In this paper, we propose a novel method to localize (or track) a foreground object and segment the foreground object from the surrounding background with occlusions for a moving ...
We propose a neural network based method for organizing images for content-based image retrieval. We use spectral histogram features, the histograms of filtered images to capture...
This paper presents an intelligent traffic light control method based on extension neural network (ENN) theory for crossroads. First, the number of passing vehicles and passing tim...
A major goal for face recognition is to identify faces where the pose of the probe is different from the stored face. Typical feature vectors vary more with pose than with identit...
Flat appearance-based systems, which combine clever image representations with standard classifiers, might be the most effective way to recognize objects using current technologie...