适于移动终端字符识别环境的自适应多阈值二值化方法

doi:10.11896/j.issn.1002-137X.2019.08.052

计算机科学 ›› 2019, Vol. 46 ›› Issue (8): 315-320.doi: 10.11896/j.issn.1002-137X.2019.08.052

适于移动终端字符识别环境的自适应多阈值二值化方法

朱德利¹, 杨德刚¹, 胡蓉², 万辉¹

(重庆师范大学计算机与信息科学学院重庆401331)¹
(西南大学计算机与信息科学学院重庆400715)²

收稿日期:2018-07-04 出版日期:2019-08-15 发布日期:2019-08-15
通讯作者: 杨德刚(1976-),男,博士,教授,CCF会员,主要研究方向为神经网络、图像处理,E-mail:ydg42@163.com
作者简介:朱德利(1979-),男,副教授,主要研究方向为机器学习与机器视觉应用,E-mail:463453339@qq.com;胡蓉(1980-),女,博士,讲师,主要研究方向为人机交互、移动视觉搜索;万辉(1980-),男,硕士,讲师,主要研究方向为机器学习、图像处理
基金资助:
重庆市教委科学技术研究项目(KJQN201800536,KJQN201800521,KJ1600322),重庆市科委基础研究与前沿探索计划(cstc2018jcyjAX0470)

Adaptive Multi-level Threshold Binaryzation Method for Optical Character Recognition in Mobile Environment

ZHU De-li¹, YANG De-gang¹, HU Rong², WAN Hui¹

(College of Computer and Information Science,Chongqing Normal University,Chongqing 401331,China)¹
(College of Computer and Information Science,Southwest University,Chongqing 400715,China)²

Received:2018-07-04 Online:2019-08-15 Published:2019-08-15

摘要/Abstract

摘要： 为了解决移动终端字符识别应用中光照不均匀、环境不可控而导致的图像二值化效果不佳的问题,提出一种基于积分图快速计算的多阈值自适应二值化方法。该方法首先以待求点为中心设置一个特定尺寸的滑窗,计算该滑窗内所有点的均值,再根据高斯函数加权计算当前滑窗的两个前置滑窗的均值。设置均值松弛因子来衡量当前点的光照情况。像素点的松弛阈值依据该点的松弛因子和光照情况的评价综合计算获得。以Lenovo ZUK Z2 Pro作为实验设备,在Android操作系统中编写程序,进行文字识别精度的测试。所提算法对前景划分的平均召回率为95.5%,平均准确率为91%。调用Tesseract 4.0的原生OCR识别引擎进行验证,在不规则阴影、多层次光照、线性光线变化等环境下,算法的文字识别准确率分别为96.8%,98.2%和93.2%,高于其他预处理算法。所提算法具有较强的鲁棒性和自适应能力,能满足移动终端字符识别应用的图像预处理要求。

关键词: 积分图像, 图像处理, 移动终端, 字符识别, 自适应二值化

Abstract: In order to solve the problem of poor binaryzation quality caused by uneven illumination and uncontrollable environment in OCR applications of mobile terminals,this paper proposed an adaptive multi-level threshold binaryzation method based on integral graph.First,a specific sliding window is set by focusing on the points to be calculated.The normal threshold is the mean value of the sliding window where the current point is located.The two front sliding windows are weighted according to the Gauss function,and then the relaxation factor is obtained according to the weights.The relaxation threshold of pixels are obtained based on the evaluation of the relaxation factor and illumination condition.Experiments were carried out in typical mobile environments such as irregular shadows,multi-level illumination and linear light changes.Lenovo ZUK Z2 Pro is used as the test equipment.The average recall of the algorithm is 95.5% and the average accuracy is 91%.The recognition accuracy of this algorithm is 96.8%,98.2% and 93.2% respectively in the environment of irregular shadow,multilevel illumination and linear light change.The result shows that the proposed algorithm has strong robustness and adaptability,and can meet the requirement of image preprocessing in the OCR application of mobile terminal

Key words: Adaptive binaryzation, Image processing, Integral graph, Mobile terminal, Optical character recognition

中图分类号:

TP391

朱德利, 杨德刚, 胡蓉, 万辉. 适于移动终端字符识别环境的自适应多阈值二值化方法[J]. 计算机科学, 2019, 46(8): 315-320. https://doi.org/10.11896/j.issn.1002-137X.2019.08.052

