摘要
图形符号的绘制是手写输入的重要部分,广泛应用于笔记记录、思维导图等方面。现有手写输入设备大多仅单纯记录手写输入的内容,而并不进行输入符号的识别和标准化处理。针对这一问题,提出一种基于标准化处理的手写符号快速识别方法。将手写符号进行几何和离散采样标准化处理,去除输入过程中尺寸、旋转、平移和采样等差异的影响;将标准化后符号与手写符号库中的模板进行形状相似性比较,得到输入符号识别结果;将标准库中的对应符号进行几何反变换,得到标准化的输入符号。基于上述处理,可以实现手写符号的快速识别和标准化处理,能有效提升手写输入过程的效率,为手写符号输入提供一种新的解决办法。
The drawing of graphic symbols is an important part of handwritten input, which is widely used in notes recording, mind mapping and so on. Most of the existing input devices for handwritten simply record the content without the recognition and standardization of input symbols. In response to this problem, a rapid handwritten symbol recognition method based on standardization was proposed. The method normalized the handwritten symbols to eliminate the influence of the size and rotation factor during the input process. The similarity between the normalized symbols and the data in the handwritten symbol database was compared to obtain the information of the input symbols. The corresponding symbols in the standard library were inversely transformed geometrically to replace the input by handwriting to obtain standardized input symbols. Based on the above processing, the rapid recognition and standardization of handwritten symbols can be realized, which can effectively improve the efficiency of handwritten input process and provide a new solution for handwritten symbol input.
作者
唐德可
王峰
王宏琦
Tang Deke;Wang Feng;Wang Hongqi(University of Chinese Academy of Sciences,Beijing 100190,China;Institute of Electronics Chinese Academy of Sciences,Beijing 100190,China;Key Laboratory of Technology in Geo-spatial Information Processing and Application System,Chinese Academy of Sciences,Beijing 100190,China)
出处
《计算机应用与软件》
北大核心
2018年第9期242-246,共5页
Computer Applications and Software
基金
国家重点研发计划项目(2017YFB0502901)
关键词
标准化
符号识别
几何变换
Standardization
Symbol recognition
Geometric transformation