Deep Learning-Based Classification Of the Defective Pistachios Via Deep Autoencoder Neural Networks

TL;DR

This paper introduces a deep autoencoder neural network approach for unsupervised classification of defective pistachios, improving sorting accuracy for defects linked to contamination and spoilage.

Contribution

It presents a novel deep autoencoder-based imaging algorithm for unsupervised defect detection in pistachios, addressing limitations of traditional methods.

Findings

Achieved 80.3% accuracy in classifying defective nuts.

Effectively distinguished nuts with dark stains, oily stains, or adhering hulls.

Demonstrated feasibility of deep autoencoder approach with limited computational resources.

Abstract

Pistachio nut is mainly consumed as raw, salted or roasted because of its high nutritional properties and favorable taste. Pistachio nuts with shell and kernel defects, besides not being acceptable for a consumer, are also prone to insects damage, mold decay, and aflatoxin contamination. In this research, a deep learning-based imaging algorithm was developed to improve the sorting of nuts with shell and kernel defects that indicate the risk of aflatoxin contamination, such as dark stains, oily stains, adhering hull, fungal decay and Aspergillus molds. This paper presents an unsupervised learning method to classify defective and unpleasant pistachios based on deep Auto-encoder neural networks. The testing of the designed neural network on a validation dataset showed that nuts having dark stain, oily stain or adhering hull with an accuracy of 80.3% can be distinguished from normal nuts. Due to the limited memory available in the HPC of university, the results are reasonable and justifiable.