摘要：This paper investigates how to construct a feature space for compression-based pattern recognition which judges the similarity between two objects x and y through the compression ratio to compress x with y (’s dictionary). Specifically, we focus on the known framework called PRDC, which represents an object x as a compression-ratio vector (CV) that lines up the compression ratios after x is compressed with multiple different dictionaries. By representing an object x as a CV, PRDC makes it possible to apply vector-based pattern recognition techniques to the compression-based pattern recognition. For PRDC, the dimensions, i.e., the dictionaries determine the quality of the CV space. This paper presents a practical technique to modify the chosen dictionaries in order to improve the performance of pattern recognition substantially: First, in order to make the dictionaries independent from each other, our method leaves any word shared by multiple dictionaries in only one dictionary and assures that any pair of dictionaries have no common words. Next, we transfer words among the dictionaries, so that all the dictionaries may keep roughly the same number of words and acquire the descriptive power evenly. The application to real image classification shows that our method increases classification accuracy by up to 8% compared with the case without our method, which demonstrates that our approach to keep the dictionaries independent is effective.
