Çiçek Türlerinin Tanınması için ESA Tabanlı Transfer Öğrenme Üzerine Bir Çalışma

Year 2021, Issue: 32, 883 - 890, 31.12.2021

Ferhat Bozkurt

https://doi.org/10.31590/ejosat.1039632

Cited By: 3

Abstract

Bitki organlarından biri olan çiçek, ekolojik düzenin önemli bir elementidir. Çiçekler insanlara faydalı olan birçok alanda kullanılmıştır. Günümüzde bilinen yaklaşık dört yüz bin çiçek çeşidi vardır. Çiçekleri şekil ve renk benzerliği nedeniyle birbirinden ayırt etmek zor bir iştir. Çiçek sınıflandırması, çok çeşitli şekiller, renk dağılımı, aydınlatma koşulları ve maruz kalma deformasyonu nedeniyle zorlu bir problemdir. Renk ve şekil olarak birbirine benzeyen çiçekleri insan gözüyle ayırt etmek bazı görüntülerde daha da zorlaşmaktadır. İnsanların belirli türleri doğru bir şekilde ayırt etmesi dikkate değer bir eğitim gerektirir ve genellikle çok spesifik morfolojik özellikler, yakından ilişkili türleri ayırt eden tek şeydir. ESA modelleri son zamanlarda araştırmacılar tarafından manuel özniteliklere olan ihtiyacı ortadan kaldırmak için birçok sınıflandırma probleminde kullanılmaktadır. Bu çalışmada, çiçek türlerinin tanınması için ESA tabanlı transfer öğrenme yöntemleri incelenmiştir. Çiçek türlerinin sınıflandırılması için, önceden eğitilmiş popüler öğrenme tekniklerden VGG16, VGG19, SqueezeNet, DenseNet-121, DenseNet-201 ve InceptionResNetV2 uygulanmaktadır. Deneysel sonuçlarda aynı çiçek veri kümesi üzerinde sınıflandırma performansları karşılaştırılmıştır. Bu çalışmada InceptionResNetV2 modelinin diğer modellere göre daha üstün sonuçlar verdiği gözlemlenmiştir. En yüksek doğruluk (%92.25), çiçek veri seti için InceptionResNetV2 modeliyle elde edilmiştir.

Keywords

Derin öğrenme, Transfer öğrenme, Evrişimli sinir ağları, Öznitelik seçme, Çiçek türleri.

A Study on CNN Based Transfer Learning for Recognition of Flower Species

Abstract

The flower that is one of the plant organs, is essential element of the ecological order. Flowers have been used in many areas that are beneficial to humans. There exist about four hundred thousand varieties of flowers known today. It is a difficult task to distinguish flowers from each other due to their similarity in shape and color. Flower classification is a challenging problem due to the high variety of shapes, color distribution, lighting conditions and deformation of exposure. It becomes more difficult to distinguish flowers that are similar in color and shape to each other with the human eye for some images. It takes remarkable training for humans to correctly distinguish between particular species, and often very specific morphological features are the only thing that distinguishes closely related species. CNN models have been recently used by researchers in many classification problems to eliminate the need for manual features. In this study, CNN-based transfer learning methods are studied for recognition of flower species. Popular pretrained learning techniques which are VGG16, VGG19, SqueezeNet, DenseNet-121, DenseNet-201, and InceptionResNetV2 are conducted for classification of flower species. Their classification performances are compared on same flower dataset in experimental results. It was observed that the InceptionResNetV2 model gives superior results than other models in experiments. The highest accuracy (92.25%) is obtained with the InceptionResNetV2 model for flower dataset.

Keywords

Deep learning, Transfer learning, Convolutional neural network, Feature selection, Flower species

