Classification of Some Barley Cultivars with Deep Convolutional Neural Networks

Abstract

The homogeneity of the seeds is an important factor in terms of processing, transportation, storage, and product quality of agricultural products. It is possible to classify the grain polymorphism of barley cultivars, which are economically important among cereal crops, in a short time with computer vision methods with high accuracy rate and almost zero cost. In this research, a novel image database consisting of 2800 images were created to classify 14 barley cultivars. Six different deep convolutional neural network models were designed based on a transfer learning method with pretrained DenseNet-121, DenseNet-169, DenseNet-201, InceptionResNetV2, MobileNetV2 and Xception networks. The models were trained and evaluated with test-time augmentation method, the best performance was obtained from DenseNet-169 model with average 96.07% recall, 96.29% precision, 96.07% F1-score, and 96.07% accuracy on a test set independent of the training set. The results showed that the transfer learning method performed using additional layers such as dropout and data augmentation with sufficient data samples in these images with high similarities prevented overfitting by increasing the model performance. As a result, it can be suggested that the provided web tool based on the transfer model has an encouraging performance in identifying seedswith a high number of cultivars such as barley.

Improving the Approval Process for Durum Wheat Grain Quality in Algeria Using Computer Vision and Machine Learning

“…For a more detailed evaluation of the model, we analyse the results using the confusion matrix for each dataset, namely impurities, varieties, and species. In Figure 4, we observe that our SVM model, after a fine-tuning process, has achieved a remarkable and competitive classification performance of barely species compared to the deep learning model Bayram and Yildiz [49]. The performance was evaluated using the F1 score see (3), which ranged from 98.62% to 99.75%.…”

Adulteration Detection of Pork in Mutton Using Smart Phone with the CBAM-Invert-ResNet and Multiple Parts Feature Fusion

“…As a typical representative of deep learning, a convolutional neural network (CNN) can effectively learn feature expressions from a large number of sample images and enhance the generalization ability of the model. It has the advantages of fast and accurate image processing and is currently widely used in the detection of agricultural products [14][15][16]. With the continuous expansion of computing requirements, the network layers of CNN models were continuously deepened to improve network performance.…”