ZHU De-li, YANG De-gang, HU Rong, WAN Hui. Adaptive Multi-level Threshold Binaryzation Method for Optical Character Recognition in Mobile Environment[J]. Computer Science, 2019, 46(8): 315-320. https://doi.org/10.11896/j.issn.1002-137X.2019.08.052

参考文献

[1]ISMAIL S M,ABDULLAH S N H S,FAUZI F.Statistical bina- rization techniques for document image analysis[J].Journal of Computer Science,2018,14(1):23-36.
[2]BATAINEH B,ABDULLAH S N,OMAR K.Adaptive binarization method for degraded document images based on surface contrast variation[J].Pattern Analysis & Applications,2015,20:1-14.
[3]DUAN S L,ZHU F,YAN X.Research of Multi window binaryzation algorithm [J].Computer Engineering and Application,2017,53(17):212-217.(in Chinese) 段锁林,朱方,严翔.多窗口图像二值化算法研究[J].计算机工程与应用,2017,53(17):212-217.
[4]LI Z,LI G Y.Research on the binaryzation of power meter in complex lighting environment [J].microcomputers and applications,2017,36(15):45-48.(in Chinese) 李真,李功燕.复杂光照环境下电力仪表的二值化研究[J].微型机与应用,2017,36(15):45-48.
[5]XIONF W,WANG X R,FENG C.Document image binaryzation based on background estimation and energy minimization [J].Computer Application 2018,38(3):1-8.(in Chinese) 熊炜,王鑫睿,冯川.基于背景估计和能量最小化的文档图像二值化[J].计算机应用2018,38(3):1-8.
[6]WU R,HUANG J H,TANG J L.Binaryzation method of text image based on gray histogram and spectral clustering [J].Journal of Electronic and Information,2009,31(10):2460-2464.(in Chinese) 吴锐,黄剑华,唐降龙.基于灰度直方图和谱聚类的文本图像二值化方法[J].电子与信息学报,2009,31(10):2460-2464.
[7]PAN M S,RONG Q S.Image fusion binaryzation method based on SOFM neural network [J].Optical Precision Engineering,2007(3):401-406.(in Chinese) 潘梅森,荣秋生.基于SOFM神经网络的图像融合二值化方法[J].光学精密工程,2007(3):401-406.
[8]VO G D,PARI C.Robust Regression For image binarization under heavy noise and nonuniform background[J].Pattern Recognition,2018,81(2):224-239.
[9]SEZGIN M,SANKUR B.Survey over image thresholding techniques and quantitative performance evaluation[J].Journal of Electronic Imaging,2004,13(1):146-168.
[10]OTSU N.A Threshold Selection Method from Gray-Level Histograms[J].IEEE Transactions on Systems,Man,and Cybernetics,1979,9(1):62-66.
[11]ZHANG Y,WU L.Fast Document Image Binarization based on an improved adaptive Otsu’s method and destination word accumulation[J].Journal of Computational Information Systems,2011,7(6):1886-1892.
[12]MICHALAK H,OKARMA K.Fast Adaptive Image Binariza- tion Using the Region Based Approach[C]∥Computer Science On-line Conference.Cham:Springer,2018:79-90.
[13]NASRI M,HOSSEIN-NEJAD Z,HOSSEINI-ZAHMATKESH P.Document Image Binarization Based on Combination of Globaland Local Thresholding Methods[J].International Journal of Image & Graphics,2018,18(2):179-186.
[14]NTIROGIANNIS K,GATOS B.Combined approach for the binarization of handwritten document images[J].Pattern Recognition Letters,2014,35:3-15.
[15]HOWE N R.ERRATUM.Document binarization with automatic parameter tuning[J].International Journal on Document Analysis & Recognition,2013,16(3):247-258.
[16]SU B,LU S,TAN C L.Robust document image binarization technique for degraded document images[J].IEEE Transactions on Image Processing,2013,22(4):1408-1417.
[17]LU D,HUANG X,SUI L X.Binarization of degraded document images based on contrast enhancement[J].International Journal on Document Analysis & Recognition,2018,21(1／2):123-135.
[18]BRADLEY D,ROTH G.Adaptive Thresholding using the integral graph[J].Journal of Graphics Gpu & Game Tools,2007,12(2):13-21.
[19]GATOS B,PRATIKAKIS I,PERANTONIS S.Adaptive de- graded document image binarization[J].Pattern Recognition,2006,39(3):317-327.

