Boosting feature selection for Neural Network based regression - Sorbonne Université Access content directly
Journal Articles Neural Networks Year : 2009

Boosting feature selection for Neural Network based regression

Kevin Bailly


The head pose estimation problem is well known to be a challenging task in computer vision and is a useful tool for several applications involving human-computer interaction. This problem can be stated as a regression one where the input is an image and the output is pan and tilt angles. Finding the optimal regression is a hard problem because of the high dimensionality of the input (number of image pixels) and the large variety of morphologies and illumination. We propose a new method combining a boosting strategy for feature selection and a neural network for the regression. Potential features are a very large set of Haar-like wavelets which are well known to be adapted to face image processing. To achieve the feature selection, a new Fuzzy Functional Criterion (FFC) is introduced which is able to evaluate the link between a feature and the output without any estimation of the joint probability density function as in the Mutual Information. The boosting strategy uses this criterion at each step: features are evaluated by the FFC using weights on examples computed from the error produced by the neural network trained at the previous step. Tests are carried out on the commonly used Pointing 04 database and compared with three state-of-the-art methods. We also evaluate the accuracy of the estimation on FacePix, a database with a high angular resolution. Our method is compared positively to a Convolutional Neural Network, which is well known to incorporate feature extraction in its first layers.
Fichier principal
Vignette du fichier
bailly09nn_draft.pdf (294.92 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-00731068 , version 1 (12-09-2012)



Kevin Bailly, Maurice Milgram. Boosting feature selection for Neural Network based regression. Neural Networks, 2009, 22 (5-6), pp.748-756. ⟨10.1016/j.neunet.2009.06.039⟩. ⟨hal-00731068⟩
239 View
1045 Download



Gmail Mastodon Facebook X LinkedIn More