Guangwei Wang
School of Computer and Information Science, Hubei Engineering University, 432000, Xiaogan, China
Zenggang Xiong
School of Computer and Information Science, Hubei Engineering University, 432000, Xiaogan, China
Yihua Lan
School of Computer and Information Technology, Nanyang Normal University, 473061, Nanyang, China
Conghuan Ye
School of Computer and Information Science, Hubei Engineering University, 432000, Xiaogan, China
ABSTRACT
In In this study, we propose an object detection approach using edge direction histogram features. Since edge points are related to shape information closely, Edge Direction Histogram (EDH) is a very simple and direct way to characterize shape information of an object. We divide an object into several parts and employ edge direction histogram method to extract the EDH features. The EDH descriptor is designed to decouple variations of the object due to affine warps and other forms of shape deformations. We further train a support vector machine classifier for each object part and apply a generalized Hough voting scheme to generate object locations and scales. We evaluate the proposed approach on two different kinds of objects: Car and h. Experimental results show that the proposed approach is efficient and robust in object detection.
PDF References Citation
How to cite this article
Guangwei Wang, Zenggang Xiong, Yihua Lan and Conghuan Ye, 2013. Object Detection Using Edge Direction Histogram Features. Information Technology Journal, 12: 8275-8280.
DOI: 10.3923/itj.2013.8275.8280
URL: https://scialert.net/abstract/?doi=itj.2013.8275.8280
DOI: 10.3923/itj.2013.8275.8280
URL: https://scialert.net/abstract/?doi=itj.2013.8275.8280
REFERENCES
- Bosch, A., A. Zisserman and X. Muoz, 2008. Image classification using ROIs and multiple kernel learning. Int. J. Comput. Vision.
Direct Link - Opelt, A., A. Pinz and A. Zisserman, 2006. A boundary-fragment-model for object detection. Proceedings of the 9th European Conference on Computer Vision, Graz, Austria, May 7-13, 2006, Springer, Berlin/Heidelberg, pp: 575-588.
CrossRef - Agarwal, S., A. Awan and D. Roth, 2004. Learning to detect objects in images via a sparse, part-based representation. IEEE Trans. Pattern Anal. Mach. Intell., 26: 1475-1490.
CrossRefDirect Link - Amit, Y. and A. Trouve, 2007. Pop: Patchwork of parts models for object recognition. Int. J. Comput. Vision, 75: 267-282.
CrossRef - Leibe, B., E. Seemann and B. Schiele, 2005. Pedestrian detection in crowded scenes. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Volume 1, June 20-25, 2005, IEEE Press, pp: 878-885.
CrossRef - Ballard, D.H., 1981. Generalizing the hough transform to detect arbitrary shapes. Patt. Recog., 13: 111-122.
CrossRef - Gu, C., J.J. Lim, P. Arbelaez and J. Malik, 2009. Recognition using regions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 20-25, 2009, IEEE Press, Miami, FL., pp: 1030-1037.
CrossRef - Crandall, D., P. Felzenszwalb and D. Huttenlocher, 2005. Spatial priors for part-based recognition using statistical models. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Volume 1, June 20-25, 2005, IEEE Press, pp: 10-17.
CrossRef - Sudderth, E.B., A. Torralba, W.T. Freeman and A.S. Willsky, 2005. Learning hierarchical models of scenes, objects and parts. Proceedings of the 10th IEEE International Conference on Computer Vision, Volume 2, October 17-21, 2005, IEEE Press, Beijing, pp: 1331-1338.
CrossRef - Felzenszwalb, P.F. and D.P. Huttenlocher, 2005. Pictorial structures for object recognition. Int. J. Comput. Vision, 61: 55-79.
CrossRef - Fergus, R., P. Perona and A. Zisserman, 2005. A sparse object category model for efficient learning and exhaustive recognition. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Volume 1, June 20-25, 2005, IEEE Press, pp: 380-387.
