Object Recognition Using Image Segmentation

The aim of the paper is to develop a system that can recognize various targeted objects in real-time by incorporating some computer vision techniques and advanced boosted Machine Learning algorithms to solve the problem of object recognition with high accuracy. The task of object detection is a combination of both, image classification and image localization. Image classification identifies the class of target object whereas localization identifies its position inside the input image. Viola-Jones is an algorithm that can work effectively for recognizing a large number of categories such as airplanes, cars, faces, etc. It works on feature extraction and uses Haar-Like features to achieve the objective. So, Viola-J ones is the algorithm that will be used for the development purpose of this paper. Also, instead of using a normal image, the image segmentation technique will be used to create segments in the image that will make it easy to analyze and process the image for further computations.