Fast Statistical Image Binarization of Colour Images for the Recognition of the QR Codes

Krzysztof Okarma, Piotr Lech

Abstract


The article concerns the fast image binarization based on the application of the statistical Monte Carlo method applied for the recognition of the QR codes from colour images, especially captured by mobile devices’ cameras. Due to limited processing possibilities of some mobile devices as well as relatively low quality of some optical systems in built-in cameras, fast binarization methods are very useful for rapid recognition of the 2-D binary codes which can be found on the packages of various products and even on the street billboards. Captured images of such QR codes usually contain some background objects, may be blurred or may contain some other distortions which can hamper or make it impossible to recognize the code even considering the presence of redundant data included using Reed-Solomon’s code. These problems may also occur in differing lighting conditions where the impact of binarization method and its results may be critical for further processing. The experimental results presented in the paper obtained for various colour spaces confirm the usefulness of the fast Monte Carlo based image binarization for the fast recognition of the QR codes, especially in presence of distortions and varying lighting conditions. Additionally, high performance of the Monte Carlo method allows checking different variants of binarization in order to choose the most appropriate one.

DOI: http://dx.doi.org/10.5755/j01.eee.21.3.10397


Keywords


Image analysis; image recognition; Monte Carlo method.

Full Text: PDF

Refbacks

  • There are currently no refbacks.


Print ISSN: 1392-1215
Online ISSN: 2029-5731