基于多特征提取的药品日期识别方法

doi:10.11959/j.issn.2096-3750.2022.00286

Abstract

Abstract:

Drug production date and expiration date are important indicators to measure the safety and effectiveness of drugs.The production date and validity period of liquid drugs in vertical bags are printed with numbers of 0～9.The recognition of the drug date of the hospital needs to meet the requirements of high speed and accuracy.The conventional template matching method and neural network recognition method have large amount of calculation and complex training.A drug date recognition method was proposed based on multi feature extraction.The combination of vertical line feature and three features for fine feature extraction of different digital characters has advantages of small amount of calculation and fast recognition speed.Compared with the recognition method of single extracted feature, it can effectively distinguish 10 different numbers, especially suitable for numbers of similar shape.It can provide patients with safe drug use guarantee, improve the management mode of the medical staff, improve the work efficiency, so as to improve the level of the pharmaceutical service of the hospital.

Key words: expiry date, character recognition, Euler number, horizontal line characteristics, vertical line feature

CLC Number:

TP274

Min WANG, Jia WU, Shuo SUN, Sheng LI, Kang WANG. Date recognition based on multi feature extraction[J]. Chinese Journal on Internet of Things, 2022, 6(3): 146-152.

Figures/Tables 10

References 31

[10]	ZHANG G , LI D , ZHOU L et al ,et al. Research on digital recognition me-thod based on intersection feature extraction[EB]. 2015.
[11]	张辰, 陈阳 . 基于模板匹配 OCR 的报告自动归档系统研究[J]. 信息技术与网络安全, 2021,40(8): 84-89.
	ZHANG C , CHEN Y . Research on automatic filing system of detec-tion report based on template matching and OCR recognition[J]. In-formation Technology and Network Security, 2021,40(8): 84-89.
[12]	黄一格, 张炎生 . 基于 BP 神经网络的手写数字识别系统[J]. 机电工程技术, 2020,49(1): 108-110.
	HUANG Y G , ZHANG Y S . Handwritten digit recognition system based on BP neural network[J]. Mechanical ＆ Electrical Engineering Technology, 2020,49(1): 108-110.
[13]	刘芳, 张云洋 . 基于像素邻域点信息的藏文图像细化算法研究[J]. 计算机技术与发展, 2018,28(4): 21-24.
	LIU F , ZHANG Y Y . Research on a Tibetan image refinement algo-rithm based on adjacent pixel points' information[J]. Computer Tech-nology and Development, 2018,28(4): 21-24.
[14]	王怀群 . 二值图象的细化[J]. 无锡轻工大学学报, 2001,20(3): 315-318.
	WANG H Q . Fine-grain processing of two valued image[J]. Journal of Wuxi University of Light Industry, 2001,20(3): 315-318.
[15]	曹仕羽 . 基于多层特征融合的名片字符识别方法[J]. 电子设计工程, 2020,28(23): 177-182.
	CAO S Y . Research on business card character recognition algorithm based on multi-layer feature fusion[J]. Electronic Design Engineering, 2020,28(23): 177-182.
[16]	宋秋平 . 基于最近邻的多特征融合的模板匹配方法研究[D]. 哈尔滨:哈尔滨工业大学, 2021.
	SONG Q P . Research on multi-feature fusion template matching method based on NNF[D]. Harbin,Harbin Institute of Technology, 2021.
[17]	林小竹, 籍俊伟, 谷莹莹 . 图像欧拉数的研究与应用[J]. 石油化工高等学校学报, 2007,20(2): 88-91.
	LIN X Z , JI J W , GU Y Y . The Euler number study of image and its ap-plication[J]. Journal of Petrochemical Universities, 2007,20(2): 88-91.
[18]	林小竹, 吴艺娟, 傅旦丹 ,等. 图像欧拉数计算复杂度分析[J]. 微电子学与计算机, 2008,25(7): 14-16.
	LIN X Z , WU Y J , FU D D ,et al. Analysis of computation complexity on Euler number of a binary image[J]. Microelectronics ＆ Computer, 2008,25(7): 14-16.
[19]	姚斌, 何立风, 康世英 ,等. 一种快速二值图像欧拉数算法[J]. 微电子学与计算机, 2017,34(7): 46-50.
[1]	国家食品药品监督管理局. 药品说明书和标签管理规定[S]. 2006.
	China Food and Drug Administration. Regulations on management of drug instructions and labels[S]. 2006.
[19]	YAO B , HE L F , KANG S Y ,et al. A fast algorithm for computing the Euler number in a binary image[J]. Microelectronics ＆ Computer, 2017,34(7): 46-50.
[20]	武威 . 基于模板匹配与结构特征的字符识别算法研究[D]. 郑州:郑州大学, 2015.
[2]	王鲁娜, 高鹏 . 视觉传感器在药品生产日期检测中的应用[EB]. 2009.
	WANG L N , GAO P . Application of vision sensor in drug production date detection[EB]. 2009.
[20]	WU W . Research of character recognition algorithm based on template matching and structural characteristic[D]. Zhengzhou,Zhengzhou University, 2015.
