An Object Detection Method Based on Independent Local Features

Ryouta Nakano; Kazuhiro Hotta; Haruhisa Takahashi

doi:10.20965/jrm.2006.p0744

single-rb.php

« previous

JRM Vol.18 No.6 pp. 744-750

doi: 10.20965/jrm.2006.p0744

(2006)

Paper:

Views over last 60 days: 461

An Object Detection Method Based on Independent Local Features

Ryouta Nakano, Kazuhiro Hotta, and Haruhisa Takahashi

The University of Electro-Communications, 1-5-1 Chofugaoka, Chofu-shi, Tokyo 182-8585, Japan

Received:

March 29, 2006

Accepted:

August 28, 2006

Published:

December 20, 2006

Keywords:

object detection, ICA, SVM, HLAC features

Abstract

This paper presents an object detection method using independent local feature extractor. Since objects are composed of a combination of characteristic parts, a good object detector could be developed if local parts specialized for a detection target are derived automatically from training samples. To do this, we use Independent Component Analysis (ICA) which decomposes a signal into independent elementary signals. We then used the basis vectors derived by ICA as independent local feature extractors specialized for a detection target. These feature extractors are applied to a candidate area, and their outputs are used in classification. However, the number of dimension of extracted independent local features is very high. To reduce the extracted independent local features efficiently, we use Higher-order Local AutoCorrelation (HLAC) features to extract the information that relates neighboring features. This may be more effective for object detection than simple independent local features. To classify detection targets and non-targets, we use a Support Vector Machine (SVM). The proposed method is applied to a car detection problem. Superior performance is obtained by comparison with Principal Component Analysis (PCA).

Cite this article as:

R. Nakano, K. Hotta, and H. Takahashi, “An Object Detection Method Based on Independent Local Features,” J. Robot. Mechatron., Vol.18 No.6, pp. 744-750, 2006.

Data files:

References

[1] E. Hjelmas and B. K. Low, “Face detection: A survey,” Computer Vision and Image Understanding, Vol.83, pp. 236-274, 2001.
[2] M.-H. Yang, D. Kriegman, and N. Ahuja, “Detection faces in images: A survey,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vol.24, pp. 34-58, 2002.
[3] A. J. Bell and T. J. Sejnowski, “An information maximization approach to blind separation and blind deconvolution,” Nearal Computation, Vol.7, pp. 1129-1159, 1995.
[4] M. J. McKeown, S. Makeig, T. Jung, A. J. Bell, and T. J. Sejnowski, “Analysis of fMRI data by blind separation into spatial independent components,” Human Brain Mapping, Vol.6, pp. 160-188, 1998.
[5] N. Otsu and T. Kurita, “A new scheme for practical flexible and intelligent vision systems,” Proc. IAPR Workshop on Computer Vision, pp. 431-435, 1988.
[6] E. Osuna, R. Freund, and F. Girosi, “Training support vector machines: An application to face detection,” Proc.IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp.130-136, 1997.
[7] MIT CBCL DataBase,
http://cbcl.mit.edu/cbcl/.
[8] C. Papageorgiou and T. Poggio, “A Trainable Object Detection System: Car Detection in Static Images,” MIT AI Memo, No.180, p. 1673, 1999.
[9] R. Kohavi, “A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection,” International Joint Conference on Artifical Intelligence, pp. 1137-1143, 1995.
[10] The FastICA package for MATLAB,
http://www.cis.hut.fi/projects/ica/fastica/.
[11] A. J. Bell and T. J. Sejnowski, “The independent components of natural scenes are edge filters,” Vision Research, Vol.37, pp. 3327-3338, 1997.
[12] Y. Freund and R. E. Schapire, “A decision-theoretic generalization of on-line learning and an application to boosting,” Computational Learning Theory: Second European Conference, pp. 23-27, 1995.
[13] P. Viola and M. J. Jones, “Robust Real-Time Face Detection,” International Journal of Computer Vision, Vol.57, No.2, pp. 137-154, 2004.
[14] K. Hotta, “A Robust Face Detector under Partial Occlusion,” Proc. IEEE International Conference on Image Processing, pp. 597-600, 2004.
[15] B. Heisele, T. Serre, M. Pontil, and T. Poggio, “Component-based Face Detection,” IEEE Conference on Computer Vision and Pattern Recognition, pp. 657-662, 2001.
[16] K. Sung and T. Poggio, “Example-based learning for view-based human face detection,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vo.20, No.1, pp. 39-51, 1998.
[17] M. Yang, D. Roth, and N. Ahuja, “A SNoW-Based Face Detector,” Advances in Neural Information Processing Systems, pp. 855-861, 2000.
[18] H. Rowley, S. Baluja, and T. Kanade, “Neural Network-Based Face Detection,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vol.20, No.1, pp. 23-38, 1998.
[19] M. S. Bartlett, J. R. Movellan, and T. J. Sejnowski, “Face Recognition by Independent Component Analysis,” IEEE Trans. on Neural Networks, Vol.13, No.6, pp. 1450-1464, 2002.
[20] K. Seo, I. Cohen, S. You, and U. Neumann, “Face Pose estimation system by combining hybrid ICA-SVM learning and reregistration,” Asian Conference on Computer Vision, pp. 27-30, 2004.
[21] T. Kurita and S. Hayamizu, “Gesture Recognition using HLAC features of PARCOR images,” IEICE Trans. Information and Systems, Vol.E86-D, No.4, pp. 719-726, 2003.
[22] K. Hotta, T. Mishima, and T. Kurita, “Scale invariant face detection and classification method using shift invariant features extracted from Log-Polar images,” IEICE Trans. Information and Systems, Vol.E84-D, No.7, pp. 867-878, 2001.
[23] R. Nakano, K. Hotta, and H. Takahashi, “Object Detection Using Independent Local Feature Extractor,” Proc. SPIE (SPIE International Symposium on Optomechatronic Technologies), Vol.6051, pp. 605106-1 – 605106-8, 2005.

