Title :
Discriminative feature fusion for image classification
Author :
Fernando, Basura ; Fromont, Elisa ; Muselet, Damien ; Sebban, Marc
Author_Institution :
ESAT-PSI, K.U. Leuven, Leuven, Belgium
Abstract :
Bag-of-words-based image classification approaches mostly rely on low level local shape features. However, it has been shown that combining multiple cues such as color, texture, or shape is a challenging and promising task which can improve the classification accuracy. Most of the state-of-the-art feature fusion methods usually aim to weight the cues without considering their statistical dependence in the application at hand. In this paper, we present a new logistic regression-based fusion method, called LRFF, which takes advantage of the different cues without being tied to any of them. We also design a new marginalized kernel by making use of the output of the regression model. We show that such kernels, surprisingly ignored so far by the computer vision community, are particularly well suited to achieve image classification tasks. We compare our approach with existing methods that combine color and shape on three datasets. The proposed learning-based feature fusion process clearly outperforms the state-of-the art fusion methods for image classification.
Keywords :
computer vision; feature extraction; image classification; learning (artificial intelligence); regression analysis; sensor fusion; LRFF; bag-of-words-based image classification; computer vision; discriminative feature fusion; learning-based feature fusion; logistic regression-based fusion method; marginalized kernel; regression model; statistical dependence; Computational modeling; Dictionaries; Image color analysis; Kernel; Logistics; Shape; Visualization;
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on
Conference_Location :
Providence, RI
Print_ISBN :
978-1-4673-1226-4
Electronic_ISBN :
1063-6919
DOI :
10.1109/CVPR.2012.6248084