Supervised Learning of a Color-Based Active Basis Model for Object Recognition

Abstract

Wu and coworkers introduced an active basis model (ABM) for detecting generic objects in static images. A grey-value local power spectrum was utilized to find a common template and deformable templates from a set of training images and to detect an object in unknown images by template matching. In this paper, we propose a color-based active basis model (color-based ABM for short) which includes color information. We adapt the framework of Wu et al. into the learning, detection, and classification of the color-based ABM. However, in order to improve the performance in object recognition, we modify the framework of Wu et al. by using different color-based features in both supervised learning and template matching algorithms. In addition, significant improvements are reported with regard to the proposed color-based ABM for object recognition.