In the paper, an e cient image database system is developed. The most important features of the proposed system include compressed domain indexing, searching by using scalable fea...
The detection of image versions from large image collections is a formidable task as two images are rarely identical. Geometric variations such as cropping, rotation, and slight p...
Fast retrieval methods are critical for large-scale and
data-driven vision applications. Recent work has explored
ways to embed high-dimensional features or complex distance
fun...
Content based image retrieval (CBIR) has been well studied in the computer vision and multimedia community. Content free image retrieval (CFIR) methods, and their complementary cha...
In this paper, we propose a novel Markov model-based formulation for the image annotation problem. In this formulation, we treat image annotation as a graph ranking problem, by de...