Semantic Knowledge-based Bayesian Refinement for Object Recognition

Even if some of previous approaches prove their effectiveness for tightly controlled environments such as industrial settings, dependable object recognition remains difficult in real environments. Thus, this paper proposes a method of robust object recognition effective in real environments. The basic idea is to recognize and predict objects via a combined use of ontology and Bayesian network. To demonstrate the benefits of the proposed approach, a case study is conducted in an actual working environment