Feature selection is an important issue for object detection. In this paper, we propose an effective wrapper-based feature selection scheme using Binary Particle Swarm Optimizatio...
A two-stage cascaded classification approach with an optimal candidate selection scheme is proposed to recognize places using images taken by camera phones. An optimal acceptance ...
The objective of this paper is to study the existing methods for unsupervised object recognition and image categorization and propose a model that can learn directly from the outp...
In real world scenes, objects to be classified are usually not visible from every direction, since they are almost always positioned on some kind of opaque plane. When moving a cam...
Boxes are the universal choice for packing, storage, and transportation. In this paper we propose a template-based algorithm for recognition of box-like objects, which is invarian...