This paper describes how a visual system can automatically define features of interest from the observation of a large enough number of natural images. The principle complements t...
Abstract-- We present a perceptual model for hiding a spreadspectrum watermark of variable amplitude and density in an image. The model takes into account the sensitivity and maski...
This paper presents a method of learning and recognizing generic object categories using part-based spatial models. The models are multiscale, with a scene component that specifie...
The problem of extracting information from large collections of imagery is a challenge with few good solutions. Computers typically cannot interpret imagery as effectively as huma...
Santosh Mathan, Deniz Erdogmus, Yonghong Huang, Mi...
— It is widely agreed that efficient visual search requires the integration of target-driven top-down information and image-driven bottom-up information. Yet the problem of gaze...