Metric learning for image-based flower cultivars identification

Plant Methods - Tập 17 - Trang 1-14 - 2021
Ruisong Zhang1, Ye Tian1, Junmei Zhang1, Silan Dai2, Xiaogai Hou3, Jue Wang2, Qi Guo3
1College of Technology, Beijing Forestry University, Beijing, China
2College of Landscape Architecture, Beijing Forestry University, Beijing, China
3College of Agriculture / College of Tree Peony, Henan University of Science and Technology, Luoyang, China

Tóm tắt

The study of plant phenotype by deep learning has received increased interest in recent years, which impressive progress has been made in the fields of plant breeding. Deep learning extremely relies on a large amount of training data to extract and recognize target features in the field of plant phenotype classification and recognition tasks. However, for some flower cultivars identification tasks with a huge number of cultivars, it is difficult for traditional deep learning methods to achieve better recognition results with limited sample data. Thus, a method based on metric learning for flower cultivars identification is proposed to solve this problem. We added center loss to the classification network to make inter-class samples disperse and intra-class samples compact, the script of ResNet18, ResNet50, and DenseNet121 were used for feature extraction. To evaluate the effectiveness of the proposed method, a public dataset Oxford 102 Flowers dataset and two novel datasets constructed by us are chosen. For the method of joint supervision of center loss and L2-softmax loss, the test accuracy rate is 91.88%, 97.34%, and 99.82% across three datasets, respectively. Feature distribution observed by T-distributed stochastic neighbor embedding (T-SNE) verifies the effectiveness of the method presented above. An efficient metric learning method has been described for flower cultivars identification task, which not only provides high recognition rates but also makes the feature extracted from the recognition network interpretable. This study demonstrated that the proposed method provides new ideas for the application of a small amount of data in the field of identification, and has important reference significance for the flower cultivars identification research.

Tài liệu tham khảo

Rousseau D, Dee H, Pridmore T. Imaging methods for phenotyping of plant traits. Phenomics in Crop Plants: Trends, Options and Limitations. 2015. p. 61-74.

Scharr H, Dee H, French AP, Tsaftaris SA. Special issue on computer vision and image analysis in plant phenotyping. Machine Vision Appl. 2016;27:607–9.

Bonnet P, Joly A, Goeau H, Champ J, Vignau C, Molino JF, Barthelemy D, Boujemaa N. Plant identification: man vs machine LifeCLEF 2014 plant identification challenge. Multimedia Tools Appl. 2016;75(3):1647–65.

Tsaftaris SA, Minervini M, Scharr H. Machine learning for plant phenotyping needs image processing. Trends Plant Sci. 2016;21(12):989–91.

Pound MP, Atkinson JA, Townsend AJ, Wilson MH, Griffiths M, Jackson AS, et al. Deep machine learning provides state-of-the-art performance in image-based plant phenotyping. Gigascience. 2017;6:1–10.

Ubbens JR, Stavness I. Deep plant phenomics: a deep learning platform for complex plant phenotyping tasks. Front Plant Sci. 2017.

Sun Y, Liu Y, Wang G, Zhang H. Deep learning for plant identification in natural environment. Comput Intell Neurosci. 2017;2017(4):7361042.

Ghosal S, Blystone D, Singh AK, Ganapathysubramanian B, Sarkar S. An explainable deep machine vision framework for plant stress phenotyping. Proc Natl Acad Sci USA. 2018;115(18):4613–8.

Lee SH, Chan CS, Wilkin P, Remagnino P. Deep-plant: plant identification with convolutional neural networks. IEEE International Conference on Image Processing (ICIP); 2015. p. 452-456.

Nguyen N, Le V T, Le T L, Hai V. Flower species identification using deep convolutional neural networks. AUN/SEED-Net Regional Conference on Computer and Information Engineering (RCCIE). 2016.

Gurnani A, Mavani V. Flower categorization using deep convolutional neural networks. 2017.

Hiary H, Saadeh H, Saadeh M, Yaqub M. Flower classification using deep convolutional neural networks. IET Comput Vision. 2018;12(6):855–62.

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

Liu ZL, Wang J, Tian Y, Dai SL. Deep learning for image-based large-flowered chrysanthemum cultivar recognition. Plant Methods. 2019;15:146.

LeCun YA, Bengio Y, Hinton GE. Deep learning. Nature. 2015;521:436–44.

Michael F. Object Classification from a Single Example Utilizing Class Relevance Metrics. Proceedings of the 17th International Conference on Neural Information Processing Systems; 2004. p. 449–456.

Lu J, Gong PH, Ye JP, Zhang CS. Learning from Very Few Samples: A Survey. 2020.

Koch G, Zemel R, Salakhutdinov R. Siamese neural networks for one-shot image recognition. International Conference on Machine Learning. 2015.

Li W, Xu J, Huo J, Wang L, Gao Y, Luo J. Distribution Consistency Based Covariance Metric Networks for Few-Shot Learning. Proc AAAI Conference Artificial Intell. 2019;33(01):8642–9.

Shulin Z, Silan D. Chinese chrysanthemum book. Beijing: China Forestry Publishing House; 2013. (in Chinese).

Wen Y, Zhang K, Li Z, Qiao Y. A Discriminative Feature Learning Approach for Deep Face Recognition. Europeon Conference on Computer Vision (ECCV); 2016. p. 499-515.

Ranjan R, Castillo C, Chellappa R. L2-constrained Softmax Loss for Discriminative Face Verification. 2017.

Chen T, Kornblith S, Norouzi M, Hinton G. A Simple Framework for Contrastive Learning of Visual Representations. Proceedings of the 37th International Conference on Machine Learning, PMLR. 2020;119: 1597-1607.

Nilsback M, Zisserman A. Automated Flower Classification over a Large Number of Classes. Proceedings of the 2008 Sixth Indian Conference on Computer Vision, Graphics & Image; 2008. p. 722-729.

Geirhos R, Rubisch P, Michaelis C, Bethge M, Wichmann F, Brendel W. ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. 2018.

He K, Zhang X, Ren S, Jian S, editors. Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2016. p. 770-778.

Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M, Berg A, Li F. ImageNet large scale visual recognition challenge. Int J Comput Vision. 2015;115(3):211–52.

Hermans A, Beyer L, Leibe B. In defense of the triplet loss for person re-identification. 2017.

He K, Zhang X, Ren S, Sun J. Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification. Proceedings of the IEEE International Conference on Computer Vision (ICCV); 2015. p. 1026-1034.

Laurens VDM, Hinton G. Visualizing Data using t-SNE. J Machine Learning Res. 2008;9(86):2579–605.

Bau D, Zhou B, Khosla A, Oliva A, Torralba A. Network Dissection: Quantifying Interpretability of Deep Visual Representations. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017. p. 3319-3327.

Thông tin
Thông tin xuất bản

Plant Methods

Tập 17

1-14

Thông tin tác giả