基于Tesseract_OCR的化工包装袋喷码质量检测算法

doi:10.16180/j.cnki.issn1007-7820.2022.07.005

电子科技 ›› 2022, Vol. 35 ›› Issue (7): 27-31.doi: 10.16180/j.cnki.issn1007-7820.2022.07.005

基于Tesseract_OCR的化工包装袋喷码质量检测算法

张茂林¹,叶轻舟¹,潘鑫²,陆华³

1. 福建工程学院电子电气与物理学院,福建福州350118
2. 福建工程学院计算机科学与数学学院,福建福州 350118
3. 福州三龙喷码科技有限公司,福建福州 350014

收稿日期:2021-02-05 出版日期:2022-07-15 发布日期:2022-08-16
作者简介:张茂林(1990-),男,讲师。研究方向:机器视觉、人工智能。|叶轻舟(1968-),男,教授。研究方向:物联网、图像处理与模式识别。
基金资助:
国家自然科学基金(41971340);国家自然科学基金(41471333);福建省科学计划项目(2018H001);福建省科学计划项目(2019I0019)

Quality Inspection Algorithm of Chemical Packaging Bag Coding Based on Tesseract_OCR

ZHANG Maolin¹,YE Qingzhou¹,PAN Xin²,LU Hua³

1. School of Electronic, Electrical Engineering and Physics,Fujian University of Technology,Fuzhou 350118,China
2. School of Computer Science and Mathematics,Fujian University of Technology,Fuzhou 350118,China
3. Fuzhou Sunlong Inkjetprint Technology Co., Ltd.,Fuzhou 350014,China

Received:2021-02-05 Online:2022-07-15 Published:2022-08-16
Supported by:
National Natural Science Foundation of China(41971340);National Natural Science Foundation of China(41471333);Project of Fujian Provincial Department of Science and Technology(2018H001);Project of Fujian Provincial Department of Science and Technology(2019I0019)

摘要/Abstract

摘要：

化工包装袋喷印信息存在人工检测效率低、漏检率高的问题。针对该问题,文中设计了一种基于机器视觉的化工包装袋喷码质量检测方法。使用均值滤波与高斯双边滤波算法对采集图像进行预处理,再通过基于局部统计的可变阈值算法进行字符区域定位。为解决喷码字符点与点的距离大于字符之间的间隙大小,导致二值图像闭运算后多个字符黏连形成连通域的问题,文中提出了一种改进连通域的动态字符分割算法,通过Tesseract_OCR引擎将分割的字符图像进行分类训练和识别。实验结果表明,该算法对喷码质量检测的精确率高达95.62%,满足化工包装袋喷码质量检测要求。

关键词: 机器视觉, Tesseract_OCR, 化工包装袋, 喷码质量检测, 预处理, 字符定位, 改进连通域, 字符分割

Abstract:

For the problems of low efficiency and high leakage rate in manual quality inspection of information printing on chemical packaging bags, a machine vision-based quality inspection method for printing codes on chemical packaging bags is designed in this study. Mean filtering and Gaussian bilateral filtering algorithms are used to pre-process the captured image, and then the character area is localized through a variable threshold algorithm based on local statistics. To solve the problem that the distance between the dots of the printout characters may be larger than the gap size between the characters, which leads to the formation of a connected domain with multiple characters sticking together after the binary image closure operation, the study proposes a dynamic character segmentation algorithm to improve the connected domain. The segmented character images are trained and recognized by Tesseract_OCR engine for classification. The experimental results show that the algorithm has the accuracy rate of 95.62% for coding quality detection, which can meet the requirements of chemical packaging bag coding quality inspection.

Key words: machine vision, Tesseract_OCR, chemical packaging bags, coding quality inspection, preprocessing, character localization, improved concatenated domain, character segmentation

中图分类号:

TP391.41

张茂林,叶轻舟,潘鑫,陆华. 基于Tesseract_OCR的化工包装袋喷码质量检测算法[J]. 电子科技, 2022, 35(7): 27-31.

ZHANG Maolin,YE Qingzhou,PAN Xin,LU Hua. Quality Inspection Algorithm of Chemical Packaging Bag Coding Based on Tesseract_OCR[J]. Electronic Science and Technology, 2022, 35(7): 27-31.

