改进卷积神经网络的手写试卷分数识别方法  

Recognition of handwritten test scores based on improved convolutional neural network

作　　者：仝梦园 金守峰[1] 陈阳 李毅 尹加杰 TONG Mengyuan;JIN Shoufeng;CHEN Yang;LI Yi;YIN Jiajie(School of Mechanical and Electrical Engineering/Xi’an Key Laboratory of Modern Intelligent Textile Equipment,Xi’an Polytechnic University,Xi’an 710048,China)

机构地区：[1]西安工程大学机电工程学院/西安市现代智能纺织装备重点实验室,陕西西安710048

出　　处：《西安工程大学学报》2020年第4期80-85,共6页Journal of Xi’an Polytechnic University

基　　金：陕西省科技计划项目(2020GY-172);西安市科技局创新引导项目(201805030YD8CG14(5));西安市现代智能纺织装备重点实验室项目(2019220614SYS021CG043)。

摘　　要：针对手写试卷分数识别中存在耗时长、错误率高的问题,提出了改进卷积神经网络(convolution neutral network,CNN)算法的手写试卷识别方法。为简化识别分数的类别,对手写试卷分数栏进行分割处理得到0~9共10类数字。为提高手写分数识别的效率,提出卷积神经网络融合贝叶斯的分类识别算法,利用构建的卷积神经网络模型提取手写数字的特征,采用主成分分析(principal component analysis,PCA)算法对特征降维,通过贝叶斯分类器对0~9的10类数字进行判别分类,在Mnist数据库中验证该算法的准确性与效率。建立试卷分数求和模型,在手写试卷分数识别后进行自动求和。实验结果表明:对3门课程的1188份试卷手写分数的识别,相对于其他算法,该方法的识别率为98.23%,平均每份试卷识别时间为7.5 s,证明了算法的实用性。Aiming at the problems of time-consuming and high error rate in handwriting test scores statistics,a handwriting test paper recognition method based on improved convolution neural network algorithm was proposed.In order to simplify the classification of the score,the score column of the handwritten test paper was divided to obtain ten types of numbers from 0 to 9.In order to improve the efficiency of handwritten score recognition,a classification and recognition algorithm of convolution neural network and Bayesian was proposed.The constructed convolution neural network model was used to extract the characteristics of handwritten digits.The PCA algorithm was used to reduce the dimensionality of the features.The bayes classifier was used to distinguish ten kinds of numbers from 0 to 9,the auuracy and efficiency of the algorithm were verified in the MNIST database.The paper score summation model was established and automatic summation is performed after recognition.The experimental results show that for the recognition of the handwritten scores of 1188 test papers in 3 courses,the algorithm in this paper has a recognition rate of 98.23%compared with other algorithms,the average recognition time per test paper is 7.5 s,and verified its practicality.

关 键 词：分数统计 数字识别 卷积神经网络 主成分分析 贝叶斯分类器 深度学习 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]