Share Email Print
cover

Proceedings Paper

Dotted and curved line character segmentation
Author(s): Khader Mohammad; Sos Agaian; Hani Saleh
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

This paper presents new methodology for addressing curvature and segmentation in text as applied to dotted line images. Several improvements are provided, including methods and procedures for handling (a) curvature in text detection and segmentation, (b) rotation angle determinations, (c) isolation of only the character pixels in the image, (d) use of a fill algorithm to solidify the dotted character, and (e) discernment of segmented characters which may be printed too closely or that touch each other. Applying the new algorithms under various lighting conditions against 90 water bottle images (from OzarkaR and DasaniR) with differing text yielded a 93% accuracy rate. Additionally, the fill algorithm presented here improved recognition by more than 20% as compared to non-filled characters.

Paper Details

Date Published: 24 January 2011
PDF: 12 pages
Proc. SPIE 7878, Intelligent Robots and Computer Vision XXVIII: Algorithms and Techniques, 78780U (24 January 2011); doi: 10.1117/12.871730
Show Author Affiliations
Khader Mohammad, The Univ. of Texas at San Antonio (United States)
Sos Agaian, The Univ. of Texas at San Antonio (United States)
Hani Saleh, The Univ. of Texas at San Antonio (United States)


Published in SPIE Proceedings Vol. 7878:
Intelligent Robots and Computer Vision XXVIII: Algorithms and Techniques
Juha Röning; David P. Casasent; Ernest L. Hall, Editor(s)

© SPIE. Terms of Use
Back to Top