Selection of universal features for image classification

Abstract

Neuromimetic algorithms, such as the HMAX algorithm, have been very successful in image classification tasks. However, current implementations of these algorithms do not scale well to large datasets. Often, target-specific features or patches are “learned” ahead of time and then correlated with test images during feature extraction. In this paper, we develop a novel method for selecting a single set of universal features that enables classification across a broad range of image classes. Our method trains multiple Random Forest classifiers using a large dictionary of features and then combines them using a majority voting scheme. This enables the selection of the most discriminative patches based on feature importance measures. Experiments demonstrate the viability of this method using HMAX features as well as the tradeoff between the number of universal features, classification performance, and processing time.