Tomato Classification using Deep Learning Techniques

Food industries and farming sector dependent on modern technology. Ripeness of tomatoes classification is the most important phase to maintain quality control and for the optimization of product usage. Manual sorting of tomatoes will be challenging part in food industries and agriculture sector. This paper contributes on tomato classification using deep learning models and classifies the tomatoes from their size and color. The Datasets contains 810 images segregated into 3 classes Matured, Half-ripen and Full-Ripen tomatoes each class contain 270 images of tomato. For the stored dataset we had applied deep learning models like SE-Net, MobileNet, DenseNet, VGG-16, ResNet and AlexNet models are performed to know which model suites well for the classification of tomatoes for the real time scenario. MobileNet and DenseNet achieved with highest accuracy. MobileNet with <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{9 8. 9 2 \%}$</tex> of accuracy and DenseNet with <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{9 7. 5 3 \%}$</tex> accuracy for classification of tomato.