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
Flower Recognition System with Optimized Features for Deep Features
Scopus
Havuzumuzda 17 atıf almış
Looking at nature, flowers are everywhere. Classification is a difficult task, as the flowers have a large number of species that are very similar to each other in shape, appearance and color. Classification of flowers can be used in various fields of application such as product monitoring, flower identification, medicinal flowers, floriculture industry, plant taxonomy. In the study, a dataset with 4317 images from 5 types of flowers was used. In the classification study carried out in three stages, deep features were extracted from images with the SqueezeNet deep learning architecture of the transfer learning approach in the first stage. In the second stage the 1000 extracted features were classified using Neural Network and Logistic Regression methods from machine learning techniques. In the third stage, the deep features extracted were optimized with the help of particle swarm algorithm and the 488 features obtained were classified using machine learning Neural Network and Logistic Regression methods again. When the results obtained at both stages were compared, it was observed that the classification with the optimized features improved the success performance. The classification success of the features obtained by deep feature extraction was obtained as 85.1% by Neural Network and 79.7% by Logistic Regression method. In the classification results performed with the optimized features, the classification success was determined as 90.1% for Neural Network and 84.2% for Logistic Regression. The effect of optimized features on classification success is also understood in the study.
Atıf Yapan Makale Bilgileri
Kurumlar (1)
Selçuk Üniversitesi
Selçuklu, Turkey