• Mohit Sarin
• Aayush Sharma
• Sumit Kumar Sar

Developing a tool for the visually impaired people is a trivial area of concern. However, use of computer vision in these devices is a fairly new trend and recent topic of interest. There are several works using computer vision techniques which focus on specific requirements of blind people. But there is no existing methods that help to solve all the basic needs of blind person. In this paper, we propose an idea of a device which can capture images in real time and comprehend its equivalent speech directly into the ear of visually impaired person. This new system may solve some of major problems of blind persons that are still exists. The prototype facilitates object detection using image recognition techniques. Open Computer Vision (OpenCV) performs image analysis, classification of images and prediction of the type of object on household object dataset. This prediction is converted to audio output using gTTS (Google Text to Speech Converter). This audio output can be fed to earphones connected to the device. A computer vision technology device provides greater accessibility for those with vision impairments. The results produced by this device will be more accurate because of the novelty of the machine learning algorithms used in this.

Object Detection, Image Recognition, gTTS, OpenCV, Computer Vision, Blind navigation

"Development of a Smart Device for Blind & Visually Impaired Person using Computer Vision", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 9, page no.676-679, September-2018, Available :http://www.jetir.org/papers/JETIR1809608.pdf

"Development of a Smart Device for Blind & Visually Impaired Person using Computer Vision", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 9, page no. pp676-679, September-2018, Available at : http://www.jetir.org/papers/JETIR1809608.pdf