24 January 2011 Dotted and curved line character segmentation
Author Affiliations +
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.
© (2011) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Khader Mohammad, Sos Agaian, Hani Saleh, "Dotted and curved line character segmentation", Proc. SPIE 7878, Intelligent Robots and Computer Vision XXVIII: Algorithms and Techniques, 78780U (24 January 2011); doi: 10.1117/12.871730; https://doi.org/10.1117/12.871730
PROCEEDINGS
12 PAGES


SHARE
Back to Top