A Convolutional Neural Network for Pedestrian Gender Recognition

详细信息    查看全文

• 作者：Choon-Boon Ng (19)
  Yong-Haur Tay (19)
  Bok-Min Goi (19)
  
• 关键词：Gender recognition ; convolutional neural network
• 刊名：Lecture Notes in Computer Science
• 出版年：2013
• 出版时间：2013
• 年：2013
• 卷：7951
• 期：1
• 页码：565-573
• 全文大小：281KB
• 参考文献：1. Cao, L., Dikmen, M., Fu, Y., Huang, T.: Gender recognition from body. In: Proceeding of the 16th ACM International Conference on Multimedia (2008), pp. 725鈥?28 (2008)
  2. Collins, M., Zhang, J., Miller, P.: Full body image feature representations for gender profiling. In: 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops, pp. 1235鈥?242 (2009)
  3. Guo, G., Mu, G., Fu, Y.: Gender from body: A biologically-inspired approach with manifold learning. In: Zha, H., Taniguchi, R.-i., Maybank, S. (eds.) ACCV 2009, Part III. LNCS, vol.聽5996, pp. 236鈥?45. Springer, Heidelberg (2010) CrossRef
  4. Bourdev, L., Maji, S., Malik, J.: Describing People: A Poselet-Based Approach to Attribute Classification. In: 2011 IEEE International Conference on Computer Vision (ICCV), pp. 1543鈥?550 (2011)
  5. LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proceedings of the IEEE聽86(11), 2278鈥?324 (1998) CrossRef
  6. Lawrence, S., Giles, C.L., Tsoi, A.C., Back, A.D.: Face recognition: a convolutional neural-network approach. IEEE Transactions on Neural Networks / A Publication of the IEEE Neural Networks Council聽8(1), 98鈥?13 (1997) CrossRef
  7. Osadchy, M., Cun, Y., Miller, M.: Synergistic face detection and pose estimation with energy-based models. The Journal of Machine Learning Research聽8, 1197鈥?215 (2007)
  8. Ciresan, D., Meier, U., Masci, J., Schmidhuber, J.: A committee of neural networks for traffic sign classification. In: The 2011 International Joint Conference on Neural Networks (IJCNN), vol.聽1(1), pp. 1918鈥?921 (2011)
  9. Ji, S., Xu, W., Yang, M., Yu, K.: 3D Convolutional Neural Networks for Human Action Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence聽35(1), 221鈥?31 (2013) CrossRef
  10. Jarrett, K., Kavukcuoglu, K., LeCun, Y.: What is the best multi-stage architecture for object recognition? In: 2009 IEEE 12th International Conference on Computer Vision, pp. 2146鈥?153 (2009)
  11. Sermanet, P., LeCun, Y.: Traffic sign recognition with multi-scale convolutional networks. In: The 2011 International Joint Conference on Neural Networks (IJCNN), pp. 2809鈥?813 (2011)
  12. Fukushima, K.: Neocognitron: A hierarchical neural network capable of visual pattern recognition. Neural Networks聽1(2), 119鈥?30 (1988) CrossRef
  13. Riesenhuber, M., Poggio, T.: Hierarchical models of object recognition in cortex. Nature Neuoscience聽2(11), 1019鈥?025 (1999) CrossRef
  14. Ranzato, M., Huang, F.J., Boureau, Y.-L., LeCun, Y.: Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition. In: 2007 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1鈥? (2007)
  15. Oren, M., Papageorgiou, C., Sinha, P., Osuna, E., Poggio, T.: Pedestrian detection using wavelet templates. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 193鈥?99 (1997)
  16. Bergstra, J., et al.: Theano: A CPU and GPU Math Compiler in Python. In: Proceedings of the Python for Scientific Computing Conference, SciPy (2010)
  17. Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS 2010), vol.聽9, pp. 249鈥?56 (2010)
  18. LeCun, Y., Kavukcuoglu, K., Farabet, C.: Convolutional networks and applications in vision. In: Proceedings of 2010 IEEE International Symposium on Circuits and Systems (ISCAS), pp. 253鈥?56 (2010)
  
• 作者单位：Choon-Boon Ng (19)
  Yong-Haur Tay (19)
  Bok-Min Goi (19)
  
  19. Universiti Tunku Abdul Rahman, Kuala Lumpur, Malaysia
  

文摘

We propose a discriminatively-trained convolutional neural network for gender classification of pedestrians. Convolutional neural networks are hierarchical, multilayered neural networks which integrate feature extraction and classification in a single framework. Using a relatively straightforward architecture and minimal preprocessing of the images, we achieved 80.4% accuracy on a dataset containing full body images of pedestrians in both front and rear views. The performance is comparable to the state-of-the-art obtained by previous methods without relying on using hand-engineered feature extractors.