Visual matching of stroke order in robotic calligraphy

Abstract

Robotic calligraphy is an interesting problem and recently draws much attention. Two major problems in robotic calligraphy are stroke shape and stroke order. Most of previous work focused on controlling brush trajectory, pressure, velocity, and acceleration to draw a desired stroke shape. As for stroke order, it was manually given from a database. Even for a software of optical character recognition (OCR), it cannot recognize the stroke order from a character image. This paper describes the automatic extraction of the stroke order of a Chinese character by visual matching. Specifically speaking, the stroke order of a Chinese character on an image can be automatically generated by the association of the standard image of the same character given with its stroke order. The proposed visual-matching method extracts the features of the Hough Lines of an input image and uses support vector machine (SVM) to associate the features with the ones of the standard image. The features used in the proposed method were evaluated on several Chinese characters. Two famous Chinese characters “Country” and “Dragon” were used to demonstrate the feasibility of the proposed method. The matched rate of the stroke order of “Country” and “Dragon” were 95.8% and 90.3%, respectively.