• Kunal Chachra
• Manish Vyas
• Rahul Dakhale
• Layeba Fayeem
• Prof. S.N.Uke

In this paper, we are going to invent a camera-based assistive text identification tool to help blind people read text from images and household objects in their daily life. The system implementation depends on three main components: First, image capture-using a system camera with the help of Open-CV, the text from this image get extracted further, second, data processing -where text will be evaluated from the images and will be identified by optical character recognition (OCR) tool, and finally, Speech output generated with respect to identified text The text will be given to input for GTTS for audio output. In addition to text identified by using OCR tool and machine learning methodologies are advantages for our implementation. The text extraction methods are used to extract the text from image or document. The extracted text is then converted into a voice and output is given to the user. We have challenges to overcome text generation and voice generation accuracy over existing work done. We are going to invent a system which will assist blind people to read text documents without any person's help.

Convolutional Neural Network, Optical character recognition, Google Text To Speech, Open Compute Vision.

"Machine Learning Based Assistive System for Visually Impaired People", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.49-55, June 2019, Available :http://www.jetir.org/papers/JETIR1907O09.pdf

"Machine Learning Based Assistive System for Visually Impaired People", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp49-55, June 2019, Available at : http://www.jetir.org/papers/JETIR1907O09.pdf