Object and Text Detection

Abstract

The main aim of our project is to develop a portable raspberry pi implemented gadget for object detection with relative motion and distance. This technology is basically used for conversion of sequence of real time objects into series of text which can be further stored into database and can be utilized to assist visually impaired people and in various security purposes as well. For that purpose, the conversion system is proposed in this project. Our system basically operates in 2 different modes. One is detecting the class of objects nearby with the help of R-CNN network, and the second one is obstacle detection using ultrasonic sensor. It includes 3 buttons for mode selection and the system operates on the basis of mode selection. It includes camera to capture an image as input, and input image is then passed to the R-CNN that recognizes number of objects inside image, their classes and types, text written inside and which is then can be passed to the database for a storage.