Grigory Antipov
ABSTRACT
This paper addresses the problem of image features selection for pedestrian gender recognition. Hand-crafted features (such as HOG) are compared with learned features which are obtained by training convolutional neural networks. The comparison is performed on the recently created collection of versatile pedestrian datasets which allows us to evaluate the impact of dataset properties on the performance of features. The study shows that hand-crafted and learned features perform equally well on small-sized homogeneous datasets. However, learned features significantly outperform hand-crafted ones in the case of heterogeneous and unfamiliar (unseen) datasets. Our best model which is based on learned features obtains 79% average recognition rate on completely unseen datasets. We also show that a relatively small convolutional neural network is able to produce competitive features even with little training data.
- L. Cao, M. Dikmen, Y. Fu, and T. S. Huang. Gender recognition from body. In ACM MM, Canada, 2008. Google Scholar
Digital Library
- K. Chatfield, K. Simonyan, A. Vedaldi, and A. Zisserman. Return of the devil in the details: Delving deep into convolutional nets. CoRR, abs/1405.3531, 2014.Google Scholar
- M. Collins, J. Zhang, P. Miller, and H. Wang. Full body image feature representations for gender profiling. In ICCV, Japan, 2009.Google ScholarCross Ref
- N. Dalal and B. Triggs. Histograms of oriented gradients for human detection. In CVPR, USA, 2005. Google ScholarDigital Library
- Y. Deng, P. Luo, C. C. Loy, and X. Tang. Pedestrian attribute recognition at far distance. In ACM MM, USA, 2014. Google ScholarDigital Library
- I. J. Goodfellow, Y. Bulatov, J. Ibarz, S. Arnoud, and V. Shet. Multi-digit number recognition from street view imagery using deep convolutional neural networks. CoRR, abs/1312.6082, 2013.Google Scholar
- J. A. Hanley and B. J. McNeil. The meaning and use of the area under a receiver operating characteristic (roc) curve. Radiology, 1982.Google Scholar
- G. E. Hinton, O. Vinyals, and J. Dean. Distilling the knowledge in a neural network. In NIPS Deep Learning Workshop, Canada, 2014.Google Scholar
- Y. Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick, S. Guadarrama, and T. Darrell. Caffe: Convolutional architecture for fast feature embedding. CoRR, abs/1408.5093, 2014.Google ScholarDigital Library
- T. Joachims. Making large scale SVM learning practical. 1999.Google Scholar
- A. Krizhevsky, I. Sutskever, and G. E. Hinton. Imagenet classification with deep convolutional neural networks. In NIPS, USA, 2012.Google Scholar
- R. Layne, T. M. Hospedales, S. Gong, et al. Person re-identification by attributes. In BMVC, UK, 2012.Google ScholarCross Ref
- Y. LeCun and Y. Bengio. Convolutional networks for images, speech, and time series. The handbook of brain theory and neural networks, 1995. Google ScholarDigital Library
- D. G. Lowe. Object recognition from local scale-invariant features. In ICCV, Canada, 1999. Google ScholarDigital Library
- C.-B. Ng, Y.-H. Tay, and B.-M. Goi. A convolutional neural network for pedestrian gender recognition. In ISNN. Springer, 2013. Google ScholarDigital Library
- T. Ojala, M. Pietik\"ainen, and D. Harwood. A comparative study of texture measures with classification based on featured distributions. Pattern recognition, 1996.Google Scholar
- A. S. Razavian, H. Azizpour, J. Sullivan, and S. Carlsson. Cnn features off-the-shelf: an astounding baseline for recognition. CoRR, abs/1403.6382, 2014.Google Scholar
- O. Russakovsky, J. Deng, H. Su, J. Krause, and S. S. et al. ImageNet Large Scale Visual Recognition Challenge. CoRR, abs/1409.0575, 2014.Google Scholar
- Y. Taigman, M. Yang, M. Ranzato, and L. Wolf. Deepface: Closing the gap to human-level performance in face verification. In CVPR, USA, 2014. Google ScholarDigital Library
Index Terms
- Learned vs. Hand-Crafted Features for Pedestrian Gender Recognition
Recommendations
Classification of radiolarian images with hand-crafted and deep features
Radiolarians are planktonic protozoa and are important biostratigraphic and paleoenvironmental indicators for paleogeographic reconstructions. Radiolarian paleontology still remains as a low cost and the one of the most convenient way to obtain dating ...
Hand-Crafted Features or Machine Learnt Features? Together They Improve RGB-D Object Recognition
ISM '14: Proceedings of the 2014 IEEE International Symposium on MultimediaRGB-D object recognition is an important research topic in computer version, and seeking a robust image representation is the most important sub problem for RGB-D object recognition. On the one hand, the recently emerging deep learning methods, which ...
Crack recognition on concrete structures based on machine crafted and hand crafted features
AbstractConcrete structures play a critical role in infrastructure development, and their safety is of utmost importance. Cracks in concrete structures can be a sign of deterioration, which may affect the overall safety of the building. Regular ...
Comments