Kurumun Atıf Alan Makalesi
Atıf Alan Yayın
A CNN-SVM study based on selected deep features for grapevine leaves classification
Scopus
Toplam 167 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
Classification of bread wheat genotypes by machine learning algorithms
Scopus
Havuzumuzda 24 atıf almış
Bread wheat, one of the staple food products, is a grain that forms the main ingredient of flour used in bakery products, especially in bread. Wheat has a large market in the world. The correct classification of bread wheat seeds is of great importance in order for the farmers to obtain an efficient harvest from bread wheat and to earn high income. In this study, a data set was created by taking 8354 images from certified 'Ayten Abla', 'Bayraktar 2000', 'Hamitbey', 'Şanlı' and 'Tosunbey' bread wheat varieties. Classification of wheat genotypes was carried out in 4 stages using images of bread wheat genotypes. In the first stage, 90 colors (C), 4 shapes (S) and 12 morphological (M) features were extracted from the images in this data set by image processing and feature selection method. The features obtained in the second stage were combined in different combinations. In the third stage, in the selection of the features that were effective in classification performance, feature selection was made from all the features combined with the Artificial Bee Colony (ABC) algorithm. Finally, bread wheat genotypes were classified by using these features, determined in three stages, as Support Vector Machines (SVM), Decision Tree (DT) and Quadratic Discriminant (QD) classifier which were machine learning algorithms. To make the classification process more accurate and objective, 10 fold cross validation was performed. The most successful classification process was obtained with SVM. The success rates obtained using 46, 94, 106, 102 and 90 features with SVM were 96.28 %, 95.81 %, 95.77 %, 95.66 % and 95.34 %, respectively.
Atıf Yapan Makale Bilgileri
Kurumlar (1)
Selçuk Üniversitesi
Selçuklu, Turkey