Random Subwindows for Robust Image Classification

We present a novel, generic image classification method based on a recent machine learning algorithm (ensembles of extremely randomized decision trees). Images are classified using randomly extracted subwindows that are suitably normalized to yield robustness to certain image transformations. Our method is evaluated on four very different, publicly available datasets (COIL-100, ZuBuD, ETH80, WANG). Our results show that our automatic approach is generic and robust to illumination, scale, and viewpoint changes. An extension of the method is proposed to improve its robustness with respect to rotation changes. International Conference on Computer Vision and Pattern Recognition (CVPR), San Diego, CA, USA, June 20-25, 2005.

• Type: Conference
• Year: 2005
• Where: CVPR
• Authors: Justus H. Piater, Louis Wehenkel, Pierre Geurts, Raphaël Marée
• Keywords: Certain Image Transformations, Computer Vision, CVPR 2005, Image Classification Method, Machine Learning Algorithm, Rotation Changes, Viewpoint Changes