Affiliation:
1. ISKENDERUN TECHNICAL UNIVERSITY
Abstract
It is important to identify a high-performance model that can classify all leaves and even differentiate according to regional variations of the same leaf type. In this study, a leaf classification model was created using 5 different datasets with different number of images and compared with models. For this purpose, 4 different pre-trained models called VGG16, InceptionV3, MobileNet and DenseNet are used. In addition, a new model was proposed and model training was carried out using these datasets . Using the all models, inputs are transformed into feature vectors by parameter transfer method and used for classification with the nearest neighbor algorithm and support vector machine. The performance of the classifications were compared with similar studies in the literature.
Publisher
Iskenderun Technical University
Reference40 articles.
1. Anubha Pearline, S., Sathiesh Kumar, V., Harini, S. (2019). A study on plant recognition using conventional image processing and deep learning approaches. Journal of Intelligent & Fuzzy Systems, 36(3):1997-2004. https://doi.org/10.3233/JIFS-169911.
2. Atabay, H. A. (2016). A convolutional neural network with a new architecture applied on leaf classification. IIOAB J, 7(5):226-331.
3. Barre, P., Stöver, B. C., Müller, K. F., Steinhage, V. (2017). Leafnet: A Computer vision system for automatic plant species identification. Ecological Informatics, 40:50-56. https://doi.org/10.1016/j.ecoinf.2017.05.005.
4. Beikmohammadi, A. & Faez, K. (2018). Leaf classification for plant recognition with deep transfer learning. In 2018 4th Iranian Conference on Signal Processing and Intelligent Systems (ICSPIS), pages 21-26. IEEE.
5. Camgözlü, Y., & Kutlu, Y. (2019). Analysis of pooling effect on CNN using leaf database. Natural and Engineering Sciences, 4(3):115-121.