Estimation of leaf dimensions through image segmentation using a new annotated dataset

• Gabriela Singulani Marques UFJF
• João Victor Corrêa de Almeida UFJF
• Karla Gabriele Florentino da Silva UNICAMP
• Artur Ferreira de Castro UFJF
• João Pedro Lemos Guadalupe UFJF
• Vinícius Macuco Leite Carvalhaes UFJF
• Paulo Victor de Magalhães Rozatto UFJF
• Luiz Maurílio da Silva Maciel UFJF
• Marcelo Bernardes Vieira UFJF
• Saulo Moraes Villela UFJF

DOI: https://doi.org/10.5753/eniac.2026.31084

Resumo

The leaf is the plant organ responsible for photosynthesis, and its morphology provides important insights. Traditional methods for estimating leaf morphology are labor-intensive, while dedicated measurement devices present high financial costs. Computer vision–based approaches emerge as a cost-effective solution. In this work, we introduce a dataset of leaf images, each accompanied by a reference square pattern. The dataset includes high-quality segmentation masks and ground-truth leaf dimensions. We applied segmentation networks on this dataset and used the resulting masks to estimate leaf dimensions using an image processing method. The experiments establish baseline results for segmentation and leaf-dimension estimation on the proposed dataset.

Referências

Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., and Adam, H. (2018). Encoder-decoder with atrous separable convolution for semantic image segmentation. In Proceedings of the European conference on computer vision (ECCV), pages 801–818, Munich, Germany. ECCV.

Fan, X. et al. (2024). Plant functional traits modulate the effects of soil acidification on above- and belowground biomass. Biogeosciences, 21:2641–2656.

Giang, T. T. H. and Ryoo, Y.-J. (2024). Sweet pepper leaf area estimation using semantic 3d point clouds based on semantic segmentation neural network. AgriEngineering, 6(1):645–656.

Pandey, S. and Singh, H. (2011). A simple, cost-effective method for leaf area estimation. Journal of botany, 2011(1):658240.

Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 779–788.

Richardson, G. A., Lohani, H. K., Potnuru, C., Donepudi, L. P., and Pankajakshan, P. (2023). Phenobot: an automated system for leaf area analysis using deep learning. Planta, 257(2):36.

Roth-Nebelsick, A. and Krause, M. (2023). The plant leaf: A biomimetic resource for multifunctional and economic design. Biomimetics, 8(2):145.

Rozatto, P. V. M., Maciel, L. M. S., Vieira, M. B., and Villela, S. M. (2025). Development of an artificial intelligence-aided software for annotating image datasets. In Brazilian Symposium on Information Systems (SBSI), pages 105–114, Recife, Brazil.

Segreto, T. H., Negri, J. D., Polegato, P. H., Pinheiro, J. M. H., Godoy, R. V., and Becker, M. (2026). A leaf-level dataset for soybean-cotton detection and segmentation. Scientific Data.

Silva, K. G. F., Maciel, L. M. S., Villela, S. M., Pedrini, H., Morais, L. E., and Vieira, M. B. (2025a). Non-destructive leaf area estimation based on a semantic segmentation deep neural network. Computers and Electronics in Agriculture, 237:110551.

Silva, K. G. F., Moreira, J. M., Calixto, G. B., Maciel, L. M. S., Miranda, M. A., and Morais, L. E. (2023). A simple and low-cost method for leaf surface dimension estimation based on digital images. In 12th Brazilian Conference on Intelligent Systems, BRACIS 2023, pages 146–161. Springer.

Silva, K. G. F., Rozatto, P. V. M., Sousa, K. O., Hudson, L. D., Meyer, A. W. S., Silva, A. F., Mendes, I. T., Borges, A. R., Morais, L. E., Maciel, L. M. S., Villela, S. M., Pedrini, H., and Vieira, M. B. (2025b). Bean leaf image dataset annotated with leaf dimensions, segmentation masks, and camera calibration. Data in Brief, 59:111328.

Tang, S., Sun, T., Peng, J., Chen, G., Hao, Y., Lin, M., Xiao, Z., You, J., and Liu, Y. (2023). Pp-mobileseg: Explore the fast and accurate semantic segmentation model on mobile devices. arXiv preprint arXiv:2304.05152.

Tech, A. R. B., Silva, A. L. C., Meira, L. A., Oliveira, M. E., and Pereira, L. E. T. (2018). Methods of image acquisition and software development for leaf area measurements in pastures. Computers and Electronics in Agriculture, 153:278–284.

Tong, R., Yang, X., Wang, Q., Li, L., Shi, Y., Mu, C., and Wang, J. (2023). The shift in key functional traits caused by precipitation under nitrogen and phosphorus deposition drives biomass change in leymus chinensis. Plants, 12(9):1781.

Zhang, Y. et al. (2025). Leaf ecological traits (morphology and gas exchange) and polycyclic aromatic hydrocarbons concentrations in shrubs and trees: A meta-analysis approach. Environmental Pollution, 364:125337.