Degraded Calligraphic Document Binarization Based on Multidimensional Side Window Clustering Segmentation
CSTR:
Author:
  • Article
  • | |
  • Metrics
  • |
  • Reference [31]
  • |
  • Related [4]
  • | | |
  • Comments
    Abstract:

    The distribution of grayscale values in calligraphic character document images exhibits significant variations under poor lighting conditions, resulting in lower image contrast in low-light areas and degradation of morphological texture features of the strokes. Traditional methods typically focus on local information such as mean, squared deviation, and entropy, while giving less consideration to morphological texture, rendering them insensitive to the features of low-contrast areas. To address these issues, this study proposes a binarization method called clustering segmentation-based side-window filter (CS-SWF) specifically designed for degraded calligraphic documents. Firstly, this method utilizes multi-dimensional SWF to describe pixel chunks with similar morphological features. Then, with multiple correction rules, it utilizes downsampling to extract low-latitude information and correct feature regions. Finally, the clustered blocks in the feature map are classified to obtain the binarization results. To evaluate the performance of the proposed method, it is compared with existing methods using F-measure (FM), peak signal-to-noise ratio (PSNR), and distance reciprocal distortion (DRD) as indicators. Experimental results on a self-constructed dataset consisting of 100 handwritten degraded document images demonstrate that the proposed binarization method exhibits greater stability in low-contrast dark regions and outperforms the comparison algorithm in terms of accuracy and robustness.

    Reference
    [1] 雷实. 书法教育主要是写好汉字. 人民教育, 2012(10): 35–37.
    [2] 冀晓萍. 中办国办印发《关于实施中华优秀传统文化传承发展工程的意见》要求 将中华优秀传统文化传承贯穿国民教育始终. 人民教育, 2017(3-4): 27.
    [3] Otsu N. A threshold selection method from gray-level histogram. IEEE Transactions on Systems, Man, and Cybernetics, 1979, 9(1): 62–66.
    [4] 魏兴凯, 蒋峥, 傅呈勋, 等. 基于光照影响因子的动态Niblack算法研究及应用. 计算机工程与设计, 2022, 43(4): 1066–1073.
    [5] Kaur A, Rani U, Josan GS. Modified Sauvola binarization for degraded document images. Engineering Applications of Artificial Intelligence, 2020, 92: 103672.
    [6] 李艺杰, 邹坤霖, 孙炜, 等. 基于Sauvola算法和神经网络的图像自适应二值化方法. 测控技术, 2020, 39(08): 62–69, 75.
    [7] 乔志凯, 陈世才, 蒙子昕, 等. 复杂光照下的船舶水尺图像二值化新方法. 中国航海, 2021, 44(4): 80–85, 93.
    [8] Pai YT, Chang YF, Ruan SJ. Adaptive thresholding algorithm: Efficient computation technique based on intelligent block detection for degraded document images. Pattern Recognition, 2010, 43(9): 3177–3187.
    [9] Singh BM, Sharma R, Ghosh D, et al. Adaptive binarization of severely degraded and non-uniformly illuminated documents. International Journal on Document Analysis and Recognition (IJDAR), 2014, 17(4): 393–412.
    [10] Bataineh B, Abdullah SNHS, Omar K. Adaptive binarization method for degraded document images based on surface contrast variation. Pattern Analysis and Applications, 2017, 20(3): 639–652.
    [11] Calderon F, Garnica-Carrillo A, Reyes-Zu?iga C. Binarization of images with variable lighting using adaptive windows. Signal, Image and Video Processing, 2022, 16(7): 1905–1912.
    [12] 刘朋远, 田瑞, 周媛奉, 等. 基于自适应混合阈值的智能电表图像二值化. 计算机应用与软件, 2023, 40(1): 210–215.
    [13] Abdullah SNHS, Ismail SM, Hasan MK, et al. Novel adaptive binarization method for degraded document images. Computers, Materials & Continua, 2021, 67(3): 3815–3832.
    [14] Lin SCF, Wong CY, Rahman MA, et al. Image enhancement using the averaging histogram equalization (AVHEQ) approach for contrast improvement and brightness preservation. Computers & Electrical Engineering, 2015, 46: 356–370.
    [15] 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. 计算机科学, 2022, 49(11): 163–169.
    [16] 冯炎. 基于背景估计和对比度补偿的退化古籍图像二值化算法. 科学技术与工程, 2015, 15(34): 105–109.
    [17] 李志杰, 王力, 张习恒. 改进樽海鞘群优化K-means算法的图像分割. 包装工程, 2022, 43(9): 207–216.
    [18] Jacobs BA, Celik T. Unsupervised document image binarization using a system of nonlinear partial differential equations. Applied Mathematics and Computation, 2022, 418: 126806.
    [19] Du ZJ, He CJ. Nonlinear diffusion system for simultaneous restoration and binarization of degraded document images. Computers & Mathematics with Applications, 2024, 153: 237–248.
    [20] Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston: IEEE, 2015. 3431–3440.
    [21] Zhang ZA, Wu CD, Coleman S, et al. DENSE-INception U-net for medical image segmentation. Computer Methods and Programs in Biomedicine, 2020, 192: 105395.
    [22] 王红霞, 武甲礼, 陈德山. 分离复杂背景下的文档图像二值化方法. 中国图象图形学报, 2023, 28(7): 2011–2025.
    [23] Ramya BN, Singh S. A novel approach to implement binarized neural network to enhance accuracy using machine learning techniques. SN Computer Science, 2023, 4(2): 174.
    [24] Yin H, Gong YH, Qiu GP. Side window filtering. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019. 8750–8758.
    [25] Ren H, Wang YJ, Dong X. Binarization algorithm based on side window multidimensional convolution classification. Sensors, 2022, 22(15): 5640.
    [26] Lu KL, Liu EH, Zhao RJ, et al. Star sensor denoising algorithm based on edge protection. Sensors, 2021, 21(16): 5255.
    [27] Castleman KR. Digital Image Processing. Englewood: Prentice Hall, 2011. 74–120.
    [28] Mansour Y, Heckel R. Zero-shot Noise2Noise: Efficient image denoising without any data. Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver: IEEE, 2023. 14018–14027.
    [29] 陈艳红, 崔晓光, 张吉祥. 硬笔书法田字格切片图像提取方法、系统、设备: 中国, 113901936A. 2022-01-07.
    [30] 徐占洋, 张家瑞, 秦飞扬, 等. 一种汉字字体二值化切片图像的提取方法及系统: 中国, 115909369A. 2023-04-04.
    [31] Pratikakis I, Gatos B, Ntirogiannis K. ICDAR 2013 document image binarization contest (DIBCO 2013). Proceedings of the 12th International Conference on Document Analysis and Recognition. Washington: IEEE, 2013. 1471–1476.
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation

徐占洋,张家瑞,侍虹言,秦飞扬,林巍.基于多维侧窗聚类分块的退化书法文档二值化.计算机系统应用,2024,33(6):223-231

Copy
Share
Article Metrics
  • Abstract:297
  • PDF: 746
  • HTML: 641
  • Cited by: 0
History
  • Received:December 20,2023
  • Revised:January 17,2024
  • Online: April 19,2024
Article QR Code
You are the first990420Visitors
Copyright: Institute of Software, Chinese Academy of Sciences Beijing ICP No. 05046678-3
Address:4# South Fourth Street, Zhongguancun,Haidian, Beijing,Postal Code:100190
Phone:010-62661041 Fax: Email:csa (a) iscas.ac.cn
Technical Support:Beijing Qinyun Technology Development Co., Ltd.

Beijing Public Network Security No. 11040202500063