Abstract: Embodiments of the technology discussed herein address problems of traditional electronic character recognition training by artificially generating handwriting in a unique way according to machine learning techniques that transform handwriting samples according to generative rules and discriminative rules. Solutions provided herein produce a wide range of artificially generated handwriting that appears to be human generated handwriting. As such, embodiments herein provide additional characters for a system's character bank that are obtained more efficiently, as compared to traditional techniques. Further, embodiments herein are designed to be suitable for machine learning, and as such, the techniques grow ever more efficient as the techniques are performed. In short, the solutions provided herein improve the computing technology itself in a manner that makes robust electronic Chinese character recognition feasible.

Abstract: Disclosed are a method which is used in a computer or a communicative mobile telephone to achieve the JiuGong input of Chinese characters and a Chinese language computer or mobile telephone thereof, in which Chinese characters are divided into two classes, that is, monolithic character and transverse character, the character fonts of starting strokes are divided into nine classes, each of which respectively corresponds to the number keys 1-9 to input, 81 radicals in nine groups are used, the JiuGong pattern introduction method is adopted, and the number keys 1-9 are used to input, so that two or three keys are enough to carry out the input of a character to be inputted. The method of this invention is easy to study and could be grasped within two minutes or three without learning by rote, even an inputter who is a tyro could in short time make the input speed up to above 30 words per minute.