In this paper, a hybrid technique for face detection in color images is presented. The proposed technique combines three analysis models, namely skin detection, automatic eye loca...
?We present a method to automatically localize captions in JPEG compressed images and the I-frames of MPEG compressed videos. Caption text regions are segmented from background ima...
In this paper, we propose a novel approach to extracting rheological properties of deformable objects based on Haptic vision, which was proposed for vision-based automatic constru...
This paper describes a framework for the estimation of shape from sparse or incomplete range data. It uses a shape representation called blending, which allows for the geometric c...
Graph-based methods form a main category of semisupervised
learning, offering flexibility and easy implementation
in many applications. However, the performance of
these methods...
Wei Liu (Columbia University), Shih-fu Chang (Colu...