Dynamic ensemble selection of convolutional neural networks and its application in flower classification

Zhibin Wang, Kaiyi Wang, Xiaofeng Wang, Shouhui Pan, Xiaojun Qiao

Abstract


In recent years, convolutional neural networks (CNNs) have achieved great success in image classification. However, CNN models usually have complex network structures that tend to cause some related problems, such as redundancy of network parameters, low training efficiency, overfitting, and weak generalization ability. To solve these problems and improve the accuracy of flower classification, the advantages of CNNs were combined with those of ensemble learning and a method was developed for the dynamic ensemble selection of CNNs. First, MobileNet models pre-trained on a public dataset were transferred to flower datasets to train thirteen different MobileNet classifiers, and a resampling strategy was used to enhance the diversity of individual models. Second, the thirteen classifiers were sorted by a classifier sorting algorithm, before ensemble selection, to avoid an exhaustive search. Finally, with the credibility of recognition results, a classifier subset was dynamically selected and integrated to identify the flower species from their images. To verify the effectiveness, the proposed method was used to classify the images of five flower species. The accuracy of the proposed method was 95.50%, an improvement of 1.62%, 3.94%, 22.04%, 13.77%, and 0.44%, over those of MobileNet, Inception-v1, ResNet-50, Inception-ResNet-v2, and the linear ensemble method, respectively. In addition, the performance of the proposed method was compared with five other methods for flower classification. The experimental results demonstrated the accuracy and robustness of the proposed method.
Keywords: flowers, classification, convolutional neural network, dynamic ensemble selection
DOI: 10.25165/j.ijabe.20221501.6313

Citation: Wang Z B, Wang K Y, Wang X F, Pan S H, Qiao X J. Dynamic ensemble selection of convolutional neural networks and its application in flower classification. Int J Agric & Biol Eng, 2022; 15(1): 216–223.

Keywords


flowers, classification, convolutional neural network, dynamic ensemble selection

Full Text:

PDF

References


Han J, Jin C, Wu L. Research on accuracy of flower recognition application based on convolutional neural. Advances in Intelligent Systems and Computing, 2019; 965: 224–232.

Yuan P, Li W, Ren S, Xu H. Recognition for flower type and variety of chrysanthemum with convolutional neural network. Transactions of the CSAE, 2018; 34(5): 152–158. (in Chinese)

Lee H, Hong K. Automatic recognition of flower species in the natural environment. Image and Vision Computing, 2017; 61: 98–114.

Hsu T, Lee C, Chen L. An interactive flower image recognition system. Multimedia Tools and Applications, 2011; 53(1): 53–73.

Guru D S, Kumar Y H S, Manjunath S. Textural features in flower classification. Mathematical and Computer Modelling, 2011; 54: 1030–1036.

Cheng K, Tan X. Sparse representations based attribute learning for flower classification. Neurocomputing, 2014; 145: 416–426.

Soleimanipour A, Chegini G R. A vision-based hybrid approach for identification of Anthurium flower cultivars. Computers and Electronics in Agriculture, 2020; 174: 1–8.

LeCun Y, Bengio Y, Hinton G. Deep learning. Nature, 2015; 521: 436–444.

Wang W, Yang Y, Wang X, Wang W, Li J. Development of convolutional neural network and its application in image classification: A survey. Optical Engineering, 2019; 58(4): 1–9.

Khan A, Sohail A, Zahoora U, Qureshi A S. A survey of the recent architectures of deep convolutional neural networks. Artificial Intelligence Review, 2020; 53: 5355–5516.

Cıbuk M, Budak U, Guo Y, Cevdet Ince M, Sengur A. Efficient deep features selections and classification for flower species recognition. Measurement, 2019; 137: 7–13.

Guo B, Hu J, Wu W, Peng Q, Wu F. The Tabu_Genetic algorithm: A novel method for hyper-parameter optimization of learning algorithms. Electronics, 2019; 8(5): 579. doi: 10.3390/electronics800579.

Toğaçar M, Ergen B, Cömert Z. Classification of flower species by using features extracted from the intersection of feature selection methods in convolutional neural network models. Measurement, 2020; 158: 107703. doi: 101016/j.measurement.2020.107703.

Hiary H, Saadeh H, Saadeh M, Yaqub M. Flower classification using deep convolutional neural networks. IET Computer Vision, 2018; 12(6): 855–862.

Mitrovic K, Milosevic D. Flower classification with convolutional neural networks. 23th International Conference on System Theory, Control and Computing. Sinaia: IEEE, 2019; pp.845–850.

Dong X, Yu Z, Cao W, Shi Y, Ma Q. A survey on ensemble learning. Frontiers of Computer Science, 2020; 14: 241–258.

