Abstract. In this paper, a new sign-wise tied mixture HMM (SWTMHMM) is proposed and applied in vision-based sign language recognition (SLR). In the SWTMHMM, the mixture densities o...
We derive a new class of photometric invariants that can be used for a variety of vision tasks including lighting invariant material segmentation, change detection and tracking, a...
Srinivasa G. Narasimhan, Visvanathan Ramesh, Shree...
Illumination invariance remains the most researched, yet the most challenging aspect of automatic face recognition. In this paper we investigate the discriminative power of colour...
In this paper we evaluate the effectiveness of two likelihood normalization techniques, the Background Model Set (BMS) and the Universal Background Model (UBM), for improving perf...
We propose a simplified and practical computational technique for estimating directional lighting in uncalibrated images of faces in frontal pose. We show that this inverse probl...