Image Classification using Random Forests and Ferns

We explore the problem of classifying images by the object categories they contain in the case of a large number of object categories. To this end we combine three ingredients: (i) shape and appearance representations that support spatial pyramid matching over a region of interest. This generalizes the representation of Lazebnik et al [16] from an image to a region of interest (ROI), and from appearance (visual words) alone to appearance and local shape (edge distributions). (ii) automatic selection of the regions of interest in training. This provides a method of inhibiting background clutter and adding invariance to the object instance's position, and (iii) the use of random forests (and random ferns) as a multi-way classifier. The advantage of such classifiers (over multi-way SVM for example) is the ease of training and testing. Results are reported for classification of the Caltech-101 and Caltech-256 data sets. We compare the performance of the random forest/ferns classifier...

• Type: Conference
• Year: 2007
• Where: ICCV
• Authors: Andrew Zisserman, Anna Bosch, Xavier Muñoz
• Keywords: Computer Vision, ICCV 2007, Multi-way Classifier, Multi-way Svm, Multiway Svm Classifier, Object Categories, Spatial Pyramid Matching