Components for Object Detection and Identification

We present a component-based system for object detection and identification. From a set of training images of a given object we extract a large number of components which are clustered based on the similarity of their image features and their locations within the object image. The cluster centers build an initial set of component templates from which we select a subset for the final recognizer. The localization of the components is performed by normalized cross-correlation. Two types of components are used, gray value components and components consisting of the magnitudes of the gray value gradient. In experiments we investigate how the component size, the number of the components, and the feature type affects the recognition performance. The system is compared to several state-of-the-art classifiers on three different data sets for object identification and detection.