Image classification using random forests and ferns
A. Bosch, Andrew Zisserman and X. Munoz
In: ICCV 2007, 14-20 Oct 2007, Rio de Janeiro, Brazil.
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 [Lazebnik06] 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 with a benchmark multi-way SVM classifier. It is shown that selecting the ROI adds about 5% to the performance and, together with the other improvements, the result is about a 10% improvement over the state of the art for Caltech-256.
|EPrint Type:||Conference or Workshop Item (Poster)|
|Project Keyword:||Project Keyword UNSPECIFIED|
|Deposited By:||Mudigonda Pawan Kumar|
|Deposited On:||21 September 2007|