Abstract
In This paper we presented new approach for cursive Arabic text recogniti on system. The objective is to propose methodology analytical offline recognition of handwritten Arabic for rapid implementation. The first part in the writing recognition system is the preprocessing phaseis the preprocessing phase to prepare the data was introduces and extracts a set of simple statistical features by twomethods : from a window which is sliding long that text line the right to left and the approach VH2D (consists in projecting every character on the abscissa, on the ordinate and the diag onals 45° and 135°) . It then injects the resulting feature vectors to Hidden Markov Model (HMM) and combined the two HMM by multi -stream approach.
Highlights
Writing arable is naturally cursive, their recognition is the dream of everyone who needed data entry in a computer
An analytical approach has been proposed, The main objective of our system is to design and implement a multi-stream approach of two types of feature extraction based on local densities and configurations of pixels and features a projection based on vertical, horizontal and diagonal 45 °, 135 ° (VH2D approach), these characteristics is considered independent of the others and the combination is in a space of probability, in [15] [16] showed the combination of classifiers for the recognition of handwriting
In opposition to printed text in most languages, the characters in cursive handwritten words are connected because of it several methods use Hidden Markov Models (HMM) for recognising handwritten words, have been very successfully. system models words and characters in the form of Hidden Markov Models is analytical: the models words are built by concatenation of models the characters. that are left-right as shown in Fig. 12 [4][5][6] gives an example of the training, showing that each character shape of the same type, independent of the word where it was written, contributes to the statistical character shape model
Summary
Writing arable is naturally cursive, their recognition is the dream of everyone who needed data entry in a computer. The Arabic writing poses many problems for systems of automatic recognition we retain essentially these problems: the segmentation of handwritten words, skew angle of lines, overlaps, ligatures, the spaces between words, the dots are positioned above or below the character body and can change the meaning of the word To overcome these problems, an analytical approach has been proposed, The main objective of our system is to design and implement a multi-stream approach of two types of feature extraction based on local densities and configurations of pixels and features a projection based on vertical, horizontal and diagonal 45 °, 135 ° (VH2D approach), these characteristics is considered independent of the others and the combination is in a space of probability (combine the outputs of classifiers with a creation of a system of higher reliability ), in [15] [16] showed the combination of classifiers for the recognition of handwriting. We describe the modeling MMC with a combination multi-stream
Sign-in/Register to view highlights & summary 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: International Journal on Natural Language Computing
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.
