基于会计信息智能化管理的票据图像处理与识别  

Bill Image Processing and Recognition Based on Intelligent Management of Accounting Information

作　　者：李宗民[1] LI Zongmin(School of Economics and Management,Zhongyuan Institute of Technology,Zhengzhou 450007,China)

机构地区：[1]中原工学院经济管理学院,郑州450007

出　　处：《河南科学》2020年第9期1394-1399,共6页Henan Science

基　　金：河南省科技厅软科学项目(172400410644);“纺织之光”中国纺织工业联合会高等教育教学改革项目(2017BKJGLX057);中原工学院技术创新管理跨学科团队项目。

摘　　要：随着数字经济时代的到来和智能技术的广泛应用,传统的会计信息处理方式已无法满足准确性、及时性、全面性等要求,会计信息的智能化处理需求日益增强.基于以上需求,综合二值化、改进型定向白游法、维纳滤波、灰度投影及卷积神经网络对会计票据图像进行预处理、倾斜校正、去噪、字符分割及识别,实现了票据信息的智能化采集,降低了会计信息处理成本,提升了会计信息处理效率.通过对150张样本票据图像的仿真实验,实验结果显示识别准确率高达98.42%,表明该方法具有有效性,对企业开展会计信息智能化处理具有应用价值.With the advent of the digital economy era and the widespread application of intelligence technology,traditional accounting information processing methods have been unable to meet the requirements of accuracy,timeliness,and comprehensiveness,etc.and the need for intelligent processing of accounting information increases.Based on the above requirements,this paper integrates binarization,the improved method of directional white run,Wiener filtering,the gray projection and convolutional neural network to preprocess,tilt correct,denoise,character segment and recognize the accounting bill image,for achieving intelligent collection of bill information,reducing the cost of accounting information processing and improving the efficiency of accounting information processing.Through the simulation experiment of 150 sample bill images,the experimental results show that the recognition accuracy rate is as high as 98.42%,indicating that the method is effective and has application value for enterprises to carry out intelligent accounting information processing.

关 键 词：会计信息 票据 信息处理 智能化 图像识别 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]