Object sorting using faster R-CNN

TL;DR

This paper compares CNN, Fast R-CNN, and Faster R-CNN models for object detection and sorting in a factory setting, demonstrating their effectiveness in automating part categorization and robotic handling.

Contribution

It introduces a comparative analysis of neural network models for industrial object sorting and integrates a robotic arm for automated handling based on classification.

Findings

Faster R-CNN outperforms CNN and Fast R-CNN in detection accuracy.

The system successfully sorts objects by color and defect status.

Robotic arm effectively picks and places objects based on model predictions.

Abstract

In a factory production line, different industry parts need to be quickly differentiated and sorted for further process. Parts can be of different colors and shapes. It is tedious for humans to differentiate and sort these objects in appropriate categories. Automating this process would save more time and cost. In the automation process, choosing an appropriate model to detect and classify different objects based on specific features is more challenging. In this paper, three different neural network models are compared to the object sorting system. They are namely CNN, Fast R-CNN, and Faster R-CNN. These models are tested, and their performance is analyzed. Moreover, for the object sorting system, an Arduino-controlled 5 DoF (degree of freedom) robot arm is programmed to grab and drop symmetrical objects to the targeted zone. Objects are categorized into classes based on color, defective and non-defective objects.