图/表 7

图1

图2

图3

图4

图5

图6

表1

参考文献 17

[1]	Ouadid Y, Fakir M, Minaoui B. Tifinagh printed character recognition through structural feature extraction[J]. International Journal of Computer Vision and Image Processing, 2016, 6(2):42-53. doi: 10.4018/IJCVIP.2016070103
[2]	Chen F, Li B, Dong R, et al. High-performance OCR on packing boxes in industry based on deep learning[C]. Nanjing: Proceedings of the Pacific Rim International Conference on Artificial Intelligence, 2018.
[3]	Wei H, Wen Y, Wang W, et al. Convolutional neural network for machine-printed traditional mongolian font recognition[C]. Bangkok: Proceedings of the International Conference on Neural Information Processing, 2018.
[4]	周阳, 沈婷婷, 席志远, 等. 基于Halcon的日化瓶瓶底喷码质量检测算法研究[J]. 仪表技术与传感器, 2020(11):101-104.
	Zhou Yang, Shen Tingting, Xi Zhiyuan. Research on quality Detection algorithms based on Halcon for bottom spray code of daily chemical bottles[J]. Instrument Technique and Sensor, 2020(11):101-104.
[5]	Berg S A, So R H Y, Seo S Y. Application of optical character recognition with Tesseract in logistics management[J]. International Journal of Internet Manufacturing and Services, 2019, 6(3):285-304. doi: 10.1504/IJIMS.2019.10022461
[6]	王红艳, 朱利民, 张潘杰, 等. 一种利用外轮廓配准的活塞侧面缺陷检测方法[J]. 西安电子科技大学学报, 2019, 46(5):75-83.
	Wang Hongyan, Zhu Limin, Zhang Panjie, et al. Method for the detection of the piston side defect based on external contour registration[J]. Journal of Xidian University, 2019, 46(5):75-83.
[7]	杨云辉. 基于单目视觉的工件定位技术研究[J]. 电子科技, 2019, 32(12):72-75.
	Yang Yunhui. Research on workpiece location technology based on monocular vision[J]. Electronic Science and Technology, 2019, 32(12):72-75.
[8]	王震, 景军锋, 张缓缓, 等. 基于主结构提取与签名算法的织物缺陷检测[J]. 电子测量与仪器学报, 2019, 33(4):36-41.
	Wang Zhen, Jing Junfeng, Zhang Huanhuan, et al. Fabric defect detection based on main structure extraction and signature algorithm[J]. Journal of Electronic Measurement and Instrumentation, 2019, 33(4):36-41.
[9]	马旭东, 袁锐波. 基于图像检测的硬币面值识别方法[J]. 电子科技, 2020, 33(2):43-47.
	Ma Xudong, Yuan Ruibo. An identification method of coins denomination based on image detection[J]. Electronic Science and Technology, 2020, 33(2):43-47.
[10]	雷涛, 张肖, 加小红, 等. 基于模糊聚类的图像分割研究进展[J]. 电子学报, 2019, 47(8):1776-1791.
	Lei Tao, Zhang Xiao, Jia Xiaohong, et al. Research progress on image segmentation based on fuzzy clustering[J]. Acta Electronica Sinica, 2019, 47(8):1776-1791.
[11]	刘小燕, 吴鑫, 孙炜, 等. 基于形态学重建和GMM的球团颗粒图像分割[J]. 仪器仪表学报, 2019, 40(3):230-238.
	Liu Xiaoyan, Wu Xin, Sun Wei, et al. Image segmentation of pellet particles based on morphological reconstruction and GMM[J]. Chinese Journal of Scientific Instrument, 2019, 40(3):230-238.
[12]	Goh T Y, Basah S N, Yazid H, et al. Performance analysis of image thresholding: Otsu technique[J]. Measurement, 2018, 114(7):298-307. doi: 10.1016/j.measurement.2017.09.052
[13]	朱亚萍, 邱锦山, 杨成忠. 基于改进连通域算法的车牌字符分割方法[J]. 杭州电子科技大学学报(自然科学版), 2016, 36(2):48-51.
	Zhu Yaping, Qiu Jinshan, Yang Chengzhong. License plate character segmentation method based on improved connected domain algorithm[J]. Journal of Hangzhou Dianzi University(Natural Sciences), 2016, 36(2):48-51.
[14]	张红霞, 王灿, 刘鑫, 等. 复杂背景图像的字符识别算法研究[J]. 计算机测量与控制, 2019, 27(8):162-166.
	Zhang Hongxia, Wang Can, Liu Xin, et al. Automatic recognition algorithms research for printed characters with local exposure[J]. Computer Measurement & Control, 2019, 27(8):162-166.
[15]	Sporici D, Cusnir E, Boiangiu C A. Improving the accuracy of tesseract 4.0 OCR engine using convolution-based preprocessing[J]. Symmetry, 2020, 12(5):172-179. doi: 10.3390/sym12010172
[16]	Robby G A, Tandra A, Susanto I, et al. Implementation of optical character recognition using tesseract with the javanese script target in android application[J]. Procedia Computer Science, 2019, 157(4):499-505. doi: 10.1016/j.procs.2019.09.006
[17]	冯玉田, 侯玖廷, 顾乐易. 基于Tesseract-OCR的燃气表自动识别研究[J]. 电子测量技术, 2019, 42(21):82-86.
	Feng Yutian, Hou Jiuting, Gu Leyi. Reseatch on automatic identification of gas meter based on Tesseract-OCR[J]. Electronic Measurement Technology, 2019, 42(21):82-86.

