{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/deep-leaf-segmentation-using-synthetic-data","title":"Deep Leaf Segmentation Using Synthetic Data","arxiv_id":"1807.10931","date":"2018-07-28","proceeding":null,"authors":["Daniel Ward","Peyman Moghadam","Nicolas Hudson"],"abstract":"Automated segmentation of individual leaves of a plant in an image is a\nprerequisite to measure more complex phenotypic traits in high-throughput\nphenotyping. Applying state-of-the-art machine learning approaches to tackle\nleaf instance segmentation requires a large amount of manually annotated\ntraining data. Currently, the benchmark datasets for leaf segmentation contain\nonly a few hundred labeled training images. In this paper, we propose a\nframework for leaf instance segmentation by augmenting real plant datasets with\ngenerated synthetic images of plants inspired by domain randomisation. We train\na state-of-the-art deep learning segmentation architecture (Mask-RCNN) with a\ncombination of real and synthetic images of Arabidopsis plants. Our proposed\napproach achieves 90% leaf segmentation score on the A1 test set outperforming\nthe-state-of-the-art approaches for the CVPPP Leaf Segmentation Challenge\n(LSC). Our approach also achieves 81% mean performance over all five test\ndatasets.","url_abs":"http://arxiv.org/abs/1807.10931v3","url_pdf":"http://arxiv.org/pdf/1807.10931v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"deep-leaf-segmentation-using-synthetic-data","repo_url":"https://github.com/DanielCWard/Deep-Leaf-Segmentation-Using-Synthetic-Data","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"deep-leaf-segmentation-using-synthetic-data","repo_url":"https://github.com/csiro-robotics/UPGen-Webpage","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"deep-leaf-segmentation-using-synthetic-data","repo_url":"https://github.com/csiro-robotics/UPGen_Webpage","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.10931","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}