OCR in round surface based on component labeling

image processing

Optical Character Recognition (OCR) refers to the process of translating, the handwritten or printed text into a format that is understood by machines for the process of editing, searching, and indexing. The recognition of character in round surface from scanned images of documents has been problem that has received much attention in the field of image processing, pattern recognition and artificial intelligence. In this method, find angle of every character in image and then recognize the character. The proposed method has three flows: Font file Teaching flow, Running Teaching flow and verification flow. In font file teaching flow create the font file using the image processing technique. In Running Teaching flow save reference data and parameters from font file and match character. In verification flow match all segments with reference data. Component labeling method used make segmentation easy to separate the single line in round surface into characters. The proposed approach is implemented using the Opencv2.4.4 and visual studio 2008.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.