• DocumentCode
    1054259
  • Title

    Iterative Cross Section Sequence Graph for Handwritten Character Segmentation

  • Author

    Dawoud, Amer

  • Author_Institution
    Rotoflex Int. Inc., Mississauga
  • Volume
    16
  • Issue
    8
  • fYear
    2007
  • Firstpage
    2150
  • Lastpage
    2154
  • Abstract
    The iterative cross section sequence graph (ICSSG) is an algorithm for handwritten character segmentation. It expands the cross section sequence graph concept by applying it iteratively at equally spaced thresholds. The iterative thresholding reduces the effect of information loss associated with image binarization. ICSSG preserves the characters´ skeletal structure by preventing the interference of pixels that causes flooding of adjacent characters´ segments. Improving the structural quality of the characters´ skeleton facilitates better feature extraction and classification, which improves the overall performance of optical character recognition (OCR). Experimental results showed significant improvements in OCR recognition rates compared to other well-established segmentation algorithms.
  • Keywords
    graph theory; handwritten character recognition; image segmentation; image thinning; optical character recognition; character skeletal structure; feature classification; feature extraction; handwritten character segmentation; image binarization; iterative cross section sequence graph; optical character recognition; Character recognition; Feature extraction; Floods; Image segmentation; Interference; Iterative algorithms; Optical character recognition software; Optical losses; Shape measurement; Skeleton; Cross section sequence graph (CSSG); handwritten character segmentation; optical character recognition (OCR); Algorithms; Artificial Intelligence; Automatic Data Processing; Computer Graphics; Handwriting; Image Enhancement; Image Interpretation, Computer-Assisted; Information Storage and Retrieval; Numerical Analysis, Computer-Assisted; Pattern Recognition, Automated; Reading; Reproducibility of Results; Sensitivity and Specificity; Signal Processing, Computer-Assisted; Subtraction Technique; User-Computer Interface;
  • fLanguage
    English
  • Journal_Title
    Image Processing, IEEE Transactions on
  • Publisher
    ieee
  • ISSN
    1057-7149
  • Type

    jour

  • DOI
    10.1109/TIP.2007.901245
  • Filename
    4271521