Shankar Ganesh, A and Swarna, V and Anandh, Ba and Sakthivel, R and Ranisangeetha, A (2019) CR based Image Processing with Audio Output for Visually Challenged People. International Journal for Research in Applied Science & Engineering Technology, 7 (III). pp. 599-604. ISSN 2321-9653

[thumbnail of OCR based Image Processing with Audio Output.pdf] Text
OCR based Image Processing with Audio Output.pdf - Published Version

Download (873kB)
Official URL: http://


Image Processing is a technique which is used to find the text in a captured image. Visually challenged people face
many problems in day to day life. One of the important problems is reading the text. A digital speech synthesizer is used for doing the same. But most of the printed works doesn’t have audio version. So the technology of Optical Character Recognition (OCR) and the technology of speech synthesis (TTS) is used. TTS will convert the text of the captured image into spoken form of that text which is easy to understand. MSER algorithm is further used for better accuracy and the image is processed to get an audio output. It can be listened through headset. Tesseract is an open source OCR engine which is useful in text detection. Open
CV (Open Source Computer Vision) is a library of programming functions through which the required algorithm is selected.
Application of this project is virtual reading environment is possible for visually challenged people. This can also help out the older people with their partial eye-sight or people with diseases like Bleitz where they can see things hazy. This provides a virtual environment for reading text in front of them and is outputted through a headphone.

Item Type: Article
Uncontrolled Keywords: Optical Character Recognition (OCR), Tesseract, Computer Vision, TTS, MSER algorithm
Divisions: PSG College of Arts and Science > Department of Electronics
Depositing User: Users 1 not found.
Date Deposited: 23 Dec 2021 06:46
Last Modified: 23 Dec 2021 06:46

Actions (login required)

View Item
View Item