A Survey of Methods and Strategies in Character Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Optical character recognition
Optical Character Recognition: An Illustrated Guide to the Frontier
Optical Character Recognition: An Illustrated Guide to the Frontier
Digital Picture Processing
Image Analysis and Mathematical Morphology
Image Analysis and Mathematical Morphology
Zoning methods for handwritten character recognition: A survey
Pattern Recognition
Hi-index | 0.00 |
In this paper we describe an application of OCR techniquesto quality control in industrial production. The purposeof the system is to verify the correct printing of numericalinformation in sachets with surgical material. Numeralsare printed on an aluminium surface covered by a transparentplastic film, which can produce shadows or reflectionsin the image. The main difficulties for character recognitionarise from low acquisition resolution, noise, heavyor light printing, and different printing patterns. The systemmust perform with an error rate lower than 0.1% andwith the minimal computation time. Thus, we have decidedto use well-known and simple algorithms, adding to themsome refinements which take advantage of specific domain-knowledge,making them more robust and reliable. The systemis currently working with real production complyingwith the required specifications.