Human eye have the ability to detect and recognize a character of some language, which they know, by the power of their brain as they are accustomed to that shape of the character font. But this thing is typically challenging for computers as it has no ability to read and learn automatically. All it needs to work is to provide it an artificial technique by human beings to make its artificial brain to read and understand from a character image, an optical character image. There are lots of algorithms available for the optical character recognition. Although no such technique yet exists, which can guarantee that its steps are 100%? In this paper, a new technique has been proposed to detect optical characters from digital images. Here the basic algorithm for character contour tracing algorithm using Fourier descriptors is used and then the proposed algorithm is used to recognize the optical character so that it can help the basic recognition technique more and more accurate.
Digital Image, Character Recognition, Fourier Descriptors, Contour Tracing, Shape Representation, Shape Similarity Measure, Feature Extraction.