Automated Defect Detection and Grading of Piarom Dates Using Deep Learning

TL;DR

An innovative deep learning framework designed specifically for the real-time detection, classification, and grading of Piarom dates is proposed, which significantly outperforms existing methods in terms of accuracy and computational efficiency, making it highly suitable for industrial applications requiring real-time processing.

Abstract

Grading and quality control of Piarom dates, a premium and high-value variety cultivated predominantly in Iran, present significant challenges due to the complexity and variability of defects, as well as the absence of specialized automated systems tailored to this fruit. Traditional manual inspection methods are labor intensive, time consuming, and prone to human error, while existing AI-based sorting solutions are insufficient for addressing the nuanced characteristics of Piarom dates. In this study, we propose an innovative deep learning framework designed specifically for the real-time detection, classification, and grading of Piarom dates. Leveraging a custom dataset comprising over 9,900 high-resolution images annotated across 11 distinct defect categories, our framework integrates state-of-the-art object detection algorithms and Convolutional Neural Networks (CNNs) to achieve high precision in defect identification. Furthermore, we employ advanced segmentation techniques to estimate the area and weight of each date, thereby optimizing the grading process according to industry standards. Experimental results demonstrate that our system significantly outperforms existing methods in terms of accuracy and computational efficiency, making it highly suitable for industrial applications requiring real-time processing. This work not only provides a robust and scalable solution for automating quality control in the Piarom date industry but also contributes to the broader field of AI-driven food inspection technologies, with potential applications across various agricultural products.

Figures (13)

• Figure 1: Examples of Piarom date images before and after preprocessing. The top row (Samples) displays raw images captured during data collection, with the black background clearly visible. The bottom row (Results) presents the images after cropping, where the black background has been removed.
• Figure 2: Overview of defect categories in the dataset. Each category includes sample images and the number of images per class (approximately 900), totaling 9,900 samples before augmentation.
• Figure 3: Schematic representation of the Piarom date defect detection and classification process. The flowchart outlines the steps from image acquisition to final analysis.
• Figure 4: Visualization of the processing pipeline. From left to right: (1) Input image after thresholding and warping, (2) Object detection output with bounding boxes, (3) Detection and classification output with bounding boxes labeled by defect class.
• Figure 5: Training and validation loss curves for YOLOv8-nano.