Student Projects
Contact Information
University: PSG College Tech (India)
Team Members: Sowmya Kumar, IIIrd Year BE Electronics & Communication Engineering
Faculty Advisers: Mr. S. Mohandass
Email Address: sowmyakumar29@gmail.com
Submission Language : English
Project Information
Title: Reading Aid (C-B-YOND)
Description:
ABSTRACT
The proposed device will assist visually handicapped people in reading the printed text matter in a multilingual format. It will look out for text signs which may be written text on road signs, printed handouts, printed books, newspapers, posters, etc. in multiple languages depending on the user. The device will be portable and wearable. It will include a small camera mounted on sunglasses, a small processing unit and a headphone. Character recognition lies at the core of the discipline of pattern recognition where the aim is to represent a sequence of characters taken from an alphabet. We present a multilingual character recognition system for printed South Indian scripts (Kannada, Telugu, Tamil and Malayalam) and English documents.
OBJECTIVES OF THE PROJECT
The main objectives of the project are to help the visually impaired people to read printed books, text material and other important text patterns and to create a portable reading aid for the blind that supports Indian languages like Tamil, Telugu, Hindi, Malayalam and English.
APPLICATIONS OF THE SYSTEM
The product can be used by people of all age groups who have vision impairment due to Macular Degeneration, Glaucoma, Diabetic Retinopathy, Retinitis Pigmentosa, Cataracts or any kind of blindness or low vision. India shoulders the largest burden of global blindness, about 3.5 million across the country with 30000 new cases being added each year. We assume that 65% of the total blind population (3.5 million) will be benefitted by the product proposed. Approximately 25000 pieces of the instrument are required per year.
SIMILAR IMPORTED INSTRUMENTS :
- Sara - Scanning and Reading Appliance - $2,795.00
- Kurzweil KNFB Mobile Reader - $1,790.00
- Intel Reader and Capture Station - $599.00
- PEARL Portable Reading Solution - $1,790.00
- Libra II Reading Machine With MP3 Player - $2,595.00
Products
SOFTWARE REQUIREMENTS:
NI LabVIEW – the ultimate graphical programming language is used for prototyping the OCR part.
International status of development
- 285 million people are visually impaired worldwide: 39 million are blind and 246 million have low vision.
- About 90% of world's visually impaired live in developing countries.
- Less than 15% of these visually impaired people in developing countries like India have access to vision enhancement or vision rehabilitation services.
- There are over 1.4 million visually impaired children up to 14 years. The vast majority of visually impaired children with low vision conditions in developing countries like India are sent to blind schools despite having usable vision because they don't have access to or cannot afford vision enhancement or vision rehabilitation services that could help to integrate them into regular schools.
Current status in our country
- India houses 3,50,00,000 blind people among its total population of 118 Crores.
- The products that help the blind in India for reading are mostly software based screen readers.
- There is no prouct available that supports our native linguistics.
TECHNICAL DETAILS :
Features of the instrument / system proposed to be taken up for development.
- Capturing a clear image: The camera mounted on the blind’s glasses should take a picture clear enough for linguistic processing.
- Text Unit Identification: One main problem to tackle is to define what to consider as a relevant text in a real time scenario. The Text identification unit takes care of this problem.
- Linguistic Processing: Identifying the lexical items is likely to contribute to the performance of the extractive summarization process.
- Multilingual OCR: We present a multilingual character recognition system for printed South Indian scripts (Kannada, Telugu, Tamil and Malayalam) and English documents.
- Text-to-Speech Interface: The Text-to-Speech module is a crucial issue for accessibility of Visually Impaired People to page contents. The speech should be clear enough for the blind to understand.
Specifications
b. CAMERA – Spy Shades Hidden Cam Glasses
- Easy capture to Included 4GB SD Card
- Easy File Transfer Via USB
- Cost - $79.95
c. HEADPHONE – Super Ear
- 50dB Sound Gain
- Can be mounted on Binoculars, Belt, etc.
- For indoor/outdoor use
- Cost - $29.95
d. PROCESSING UNIT - Text to Speech chip for SpeakJet TTS256
The TTS256 is an 8-bit microprocessor programmed with letter-to-sound rules. This built-in algorithm allows for the automatic real-time translation of English ASCII characters into allophone addresses compatible with the Magnevation SpeakJet Speech Synthesizer IC. The TTS256 is offered in a through-hole, 28-pin package. Supplied power should be +5V.
PRESENT SYSTEM:
Accessing the Web on Handheld Devices for Visually Impaired People:
An automatic summarization system to ease web browsing for visually impaired people on handheld devices was proposed. It presented a text-to-speech interface to ease the understanding of web pages content. To our knowledge, that was the first to use both statistical and linguistic techniques for text summarization for browsing on mobile devices. But our proposal stands for reading texts in the textbooks and we also try to identify various languages.
Language Identification from an Indian Multilingual Document
In order to reach a larger cross section of people, it is necessary that a document should be composed of text contents in different languages. But on the other hand, this causes practical difficulty in the OCR of such a document, because the language type of the text should be pre-determined, before employing a particular OCR. Character recognition lies at the core of the discipline of pattern recognition where the aim is to represent a sequence of characters taken from an alphabet. Though many kinds of features have been developed and their test performances on standard database have been reported, there is still room to improve the recognition rate by developing improved features. We present a multilingual character recognition system for printed South Indian scripts (Kannada, Telugu, Tamil and Malayalam) and English documents. South Indian languages are most popular languages in India and around the world. The proposed multilingual character recognition is based on Fourier transform and principal component analysis (PCA), which are two commonly used techniques of image processing and recognition. PCA and Fourier transforms are classical feature extraction and data representation techniques widely used in the area of pattern recognition and computer vision.
Principle or operation.
The proposed device will assist visually handicapped people in reading the printed text matter in a multilingual format. It will look out for text signs which may be written text on road signs, printed handouts, printed books, newspapers, posters, etc. in multiple languages depending on the user. The device will be portable and wearable. It will include a small camera mounted on sunglasses, a small processing unit and a headphone. Character recognition lies at the core of the discipline of pattern recognition where the aim is to represent a sequence of characters taken from an alphabet. We present a multilingual character recognition system for printed South Indian scripts (Kannada, Telugu, Tamil and Malayalam) and English documents.
Block/schematic/circuit diagram
The Processor Unit consists of the text unit identifier with multi lingual capability.
Description of various sub-systems etc.
Camera:
The camera mounted on sunglasses is used to capture the book or readable material that a visually impaired wants to read. It takes the picture and routes it to the processing unit for further processing.
Processor unit:
The processing of the photos taken by the camera is done by the processing unit, as stated in the techniques above. The photos are processed for recognition of words of various languages. It also incorporates the text to speech conversion to facilitate the speech out through headphone. OpenCV (Open Source Computer Vision Library), an open source software may be used for optical character recognition.
Headphone:
The headphone is used to speak out the contents of the book to the visually impaired. It is also attached to the sunglasses to facilitate the user with a portable device.
10. WORK PLAN :
