Journal of Computer Science

Handwritten Characters Extraction from Form Based on Line Shape Characteristics

Ali Qusay Al-Faris, Dzulkifli Mohamad, Umi Kalthum Ngah and Nor Ashidi Mat Isa

DOI : 10.3844/jcssp.2011.1778.1783

Journal of Computer Science

Volume 7, Issue 12

Pages 1778-1783


Problem statement: Data entry form is a convenient and successful tool for information collection by filling in the sheets using pen and handwriting. One of the most important fields in these forms is the data filled boxes. Extracting the handwriting from the data entry forms is important for many purposes such as in documenting and archiving. The extraction process is also important in situations such as when it is necessary to the handwritten recognition process. Approach: A simple and effective approach is presented to extract handwritten characters, including digits and letters of any language from data filled boxes of data entry form and to deal with cases of overlaps between the handwritten characters and boxes’ lines. The proposed approach is based on line shape characteristic by detecting and removing the vertical and horizontal straight boxes’ lines, while preserving the curved lines which represent the handwritten characters. The problem of the handwritten characters overlapping with the data filled boxes’ line is solved using morphology dilation to reconstruct the broken characters after the removal of the boxes’ lines. Results: Experimental results have demonstrated that the proposed approach can extract handwriting from data filled boxes with overall 94.052% for data collection of 150 forms. Conclusion: The proposed algorithm has been successfully implemented and tested to achieve the objectives of handwritten extraction of any language from data filled boxes. However, this work could not deal with situations whereby the characters touch other immediate characters.


© 2011 Ali Qusay Al-Faris, Dzulkifli Mohamad, Umi Kalthum Ngah and Nor Ashidi Mat Isa. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.