article · IEEE Access
Tomato sorting and grading require efficient automation because manual methods are costly, labour-intensive, and slow. A hybrid quality sorting method focuses on colour features in tomato images by combining pre-trained convolutional neural networks for feature extraction with traditional machine learning classifiers. Using an image dataset captured with an NVIDIA Jetson TX1 single-board computer, image preprocessing and fine-tuning were implemented to allow deep layers to capture significant features. The extracted features were evaluated across support vector machines, random forest, and k-nearest neighbours classifiers. Pairing Inceptionv3 for feature extraction with a support vector machine classifier achieved the strongest results. This combination attained 97.50% accuracy for binary classification between healthy and rejected tomatoes, and 96.67% accuracy for classifying tomatoes as ripe, unripe, or rejected. Tested on an external public dataset, the same model configuration reached 97.54% accuracy in categorising tomatoes into ripe, unripe, old, or damaged classes.
Manual sorting of produce requires considerable labour and expense during large-scale agricultural production. Developing automated visual grading models that accurately distinguish ripe, unripe, and damaged tomatoes can help producers meet strict market and consumer quality standards more reliably while reducing reliance on slow, repetitive manual labour.
This work enables automated inline grading and sorting for commercial tomato growers and packing facilities. The system was developed using an NVIDIA Jetson TX1 embedded board and tested across both locally collected and public image datasets, demonstrating an applied and tested technology. Commercial deployment would require integrating these classification algorithms into physical packing lines and sorting hardware.
AI-generated from the published abstract. Always read the original work before citing.
The demand for high-quality tomatoes to meet consumer and market standards, combined with large-scale production, has necessitated the development of an inline quality grading. Since manual grading is time-consuming, costly, and requires a substantial amount of labor. This study introduces a novel approach for tomato quality sorting and grading, focusing specifically on the color feature of tomato images. The method leverages pre-trained convolutional neural networks (CNNs) for feature extraction and traditional machine-learning algorithms for classification (hybrid model). The single-board computer NVIDIA Jetson TX1was used to create a tomato image dataset. Image preprocessing and fine-tuning techniques were applied to enable deep layers to learn and concentrate on complex and significant features. The extracted features were then classified using traditional machine learning algorithms namely: support vector machines (SVM), random forest (RF), and k-nearest neighbors (KNN) classifiers. Among the proposed hybrid models, the CNN-SVM method has outperformed other hybrid approaches, attaining an accuracy of 97.50% in the binary classification of tomatoes as healthy or rejected and 96.67% in the multiclass classification of them as ripe, unripe, or rejected when Inceptionv3 was used as feature extractor. Once another dataset (public dataset) was used, the proposed hybrid model CNN-SVM achieved an accuracy of 97.54% in categorizing tomatoes as ripe, unripe, old, or damaged outperforming other hybrid models when Inceptionv3 was used as a feature extractor. The performance metrics accuracy, recall, precision, specificity, and F1-score of the best-performing proposed hybrid model were evaluated.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1109/access.2024.3352745
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
