Malayalam text to braille system with OCR and SVM
Era of technology, the knowledge resources are at the finger tips, it make lives easy but in the society there are various kind of people including differently able people, visually impaired people .Considering about visually impaired people they have only two sources of knowledge, they are audio and Braille script. Braille is a tactile writing system, Braille education remains important for developing reading skills among blind and visually impaired people. Visually impaired people can read computer screens and other electronic supports with refreshable braille displays and there are portable braille note takers and computer that prints with a braille embosser for their use. Each Braille character made up of six raised dots that arranged in rectangular blocks called cells. The number and the arrangement of these dots are different one character from another, since there are various braille alphabets vary from language to language. Translating normal text into braille is took very special place among visually impaired people, because it is the way to learn and gather information for them. This traditional translators are time consuming and while using it, it is too difficult to re-corrections.
Most of the knowledge resources for visually impaired people are available in English. According to the article that referred here, that proposed system deals with conversion of printed Malayalam text into Braille. The main part of the system is a Malayalam OCR system, OCR standards for optical character recognition system. In India they use braille alphabet called Bharati Braille. The history of Bharati Braille dates back to the period prior to India’s independence, it is consists of the six dot system for the languages in India. Bharati Braille assigns the cells to the basic sounds of the Indian languages known as “aksharas”; this follows grade 1 Braille in English, in a manner where vowels and consonants that find direct equivalents in English are given the same representation as in English. Bharati Braille retains all the basic conventions relating to the representation of numerals, punctuation and special symbols just as in Standard English. Malayalam Braille is one of the Bharati Braille alphabets.
Early mid-1960s it is started to automation text into braille transliteration, this process can be done at software level or at hardware level. Most of researches and products are at software level and those systems are related to the background of English.
Duxbury Braille Translation (DBT)
The system with English interface, window based software that automates the process of conversion from regular print to Braille and vice versa.
Duxbury Braille Board (DBB)
Window-based software system that can translate from English text to Braille system. When user inputs using the normal keyboard its corresponding braille cell will be display on the screen, this system supports only English language.
Win Braille (Index Braille, 2007)
Braille maker are also good Window-based software system for braille transliteration, than means text to Braille transliterations and these are based on English.
Moreover, P. Blenkorn have worked on the problem of converting Word-Processed Documents into formatted Braille document. They have use DLL written in C, to translate Text to Braille. Conversion of English characters in to Braille using Neural network done by M. Y. Hassan and he presented it on a paper. This artificial neural network was designed and tested to convert English characters into grade I literary Braille code. Vandana proposed a method for implementing Gurmukhi to Braille. The user inputs are applied to Gurmukhi directly. Likewise, there are so many systems that based on software and hardware level researches.
The proposed system will be an SVM based printed Malayalam text to braille transliteration system. The SVM is a new type of classifier based on novel statistical learning techniques. The principle of an SVM is to map the input data onto a higher dimensional feature space nonlinearly related to the input space and determine a separating hyperplane with maximum margin between the two classes in the feature space, these two classes are the implements of SVM classifier in its basic form and in proposed system SVM is used to classify and to identify the characters. The main part of this proposed system is a Malayalam OCR system. Malayalam OCR standard to Malayalam Optical Character Recognition, which is a process that can convert text, present in digital image, to editable text and allows system to recognize characters through optical mechanisms. The process involves some pre-processing of the image file, then acquisition of important knowledge about written text and the output of the OCR should ideally be same as input in formatting.
There are very limited knowledge resources for visually impaired persons available in Braille script, they can only get their academic books. It is possible to provide that all the study material whether that is an e-book, scanned papers or other available to the visually impaired people, by using this proposed system and more material will be available to them, for studying. The system will be used for reproducing most textbooks and publications. The printed Malayalam text to Braille transliteration system will finds in all places and where instructions and notices are to be read and also in assisted filling of application forms.
References:
(1) International journal of current engineering and technology
Most of the knowledge resources for visually impaired people are available in English. According to the article that referred here, that proposed system deals with conversion of printed Malayalam text into Braille. The main part of the system is a Malayalam OCR system, OCR standards for optical character recognition system. In India they use braille alphabet called Bharati Braille. The history of Bharati Braille dates back to the period prior to India’s independence, it is consists of the six dot system for the languages in India. Bharati Braille assigns the cells to the basic sounds of the Indian languages known as “aksharas”; this follows grade 1 Braille in English, in a manner where vowels and consonants that find direct equivalents in English are given the same representation as in English. Bharati Braille retains all the basic conventions relating to the representation of numerals, punctuation and special symbols just as in Standard English. Malayalam Braille is one of the Bharati Braille alphabets.
Early mid-1960s it is started to automation text into braille transliteration, this process can be done at software level or at hardware level. Most of researches and products are at software level and those systems are related to the background of English.
Duxbury Braille Translation (DBT)
The system with English interface, window based software that automates the process of conversion from regular print to Braille and vice versa.
Duxbury Braille Board (DBB)
Window-based software system that can translate from English text to Braille system. When user inputs using the normal keyboard its corresponding braille cell will be display on the screen, this system supports only English language.
Win Braille (Index Braille, 2007)
Braille maker are also good Window-based software system for braille transliteration, than means text to Braille transliterations and these are based on English.
Moreover, P. Blenkorn have worked on the problem of converting Word-Processed Documents into formatted Braille document. They have use DLL written in C, to translate Text to Braille. Conversion of English characters in to Braille using Neural network done by M. Y. Hassan and he presented it on a paper. This artificial neural network was designed and tested to convert English characters into grade I literary Braille code. Vandana proposed a method for implementing Gurmukhi to Braille. The user inputs are applied to Gurmukhi directly. Likewise, there are so many systems that based on software and hardware level researches.
The proposed system will be an SVM based printed Malayalam text to braille transliteration system. The SVM is a new type of classifier based on novel statistical learning techniques. The principle of an SVM is to map the input data onto a higher dimensional feature space nonlinearly related to the input space and determine a separating hyperplane with maximum margin between the two classes in the feature space, these two classes are the implements of SVM classifier in its basic form and in proposed system SVM is used to classify and to identify the characters. The main part of this proposed system is a Malayalam OCR system. Malayalam OCR standard to Malayalam Optical Character Recognition, which is a process that can convert text, present in digital image, to editable text and allows system to recognize characters through optical mechanisms. The process involves some pre-processing of the image file, then acquisition of important knowledge about written text and the output of the OCR should ideally be same as input in formatting.
There are very limited knowledge resources for visually impaired persons available in Braille script, they can only get their academic books. It is possible to provide that all the study material whether that is an e-book, scanned papers or other available to the visually impaired people, by using this proposed system and more material will be available to them, for studying. The system will be used for reproducing most textbooks and publications. The printed Malayalam text to Braille transliteration system will finds in all places and where instructions and notices are to be read and also in assisted filling of application forms.
References:
(1) International journal of current engineering and technology
Comments
Post a Comment