An ontology-based hybrid methodology for image synthesis and identification with convex objects

ABSTRACT

One of the core challenges in developing a computer system for machine learning is to make the system learn efficiently and effectively like a real human by grasping the domain knowledge exemplified by human experts. In this challenge, we have introduced a hybrid image synthesis model that can simulate one of the human’s learning capabilities in the vision field – the ability to synthesize images of convex objects by identifying solid geometries and textures of specific objects using few photographs. We have incorporated an ontology-based, domain knowledge on solid geometries into our model to synthesize large number of training images with only a minimum number of input images. Our initial experiments have shown that our model has convincing improvements by demonstrating a substantially better FAR/FRR/EER results when it is compared with a smaller set of non-synthetic images.

KEYWORDS:

• Ontology
• pattern recognition
• image synthesis
• feature extraction
• object identification
• solid geometries

Notes on contributors

Nanfei Sun received M. Sci. degree and Ph. D. degree in computer science in 2001 and 2006. He has been working on projects for IBM T.J. Watson research centre before he started his job as a software engineer for Hubwoo USA LP between 2006 and 2014. Since 2015, he has been a visiting assistant professor of Management Information System at the University of Houston-Clear Lake in Houston Texas (77058). His current research interests cover computer vision, machine learning, and data analytics.

Dr Jian (Denny) Lin is an Assistant Professor of the Department of Management Information Systems, University of Houston – Clear Lake, USA. He received his M. S. and Ph. D., both in Computer Science, in 2006 and 2009, respectively. His research interests include but not limited to: real-time and embedded systems, fault-tolerant computing, computer networks, signal processing and simulations. Dr. Lin is a committee member of several IEEE conferences.

Michael Yu-Chi Wu received the B.Sci. degree in electrical engineering in 1998, the M.Sci. degree in computer and information systems in 2000, the M.Sci. degree in electrical engineering in 2001, and the Ph.D. degree in electrical engineering in 2008, all from the New Jersey Institute of Technology in Newark, NJ (07102). Between 2008 and 2014, he worked as a software developer at several companies, including the Hewlett Packard Enterprise. Since 2014, he has been an assistant professor of Management Information Systems at the University of Houston – Clear Lake in Houston, Texas (77058). His current research interests include software qualities and simulations.

Disclosure statement

No potential conflict of interest was reported by the authors.

ORCID

Nanfei Sun http://orcid.org/0000-0002-4010-1514