Learned vs. Hand-Crafted Features for Pedestrian Gender Recognition - Archive ouverte HAL Access content directly
Conference Papers Year : 2015

Learned vs. Hand-Crafted Features for Pedestrian Gender Recognition

Grigory Antipov
Sid-Ahmed Berrani
  • Function : Author
  • PersonId : 878178
Natacha Ruchaud
  • Function : Author
  • PersonId : 989034
Jean Luc Dugelay
  • Function : Author


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.
No file

Dates and versions

hal-01380429 , version 1 (13-10-2016)



Grigory Antipov, Sid-Ahmed Berrani, Natacha Ruchaud, Jean Luc Dugelay. Learned vs. Hand-Crafted Features for Pedestrian Gender Recognition. Conférence internationale, Oct 2015, Brisbane, Australia. ⟨10.1145/2733373.2806332⟩. ⟨hal-01380429⟩


110 View
0 Download



Gmail Mastodon Facebook X LinkedIn More