[21]	倪桂博, 梁晓尊 . 基于结构形状的印刷体数字识别方法[J]. 软件导刊, 2010,9(5): 67-68.
[3]	吴冰航 . 基于机器视觉的工业 OCR 识别系统的设计与实现[D]. 成都,电子科技大学, 2021.
	WU B H . Design and implementation of industrial OCR recognition system based on machine vision[D]. Chengdu,University of Electron-ic Science and Technology of China, 2021.
[21]	NI G B , LIANG X Z . The method of printed figures based on struc-ture[J]. Software Guide, 2010,9(5): 67-68.
[22]	刘建华, 牛秦洲, 程小辉, 王勇 . 基于特征的印刷体数字符号识别系统[J]. 桂林工学院学报, 2005,25(1): 101-103.
[4]	荆涛, 王仲 . 光学字符识别技术与展望[J]. 计算机工程, 2003,29(2): 1-2,80.
	JING T , WANG Z . A survey of optical character recognition[J]. Com-puter Engineering, 2003,29(2): 1-2,80.
[22]	LIU J H , NIU Q Z , CHENG X H ,et al. Feature-based printed numer-als' recognition system[J]. Journal of Guilin Institute of Technology, 2005,25(1): 101-103.
[23]	刘慧 . 基于模糊划分的脱机手写汉字笔画特征提取方法[D]. 保定:河北大学, 2014.
[5]	陈爱斌, 陆丽娜 . 基于多特征的印刷体数字识别[J]. 计算技术与自动化, 2011,30(3): 105-108.
	CHEN A B , LU L N . The printed number character recognition based on features[J]. Computing Technology and Automation, 2011,30(3): 105-108.
[23]	LIU H . Research on offline handwritten Chinese character stroke fea-ture extraction based on fuzzy partition[D]. Baoding,Hebei Universi-ty, 2014.
[24]	. 手写体数字识别方法的研究与实现[D]. 太原,太原科技大学,, 2013.
[6]	万泉全 . 基于二级特征提取的车牌字符识别研究及实现[D]. 西安:长安大学, 2013.
	WAN Q Q . Research and achievement of tow-level feature extraction based license plate character recognition[D]. Xi'an,Changan Univer-sity, 2013.
[24]	HAO M L . Research and implementation of handwritten digital recognition method[D]. Taiyuan,Taiyuan University of Science and Technology, 2013.
[25]	肖剑 . 基于机器视觉的半导体表面字符质量检测系统研究[D]. 西安,西安科技大学, 2020.
[7]	宫义山, 王鹏 . 基于模板匹配的发票号码识别算法[J]. 沈阳工业大学学报, 2015,37(6): 673-678.
	GONG Y S , WANG P . Identification algorithm for invoice number based on template matching[J]. Journal of Shenyang University of Technology, 2015,37(6): 673-678.
[25]	XIAO J . Research on semiconductor surface character quality detec-tion system based on machine vision[D]. Xi'an,Xi'an University of Science and Technology, 2020.
[26]	刘丽丽 . 模板匹配联合特征法在车牌字符识别中的应用[J]. 工程建设与设计, 2022(2): 62-66.
[8]	王慧 . 基于模板匹配的手写体字符识别算法研究[D]. 北京,北京交通大学, 2012.
	WANG H . Handwritten character recognition algorithm based on tem-plate matching method[D]. Beijing,Beijing Jiaotong University, 2012.
[26]	LIU L L . Application of template matching and feature method in li-cense plate characters recognition[J]. Construction ＆ Design for En-gineering, 2022(2): 62-66.
[27]	姚斌, 何立风, 康世英 ,等. 基于图论的二值图像八邻接欧拉数算法[J]. 海军工程大学学报, 2016,28(5): 36-40.
[9]	WANG J , YAN W Q . BP-neural network for plate number recognition[J]. International Journal of Digital Crime and Forensics, 2016,8(3): 34-45.
[10]	张庚, 李丹周亮 ,等. 基于交点特征提取的数字识别方法研究[EB]. 2015.
[27]	YAO B , HE L F , KANG S Y ,et al. A graph-theory-based algorithm for computing 8-neighborhood Euler number in a binary image[J]. Journal of Naval University of Engineering, 2016,28(5): 36-40.
[28]	曹林伟 . 基于 PCNN 的医学图像检索[D]. 鞍山,辽宁科技大学, 2014.
	CAO L W . Medical image retrieval based on PCNN[D]. Anshan,Uni-versity of Science and Technology Liaoning, 2014.
[29]	原玉磊, 蒋理兴, 钦桂勤 . 基于字符特征的数字字符识别算法[J]. 海洋测绘, 2009,29(1): 56-58.
	YUAN Y L , JIANG L X , QIN G Q . Digital character recognition algorithm based on character feature[J]. Hydrographic Surveying and Charting, 2009,29(1): 56-58.
[30]	张友菊 . 宋体印刷数字快速识别算法的研究和应用[J]. 中国科技信息, 2008(20): 127,129.
	ZHANG Y J . Research and Application of Song Script Printed Digital Rapid Recognition Algorithm[J]. China Science and Technology In-formation, 2008(20): 127,129.
[31]	黄雨 . 基于数字的模式识别算法研究[D]. 四平,吉林师范大学, 2017.
	HUANG Y . The research of pattern recognition arithmetic base on dig-ital[D]. Siping,Jilin Normal University, 2017.

Metrics

Recommended 0

No Suggested Reading articles found!

方法	字符准确率	检测时间/s
模板点匹配	89.57%	1.677
BP神经网络	82.24%	2.835
本文	98.23%	1.933

Date recognition based on multi feature extraction

RichHTML

PDF下载

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 10

References 31

Related Articles 0

Metrics

Recommended 0