Incremental object classification using hierarchical generative Gaussian mixture and topology based feature representation

This paper presents an adaptive object classification based on incremental feature extraction / representation and a hierarchical feature classifier that offers plasticity to accommodate variant input dimension and reduces forgetting problem of previously learned information. The proposed feature representation method applies incremental prototype generation with a cortex-like mechanism to conventional feature representation method to enable an incremental reflection of various object characteristics in learning process. A classifier based on a hierarchical generative model recognizes various objects with variant feature dimensions during the learning process. Experimental results show that the adaptive object classification model successfully classifies an object class against background with enhanced stability and flexibility.