本文检测算法结果目测校验结果	喷码质量合格/包	喷码质量不合格/包	目测校验结果合计
喷码质量合格/包	939	44	983
喷码质量不合格/包	0	17	17
本文检测算法结果合计/包	939	61	1 000

基于Tesseract_OCR的化工包装袋喷码质量检测算法

Quality Inspection Algorithm of Chemical Packaging Bag Coding Based on Tesseract_OCR

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 7

参考文献 17

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	宗圣康,程建鹏,张西良. 基于光斑位置的起重机轨道高度差自动检测方法[J]. 电子科技, 2022, 35(1): 21-28.
[2]	司明明,陈玮,胡春燕,尹钟. 融合Resnet50和U-Net的眼底彩色血管图像分割[J]. 电子科技, 2021, 34(8): 19-24.
[3]	马鼎,吴定祥,唐立军. 环形陶瓷金属涂层缺陷检测方法研究[J]. 电子科技, 2021, 34(6): 28-33.
[4]	杨凌霄,王振营,刘群坡,王高伟,杨彦超. 基于H-S直方图的苹果着色率检测算法研究[J]. 电子科技, 2021, 34(5): 13-17.
[5]	晏子杰,王京梅,陈卓,刘宇. 软件可编程的FPGA网络测量引擎技术实现[J]. 电子科技, 2021, 34(2): 27-32.
[6]	葛靖,刘子龙. 基于CNN和LSTM的睡眠呼吸暂停检测算法[J]. 电子科技, 2021, 34(2): 21-26.
[7]	朱健安,魏云冰,朱鹏杰,蒋成成,朱成名. 基于优化灰色傅里叶残差修正的中长期负荷预测[J]. 电子科技, 2021, 34(12): 49-55.
[8]	苏烨,李筠,杨海马,刘瑾,江声华. 基于Faster R-CNN的钢轨表面缺陷识别研究[J]. 电子科技, 2020, 33(9): 63-68.
[9]	谢智烜,姚红兵,范宁,陈枫. 面向多目标透镜的连通域标记检测算法[J]. 电子科技, 2020, 33(4): 50-54.
[10]	周文凯,韩芳,孔维健. 基于Faster-RCNN的极验点选式验证码识别[J]. 电子科技, 2019, 32(9): 42-46.
[11]	孙腾飞,蒋红海. 基于模式分类的喷嘴料液雾滴速度测量研究[J]. 电子科技, 2019, 32(8): 33-37.
[12]	毕灶荣，童东兵，陈巧玉. 基于快速MFCC计算的说话人识别系统的设计[J]. , 2018, 31(4): 25-.
[13]	章佳佳，杨振超，周律. 基于Matlab图像处理的果核分拣系统[J]. , 2017, 30(9): 50-.
[14]	杨振超，章佳佳，周律，吴飞. 基于LabVIEW的马铃薯分拣技术[J]. , 2017, 30(9): 72-.
[15]	曹伟东，张中炜. 机器视觉下升降机内人数检测算法[J]. , 2016, 29(9): 22-.