Cognitive Object Recognition System - It is all in the brain!

Automated object recognition is an important and challenging problem. The technology is crucial for a number of Army applications including video surveillance, Automatic Target Recognition and Simultaneous Localization and Mapping. While feature-based or template matching-based classification algorithms are used in certain Army applications, it has been observed that their classification accuracy depends on the quality of the training dataset. Often the lack of a representative set of training images severely affects performance. Moreover, the algorithms generally perform poorly when the object is occluded. Each of these methods addresses certain aspects of recognition while ignoring others. Thus, there is a need for a psychologically inspired and comprehensive approach to object recognition. Research in Neuroscience has indicated that humans do not use one specific algorithm but simultaneously use a combination of multiple classification algorithms. Thus, we propose Cognitive Object Recognition System based on the latest psychological models that combines Geon-theory and Feature-based recognition methods. Decisions about object classes will be achieved by optimally fusing the decision from each.