We present an interactive application that enables users to improve the visual aesthetics of their digital photographs using spatial recomposition. Unlike earlier work that focuse...
The existing methods for offline training of cascade classifiers take a greedy search to optimize individual classifiers in the cascade, leading inefficient overall performance. W...
We present a method for the simultaneous detection and segmentation of people from static images. The proposed technique requires no manual segmentation during training, and explo...
This paper presents a bottom-up tracking algorithm for surveillance applications where speed and reliability in the case of multiple matches and occlusions are major concerns. The...
Recognizing texts from camera images is a known hard problem because of the difficulties in text segmentation from the varied and complicated backgrounds. In this paper, we propo...