Loading

Text Independent Writer Verification using Spatial Domain Technique under Varying Writing Conditions
Sharada L. Kore1, Shaila D. Apte2

1Sharada L. Kore, Ph.D. Research Scholar, Bharati Vidyapeeth Deemed University College of Engineering, Pune, India.

Shaila D. Apte, Anubhuti Solutions, Pune, India.

Manuscript received on 08 July 2023 | Revised Manuscript received on 05 August 2023 | Manuscript Accepted on 15 September 2023 | Manuscript published on 30 September 2023 | PP: 30-34 | Volume-12 Issue-10, September 2023 | Retrieval Number: 100.1/ijitee.J971509121023 | DOI: 10.35940/ijitee.J9715.09121023

Open Access | Editorial and Publishing Policies | Cite | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: The present work reports the results of text independent writer verification under different environment such as writing instrument, ink width, paper quality, image size, image type, scanning devices and resolution. It is observed that the style of a writer and the type of writing instrument used greatly affects the handwriting. Also, the quality of handwritten samples greatly affects the performance of writer verification system. The objective of our work is to verify a writer under the changing conditions. To improve verification rate, the directional information is captured from the image contours and the histogram of chain code is used as feature. The system is tested on our own created dataset of 261 writers with 2 samples each with different writing instruments. Total of 50% samples are used to train the system and the system is tested for remaining 50% samples. The system is tested using chain code. The total error rate (TER) is 0.76 %. The method works even under poor resolution.

Keywords: Chain Code, Handwriting Identification, Pattern Recognition, Person Authentication, Writer Verification.
Scope of the Article: Information Technology