{"id":14970721,"url":"https://github.com/ecodynizw/imageseg","last_synced_at":"2025-10-30T15:40:14.911Z","repository":{"id":52379166,"uuid":"433785862","full_name":"EcoDynIZW/imageseg","owner":"EcoDynIZW","description":"R package for deep learning image segmentation","archived":false,"fork":false,"pushed_at":"2023-11-17T02:16:21.000Z","size":18116,"stargazers_count":18,"open_issues_count":0,"forks_count":2,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-31T19:12:13.423Z","etag":null,"topics":["image-segmentation","keras","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"R","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/EcoDynIZW.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2021-12-01T10:43:10.000Z","updated_at":"2024-11-23T19:15:22.000Z","dependencies_parsed_at":"2023-11-21T22:07:45.925Z","dependency_job_id":"99ecf960-ff75-4884-a95c-06dae45a13aa","html_url":"https://github.com/EcoDynIZW/imageseg","commit_stats":{"total_commits":48,"total_committers":1,"mean_commits":48.0,"dds":0.0,"last_synced_commit":"ebf161bdf39c382d85dee9f7c4be68d25bd06b77"},"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EcoDynIZW%2Fimageseg","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EcoDynIZW%2Fimageseg/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EcoDynIZW%2Fimageseg/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EcoDynIZW%2Fimageseg/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/EcoDynIZW","download_url":"https://codeload.github.com/EcoDynIZW/imageseg/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":238337323,"owners_count":19455290,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["image-segmentation","keras","tensorflow"],"created_at":"2024-09-24T13:44:02.532Z","updated_at":"2025-10-26T13:31:13.867Z","avatar_url":"https://github.com/EcoDynIZW.png","language":"R","funding_links":[],"categories":[],"sub_categories":[],"readme":"# imageseg\n\nR package for deep learning image segmentation using the U-Net model architecture by Ronneberger (2015), implemented in Keras and TensorFlow. It provides pre-trained models for forest structural metrics (canopy density and understory vegetation density) and a workflow to apply these on custom images.\n\nIn addition, it provides a workflow for easily creating model input and model architectures for general-purpose image segmentation based on the U-net architecture. Model can be trained on grayscale or color images, and can provide binary or multi-class image segmentation as output.\n\nThe package can be found on CRAN: \n\nhttps://cran.r-project.org/web/packages/imageseg/index.html\n\nThe preprint of the paper describing the package is available on bioRxiv:\n\nhttps://doi.org/10.1101/2021.12.16.469125\n\n\n# Installation\n\nFirst, install the R package \"R.rsp\" which enables the static vignettes. \n\n``` r\ninstall.packages(R.rsp)\n``` \n\nInstall the imageseg package from CRAN via:\n\n``` r\ninstall.packages(imageseg)\n``` \n\nAlternatively you can install from GitHub (requires remotes package and R.rsp):\n\n``` r\nlibrary(remotes)   \ninstall_github(\"EcoDynIZW/imageseg\", build_vignettes = TRUE)\n```\n\nUsing imageseg requires Keras and TensorFlow. See the vignette for information about installation and initial setup:\n\n# Tutorial\n\nSee the vignette for an introduction and tutorial to imageseg.\n\n``` r\nbrowseVignettes(\"imageseg\")\n```\n\nThe vignette covers:\n\n* Installation and setup\n* Sample workflow for canopy density assessments\n* Training new models\n* Continued training of existing models\n* Multi-class image segmentation models\n* Image segmentation based on grayscale images\n\n\n\n# Forest structure model download\n\nThe models, example predictions, training data and R script for model training for both the canopy and understory model are available from Dryad as a single download:\n\nhttps://doi.org/10.5061/dryad.x0k6djhnj\n\n\nSee the \"Usage Notes\" section for details on the dataset. \n\n\nThe models and script (without the training data) are also hosted on Zenodo and can be downloaded individually from:\n\nhttps://doi.org/10.5281/zenodo.6861157\n\nThe **pre-trained models** for forest canopy density and understory vegetation density are available for download. The zip files contain the model (as .hdf5 files) and **example classifications** to give an impression of model performance and output:\n\n*Canopy model*: https://zenodo.org/record/6861157/files/imageseg_canopy_model.zip?download=1\n\n*Understory model*: https://zenodo.org/record/6861157/files/imageseg_understory_model.zip?download=1\n\n\nPlease see the vignette for further information on how to use these models.\n\n\n\n# Training data download\n\nTraining data for both the canopy and understory model are included in the Dryad dataset download in the zip files:\n\n*imageseg_canopy_training_data.zip* \n\n*imageseg_understory_training_data.zip*\n\nFor details, please see the Usage Notes and the info.txt files contained in the zip files.\n\nThe training data are not required for users who only wish to use the pre-trained models on their own images.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fecodynizw%2Fimageseg","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fecodynizw%2Fimageseg","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fecodynizw%2Fimageseg/lists"}