Abstract
This paper presents noise robust object detection using self-quotient ε-filter (SQEF) and histograms of oriented gradients (HOG). Although object detection combining HOG and support vector machine (SVM) is a promising approach, when the images are corrupted with noise, it is difficult to realize a good detection performance. To handle noise corrupted images, we employ SQEF, and apply it to object detection combining HOG and SVM. SQEF is an improved self-quotient filter (SQF), and can clearly extract features from the images not only when they have illumination variations but also when they are corrupted with noise. We confirmed the effectiveness of our approach by using human images and car images. Throughout the experiments, our approach can realize a robust object detection from noise corrupted images using the data trained by intact images without noise.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Vadakkepat, P., Lim, P., Silva, L.C.D., Jing, L., Ling, L.L.: Multimodal Approach to Human-Face Detection and Tracking. IEEE Trans. on Industrial Electronics 55(3), 1385–1393 (2008)
Hsiao, P.-Y., Lu, C.-L., Fu, L.-C.: Multilayered Image Processing for Multiscale Harris Corner Detection in Digital Realization. IEEE Trans. on Industrial Electronics 57(5), 1799–1805 (2010)
Huang, W.-C., Wu, C.-H.: Adaptive color image processing and recognition for varying backgrounds and illumination conditions. IEEE Trans. on Industrial Electronics 45(2), 351–357 (1998)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proc. of Int’l Conf. on Computer Vision and Pattern Recognition, pp. 886–893 (2005)
Mohan, A., Papageorgiou, C., Poggio, T.: Example-based object detection in images by components. IEEE Trans. on Pattern Recognition and Machine Intelligence 23, 349–361 (2001)
Freeman, W.T., Tanaka, K., Ohta, J., Kyuma, K.: Computer vision for computer games. In: Proc. of Int’l Conf. on Automatic Face and Gesture Recognition, pp. 100–105 (1996)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int’l Journal of Computer Vision 60, 91–110 (2004)
Belongie, S., Malik, J., Puzicha, J.: Matching shapes. In: Proc. of Int’l Conf. on Computer Vision, pp. 454–461 (2001)
Matsumoto, M.: Self-quotient -filter for feature extraction from noise corrupted image. IEICE Transactions on Information and Systems E93-D(11), 3066–3075 (2010)
Wang, H., Zhang, J.J., Li, S.Z., Wang, Y.: Shape and texture preserved non-photorealistic rendering. Computer Animation and Virtual Worlds (2004)
Gooch, B., Reinhard, E., Gooch, A.: Human facial illustrations: Creations and psychological evaluation. ACM Transactions on Graphics 23(1), 27–44 (2004)
Arakawa, K., Matsuura, K., Watabe, H., Arakawa, Y.: A method of noise reduction for speech signals using component separating ε-filters. IEICE Trans. on Fundamentals J85-A(10), 1059–1069 (2002)
Arakawa, K., Okada, T.: ε-separating nonlinear filter bank and its application to face image beautification. IEICE Trans. on Fundamentals J90-A(4), 52–62 (2005)
Tomasi, C., Manduchi, R.: Bilateral filtering for gray and color images. In: Proc. IEEE Int’l Conf. on Computer Vision, pp. 839–846 (1998)
Chang, C.-C., Lin, C.-J.: LIBSVM: a library for support vector machines (2001)
Oren, M., Papageorgiou, C.P., Sinha, P., Osuna, E., Poggio, T.: Pedestrian Detection Using Wavelet Templates. In: Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, pp. 193–199 (1997)
Papageorgiou, C., Poggio, T.: A Trainable System for Object Detection. International J. of Computer Vision 38(1), 15–33 (2000)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag GmbH Berlin Heidelberg
About this paper
Cite this paper
Matsumoto, M. (2012). SVM-Based Object Detection Using Self-quotient ε-Filter and Histograms of Oriented Gradients. In: Madani, K., Dourado Correia, A., Rosa, A., Filipe, J. (eds) Computational Intelligence. IJCCI 2010. Studies in Computational Intelligence, vol 399. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-27534-0_18
Download citation
DOI: https://doi.org/10.1007/978-3-642-27534-0_18
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-27533-3
Online ISBN: 978-3-642-27534-0
eBook Packages: EngineeringEngineering (R0)