growth of digital image storage. However, existing approaches have severe limitations. I...