A Novel Plausible Model for Visual Perception

摘要：

Traditionally, how to bridge the gap between the low level visual features and the high level semantic concepts has been a tough task for the researchers. In this paper, we propose a novel plausible model, namely globally connected and locally autonomic Bayesian network (GCLABN), to model the process of visual perception. The new model takes advantage of both the low level visual features, such as colors, textures and shapes, of the target object and the interrelationship between the known objects, and integrates them into a Bayesian framework, which possesses both firm theoretical foundation and wide practical applications. According to our meticulous analysis, in many aspects, the novel model theoretically outperforms the original Bayesian network, which has been successfully applied to many related areas, such as object detection, scene analysis and other similar tasks. Finally, although the GCLABN is designed for the visual perception, it also has great potential to be applied to other areas.

关键词： Visualperception Bayesian network.

作者: Zhiwei Shi Zhongzhi Shi Hong Hu

作者单位: Key Laboratory of Intelligent Information Processing,Institute of Computing Technology, CAS, Beijing 200080, China

会议类型: 国际会议

会议名称: Firth IEEE International Conference on Cognitive Informatics(第五届认知信息国际会议)

会议地点: 北京

会议语种:英文

页码: 19-24

在线出版日期: 2006-07-17（万方平台首次上网日期，不代表论文的发表时间）