基于对比度补偿的古籍图像二值化算法研究

冯炎

Chinese

您当前的位置：

首页 >

文章列表页 >

基于对比度补偿的古籍图像二值化算法研究

更新时间：2026-09-04

- 基于对比度补偿的古籍图像二值化算法研究
- Study of Ancient Books Image Binarization Based on Contrast Compensation
- 微电子学与计算机 2016年33卷第4期页码：50-54
- 作者机构：
  
  西藏大学现代教育技术中心,西藏,拉萨,850000
- 作者简介：
- 基金信息：
  
  西藏自治区自然科学基金项目 2015ZR-14-4国家自然科学基金项目 61262086
- DOI：
  中图分类号：
- 纸质出版：2016
- 稿件说明：
移动端阅览
冯炎. 基于对比度补偿的古籍图像二值化算法研究[J]. 微电子学与计算机, 2016, 33(4): 50-54, 59.

FENG Yan. Study of Ancient Books Image Binarization Based on Contrast Compensation[J]. 2016, 33(4): 50-54.
冯炎. 基于对比度补偿的古籍图像二值化算法研究[J]. 微电子学与计算机, 2016, 33(4): 50-54, 59. DOI：

FENG Yan. Study of Ancient Books Image Binarization Based on Contrast Compensation[J]. 2016, 33(4): 50-54. DOI：

摘要

环境因素及不当保存会使古籍退化严重

对此设计一种二值化算法来解决具有均匀字符大小的退化古籍图像的低对比度问题

从而更好地揭示古籍所记载内容.算法首先利用Canny算子提取图像文本的边缘信息并估计平均笔划宽度

根据笔划宽度来估计古籍图像背景

然后用背景信息来对古籍进行对比度补偿

从而提高古籍图像对比度

最后利用Howe的算法对补偿后的古籍进行二值化处理

后处理算法进一步提高了图像质量

得到最终的二值图像.实验结果证实了该算法的有效性.该算法优于在ICFHR2014国际会议上获得第一名的Mesquita的算法.

Abstract

Many environmental factors and improper handling cause ancient document to suffer a high degree of degradation. In order to solve the problems that arise in the binarization of old books images having a uniform character-size characterized by variations in image contrast

we try to design a binarization algorithm in order to better reveal the contents recorded in ancient books. Fist we will detect text stroke edges by Cannys method and calculate stroke widths

the ancient books image background is estimated through the calculated stroke width. Next step

we compensate the ancient document contrast by using the estimated background. Then

the document text is segmented by Howes binarization algorithm. Further improvements are achieved by a postprocessing step. Finally the performance of the algorithm is analyzed and evaluated

the proposed method is better than Mesquita method which achieved the best performance in the ICFHR2014.

关键词

Keywords

references

Pratikakis I, Gatos B, Ntirogiannis K. ICDAR 2011 documentimage binarization contest (DIBCO 2011)[C]//Proc. 11th ICDAR. Beijing: IAPR, 2011: 1506-1510.

Ziaie Nafchi H, Farrahi Moghaddam R, Cheriet M. Phase-based binarization of ancient document images: Model and applications[J]. Image Processing, IEEE Transactions on, 2014, 23(7): 2916-2930. DOI: 2916

Birattari M, Yuan Z, Balaprakash P, et al. F-Race anditerated F-Race: An overview[M]//Experimental Methods for the Analysis of Optimization Algorithms. Berling: Springer, 2010: 311-336.

Howe N. Document binarization with automatic parameter tuning[J]. Int. J. Document Anal. Recognit., 2013, 16(3): 247-258. DOI: 247

Mesquita R G, Mello C A B, Almeida L H E V. A newthresholding algorithm for document images based on the perceptionof objects by distance[J]. Integrated Computer-Aided Engineering, 2014, 21 (2): 133-146. DOI: 133

Lu H, Kot A C, Shi Y Q. Distance-reciprocaldistortion measure for binary document Images[J]. IEEE Signal Processing Letters, 2004, 11, (2): 228-231. DOI: 228

Rafael C Gonzalez, Richard E Woods. 数字图像处理[M]. 北京: 电子工业出版社, 2010.

Mesquita R G, Silva R A M A, Mello C A B, et al. Parameter tuning for document image binarization using a racing algorithm[J]. Expert Systems with Applications, 2015, 42(5): 2593-2603. DOI: 2593

Ntirogiannis K, Gatos B, Pratikakis I. A performance evaluation methodology for historical document image binarization[J]. IEEE Trans. Image Process, 2013, 22(2, ): 595-609. DOI: 595

Ntirogiannis K, Gatos B, Pratikakis I. ICFHR2014 competition on handwritten document image binarization (H-DIBCO 2014)[C]//Proc. 14th ICFHR. The Island of Crete: IAPR, 2014: 809-813.

Pratikakis I, Gatos B, Ntirogiannis K. ICDAR 2013 document image binarization contest (DIBCO 2013)[C]//Proc. 12th ICDAR. Washington DC: LAPR, 2013: 1471-1476.

Howe N. Document image binarization using Markov field model[C]//Proc. 11th ICDAR. Beijing: IAPR, 2011: 6-10.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

AlN/GaN混合缓冲层双异质结p-GaN HEMT直流特性仿真

基于监控指标关联性的微服务异常检测

低功耗设计的双链电源关断策略的实现与验证

一种用于极低压boost系统的高效率电荷泵

基于多尺度融合与小目标增强的航拍车辆检测算法