Image recognition and classification based on REM with LBP feature
Ying Jiang, Yanjiang Wang · 2016
The computer vision research aims to enable computer to recognize images as easily as human. Human can segregate target from its surrounding environment, which is associated with human memory mechanism. However, it is not quite clear about how the visual images are stored and retrieved in the human brain. This paper attempts to introduce the REM (Retrieving Effective from Memory) model into image learning and recognition and study how a computer can learn and recognize visual images as human do. First, the feature vector of the visual image is extracted by the local binary pattern (LBP) method. Then the probe image is matched in parallel to the studied images. Finally the Bayesian decision is used to calculate the likelihood ratio between the probe image feature vector and that of each studied image. If this ratio is greater than value 1, the probe image is thought to have been studied and match with the studied image with the maximal likelihood. Experimental results show that the REM model can gain good recognition performance not only in the classification of the same object with small rotation angels but also in the classification of the same image category, and the false alarm rate is far lower than other recognition method.