Recognition of Japanese Connected Cursive Characters Using Multiple Softmax Outputs

It is difficult to recognize cursive characters kuzushiji in classic Japanese literature because multiple characters are connected. In this study, we propose a method for correctly recognizing consecutive kuzushiji characters by using multiple candidate regions as input to a neural network even if character regions are misaligned. An evaluation using an image database of three consecutive kuzushiji characters demonstrated that the proposed method had a higher accuracy rate than a method in which the character images were cropped based on the detected boundary.