Simply choosing one model out of a large set of possibilities for a given vision task is a surprisingly difficult problem, especially if there is limited evaluation data with whi...
Object recognition systems aiming to work in real world settings should use multiple cues in order to achieve robustness. We present a new cue integration scheme which extends the...
The visualization of 3D vector and tensor fields in a 2D image is challenging because the large amount of information will either be mixed during projection to 2D or lead to seve...
We present a patch-based algorithm for the purpose of object classification in video surveillance. Within detected regions-of-interest (ROIs) of moving objects in the scene, a feat...
In this paper, we derive bounds on the Structural SIMilarity (SSIM) Index as a function of quantization rate for fixed-rate uniform quantization of image discrete cosine transform...
Sumohana S. Channappayya, Alan C. Bovik, Robert W....