International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395 -0056
Volume: 04 Issue: 04 | Apr -2017
p-ISSN: 2395-0072
www.irjet.net
NEURAL NETWORK BASED ASSISTIVE SYSTEM FOR TEXT DETECTION WITH VOICE OUTPUT R.Aravind [1], R.P.Jagadesh [2], M.Sankari [3], N.Praveen [4], Mrs. S.Arokia Magdaline[5] Students[1,2,3,4], Assistant Professor[5], Dept. of Electronics and Communication Engineering , Parisutham Institute of Technology and Science , Tamil Nadu , India ---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract – As per the World Health organization (WHO),
285 million people are estimated to be visually impaired worldwide among which 90% live in developing countries and 45 million blind individuals world-wide E v e n though there are many existing solutions to the problem of assisting individuals who are blind to read, none of them provide a reading experience that in any way equivalent to that of the sighted population. In specific, there is a need for a portable text reader that is reasonable and readily existing to the blind community. Addition to the specially enabled in the IT revolution is both a social responsibility as well as a computational test in the rapidly advancing digital world today. This work suggests a smart reader for blind people using raspberry pi. This paper lectures the assimilation of a complete Text Read-out system designed for the blind. The system consists of a webcam interfaced with raspberry pi which accepts a page of printed text. The OCR (Optical Character Recognition) package installed in raspberry pi tests it into a digital article which is then subjected to skew modification, segmentation, before feature extraction to perform sorting.
Key Words: Raspberry pi, Web Cam, Optical character recognition, Audio amplifier.
The restriction is that it is very hard for blind users to find the position of the bar code and to properly point the bar code reader at the bar code.
3. PROPOSED SYSTEM To overcome the hitches sharp and also to assist blind persons to read text from those kinds of inspiring patterns and backgrounds found on many everyday commercial products of Hand-held objects, then have to conceived of a camera-based assistive text reading basis to track the object of interest within the camera view and extract print text evidence from the object. Text localization to obtain text comprising image regions then text acknowledgment to renovate image-based text information into clear codes. The audio output factor is to inform the blind user of predictable text codes in the form of speech or audio .The projected system is a camera based system in which the image is captured by the camera and the text is vague using neural OCR .Then the text is rehabilitated into audio in the speech synthesizer and can be caught using a headphone.
3.1 BLOCK DIAGRAM
1. INTRODUCTION
Reading is apparently essential in today’s society. Printed text is everywhere in the form of reports, receipts, bank statements, restaurant menus, classroom handouts, product packages, instructions on medicine bottles, etc. And while optical aids, video magnifiers, and screen readers can help blind users and those with low vision to access documents, there are few devices that can provide good access to common hand-held objects such as invention packages, and objects printed with text such as prescription medication bottles.
2. EXISTING MODEL Today, there are already a few systems that have some ability for portable use, but they cannot handle product labeling. For example, portable bar code readers designed to help blind people pinpoint different products in an extensive creation database can enable users who are blind to access material about these products.
Fig.1 Block diagram
© 2017, IRJET
|
Impact Factor value: 5.181
|
ISO 9001:2008 Certified Journal
|
Page 44