The objective of Optical Character Recognition (OCR) is automatic reading of optically sensed document text materials to translate human-readable characters to machinereadable codes. In Optical Character Recognition, the text lines in a document must be segmented properly before recognition. English Character Recognition (CR) has been extensively studied in the last half century and progressed ...

Image segmentation is a major task of handwritten document processing. Many of the proposed techniques for image segmentation are complementary, in the sense that each of them using a different approach, can solve different difficult problems such as overlapping, touching components, influence of author style etc. In this paper a combination method of different segmentation techniques is presen...

In the paper is presented one new approach for adaptive processing and compression of images of scanned documents, which contain text and pictures. In order to achieve high compression with maximum retained quality, the document content is analyzed and two corresponding regions of interest are set. Then, each region is processed as follows: the text – with lossless and the picture – with lossy ...

Document image enhancement methods are often used to improve the accuracy and efficiency of automated document analysis recognition tasks such as character recognition. These images could be degraded or damaged for various reasons including aging, fading handwriting, poor lighting conditions, watermarks, etc. In recent years, with improvement computer performance continuous development deep lea...

the historical documents are the important traces of the history. Historical documents carry the information about the tradition, religion, science, literature, war strategies of the ancient times, which are very useful to understand the life and culture of the ancient civilizations. These historical documents are usually recovered from the archaeological findings. Historical documents are usua...

In this paper, a new approach to identification of handwritten symbols in arbitrary complex environments is presented. 20 different pictograms drawn in different backgrounds can be identified with a recognition accuracy of 90%. In order to perform this challenging task, we use pattern spotting techniques based on pseudo 2-D Hidden Markov Models (P2DHMMs). Practical applications of our approach ...