from the conferences organized by TANGER Ltd.
The article deals with the acquisition of character positions from the input image and with modifications to increase the accuracy of recognition that precedes it. As the input image is meant a camera output or a photo of text information in the surface on different types of blanks. The input image itself contains many defects, for example noise, holes, light reflection, uneven surface caused by cutting or welding etc. All of these defects have to be eliminated to increase the accuracy of the algorithms for image recognition. In the article, there are described methods of improving the input image, which are suitable for all types of text, but it is mainly aimed at industrial products and materials that exhibit a large percentage of defects caused by metallurgical processes.
Keywords: Image recognition, image filters, blank defects, binarization, character detection.© This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.