Cost Effective Approach for Object Sorting

Abstract

Modernization, although, has led into the development in terms of sophistication of human efforts in bringing out mass-production of more precisely manufactured goods; yet it in some ways it needs to be modified to be a smarter intelligent system. Intelligence in terms of decision making ability of machines, more specifically, robots. Modern day needs have broken the traditional belief of human interference just as an instructor to a machine or robot, and it is leaping towards an era demanding self motivated and corrective decision-maker automations. In many situations, autonomous systems do provide effective solutions to menial or dangerous tasks. In many cases, it is desirable to design an automated system that can identify objects and relocate them if the object meets certain prescribed criterion. This paper presents a similar but simplified system which will sort the objects according to different parameters such as color and size using simple image processing technique. The system is trained initially with a set of images defined as the reference images. Then while execution, real time images are compared with the reference image parameters and respective output is then fed to the placing system through parallel port of the computer.