Learned vs. Hand-Crafted Features for Pedestrian Gender Recognition
Open Access
- 13 October 2015
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1263-1266
Abstract
International audienceThis 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 dataKeywords
This publication has 13 references indexed in Scilit:
- Pedestrian Attribute Recognition At Far Distance2014
- Caffe2014
- Return of the Devil in the Details: Delving Deep into Convolutional Nets2014
- A Convolutional Neural Network for Pedestrian Gender RecognitionLecture Notes in Computer Science, 2013
- Person Re-identification by Attributes2012
- Full body image feature representations for gender profiling2009
- Gender recognition from body2008
- Histograms of Oriented Gradients for Human Detection2005
- Object recognition from local scale-invariant features1999
- The meaning and use of the area under a receiver operating characteristic (ROC) curve.Radiology, 1982