Abstract

    Popular object category recognition systems currently use an approach that represents images by a bag of visual words. However, these systems can be improved in two ways using the framework of visual bits with optimization. First, instead of representing each image feature by a single visual word, each feature is represented by a sequence of visual bits. Second, instead of separating the processes of codebook generation and classifier training, we unify them into a single framework. We propose a new way to learn visual bits using direct feature selection to avoid the complicated optimization framework. Our results confirm that visual bits outperform the bag of words model on object category recognition.

About

    Joel Jurik was a senior computer engineering student at the University of Central Florida at the time of the Computer Vision REU. His interests are image processing, computer vision, computer networks, and software development. He has interned for Lockheed Martin, was a member of the UCF Programming Team, and was part of many other clubs and organizations. He plans to pursue a Ph.D. in computer engineering.