Plant-Leaf Recognition Based on Sample Standardization and Transfer Learning
Source abstract
Abstract
In recent years, deep-learning methods have significantly improved the classification results in the field of plant-leaf recognition. However, limited by the model input, the original image needs to be compressed to a certain size before it can be input into the convolutional neural network. This results in great changes in the shape and texture information of some samples, thus affecting the classification accuracy of the model to a certain extent. Therefore, a minimum enclosing quadrate (MEQ) method is proposed to standardize the sample datasets. First, the minimum enclosing rectangle (MER) of the leaf is obtained in the original image, and the target area is clipped. Then, the minimum enclosing quadrate of the leaf is obtained by extending the short side of the rectangle. Finally, the sample is compressed to fit the input requirements of the model. In addition, in order to further improve the classification accuracy of plant-leaf recognition, an EC-ResNet50 model based on transfer-learning strategy is proposed and further combined with the MEQ method. The Swedish leaf, Flavia leaf, and MEW2012 leaf datasets are used to test the performance of the proposed methods, respectively. The experimental results show that using the MEQ method to standardize datasets can significantly improve the classification accuracy of neural networks. The Grad-CAM visual analysis reveals that the convolutional neural network exhibits a higher degree of attention towards the leaf surface features and utilizes more comprehensive feature regions during recognition of the leaf samples processed by MEQ method. In addition, the proposed MEQ + EC-ResNet50 method also achieved the best classification results among all the compared methods. This experiment provides a widely applicable sample standardization method for leaf recognition research, which can avoid the problem of sample deformation caused by compression processing and reduce the interference of redundant information in the image to the classification results to a certain degree.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Smart Agriculture and AI · Remote Sensing in Agriculture · Remote Sensing and Land Use
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Science, Northeast Forestry University, Hexing Road 26, Harbin 150040, China
Funding
Fundamental Research Funds for the Central Universities · Northeast Forestry University · Project of National Natural Science Foundation of China
References (37)
Show source-provided references
1. How many species of seed plants are there?10.2307/3647306 ↗
2. Plant leaf recognition by integrating shape and texture features10.1016/j.patcog.2020.107809 ↗
3. Plant recognition via leaf shape and margin features10.1007/s11042-019-07846-0 ↗
4. Invariant leaf image recognition with histogram of Gaussian convolution vectors10.1016/j.compag.2020.105714 ↗
5. Pyramided and optimized blurred shape model for plant leaf classification10.1049/ipr2.12830 ↗
6. Composite descriptor based on contour and appearance for plant species identification10.1016/j.engappai.2024.108291 ↗
7. TA-CNN: Two-way attention models in deep convolutional neural network for plant recognition10.1016/j.neucom.2019.07.016 ↗
8. Multiple attentional pyramid networks for Chinese herbal recognition10.1016/j.patcog.2020.107558 ↗
9. Leaf recognition using convolutional neural networks based features10.1007/s11042-022-13199-y ↗
10. Sun, X.B., Xu, L., Zhou, Y.F., and Shi, Y.J. (2023). Leaves and Twigs Image Recognition Based on Deep Learning and Combined Classifier Algorithms. Forests, 14.10.3390/f14061083 ↗
11. Plant leaf identification based on shape and convolutional features10.1016/j.eswa.2023.119626 ↗
12. Plant Leaf Recognition Method With New Convolution Neural Network
13. Overview of handcrafted features and deep learning models for leaf recognition10.36909/jer.v9i1.7737 ↗
14. Rice leaf diseases prediction using deep neural networks with transfer learning10.1016/j.envres.2021.111275 ↗
15. Automated tomato leaf disease classification using transfer learning-based deep convolution neural network10.1007/s41348-020-00403-0 ↗
16. Zhang, R.L., Zhu, Y.J., Ge, Z.S.J., Mu, H.B., Qi, D.W., and Ni, H.M. (2022). Transfer Learning for Leaf Small Dataset Using Improved ResNet50 Network with Mixed Activation Functions. Forests, 13.10.3390/f13122072 ↗
17. Zhou, D.X., Ma, X.T., and Feng, S. (2023). An Effective Plant Recognition Method with Feature Recalibration of Multiple Pretrained CNN and Layers. Appl. Sci., 13.10.3390/app13074531 ↗
18. A Threshold Selection Method from Gray-Level Histograms10.1109/TSMC.1979.4310076 ↗
19. He, K., Zhang, X., Ren, S., and Sun, J. (2015). Deep Residual Learning for Image Recognition. arXiv.10.1109/CVPR.2016.90 ↗
20. Shafiq, M., and Gu, Z.Q. (2022). Deep Residual Learning for Image Recognition: A Survey. Appl. Sci., 12.10.3390/app12188972 ↗
21. RSigELU: A nonlinear activation function for deep neural networks10.1016/j.eswa.2021.114805 ↗
22. Linearized sigmoidal activation: A novel activation function with tractable non-linear characteristics to boost representation capability10.1016/j.eswa.2018.11.042 ↗
23. Jiang, Y.Y., Xie, J.Y., and Zhang, D. (2022). An Adaptive Offset Activation Function for CNN Image Classification Tasks. Electronics, 11.10.3390/electronics11223799 ↗
24. Rectified Exponential Units for Convolutional Neural Networks10.1109/ACCESS.2019.2928442 ↗
25. Clevert, D.-A., Unterthiner, T., and Hochreiter, S. (2015). Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs). arXiv.
26. Ramachandran, P., Zoph, B., and Le, Q.V. (2018). Searching for Activation Functions. arXiv.
27. Wu, Z., Jiang, F., and Cao, R. (2022). Research on recognition method of leaf diseases of woody fruit plants based on transfer learning. Sci. Rep., 12.10.1038/s41598-022-18337-y ↗
28. Söderkvist, O. (2001). Computer Vision Classification of Leaves from Swedish Trees. [Master’s Thesis, Linköping University].
29. Shah, M.P., Singha, S., and Awate, S.P. (2017, January 17–20). Leaf classification using marginalized shape context and shape+texture dual-path deep convolutional neural network. Proceedings of the 2017 IEEE International Conference on Image Processing (ICIP), Beijing, China.10.1109/ICIP.2017.8296403 ↗
30. Multi-Organ Plant Classification Based on Convolutional and Recurrent Neural Networks10.1109/TIP.2018.2836321 ↗
31. How deep learning extracts and learns leaf features for plant classification10.1016/j.patcog.2017.05.015 ↗
32. Multiscale Fourier descriptor based on triangular features for shape retrieval10.1016/j.image.2018.11.004 ↗
33. MaskCOV: A random mask covariance network for ultra-fine-grained visual categorization10.1016/j.patcog.2021.108067 ↗
34. Simonyan, K., and Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv.
35. Wu, S.G., Bao, F.S., Xu, E.Y., Wang, Y.X., Chang, Y.F., and Xiang, Q.L. (2007, January 15–18). A Leaf Recognition Algorithm for Plant Classification Using Probabilistic Neural Network. Proceedings of the 2007 IEEE International Symposium on Signal Processing and Information Technology, Giza, Egypt.10.1109/ISSPIT.2007.4458016 ↗
36. Leaf recognition of woody species in Central Europe10.1016/j.biosystemseng.2013.04.007 ↗
37. Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization10.1007/s11263-019-01228-7 ↗