Regression in Convolutional Neural Networks applied to Plant Leaf Counting
Resumo
Recent studies have shown that computer vision techniques developed to boost the count of plant leaves brings significant improvements. In this paper, a proposal was presented for plant leaf counting using Convolutional Neural Networks (CNNs). To accomplish the training process, CNNs architectures were adapted to solve regression problems. To evaluate the proposed method, an image dataset with 810 images of three species (Arabidopsis, Tobacco and one mutation) was used. The results showed that Xception architecture obtained the best results with R2 of 0.96 and MAE (mean absolute error) of 0.46.
Palavras-chave:
convolutional neural networks, leaf counting,
Regression
Referências
Ministério da agricultura, pecuária e abastecimento. agricultura: agropecuária puxa o pib de http://www.agricultura.gov.br/noticias/agropecuaria-puxa-o-pib-de2017.2018.
C. A. F.de SOUSA. Fenotipagem de plantas: As novas técnicas que estão surgindo para atender aos desafios atuais e futuros, 2014.
Frederick B. Churchill. Wilhelm johannsen's genotype-phenotype distinction. Journal of the History of Biology, 7 : 5 - 30, DOI: 10.1007/bf00179291
M. Minervini, H. Scharr, and S. A. Tsaftaris. Image analysis: The new bottleneck in plant phenotyping [applications corner]. IEEE Signal Processing Magazine, 32 (4): 126 - 131, July DOI: 10.1109/msp.2015.2405111
Mengye Ren and Richard S. Zemel. End-to-end instance segmentation and counting with recurrent attention. CoRR, abs/1605.09410, DOI: 10.1109/cvpr.2017.39
Bernardino Romera-Paredes and Philip H. S. Torr. Recurrent instance segmentation. CoRR, abs/1511.08250, DOI: 10.1007/978-3-319-46466-4_19
Andrei Dobrescu, Mario Valerio Giuffrida, and Sotirios A. Tsaftaris. Leveraging multiple datasets for deep leaf counting. CoRR, abs/1709.01472, DOI: 10.1101/185173
Massimo Minervini, Andreas Fischbach, Hanno Scharr, and Sotirios A. Tsaftaris. Finely-grained annotated datasets for image-based plant phenotyping. Pattern Recognition Letters, 81 : 80 - 89, DOI: 10.1016/j.patrec.2015.10.013
Hanno Scharr, Massimo Minervini, Andreas Fischbach, and Sotirios Tsaftaris. Annotated image datasets of rosette plants, 07 2014.
Jonathan Bell and Hannah M. Dee. Aberystwyth leaf evaluation dataset, November 2016.
Jordan Ubbens, Mikolaj Cieslak, Przemyslaw Prusinkiewicz, and Ian Stavness. The use of plant models in deep learning: an application to leaf counting in rosette plants. Plant Methods, 14 (1):6, Jan DOI: 10.1186/s13007-018-0273-z
Shubhra Aich and Ian Stavness. Leaf counting with deep convolutional and deconvolutional networks. CoRR, abs/1708.07570, DOI: 10.1109/iccvw.2017.244
François Chollet. Xception: Deep learning with depthwise separable convolutions. CoRR, abs/1610.02357, DOI: 10.1109/cvpr.2017.195
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. CoRR, abs/1512.03385, DOI: 10.1109/cvpr.2016.90
Christian Szegedy, Sergey Ioffe, and Vincent Vanhoucke. Inceptionv4, inception-resnet and the impact of residual connections on learning. CoRR, abs/1602.07261
Barret Zoph, Vijay Vasudevan, Jonathon Shlens, and Quoc V. Le. Learning transferable architectures for scalable image recognition. CoRR, abs/1707.07012, DOI: 10.1109/cvpr.2018.00907
J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei. ImageNet: A Large-Scale Hierarchical Image Database. In CVPR09, DOI: 10.1109/cvprw.2009.5206848
Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens, and Zbigniew Wojna. Rethinking the inception architecture for computer vision. CoRR, abs/1512.00567, DOI: 10.1109/cvpr.2016.308
C. A. F.de SOUSA. Fenotipagem de plantas: As novas técnicas que estão surgindo para atender aos desafios atuais e futuros, 2014.
Frederick B. Churchill. Wilhelm johannsen's genotype-phenotype distinction. Journal of the History of Biology, 7 : 5 - 30, DOI: 10.1007/bf00179291
M. Minervini, H. Scharr, and S. A. Tsaftaris. Image analysis: The new bottleneck in plant phenotyping [applications corner]. IEEE Signal Processing Magazine, 32 (4): 126 - 131, July DOI: 10.1109/msp.2015.2405111
Mengye Ren and Richard S. Zemel. End-to-end instance segmentation and counting with recurrent attention. CoRR, abs/1605.09410, DOI: 10.1109/cvpr.2017.39
Bernardino Romera-Paredes and Philip H. S. Torr. Recurrent instance segmentation. CoRR, abs/1511.08250, DOI: 10.1007/978-3-319-46466-4_19
Andrei Dobrescu, Mario Valerio Giuffrida, and Sotirios A. Tsaftaris. Leveraging multiple datasets for deep leaf counting. CoRR, abs/1709.01472, DOI: 10.1101/185173
Massimo Minervini, Andreas Fischbach, Hanno Scharr, and Sotirios A. Tsaftaris. Finely-grained annotated datasets for image-based plant phenotyping. Pattern Recognition Letters, 81 : 80 - 89, DOI: 10.1016/j.patrec.2015.10.013
Hanno Scharr, Massimo Minervini, Andreas Fischbach, and Sotirios Tsaftaris. Annotated image datasets of rosette plants, 07 2014.
Jonathan Bell and Hannah M. Dee. Aberystwyth leaf evaluation dataset, November 2016.
Jordan Ubbens, Mikolaj Cieslak, Przemyslaw Prusinkiewicz, and Ian Stavness. The use of plant models in deep learning: an application to leaf counting in rosette plants. Plant Methods, 14 (1):6, Jan DOI: 10.1186/s13007-018-0273-z
Shubhra Aich and Ian Stavness. Leaf counting with deep convolutional and deconvolutional networks. CoRR, abs/1708.07570, DOI: 10.1109/iccvw.2017.244
François Chollet. Xception: Deep learning with depthwise separable convolutions. CoRR, abs/1610.02357, DOI: 10.1109/cvpr.2017.195
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. CoRR, abs/1512.03385, DOI: 10.1109/cvpr.2016.90
Christian Szegedy, Sergey Ioffe, and Vincent Vanhoucke. Inceptionv4, inception-resnet and the impact of residual connections on learning. CoRR, abs/1602.07261
Barret Zoph, Vijay Vasudevan, Jonathon Shlens, and Quoc V. Le. Learning transferable architectures for scalable image recognition. CoRR, abs/1707.07012, DOI: 10.1109/cvpr.2018.00907
J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei. ImageNet: A Large-Scale Hierarchical Image Database. In CVPR09, DOI: 10.1109/cvprw.2009.5206848
Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens, and Zbigniew Wojna. Rethinking the inception architecture for computer vision. CoRR, abs/1512.00567, DOI: 10.1109/cvpr.2016.308
Publicado
09/09/2019
Como Citar
DA SILVA, Neemias Bucéli; GONÇALVES, Wesley Nunes.
Regression in Convolutional Neural Networks applied to Plant Leaf Counting. In: WORKSHOP DE VISÃO COMPUTACIONAL (WVC), 15. , 2019, São Bernardo do Campo.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2019
.
p. 49-54.
DOI: https://doi.org/10.5753/wvc.2019.7627.