相关文章 15

[1]	郭拯危, 付泽文, 李宁, 白澜. 高分辨率斜视聚束SAR回波仿真加速算法研究 Study on Acceleration Algorithm for Raw Data Simulation of High Resolution Squint Spotlight SAR 计算机科学, 2022, 49(8): 178-183. https://doi.org/10.11896/jsjkx.210600066
[2]	于滨, 李学华, 潘春雨, 李娜. 基于深度强化学习的边云协同资源分配算法 Edge-Cloud Collaborative Resource Allocation Algorithm Based on Deep Reinforcement Learning 计算机科学, 2022, 49(7): 248-253. https://doi.org/10.11896/jsjkx.210400219
[3]	来腾飞, 周海洋, 余飞鸿. 视频流的实时景深延拓算法 Real-time Extend Depth of Field Algorithm for Video Processing 计算机科学, 2022, 49(6A): 314-318. https://doi.org/10.11896/jsjkx.201100187
[4]	姚烨, 朱怡安, 钱亮, 贾耀, 张黎翔, 刘瑞亮. 一种基于异质模型融合的 Android 终端恶意软件检测方法 Android Malware Detection Method Based on Heterogeneous Model Fusion 计算机科学, 2022, 49(6A): 508-515. https://doi.org/10.11896/jsjkx.210700103
[5]	刘伟业, 鲁慧民, 李玉鹏, 马宁. 指静脉识别技术研究综述 Survey on Finger Vein Recognition Research 计算机科学, 2022, 49(6A): 1-11. https://doi.org/10.11896/jsjkx.210400056
[6]	詹瑞, 雷印杰, 陈训敏, 叶书函. 基于多重差异特征网络的街景变化检测 Street Scene Change Detection Based on Multiple Difference Features Network 计算机科学, 2021, 48(2): 142-147. https://doi.org/10.11896/jsjkx.200500158
[7]	张育龙, 王强, 陈明康, 孙静涛. 图像去雨算法在云物联网应用中的研究综述 Survey of Intelligent Rain Removal Algorithms for Cloud-IoT Systems 计算机科学, 2021, 48(12): 231-242. https://doi.org/10.11896/jsjkx.201000055
[8]	寇喜超, 张鸿锐, 冯杰, 郑雅羽. 基于多级文本检测的复杂文档图像扭曲矫正算法 Distortion Correction Algorithm for Complex Document Image Based on Multi-level TextDetection 计算机科学, 2021, 48(12): 249-255. https://doi.org/10.11896/jsjkx.200700072
[9]	姚楠, 张征. 基于三维图像的疤痕面积计算 Scar Area Calculation Based on 3D Image 计算机科学, 2021, 48(11A): 308-313. https://doi.org/10.11896/jsjkx.201100044
[10]	冯一凡, 赵雪青, 师昕, 杨坤. 基于光照叠加的颜色恒常计算方法 Light Superposition-based Color Constancy Computational Method 计算机科学, 2021, 48(11A): 386-390. https://doi.org/10.11896/jsjkx.210200053
[11]	宋一言, 唐东林, 吴续龙, 周立, 秦北轩. 改进穿线法与HOG+SVM结合的数码管图像读数研究 Study on Digital Tube Image Reading Combining Improved Threading Method with HOG+SVM Method 计算机科学, 2021, 48(11A): 396-399. https://doi.org/10.11896/jsjkx.210100123
[12]	谢海平, 李高源, 杨海涛, 赵洪利. 超分辨率重构遥感图像分类研究 Classification Research of Remote Sensing Image Based on Super Resolution Reconstruction 计算机科学, 2021, 48(11A): 424-428. https://doi.org/10.11896/jsjkx.210300132
[13]	蔡玉鑫, 汤志伟, 赵博, 杨明, 吴禹非. 基于嵌入式多核DSP的加速软件系统 Accelerated Software System Based on Embedded Multicore DSP 计算机科学, 2020, 47(6A): 622-625. https://doi.org/10.11896/JsJkx.190400079
[14]	马虹. 基于5G的视觉辅助BDS移动机器人融合定位算法 Fusion Localization Algorithm of Visual Aided BDS Mobile Robot Based on 5G 计算机科学, 2020, 47(6A): 631-633. https://doi.org/10.11896/JsJkx.190400156
[15]	宋娅菲, 谌雨章, 沈君凤, 曾张帆. 基于改进残差网络的水下图像重建方法 Underwater Image Reconstruction Based on Improved Residual Network 计算机科学, 2020, 47(6A): 500-504. https://doi.org/10.11896/JsJkx.200100084

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

适于移动终端字符识别环境的自适应多阈值二值化方法

Adaptive Multi-level Threshold Binaryzation Method for Optical Character Recognition in Mobile Environment

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0