背景估计和局部自适应集成的手写图像二值化

doi:10.11896/jsjkx.210900225

计算机科学 ›› 2022, Vol. 49 ›› Issue (11): 163-169.doi: 10.11896/jsjkx.210900225

• 计算机图形学&多媒体 • 上一篇下一篇

背景估计和局部自适应集成的手写图像二值化

何皇兴¹, 陈爱国¹, 王蛟龙²

1 江南大学人工智能与计算机学院江苏无锡 214122
2 江南大学物联网工程学院江苏无锡 214122

收稿日期:2021-09-27 修回日期:2022-03-15 出版日期:2022-11-15 发布日期:2022-11-03
通讯作者: 陈爱国(agchen@jiangnan.edu.cn)
作者简介:(hhx97@qq.com)
基金资助:
国家自然科学基金(61702225)

Handwritten Image Binarization Based on Background Estimation and Local Adaptive Integration

HE Huang-xing¹, CHEN Ai-guo¹, WANG Jiao-long²

1 School of Artificial Intelligence and Computer Science,Jiangnan University,Wuxi,Jiangsu 214122,China
2 School of Internet of Things Engineering,Jiangnan University,Wuxi,Jiangsu 214122,China

Received:2021-09-27 Revised:2022-03-15 Online:2022-11-15 Published:2022-11-03
About author:HE Huang-xing,born in 1997,master.His main research interests include ima-ge processing and machine learning.
CHEN Ai-guo,born in 1975,associate professor.His main research interests include machine learning,artificial intelligence and pattern recognition.
Supported by:
National Natural Science Foundation of China(61702225).

摘要/Abstract

摘要： 手写文档图像中存在光照不均、笔墨浸染、纸张退化、阴影等复杂情况,针对文档图像在复杂背景下二值化后OCR效果不理想的问题,提出了一种对改进的背景估计和局部自适应集成的二值化方法。首先利用局部自适应方法得到具有高召回率的二值化图像,然后对背景估计的方法进行改进得到具有高精确率的二值化图像,最后基于连通域的方法将两种类型的图像集成得到结果。使用4种评价指标在DIBCO2013和DIBCO2016手写数据集上进行了对比实验,结果表明该方法整体性能优于Otsu,Wolf,Niblack,Sauvola,Singh和Howe等经典算法。

关键词: 图像处理, 手写文档图像, 二值化, 背景估计, 二值化集成

Abstract: In handwritten document images,there are often uneven lighting,ink stains,paper degradation,shadows and other complex conditions.In order to solve the problem that OCR effect of document image is not ideal after binarization in complex background,a binarization method of improved background estimation and local adaptive integration is proposed.In this method,the local adaptive binarization method is first used to obtain the binarization image with high recall rate,then the improved background estimation method is used to obtain the binarization image with high accuracy rate,and finally the two types of binarization images are integrated based on the connected domain method to obtain the final binarization image.Experimental results on DIBCO2013 and DIBCO2016 handwritten data sets show that the proposed method has better overall performance than Otsu,Wolf,Niblack,Sauvola,Singh and Howe.

Key words: Image processing, Handwritten document image, Binarization, Background estimate, Binary integration

中图分类号:

TP391

何皇兴, 陈爱国, 王蛟龙. 背景估计和局部自适应集成的手写图像二值化[J]. 计算机科学, 2022, 49(11): 163-169. https://doi.org/10.11896/jsjkx.210900225

HE Huang-xing, CHEN Ai-guo, WANG Jiao-long. Handwritten Image Binarization Based on Background Estimation and Local Adaptive Integration[J]. Computer Science, 2022, 49(11): 163-169. https://doi.org/10.11896/jsjkx.210900225

