A Survey on Portable Camera-Based Assistive Text and Product Label Reading From Hand-Held Objects fo

Page 1

International Research Journal of Engineering and Technology (IRJET) Volume: 04 Issue: 03| Mar -2017

www.irjet.net

e-ISSN: 2395 -0056 p-ISSN: 2395-0072

A Survey on Portable Camera-Based Assistive Text and Product Label Reading From Hand-Held Objects for Blind Persons Ms KOMAL MOHAN KALBHOR1,MR KALE S.D.2 PG Scholar,Departement of Electronics and telecommunication,SVPM College of Engineering,Malegaon(BK),Maharashtra,India Asst.Proffessor, Departement of Electronics and telecommunication,SVPM College of Engineering,Malegaon(BK),Maharashtra,India -------------------------------------------------------------------****--------------------------------------------------------------------------Abstract: For blind person new approach a camera-based

product packages and objects printed with text such as

assistive text reading framework to help read text labels and product packaging from hand-held objects in their daily lives. To seperate the object from cluttered backgrounds or other surrounding objects in the camera view, first developed an efficient and effective motion based method to define a region of interest (ROI) in the video basking the user to shake the object. This method unfairly moving object region by mixtureof-Gaussians-based background subtraction method. In the extracted ROI, text localization and recognition are carried to obtain text information. To automatically localize the text regions from the object ROI, propose a novel text localization algorithm by learning gradient features of stroke orientations and distributions of edge pixels in an Adaboost model. Text characters in the localized text regions are then binarizedand recognized by off-the-shelf optical character recognition software.

prescription medication bottles.

Keywords: Assistive devices, distribution of edge

minimicrophone is employed for speech output. The

pixels, hand-held objects, optical character recognition

main contributions of this paper are:

This paper presents a prototype system of assistive text reading. There are three main parts included scene capture, data processing, and audio output. The scene capture component collects scenes containing objects of interest in the form of images or video. The data processing component is used object-of-interest detection and text localization to obtain image regions containing text, and text recognition. The recognized text codes is informed by audio output component to the

(OCR),stroke orientation, text reading, and text region

user.

A

Bluetooth

earpiece

with

1) a novel motion-based algorithm are used to solve

localization.

I.

blind

the aiming problem for blind users by their simply

INTRODUCTION

shaking the object of interest for a brief period.

Reading is necessary in today’s society. Text is everywhere in the form of printing reports, receipts,

2) a novel algorithm of automatic text localization to

bank statements, restaurant menus, product packages,

obtain text regions from complex background and

instructions on medicine bottles etc. And while optical

multiple text patterns.

aids, video magnifiers, and screen readers can help

3) a portable camera-based assistive framework to aid

blind persons and those with less vision to access

blind persons reading text from hand-held objects.

documents, there are few devices that can provide better access to common hand-held objects such as Š 2017, IRJET

|

Impact Factor value: 5.181

|

ISO 9001:2008 Certified Journal

|

Page 53


Turn static files into dynamic content formats.

Create a flipbook
Issuu converts static files into: digital portfolios, online yearbooks, online catalogs, digital photo albums and more. Sign up and create your flipbook.
A Survey on Portable Camera-Based Assistive Text and Product Label Reading From Hand-Held Objects fo by IRJET Journal - Issuu