Fruit Classification by Assessing Slice Hardness Based on RGB Imaging. Case Study: Apple Slices
[ 1 ] Instytut Konstrukcji Maszyn, Wydział Inżynierii Mechanicznej, Politechnika Poznańska | [ P ] pracownik
2024
artykuł naukowy
angielski
- apple slice
- hardness
- quality
- machine learning
- convolutional neural network
EN Correct grading of apple slices can help ensure quality and improve the marketability of the final product, which can impact the overall development of the apple slice industry post-harvest. The study intends to employ the convolutional neural network (CNN) architectures of ResNet-18 and DenseNet-201 and classical machine learning (ML) classifiers such as Wide Neural Networks (WNN), Naïve Bayes (NB), and two kernels of support vector machines (SVM) to classify apple slices into different hardness classes based on their RGB values. Our research data showed that the DenseNet-201 features classified by the SVM-Cubic kernel had the highest accuracy and lowest standard deviation (SD) among all the methods we tested, at 89.51 % ± 1.66 %. This classifier has proved to be the best compared to the others with two features, DenseNet-201 and ResNet-18, along with WNN, NB, and SVM (cubic and linear) kernels.
7 - 18
CC BY-NC-ND (uznanie autorstwa - użycie niekomercyjne - bez utworów zależnych)
otwarte czasopismo
ostateczna wersja opublikowana
w momencie opublikowania
publiczny
70
0,8 [Lista 2023]