参考文献

[1]SULAIMAN A,OMAR K,NASRUDIN M F.Degraded historical document binarization:A review on issues,challenges,techniques,and future directions[J].Journal of Imaging,2019,5(4):48.
[2]OTSU N.A Threshold Selection Method from Gray-Level Histograms[J].IEEE Transactions on Systems Man & Cyberne-tics,1979,9(1):62-66.
[3]NIBLACK W.An Introduction to Digital Image Processing[M].Englewood Cliffs,NJ:Prentice-Hall,Inc,1986:115-116.
[4]SAUVOLA J,PIETIKÄINEN M.Adaptive document image binarization[J].Pattern Recognition,2000,33(2):225-236.
[5]HADJADJ Z,MEZIANE A,CHERFA Y,et al.ISauvola:Im-proved Sauvola’s algorithm for document image binarization[C]//International Conference on Image Analysis and Recognition.Póvoa de Varzim,Portugal:Springer,2016:737-745.
[6]ZHU D L,YANG D G,HU R,et al.Adaptive Multi-levelThreshold Binaryzation Method for Optical Character Recognition in Mobile Environment[J].Computer Science,2019,46(8):315-320.
[7]HOWE N R.Document binarization with automatic parameter tuning[J].International Journal on Document Analysis and Reco-gnition,2013,16(3):247-258.
[8]BHOWMIK S,SARKAR R,DAS B,et al.GiB:a Game theory In-spired Binarization technique for degraded document images[J].IEEE Transactions on Image Processing,2018,28(3):1443-1455.
[9]BARDOZZO F,DE LA OSA B,HORANSKÁ L′,et al.Sugeno integral generalization applied to improve adaptive image binarization[J].Information Fusion,2021,68:37-45.
[10]RANI U,KAUR A,JOSAN G.A New Contrast Based Degraded Document Image Binarization[J].Cognitive Computing in Human Cognition,2020,17(1):83-90.
[11]SUN G D,XU Y,XU L,et al.Binarization method of instrument image with uneven illumination and ghosting[J].Journal of Applied Optics,2020,41(1):74-78.
[12]WESTPHAL F,LAVESSON N,GRAHN H.Document image binarization using recurrent neural networks[C]//2018 13th IAPR International Workshop on Document Analysis Systems(DAS).Vienna,Austria:IEEE,2018:263-268.
[13]KANG S,IWANA B K,UCHIDA S.Complex image processing with less data—Document image binarization by integrating multiple pre-trained U-Net modules[J].Pattern Recognition,2021,109:107577.
[14]CASTELLANOS F J,GALLEGO A J,CALVO-ZARAGOZA J.Unsupervised neural domain adaptation for document image binarization[J].Pattern Recognition,2021,119(2):108099.
[15]TENSMEYER C,MARTINEZ T.Historical document image binarization:A review[J].SN Computer Science,2020,1(3):1-26.
[16]MUSTAFA W A,KADER M M M A.Binarization of document images:A comprehensive review[J].Journal of Physics:Confe-rence Series,2018,1019(1):012023.
[17]XU H Y,MA L L,WU J,et al.Document image binarization based on background estimation and edge detection[J].Compu-ter Applications and Software,2014,31(8):196-200.
[18]HEDJAM R,NAFCHI H Z,KALACSKA M,et al.Influence of color-to-gray conversion on the performance of document image binarization:Toward a novel optimization problem[J].IEEE Transactions on Image Processing,2015,24(11):3637-3651.
[19]WOLD S,ESBENSEN K,GELADI P.Principal component ana-lysis[J].Chemometrics and Intelligent Laboratory Systems,1987,2(1/2/3):37-52.
[20]ITU-R R,BT.Studio encoding parameters of digital television for standard 4:3 and wide-screen 16:9 aspect ratios[S].Geneva,Switzerland:ITU,2011.
[21]PRATIKAKIS I,GATOS B,NTIROGIANNIS K.ICDAR 2013 Document Image Binarization Contest(DIBCO 2013)[C]//2013 12th International Conference on Document Analysis and Recognition.Washington,DC,USA:IEEE,2013:1471-1476.
[22]PRATIKAKIS I,ZAGORIS K,BARLAS G,et al.ICFHR2016 Handwritten Document Image Binarization Contest(H-DIBCO 2016)[C]//2016 15th International Conference on Frontiers in Handwriting Recognition(ICFHR).Shenzhen,China:IEEE,2016:619-623.
[23]WOLF C,JOLION J M.Extraction and Recognition of Artificial Text in Multimedia Documents[J].Formal Pattern Analysis & Applications,2004,6(4):309-326.
[24]SINGH O I,JAMES O,SINAM T,et al.Local Contrast andMean based Thresholding Technique in Image Binarization[J].International Journal of Computer Applications,2013,51(6):4-10.

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]	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
[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]	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
[5]	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
[6]	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
[7]	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
[8]	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
[9]	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
[10]	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
[11]	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
[12]	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
[13]	苗益, 赵增顺, 杨雨露, 徐宁, 杨皓然, 孙骞. 图像描述技术综述 Survey of Image Captioning Methods 计算机科学, 2020, 47(12): 149-160. https://doi.org/10.11896/jsjkx.200500039
[14]	凌晨, 张鑫彤, 马雷. 基于Mask R-CNN算法的遥感图像处理技术及其应用 Remote Sensing Image Processing Technology and Its Application Based on Mask R-CNN Algorithms 计算机科学, 2020, 47(10): 151-160. https://doi.org/10.11896/jsjkx.190900119
[15]	郭兰英, 韩睿之, 程鑫. 基于可变形卷积神经网络的数字仪表识别方法 Digital Instrument Identification Method Based on Deformable Convolutional Neural Network 计算机科学, 2020, 47(10): 187-193. https://doi.org/10.11896/jsjkx.191000035

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

背景估计和局部自适应集成的手写图像二值化

Handwritten Image Binarization Based on Background Estimation and Local Adaptive Integration

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