Global and Local Features Based Classification for Bleed-Through Removal

被引：3

作者：

Hu X. ^{[1
]}

Lin H. ^{[1
]}

Li S. ^{[1
]}

Sun B. ^{[1
]}

机构：

[1] College of Electrical and Information Engineering, Hunan University, Changsha

来源：

Sensing and Imaging | 2016年 / 17卷 / 01期

关键词：

Bleed-through; Classification; Extreme learning machine; Features extraction; Scanned document image;

D O I：

10.1007/s11220-016-0134-7

中图分类号：

学科分类号：

摘要：

The text on one side of historical documents often seeps through and appears on the other side, so the bleed-through is a common problem in historical document images. It makes the document images hard to read and the text difficult to recognize. To improve the image quality and readability, the bleed-through has to be removed. This paper proposes a global and local features extraction based bleed-through removal method. The Gaussian mixture model is used to get the global features of the images. Local features are extracted by the patch around each pixel. Then, the extreme learning machine classifier is utilized to classify the scanned images into the foreground text and the bleed-through component. Experimental results on real document image datasets show that the proposed method outperforms the state-of-the-art bleed-through removal methods and preserves the text strokes well. © 2016, Springer Science+Business Media New York.

引用

共 27 条

[1]

Dubois E., Pathak A., Reduction of bleed-through in scanned manuscript documents, In Proceedings of image processing, image quality, image capture systems conference, pp. 177-180, (2001)

[2]

Tonazzini A., Bedini L., Salerno E., Independent component analysis for document restoration, Document Analysis and Recognition, 7, 1, pp. 17-27, (2004)

[3]

Tonazzini A., Bedini L., Salerno E., A Markov model for blind image separation by a mean-field em algorithm, IEEE Transactions on Image Processing, 15, 2, pp. 473-482, (2006)

[4]

Rowley-Brooke R., Pitie F., Kokaram A., A non-parametric framework for document bleed-through removal, In Proceedings of IEEE conference on computer vision and pattern recognition, 9, pp. 2954-2960, (2013)

[5]

Wolf C., Document ink bleed-through removal with two hidden Markov random fields and a single observation field, IEEE Transactions on Pattern Analysis and Machine Intelligence, 32, 3, pp. 431-447, (2009)

[6]

Wolf C., Doermann D., Binarization of low quality text using a Markov random field model, In Proceedings of international conference on pattern recognition, 3, pp. 160-163, (2002)

[7]

Liu Y., Srihari S.N., Document image binarization based on texture features, IEEE Transactions on Pattern Analysis and Machine Intelligence, 19, 5, pp. 540-544, (1997)

[8]

Solihin Y., Leedham C.G., Integral ratio: A new class of global thresholding techniques for handwriting images, IEEE Transactions on Pattern Analysis and Machine Intelligence, 21, 8, pp. 761-768, (1999)

[9]

Lelore T., Bouchara F., Super-resolved binarization of text based on the FAIR algorithm, In Proceedings of international conference on document analysis and recognition, 18, 21, pp. 839-843, (2011)

[10]

Su B., Lu S., Tan C.L., Binarization of historical document images using the local maximum and minimum, In Proceedings of international workshop on document analysis systems, pp. 159-166, (2010)

← 1 2 3 →