Classification of flower species by using features extracted from the intersection of feature selection methods in convolutional neural network models

---

Toğaçar M., Ergen B., CÖMERT Z.

Measurement: Journal of the International Measurement Confederation, cilt.158, 2020 (SCI-Expanded, Scopus)

• Yayın Türü: Makale / Tam Makale
• Cilt numarası: 158
• Basım Tarihi: 2020
• Doi Numarası: 10.1016/j.measurement.2020.107703
• Dergi Adı: Measurement: Journal of the International Measurement Confederation
• Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Compendex, INSPEC
• Anahtar Kelimeler: Deep learning, Feature intersection, Feature selection, Flower species, Image processing
• Samsun Üniversitesi Adresli: Evet

Özet

It is important for the sensitivity of ecological balance that image processing methods and techniques give better results day by day. Today, researchers use deep learning in image-based object recognition. Recently, the use of deep learning methods on plant species has increased. In this study, a hybrid method that is used together with feature selection methods and Convolutional Neural Network (CNN) models is presented. In the proposed model, CNN models are used for feature extraction. The features obtained from these models are combined and efficient features are selected with feature selection methods. The aim here is to subtract and classify intersecting features between the features obtained by feature selection methods. When the results of the experiments are compared, the intersection of the features obtained by feature selection methods are contributed to the classification performance. The classification success achieved by the Support Vector Machine (SVM) method was 98.91%.