Evolutionary feature selection for probabilistic object recognition, novel object detection and object saliency estimation using GMMs

Abstract

This paper presents a method for object recognition, novel object detection, and estimation of the most salient object within a set. Objects are sampled using a scale invariant region detector, and each region is characterized by the subset of texture and color descriptors selected by a Genetic Algorithm (GA). Using multiple views of an object, and multiple regions per view, objects are modeled using mixtures of Gaussians, where each object represents a possible class for a particular image region. Given a set of objects, the GA learns a corresponding Gaussian Mixture Models (GMM) for each object in the set employing a one vs. all training scheme. Thence, given an input image where interest regions are detected, if a large majority of the regions are classified as regions of object O then it is assumed that said object appears in the imaged scene. The GA’s fitness function promotes: 1) a high classification accuracy, 2) the selection of a minimal subset of descriptors, and 3) a high separation among models. The separation between two GMMs is computed using a weighted version of Fisher’s linear discriminant, which is also used to estimate the most “salient” object among the set of modeled objects. Object recognition and novel object detection are done using confidence-based classification. Hence, when a non-modeled object is sampled, the detected regions are thereby identified as belonging to an unseen object and a new GMM is trained accordingly. Experimental results on the COIL-100 data set confirm the soundness of the approach.