Abstract
The aim of this work is to recognize the printed Latin's characters. In this work two methods for constructing the feature space are used. These methods are Variance and Fractal dimension methods, as a result they have real values for every character in the Latin's language, and from these values they constructed the feature space extractions for every character in the Latin's language. After that, these features are given to the Back Propagation network for recognizing the characters. The result is a highest recognition for the characters is obtained, it is about 82.75% characters while the unrecognized characters are 17.25.
Highlights
Pattern Recognition could be considered as one of the most important and widest branches in the field of Digital Image Handling, whichJamal S
2.4 Feature Extraction Another important step before recognition is the feature space construction which will be used as a standard in the recognition phase [9]
This will contain all the letters that are presented in the language, the feature space is constructed after the page which is containing the character(s) is scanned and converted to a black and white image (Note that the image that is used in this work is in .bmp format because it hasn’t any compress and no lossy)
Summary
Pattern Recognition could be considered as one of the most important and widest branches in the field of Digital Image Handling, which. Word boundaries are found by looking for vertical gap in the segmented line and checking them to identify the beginning of words, but this process may isolate portions of word [fig 3]. 2.4 Feature Extraction Another important step before recognition is the feature space construction which will be used as a standard in the recognition phase [9] This will contain all the letters that are presented in the language, the feature space is constructed after the page which is containing the character(s) is scanned and converted to a black and white image (Note that the image that is used in this work is in .bmp format because it hasn’t any compress and no lossy). There are several methods to generate the feature space for the character; two methods of them are used in this work that is [fig.4]: 2.4.1 Variance 2.4.2 Fractals for the text of the printed Latin character
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: AL-Rafidain Journal of Computer Sciences and Mathematics
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
