Recognizing Characters in Scene Images

Jun Ohya, Akio Shio, Shigeru Akamatsu

Research output: Contribution to journalArticlepeer-review

178 Citations (Scopus)


An effective algorithm for character recognition in scene images is studied. Scene images are segmented into regions by an image segmentation method based on adaptive thresholding. Character candidate regions are detected by observing gray-level differences between adjacent regions. To ensure extraction of multisegment characters as well as single-segment characters, character pattern candidates are obtained by associating the detected regions according to their positions and gray levels. A character recognition process selects patterns with high similarities by calculating the similarities between character pattern candidates and the standard patterns in a dictionary and then comparing the similarities to the thresholds. A relaxational approach to determine character patterns updates the similarities by evaluating the interactions between categories of patterns, and finally character patterns and their recognition results are obtained. Highly promising experimental results have been obtained using the method on 100 images involving characters of different sizes and formats under uncontrolled lighting.

Original languageEnglish
Pages (from-to)214-220
Number of pages7
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Issue number2
Publication statusPublished - 1994 Feb
Externally publishedYes


  • Adaptive thresholding
  • character pattern extraction
  • character recognition
  • image processing
  • image segmentation
  • pattern recognition
  • relaxation
  • scene images

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics


Dive into the research topics of 'Recognizing Characters in Scene Images'. Together they form a unique fingerprint.

Cite this