References

• Arinda, Y. K., Rahman, M. A., & Alamsyah, D. (2018). Klasifikasi Jenis Bunga menggunakan SVM dengan Fitur HSV dan HOG. Ijccs, no. x, 1-12.
• Bayram, E., & Nabiyev, V. (2021). Classification of Camouflage Images Using Local Binary Patterns (LBP). In 2021 29th Signal Processing and Communications Applications Conference (SIU) (pp. 1-4). IEEE.
• Christenhusz, M. J., & Byng, J. W. (2016). The number of known plants species in the world and its annual increase. Phytotaxa, 261(3), 201-217.
• Chen, B., Liu, J., Sun, J., Liu, J. (2019). Flowers Classification via Deep Learning Models. http://noiselab.ucsd.edu/ECE228_2019/Reports/Report40.pdf (accessed November 10, 2021).
• Coban, O. (2021). IRText: An Item Response Theory-Based Approach for Text Categorization. Arabian Journal for Science and Engineering, 1-17.
• Erdem, E., & Aydin, T. (2021). A CNN-based hybrid model to detect Coronavirus disease. Avrupa Bilim ve Teknoloji Dergisi, (27), 66-73.
• FatihahSahidan, N., Juha, A. K., Mohammad, N., & Ibrahim, Z. (2019). Flower and leaf recognition for plant identification using convolutional neural network. Indonesian Journal of Electrical Engineering and Computer Science, 16(2), 737-743.
• Gadkari, S., Mathias, J., & Pansare, A. (2019). Analysis of Pre-Trained Convolutional Neural Networks to Build a Flower Classification System. International Journal for Research in Applied Science & Engineering Technology (IJRASET), 2321-9653, Vol 7, Issue 11.
• Ghazi, M. M., Yanikoglu, B., & Aptoula, E. (2017). Plant identification using deep neural networks via optimization of transfer learning parameters. Neurocomputing, 235, 228-235.
• Guo, B., Hu, J., Wu, W., Peng, Q., & Wu, F. (2019). The Tabu_genetic algorithm: a novel method for hyper-parameter optimization of learning algorithms. Electronics, 8(5), 579.
• Gurnani, A., Mavani, V., Gajjar, V. and Khandhediya, Y., (2017). Flower Categorization using Deep Convolutional Neural Networks, ArXiv, 4321-4324.
• Kim, P. (2017). Convolutional neural network. In MATLAB deep learning (pp. 121-147). Apress, Berkeley, CA.
• Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 25, 1097-1105.
• Li, Y., Hao, Z. B., & Lei, H. (2016). Survey of convolutional neural network. Journal of Computer Applications, 36(9), 2508-2515.
• Luus, F., Khan, N., & Akhalwaya, I. (2019). Active learning with tensorboard projector. arXiv preprint arXiv:1901.00675.
• Lv, R., Li, Z., Zuo, J., & Liu, J. (2021). Flower Classification and Recognition Based on Significance Test and Transfer Learning. In 2021 IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE) (pp. 649-652). IEEE.
• Madoui, S., Charef, N., Arrar, L., Baghianni, A., & Khennouf, S. (2018). In vitro Antioxidant Activities of Various Extracts from Flowers-Leaves Mixture of Algerian Cytisus triflorus. Annual Research & Review in Biology, 1-13.
• Mamaev, A., Flowers Recognition | Kaggle, (2018). https://www.kaggle.com/alxmamaev/flowers-recognition (accessed November 10, 2021).
• Mitrović, K., & Milošević, D. (2019). Flower classification with convolutional neural networks. In 2019 23rd International Conference on System Theory, Control and Computing (ICSTCC) (pp. 845-850). IEEE.
• Nahzat, S., & Yağanoğlu, M. (2021). Diabetes Prediction Using Machine Learning Classification Algorithms. Avrupa Bilim ve Teknoloji Dergisi, (24), 53-59.
• Narvekar, C., & Rao, M. (2020). Flower classification using CNN and transfer learning in CNN-Agriculture Perspective. In 2020 3rd International Conference on Intelligent Sustainable Systems (ICISS) (pp. 660-664). IEEE.
• Raj, A. P. S. S., & Vajravelu, S. K. (2019). DDLA: dual deep learning architecture for classification of plant species. IET Image Processing, 13(12), 2176-2182.
• Roddy, A. B., Jiang, G. F., Cao, K., Simonin, K. A., & Brodersen, C. R. (2019). Hydraulic traits are more diverse in flowers than in leaves. New Phytologist, 223(1), 193-203.
• Sangale, R., Jangada, R., De, A., Sanga, N., & Deokar, S. (2020). Flower Recognition Using Deep Learning. International Journal of Research Publication and Reviews Vol (1) Issue (8), 20-23.
• Seeland, M., Rzanny, M., Alaqraa, N., Wäldchen, J., & Mäder, P. (2017). Plant species classification using flower images—A comparative study of local feature representations. PloS one, 12(2), e0170629.
• Seeland, M., Rzanny, M., Boho, D., Wäldchen, J., & Mäder, P. (2019). Image-based classification of plant genus and family for trained and untrained plant species. BMC bioinformatics, 20(1), 1-13.
• Toğaçar, M., Ergen, B., & Özyurt, F. (2020). Evrişimsel Sinir Ağı Modellerinde Özellik Seçim Yöntemlerini Kullanarak Çiçek Görüntülerinin Sınıflandırılması. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, 32(1), 47-56.
• Turkoglu, M., & Hanbay, D. (2019). Plant Recognition System based on Deep Features and Color-LBP method. In 2019 27th Signal Processing and Communications Applications Conference (SIU) (pp. 1-4). IEEE.
• Voulodimos, A., Doulamis, N., Doulamis, A., & Protopapadakis, E. (2018). Deep learning for computer vision: A brief review. Computational intelligence and neuroscience, 2018.
• Wäldchen, J., & Mäder, P. (2018). Plant species identification using computer vision techniques: A systematic literature review. Archives of Computational Methods in Engineering, 25(2), 507-543.
• Yıldıran, S. T., Yanıkoğlu, B., & Abdullah, E. (2014). Plant identification using local invariants. In 2014 22nd Signal Processing and Communications Applications Conference (SIU) (pp. 2094-2097). IEEE.
• Zhang, Q., Yang, L. T., Chen, Z., & Li, P. (2018). A survey on deep learning for big data. Information Fusion, 42, 146-157.