Multiclass Adaboost and Coupled Classifiers for Object Detection
Building robust and fast multiclass object detection systems is a important goal of computer vision. In the present paper we extend the well-known work of Viola and Jones on boosted cascade classifiers to the multiclass case with the goal of building multiclass and multiview object detectors. We propose to use nested cascades of multiclass boosted classifiers and we introduce the concept of coupled components in multiclass classifiers. We evaluate the system by building several multiview face detectors, each one built to detect a different number of classes. Thus, we present results showing how well the system scales. Promising results are obtained in the BioID database, showing the potentiality of the proposed methods for building object detectors.
KeywordsMulticlass Adaboost Coupled Components Object Detection
- 1.Bourdev, L., Brandt, J.: Robust object detection via soft cascade. In: Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), vol. 2, pp. 236–243 (2005)Google Scholar
- 3.Jones, M., Viola, P.: Fast multi-view face detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (June 2003)Google Scholar
- 8.Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, pp. 511–518 (2001)Google Scholar
- 9.Wu, B., Ai, H., Huang, C., Lao, S.: Fast rotation invariant multi-view face detection based on real adaboost. In: Proc. of the 6th Int. Conf. on Face and Gesture Recognition, pp. 79–84 (2004)Google Scholar
- 10.Wu, B., Nevatia, R.: Cluster boosted tree classifier for multi-view, multi-pose object detection. In: Proc. of the Eleventh IEEE Int. Conf. on Computer Vision (ICCV 2007) (2007)Google Scholar