There are many reports of medical errors mainly caused by the similarity of drug names in Japanese such as (Amaryl) and (Almarl). In order to prevent such errors, one of we studied methods of measuring the similarity of drug names and implemented a search engine to find pairs of similar medicine names in Japan. However, the existing methods only evaluate sequences of common substrings. In addition, although some methods take the similarity of character (letter) shapes into consideration, they assume that the similarity of each character pair is given, usually by hand. In order to define the objective similarity index of medicine names, it is also necessary to measure the similarity of character shape objectively. In this study, we propose a method of evaluating character similarity by image processing and apply the method if defining medicine name similarity.