期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2019
卷号：7
期号：4
页码：2366-2371
DOI：10.15680/IJIRCCE.2019. 0704028
出版社：S&S Publications
摘要：Text and speech is the main medium for human communication. A person needs vision to access the
information from the image. This paper proposes an image based assistive text reading to help visually impaired person
in reading both text and objects present in the image. In this system the objects in the image is identified by the faster
Regional Convolutional Neural Network (faster RCNN) object recognition algorithm. The proposed idea involves text
identification from image using pytesseract in python and generates audio description about the objects in the image.
This is a prototype for visually impaired people to recognize the products in real world by extracting the objects on
Image and converting it into speech. Proposed method is carried out by using Deep Learning methods, python and
OpenCV. This technology helps millions of people in the world who experience a significant loss of vision.
