山西大学学报（自然科学版）2011，Vol.34Issue(3)：351-356,6.
基于支持向量机的空白试卷识别方法
Recognition of Blank Examination Paper Based on Support Vector Machine
摘要
Abstract
Usually,it is difficult to use image pixel gray values of examination paper to directly distinguish blank examination papers and non blank examination papers. However, by using support vector machine (SVM) method,it can identify blank examination paper effectively. We constructed two two-dimensional linear separable SVM,one was the SVM l,by taking the maximum of standard deviation which the image pixel gray values of columns vector and rows vector as features. Another was the SVM 2, by taking the maximum of standard deviation of standard deviation which the image pixel gray values of columns vector and rows vector as features. In practice,most of the blank examination papers was identified by using the SVM 1. For individual examination paper samples is located in the margin (between the hyperplane and the closest training points) of SVM 1,there may be recognition errors. In this case,we can use the SVM 2 for further recognition. The methods achieve a perfect performance in HSK blank examination paper recognition.关键词
空白试卷识别/支持向量机/特征提取Key words
blank examination paper recognition/support vector machine/feature extraction分类
信息技术与安全科学引用本文复制引用
贾志先..基于支持向量机的空白试卷识别方法[J].山西大学学报（自然科学版）,2011,34(3):351-356,6.基金项目
全国教育科学规划课题(FFB108172) （FFB108172）
新疆高校科研计划重点项目(XJEDU2010149) （XJEDU2010149）
