Abstract

Tainted documents are degraded or ruined documents of low quality and of worn out look. The taintations are like disparity variation, smear, ooze, uneven illumination. To enhance the visual quality of the tainted document binarization technique is applicable. Binarization can binarize all the tainted documents but performing binarization to faultily tainted documents is a complicated task, the complication is observed in the identification of variations between the document background and text foreground. The system uses OTSU binarization that can binarize any kind of taintations. The proposed technique addresses the variations between background and foreground text of the document and calculates the optimum threshold separating the two classes so that their combined spread is minimal or equivalent hence the vision quality increases. Enhancement of vision quality also results in the enhancement of document size. Compression is performed on the binarized tainted document to reduce the tainted document size. The compression technique projected to use in this paper is Run Length coding which helps to reduce the size of the tainted document. Run Length coding is lossless compression technique which is very successful in dealing with binary images.

Highlights

  • Image processing is the rapid developing technology in the recent technical era

  • In the process of improving degraded documents binarization or segmentation is the suitable approach to enhance the visual quality of any image[1, 9, 10]

  • The natural way of separating fore ground objects or regions from the background is through Thresholding process, i.e. the separation of low intensity and high intensity regions

Read more

Summary

Introduction

Compared to the initial stage of image processing the current stage is extensively improved. Immediate result of this improvement is: it became a domain to reconstruct, reproduce and reinvent many applications. Segmentation is process of separating an image into contours corresponding to objects. The objects or segmentation regions are usually separated by identifying the common properties. Thresholding process takes gray scale images and process the every pixel of them to create the binary images. It sets the all the pixels whose intensity value below some given threshold to zero and all pixels whose intensity value above that threshold to one [2]

Methods
Discussion
Conclusion
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.