Sparse patch-histograms for object classification in cluttered images

TL;DR: A novel model for object recognition and detection that follows the widely adopted assumption that objects in images can be represented as a set of loosely coupled parts is presented and yields very competitive results for the commonly used Caltech object detection tasks.

Abstract: We present a novel model for object recognition and detection that follows the widely adopted assumption that objects in images can be represented as a set of loosely coupled parts. In contrast to former models, the presented method can cope with an arbitrary number of object parts. Here, the object parts are modelled by image patches that are extracted at each position and then efficiently stored in a histogram. In addition to the patch appearance, the positions of the extracted patches are considered and provide a significant increase in the recognition performance. Additionally, a new and efficient histogram comparison method taking into account inter-bin similarities is proposed. The presented method is evaluated for the task of radiograph recognition where it achieves the best result published so far. Furthermore it yields very competitive results for the commonly used Caltech object detection tasks.