Industrial object, machine part and defect recognition towards fully automated industrial monitoring employing deep learning. The case of multilevel VGG19

TL;DR

This paper introduces a modified VGG19 model called Multipath VGG19 for industrial object and defect recognition, demonstrating improved accuracy across multiple datasets for automated industrial monitoring.

Contribution

The study proposes a novel Multipath VGG19 architecture that enhances feature extraction for industrial recognition tasks, outperforming traditional VGG19 in accuracy.

Findings

Achieved top classification in 5 out of 6 datasets.

Average classification improvement of 6.95%.

Validated effectiveness of the proposed model.

Abstract

Modern industry requires modern solutions for monitoring the automatic production of goods. Smart monitoring of the functionality of the mechanical parts of technology systems or machines is mandatory for a fully automatic production process. Although Deep Learning has been advancing, allowing for real-time object detection and other tasks, little has been investigated about the effectiveness of specially designed Convolutional Neural Networks for defect detection and industrial object recognition. In the particular study, we employed six publically available industrial-related datasets containing defect materials and industrial tools or engine parts, aiming to develop a specialized model for pattern recognition. Motivated by the recent success of the Virtual Geometry Group (VGG) network, we propose a modified version of it, called Multipath VGG19, which allows for more local and global feature extraction, while the extra features are fused via concatenation. The experiments verified the effectiveness of MVGG19 over the traditional VGG19. Specifically, top classification performance was achieved in five of the six image datasets, while the average classification improvement was 6.95%.