Creating Efficient Visual Codebook Ensembles for Object Categorization

An image comprises information, such as color, texture, shape, and intensity, which humans use in parallel for perception. Based on this knowledge, three methods of constructing visual codebook ensembles are proposed in this paper. The first technique introduced diverse individual visual codebooks by randomly choosing interesting points. The second technique was based on a random subtraining image data set with random interesting points. The third method directly utilized different patch information for constructing an ensemble with high diversity. The codebook ensembles were learned to capture and convey image properties from different aspects. Based on these codebook ensembles, different types of image presentations could be obtained. A classification ensemble could be learned based on the different expression data sets from the same training image set. The use of a classification ensemble to categorize new images can lead to improved performance. The detailed experimental analyses on several data sets revealed that the present ensemble approaches were resistant to variations in view, lighting, occlusion, and intraclass variations. In addition, they resulted in state-of-the-art performance in categorization.