An Efficient Radical-Based Algorithm for Stroke-Order Free and Stroke-Number Free Online Kanji Character Recognition
Wenjie Cai, Seiichi Uchida, Hiroaki Sakoe, Minami Tateishi · 2013
This paper investigates improvements of an online handwriting stroke-order analysis algorithm ― radical-based cube search (RBCS ), which based on free stroke-order generation model called cube graph and dynamic programming (DP). We propose a novel model to resolve both of the stroke-order free and the stroke-number free problems, with lower time complexity of stroke-order search DP. By dividing character into radicals, the model is decomposed into intra-radical graphs and an inter-radical graph. This decomposition considerably reduces the time and spatial complexity. Within the intra-radical graphs, we resolve the stroke-number free problem by using a model called multilayer cube graph. Experimental results showed a higher recognition accuracy of 91.65%, and a practical average recognition time of 0.45s per character.