Recognition of Japanese Connected Cursive Characters Using Multiple Softmax Outputs
Kazuya Ueki, Tomoka Kojima, Ryou Mutou, Rostam Sayyed Nezhad, Yasuaki Hagiwara · 2020
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.