Product Re-identification System in Fully Automated Defect Detection

TL;DR

This paper presents a neural network-based product re-identification system integrated with an image search engine, demonstrating improved accuracy on a small dataset for automated defect detection.

Contribution

It introduces AlphaAlexNet, an improved neural network for product re-identification, and explores combining neural features with Vearch for better identification accuracy.

Findings

AlphaAlexNet improves identification accuracy by 4%.

Combining neural networks with Vearch shows potential for small datasets.

Future work aims to develop algorithms requiring fewer training images.

Abstract

In this work, we introduce a method and present an improved neural work to perform product re-identification, which is an essential core function of a fully automated product defect detection system. Our method is based on feature distance. It is the combination of feature extraction neural networks, such as VGG16, AlexNet, with an image search engine - Vearch. The dataset that we used to develop product re-identification systems is a water-bottle dataset that consists of 400 images of 18 types of water bottles. This is a small dataset, which was the biggest challenge of our work. However, the combination of neural networks with Vearch shows potential to tackle the product re-identification problems. Especially, our new neural network - AlphaAlexNet that a neural network was improved based on AlexNet could improve the production identification accuracy by four percent. This indicates that an ideal production identification accuracy could be achieved when efficient feature extraction methods could be introduced and redesigned for image feature extractions of nearly identical products. In order to solve the biggest challenges caused by the small size of the dataset and the difficult nature of identifying productions that have little differences from each other. In our future work, we propose a new roadmap to tackle nearly-identical production identifications: to introduce or develop new algorithms that need very few images to train themselves.