A novel method to recognize object in Images using Convolution Neural Networks

Abstract

Detection and recognition of object is challenging task nowadays in the computer vision domain. To solve this problem, we have many techniques and algorithms that help us to detect objects in natural environment. Prime components of object detection are classification and feature extraction. In this paper we have used a method called Convolution Neural Network (CNN) a technique for training images for object recognition. Machine learning techniques are applied on computer vision domain. This research aims to propose a new design and a methodology to support a system in order to recognize the object and give us the pop-up message in case the object is considered as a weapon. Image processing techniques are used to develop the system. This experiment is conducted to access the following qualities, say, to verify whether the system is able to detect the object and to measure the accuracy of the proposed system.