article · Neural Computing and Applications
Global coffee price fluctuations present economic difficulties for nations reliant on coffee production, heightening the need for accurate classification amidst growing interest in specialty coffee. Deep learning approaches using pre-trained convolutional neural network models offer an automated route to identify coffee types. An evaluation comparing models such as AlexNet, LeNet, HRNet, GoogleNet, MobileNetV2, ResNet-50, VGG, EfficientNet, Darknet, and DenseNet demonstrates how model architecture affects predictive success on a coffee dataset. Implementing transfer learning and fine-tuning allows these networks to generalise effectively, with top architectures reaching rapid convergence and high performance. Evaluated metrics show perfect or near-perfect results, including sensitivity and accuracy scores reaching 1.0000, a precision of 0.9924, and an F1 score of 0.9962. These findings underline the direct influence of architectural choice when deploying deep learning for automated coffee bean sorting and recognition.
Specialty coffee markets require dependable and precise sorting methods to maintain quality standards and fair economic returns for producers. Automated identification through deep learning removes the inconsistencies of manual inspection. Demonstrating that existing computer vision architectures can achieve near-perfect classification enables more reliable sorting systems, helping protect producers and supply chains from the market volatility caused by misidentified or inconsistent coffee grades.
The approach could enable automated coffee sorting systems and digital inspection tools for specialty coffee traders, roasters, and processing facilities. By validating pre-trained computer vision architectures on a coffee dataset, the work provides a benchmarked algorithmic basis for commercial sorting equipment. Because the investigation relies on comparative dataset testing rather than operational field deployment, the technology remains early-stage applied research that requires integration into physical hardware and testing in processing environments.
AI-generated from the published abstract. Always read the original work before citing.
Abstract Coffee bean production can encounter challenges due to fluctuations in global coffee prices, impacting the economic stability of some countries that heavily depend on coffee production. The primary objective is to evaluate how effectively various pre-trained models can predict coffee types using advanced deep learning techniques. The selection of an optimal pre-trained model is crucial, given the growing popularity of specialty coffee and the necessity for precise classification. We conducted a comprehensive comparison of several pre-trained models, including AlexNet, LeNet, HRNet, Google Net, Mobile V2 Net, ResNet (50), VGG, Efficient, Darknet, and DenseNet, utilizing a coffee-type dataset. By leveraging transfer learning and fine-tuning, we assess the generalization capabilities of the models for the coffee classification task. Our findings emphasize the substantial impact of the pre-trained model choice on the model's performance, with certain models demonstrating higher accuracy and faster convergence than conventional alternatives. This study offers a thorough evaluation of pre-trained architectural models regarding their effectiveness in coffee classification. Through the evaluation of result metrics, including sensitivity (1.0000), specificity (0.9917), precision (0.9924), negative predictive value (1.0000), accuracy (1.0000), and F1 score (0.9962), our analysis provides nuanced insights into the intricate landscape of pre-trained models.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1007/s00521-024-09623-z
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.
