Kurumun Atıf Alan Makalesi
Atıf Alan Yayın
A CNN-SVM study based on selected deep features for grapevine leaves classification
Scopus
Toplam 166 atıf DOI
The main product of grapevines is grapes that are consumed fresh or processed. In addition, grapevine leaves are harvested once a year as a by-product. The species of grapevine leaves are important in terms of price and taste. In this study, deep learning-based classification is conducted by using images of grapevine leaves. For this purpose, images of 500 vine leaves belonging to 5 species were taken with a special self-illuminating system. Later, this number was increased to 2500 with data augmentation methods. The classification was conducted with a state-of-art CNN model fine-tuned MobileNetv2. As the second approach, features were extracted from pre-trained MobileNetv2′s Logits layer and classification was made using various SVM kernels. As the third approach, 1000 features extracted from MobileNetv2′s Logits layer were selected by the Chi-Squares method and reduced to 250. Then, classification was made with various SVM kernels using the selected features. The most successful method was obtained by extracting features from the Logits layer and reducing the feature with the Chi-Squares method. The most successful SVM kernel was Cubic. The classification success of the system has been determined as 97.60%. It was observed that feature selection increased the classification success although the number of features used in classification decreased.
Atıf Kaynağı
Atıf Yapan Yayın
Segmentation of dry bean (Phaseolus vulgaris L.) leaf disease images with U-Net and classification using deep learning algorithms
Scopus
Havuzumuzda 33 atıf almış
Detecting plant diseases is a challenging and time-consuming task that requires expertise and laboratory conditions. Deep learning methods have been proposed as a solution to this problem, and their effectiveness in plant disease detection has become a popular research topic in recent years. This study aimed to investigate the performance of the U-Net architecture, which has been successful in medical image segmentation, in the segmentation of agricultural images. Sixty images, including angular leaf spot and bean rust diseases commonly found in bean plants, were used in the study. The images were segmented with U-Net, and then, in the first stage, only the images containing diseases were classified. In the second stage, classification was performed using raw images. Deep learning methods VGG16, AlexNet, MobileNet-v2, and DenseNet201 were used for the classifications. The results showed that the classification accuracy was higher for the segmented images than for the raw images. The highest accuracy rate, 100%, was achieved with DenseNet201 in the classification carried out by removing the segmented diseased regions. Using the U-Net architecture, which has demonstrated good performance with relatively few medical images, promising results were achieved in segmenting plant diseases. A software was developed to obtain only the images of the diseased areas by overlapping the original images with the segmented images. The proposed end-to-end system achieved higher classification accuracy by focusing deep learning architectures only on the desired regions. Finally, 100% classification accuracy was achieved with the DenseNet201 architecture using only segmented diseased images.
Atıf Yapan Makale Bilgileri
Kurumlar (1)
Selçuk Üniversitesi
Selçuklu, Turkey