Driving Active Contours to Concave Regions

MOSA, Qusay O, ALFOUDI, Ali Saeed, BRISAM, Ahmed A, OTEBOLAKU, Abayomi and LEE, Gyu Myoung (2022). Driving Active Contours to Concave Regions. Webology, 19 (1), 5131-5140.

[img]
Preview
PDF
20220123025111pmWEB19345.pdf - Published Version
Creative Commons Attribution Non-commercial No Derivatives.

Download (302kB) | Preview
Official URL: https://www.webology.org/abstract.php?id=1109
Open Access URL: https://www.webology.org/data-cms/articles/2022012... (Published version)
Related URLs:

    Abstract

    Broken characters restoration represents the major challenge of optical character recognition (OCR). Active contours, which have been used successfully to restore ancient documents with high degradations have drawback in restoring characters with deep concavity boundaries. Deep concavity problem represents the main obstacle, which has prevented Gradient Vector Flow active contour in converge to objects with complex concavity boundaries. In this paper, we proposed a technique to enhance (GVF) active contour using particle swarm optimization (PSO) through directing snake points (snaxels) toward correct positions into deep concavity boundaries of broken characters by comparing with genetic algorithms as an optimization method. Our experimental results showed that particle swarm optimization outperform on genetic algorithm to correct capturing the converged areas and save spent time in optimization process.

    Item Type: Article
    Uncontrolled Keywords: Information & Library Sciences; 0805 Distributed Computing; 0807 Library and Information Studies
    Identification Number: https://doi.org/10.14704/web/v19i1/web19345
    Page Range: 5131-5140
    SWORD Depositor: Symplectic Elements
    Depositing User: Symplectic Elements
    Date Deposited: 08 Feb 2022 18:14
    Last Modified: 09 Feb 2022 08:00
    URI: https://shura.shu.ac.uk/id/eprint/29709

    Actions (login required)

    View Item View Item

    Downloads

    Downloads per month over past year

    View more statistics