Sliding Window Technique for Handwritten Text Line Segmentation

Sunanda Dixit, H.N. Suresh


Document image processinghas attained sizable headway with increasingly rampant applicability in document imaging system. Extraction and analysis of information from document images has attained prominence recently. Optical Character Recognition (OCR) technique analyses and integrates the digitized data with other electronically generated data. Despite several successful works in OCR all over the world, development of OCR tools in Indian languages is still an ongoing and a challenging process. Text line segmentation and skew estimation for handwritten documents are complicated and exhibit diverse problems. A better text line segmentation technique for south Indian Kannada language is presented here. The processing of Kannada language is very crucial factor because the Kannada letters are in crucial shapes and it is harder to segment the touching lines and letters from the Kannada image documents. The challenges present in Kannada language process and the existing text line segmentation methods has been improved by our intended method, which utilizing two major techniques namely, sliding window and adaptive histogram equalization

Full Text:



  • There are currently no refbacks.