Automatic segmentation and reconstruction of historical manuscripts in gradient domain. Issue 4 (1st April 2018)

• Record Type: Journal Article
• Authors: Baig, Asim; Al‐Ma'adeed, Somaya A.S.; Bouridane, Ahmed; Cheriet, Mohamed
• Is Part Of: IET image processing. Volume 12:Issue 4(2018)
• Page Start: 502
• Page End: 512
• Publication Date: 2018-04-01
• Subjects: edge detection -- image segmentation -- image reconstruction -- gradient methods -- interpolation -- pattern clustering -- image denoising -- document image processing; scanned documents -- subjective evaluations -- objective evaluations -- writing styles -- standard databases -- noise removal -- interpolation -- Poisson method -- clustering efficiency -- Harris corner detectors -- fully automated segmentation approach -- digital palaeography -- gradient domain -- historical manuscript automatic segmentation -- historical manuscript reconstruction technique; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2017.0223
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Separating content from noise in historical manuscripts is a fundamental task in digital palaeography. This study presents a fully automated segmentation approach based on the response of Harris corner detectors. The strength and clustering efficiency of the detected corners in the manuscripts are evaluated and used to segment the content from the background and noise. In addition, a manuscript reconstruction technique is proposed from the gradient field using the Poisson method to guide the interpolation. This reconstruction is able to remove noise significantly and hence enhances the contrast of the content thus making it easier for users to read and process these documents. The proposed approaches are evaluated using various standard databases to highlight their effectiveness and robustness to a multitude of noise and writing styles. Subjective and objective evaluations of the experimental results show that these techniques are able to successfully segment and reconstruct a very diverse set of scanned documents. An analysis of the results has also shown that the proposed technique compares favourably against similar counterparts.