This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.

[1] [1] E. Hjelmas and B. K. Low, “Face detection: A survey,” Computer Vision and Image Understanding, Vol.83, pp. 236-274, 2001.

[2] [2] M.-H. Yang, D. Kriegman, and N. Ahuja, “Detection faces in images: A survey,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vol.24, pp. 34-58, 2002.

[3] [3] A. J. Bell and T. J. Sejnowski, “An information maximization approach to blind separation and blind deconvolution,” Nearal Computation, Vol.7, pp. 1129-1159, 1995.

[4] [4] M. J. McKeown, S. Makeig, T. Jung, A. J. Bell, and T. J. Sejnowski, “Analysis of fMRI data by blind separation into spatial independent components,” Human Brain Mapping, Vol.6, pp. 160-188, 1998.

[5] [5] N. Otsu and T. Kurita, “A new scheme for practical flexible and intelligent vision systems,” Proc. IAPR Workshop on Computer Vision, pp. 431-435, 1988.

[6] [6] E. Osuna, R. Freund, and F. Girosi, “Training support vector machines: An application to face detection,” Proc.IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp.130-136, 1997.

[7] [7] MIT CBCL DataBase,
http://cbcl.mit.edu/cbcl/.

[8] [8] C. Papageorgiou and T. Poggio, “A Trainable Object Detection System: Car Detection in Static Images,” MIT AI Memo, No.180, p. 1673, 1999.

[9] [9] R. Kohavi, “A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection,” International Joint Conference on Artifical Intelligence, pp. 1137-1143, 1995.

[10] [10] The FastICA package for MATLAB,
http://www.cis.hut.fi/projects/ica/fastica/.

[11] [11] A. J. Bell and T. J. Sejnowski, “The independent components of natural scenes are edge filters,” Vision Research, Vol.37, pp. 3327-3338, 1997.

[12] [12] Y. Freund and R. E. Schapire, “A decision-theoretic generalization of on-line learning and an application to boosting,” Computational Learning Theory: Second European Conference, pp. 23-27, 1995.

[13] [13] P. Viola and M. J. Jones, “Robust Real-Time Face Detection,” International Journal of Computer Vision, Vol.57, No.2, pp. 137-154, 2004.

[14] [14] K. Hotta, “A Robust Face Detector under Partial Occlusion,” Proc. IEEE International Conference on Image Processing, pp. 597-600, 2004.

[15] [15] B. Heisele, T. Serre, M. Pontil, and T. Poggio, “Component-based Face Detection,” IEEE Conference on Computer Vision and Pattern Recognition, pp. 657-662, 2001.

[16] [16] K. Sung and T. Poggio, “Example-based learning for view-based human face detection,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vo.20, No.1, pp. 39-51, 1998.

[17] [17] M. Yang, D. Roth, and N. Ahuja, “A SNoW-Based Face Detector,” Advances in Neural Information Processing Systems, pp. 855-861, 2000.

[18] [18] H. Rowley, S. Baluja, and T. Kanade, “Neural Network-Based Face Detection,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vol.20, No.1, pp. 23-38, 1998.

[19] [19] M. S. Bartlett, J. R. Movellan, and T. J. Sejnowski, “Face Recognition by Independent Component Analysis,” IEEE Trans. on Neural Networks, Vol.13, No.6, pp. 1450-1464, 2002.

[20] [20] K. Seo, I. Cohen, S. You, and U. Neumann, “Face Pose estimation system by combining hybrid ICA-SVM learning and reregistration,” Asian Conference on Computer Vision, pp. 27-30, 2004.

[21] [21] T. Kurita and S. Hayamizu, “Gesture Recognition using HLAC features of PARCOR images,” IEICE Trans. Information and Systems, Vol.E86-D, No.4, pp. 719-726, 2003.

[22] [22] K. Hotta, T. Mishima, and T. Kurita, “Scale invariant face detection and classification method using shift invariant features extracted from Log-Polar images,” IEICE Trans. Information and Systems, Vol.E84-D, No.7, pp. 867-878, 2001.

[23] [23] R. Nakano, K. Hotta, and H. Takahashi, “Object Detection Using Independent Local Feature Extractor,” Proc. SPIE (SPIE International Symposium on Optomechatronic Technologies), Vol.6051, pp. 605106-1 – 605106-8, 2005.