Li J, Wu S, Liu C, Yu Z, Wong H. Semi-supervised deep coupled ensemble learning with classification landmark exploration. IEEE Transactions on Image Processing, 2020; 29: 538–550.

Zvarevashe K, Olugbara O. Ensemble learning of hybrid acoustic features for speech emotion recognition. Algorithms, 2020; 13(3): 70. doi: 10.3390/a13030070.

Yang X, Xu Y, Quan Y, Ji H. Image denoising via sequential ensemble learning. IEEE Transactions on Image Processing, 2020; 29: 5038–5049.

Bae K I, Park J, Lee J, Lee Y, Lim C. Flower classification with modified multimodal convolutional neural networks. Expert System with Applications, 2020; 159: 113455. doi: 10.1016/j.eswa.2020.113455.

Huang B, Hu Y, Sun Y, Hao X, Yan C. A flower classification framework based on ensemble of CNNs. PCM 2018. Lecture Notes in Computer Science, 2018; 11166: 235–244.

Wang Z, Wang K, Wang X, Pan S. A convolutional neural network ensemble for flower image classification. 9th International Conference on Computing and Pattern Recognition. Xiamen: ACM, 2020; pp.225–230.

Li H, Wang X, Ding S. Research and development of neural network ensembles: a survey. Artificial Intelligence Review, 2018; 49(4): 455–479.

Akbari E, Dahlan H M, Ibrahim R, Alizadeh H. Hierarchical cluster ensemble selection. Engineering Applications of Artificial Intelligence, 2015; 39:146–156.

Yin X, Huang K, Hao H. DE2: dynamic ensemble of ensembles for learning nonstationary data. Neurocomputing, 2015; 165: 14–22.

Flower dataset. Available: http://download.tensorflow.org/data/ flowers.tar.gz. Accessed on [2020-02-18].

Subject Database of China Plant. Available: http://www.plant.csdb.cn/photo. Accessed on [2020-02-20].

Howard A G, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, et al. MobileNets: efficient convolutional neural networks for mobile vision applications. 2017; arXiv: 1704.04861.

Yan Y, Yin X C, Wang Z B, Yin X W, Yang C, Hao H W. Sorting-based dynamic classifier ensemble selection. 12th International Conference on Document Analysis and Recognition, Washington: IEEE, 2013; pp.673–677. doi: 10.1109/ICDAR.2013.138.

Cruz R M O, Sabourin R, Cavalcanti G D C. Dynamic classifier selection: recent advances and perspectives. Information Fusion, 2018; 41: 195–216.

Alam K M R, Siddique N, Adeli H. A dynamic ensemble learning algorithm for neural networks. Neural Computing and Applications, 2020; 32: 8675–8690.

Tang E, Suganthan P N, Yao X. An analysis of diversity measures. Machine Learning, 2006; 65(1): 247–271.

Bishop C M. Pattern recognition and machine learning. Springer Science+Business Media, LLC. 2006; 68p.

Liu C. Classifier combination based on confidence transformation. Pattern Recognition, 2005; 38: 11–28.

Luus F, Khan N, Akhalwaya I. Active learning with TensorBoard, 2019; arXiv: 1901.00675.

Chen B, Liu J, Sun J, Liu J. Flowers classification via deep learning models. Available: http://noiselab.ucsd.edu/ECE228/Posters/Group40.pdf. Accessed on [2019-07-25]

Rahman M A, Kuswari A Y. Klasifikasi Jenis Bunga menggunakan SVM dengan Fitur HSV dan HOG. Yukiyu Science. Available: http://eprints.mdp.ac.id/id/eprint/2657. Accessed on [2020-03-16].

Han Y Y, Wang K Y, Liu Z Q, Pan S H, Zhao X Y, et al. Golden seed breeding cloud platform for the management of crop breeding material and genealogical tracking. Computers and Electronics in Agriculture, 2018; 152: 206–214.

Yue Y, Zhao G, Sun R. Breeding data service platform based on the new architecture of cloud technology. 3th Advanced Information Technology, Electronic and Automation Control Conference, Chongqing: IEEE, 2018; pp.1457–1463.

Chen S, Gao H, Li L, Liu Y. An information acquisition and management system for maize breeding. In: 6th IEEE International Conference on Software Engineering and Service Science, Beijing: IEEE, 2015; pp.807–813. doi: 10.1109/ICSESS.2015.7339179.

Han Y Y, Wang K Y, Liu Z Q, Pan S H, Zhao X Y, et al. A crop trait information acquisition system with multitag-based identification technologies for breeding precision management. Computers and Electronics in Agriculture, 2017; 135: 71–80.




Copyright (c) 2022 International Journal of Agricultural and Biological Engineering

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

2023-2026 Copyright IJABE Editing and Publishing Office