CrossRef - Bouchard, G. and B. Triggs, 2005. Hierarchical part-based visual object categorization. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Volume 1, June 20-25, 2005, IEEE Press, pp: 710-715.
CrossRef - Wang, G. and C. Chen, 2010. Using non-symmetry and anti-packing representation model for object detection. Proceedings of the International Conference on Computational Intelligence and Software Engineering, December 10-12, 2010, IEEE Press, Wuhan, pp: 1-4.
CrossRef - Zhang, H., W. Gao, X. Chen and D. Zhao, 2006. Object detection using spatial histogram features. Image Vision Comput., 24: 327-341.
CrossRef - Shotton, J., A. Blake and R. Cipolla, 2005. Contour-based learning for object detection. Proceedings of the 10th IEEE International Conference on Computer Vision, Volume 1, October 17-21, 2005, IEEE Press, pp: 503-510.
CrossRef - Sullivan, J., O. Danielsson and S. Carlsson, 2008. Exploiting part-based models and edge boundaries for object detection. Proceedings of the Computing: Techniques and Applications, Digital Image, December 1-3, 2008, IEEE Press,Canberra, ACT., pp: 199-206.
CrossRef - Grauman, K. and T. Darrell, 2007. The pyramid match kernel: Efficient learning with sets of features. J. Mach. Learn. Res., 8: 725-760.
Direct Link - Lee, K.M., 2008. Component-based face detection and verification. Pattern Recognition Lett., 29: 200-214.
CrossRef - Zhu, L., Y. Chen, A. Yuille and W. Freeman, 2010. Latent hierarchical structural learning for object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 13-18, 2010, IEEE Press, San Francisco, CA., pp: 1062-1069.
CrossRef - Leibe, B., A. Leonardis and B. Schiele, 2008. Robust object detection with interleaved categorization and segmentation. Int. J. Comput. Vision, 77: 259-289.
CrossRef - Leordeanu, M., M. Hebert and R. Sukthankar, 2007. Beyond local appearance: Category recognition from pairwise interactions of simple features. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 17-22, 2007, IEEE Press, Minneapolis, MN., pp: 1-8.
CrossRef - Matthews, I. and S. Baker, 2004. Active appearance models revisited. Int. J. Comput. Vision, 60: 135-164.
CrossRef - Dalal, N. and B. Triggs 2005. Histograms of oriented gradients for human detection. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Volume 1, June 25, 2005, San Diego, CA., USA., pp: 886-893.
CrossRef - Fergus, R., P. Perona and A. Zisserman, 2003. Object class recognition by unsupervised scale-invariant learning. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Volume 2, June 18-20, 2003, IEEE Press, pp: II-264-II-271.
CrossRef - Agarwal, S. and D. Roth, 2002. Learning a sparse representation for object detection. Proceedings of the 7th European Conference on Computer Vision Copenhagen, Denmark, Volume 2353, May 28-31, 2002, Springer, Berlin/Heidelberg, pp: 113-127.
CrossRef - Schneiderman, H. and T. Kanade, 2004. Object detection using the statistics of parts. Int. J. Comput. Vision, 56: 151-177.
CrossRef - Ferrari, V., L. Fevrier, F. Jurie and C. Schmid, 2008. Groups of adjacent contour segments for object detection. IEEE Trans. Pattern Anal. Mach. Intell., 30: 36-51.
CrossRef - Ferrari, V., T. Tuytelaars and L. Van Gool, 2006. Object detection by contour segment networks. Proceedings of the 9th European Conference on Computer Vision, Graz, Austria, Volume 3953, May 7-13, 2006, Springer, Berlin/Heidelberg, pp: 14-28.
CrossRef - Lan, Y., H. Ren, Y. Zhang, H. Yu and G. Wang, 2011. A novel object representation model for object detection. Proceedings of the 4th International Workshop on Advanced Computational Intelligence, October 19-21, 2011, IEEE Press, Wuhan, pp: 59-63.
CrossRef