基于词典的联机手写日文病名识别系统的分析与实现-analysis and implementation of online handwritten japanese disease name recognition system based on dictionary.docx

Lexicon Driven On-line Handwritten Japanese Disease Name RecognitionAbstractWith the quick development of computer science and internet, many kinds of pen-based input electronic devices, such as tablet PCs, electronic whiteboards and e-pens, have been widely used. Users can input any text freely on a large writing area. Therefore, on-line recognition of handwriting character string becomes an attractive research topic in pattern recognition fields.This dissertation focuses on on-line recognition of handwritten Japanese disease name, a special character string. Based on referencing of some of the successful approaches for off-line handwritten address string recognition, and analyzing the features of disease name, we choose lexicon driven recognition method for on-line handwritten Japanese disease name recognition. The main contents of this dissertation are as follows:Collection of the samples for on-line handwritten Japanese disease name by using Technote. It includes the layout design of A4 paper, and preprocessing of sampled on-line handwritten disease name.Adoption of nonlinear classifiers for classification of the stroke features. After feature extraction for each stroke of on-line handwritten Japanese disease name, support vector machine (SVM) and kernel-based nonlinear representor (KNR) are adopted for classification of the stroke features.Study on an effective lexicon driven recognition method for on-line handwritten Japanese disease name recognition. The lexicon contains 21,713 disease name phrases, which are stored in a Tree structure. In segmentation, an online handwritten disease name string inputted is over-segmented into primitive segments according to the features such as spatial information between adjacent strokes. Then one or more consecutive primitive segments form a candidate character pattern. TheIIcombination of all candidate patterns is represented by a segmentation candidate lattice, where each node denotes a segmentation point and each arc