Publication

Abstract : Vision is the most advanced of our senses, so it is not surprising that images contribute important role in human perception. Image analysis is one of the most prominent fields in deep learning, Object detection is a well known computer technology connected with computer vision and image processing that focuses on detecting objects or its instances of a certain class(such as humans, flowers, animals)in digital images and videos. Images are easy to generate and handle, and they are exactly the right type of data for machine learning, easy to understand for human beings but difficult for computers. Recognising shapes involves distinguishing among shapes and associating shapes with shape names. The shapes “Triangle” and “Rectangle” can be easily identified by humans but it is very tedious for a computer. Understanding shape properties involves learning the defining characteristics or attributes of shapes. The system is able to predict the shape for which it has no prior information. The procedure of shape detection is actually a natural extension of the edge detection at pixel level to the difficulty of global contour detection. A tool for a systematic analysis of edge based shape detection is provided by this filtering scheme. Shape detection can be used for various purposes including retrieval and surveillance. The system find shapes in the real world from the captured video. The basic 2-D shapes are determined by the technique. The videos are captured by the camera and the RGB image is converted to grey scale image and edges are detected and is compared with the dataset and shapes are predicted. Index Terms: Edge detection, Machine learning, Object detection.