{"id":15637487,"url":"https://github.com/adgaudio/ietk-ret","last_synced_at":"2025-10-18T01:39:43.885Z","repository":{"id":62570335,"uuid":"237892095","full_name":"adgaudio/ietk-ret","owner":"adgaudio","description":"Re-colorize and enhance color fundus images.  Image Enhancement Toolkit for Retinal Fundus Images (IETK-Ret).  ","archived":false,"fork":false,"pushed_at":"2021-11-29T00:47:08.000Z","size":38909,"stargazers_count":27,"open_issues_count":0,"forks_count":6,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-04-30T06:44:40.519Z","etag":null,"topics":["color","color-correction","dark-channel-prior","dehazing","image-enhancement","image-processing","medical-image-processing","pixel-color-amplification","retinal-fundus-images"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/adgaudio.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}},"created_at":"2020-02-03T05:30:30.000Z","updated_at":"2025-03-27T01:47:08.000Z","dependencies_parsed_at":"2022-11-03T17:15:40.859Z","dependency_job_id":null,"html_url":"https://github.com/adgaudio/ietk-ret","commit_stats":null,"previous_names":[],"tags_count":10,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adgaudio%2Fietk-ret","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adgaudio%2Fietk-ret/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adgaudio%2Fietk-ret/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adgaudio%2Fietk-ret/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/adgaudio","download_url":"https://codeload.github.com/adgaudio/ietk-ret/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251658196,"owners_count":21622819,"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":["color","color-correction","dark-channel-prior","dehazing","image-enhancement","image-processing","medical-image-processing","pixel-color-amplification","retinal-fundus-images"],"created_at":"2024-10-03T11:11:49.861Z","updated_at":"2025-10-18T01:39:38.844Z","avatar_url":"https://github.com/adgaudio.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# IETK-Ret - Image Enhancement Toolkit for Retinal Fundus Images\n\nThis repository contains a collection of enhancement methods useful for\nretinal fundus images, with emphasis on **Pixel Color Amplification**.  \nThese methods are very useful as a **pre-processing step to fundus image\nanalysis and machine learning**.  They have applicability to a wide\nvariety of image domains, but we focus on retinal fundus images.\n\nI would be happy to link to your paper in the \"papers\" section if you\nuse this code or method.  Please cite or acknowledge the below paper if you use\nthe code or method.  Thank you!\n\n\u003e A. Gaudio, A. Smailagic, A. Campilho, “Enhancement of Retinal Fundus Images via Pixel Color Amplification,” In: Karray F., Campilho A., Wang Z. (eds) Image Analysis and Recognition. ICIAR 2020. Lecture Notes in Computer Science, vol 11663. Springer, Cham (accepted)\n\n\n# Some Example Results\n\n![Example: correcting over-exposure](./iciar2020/pic1.png)\n![Example: correcting under-exposure](./iciar2020/pic2.png)\n![Example: improving segmentation](./iciar2020/pic3.png)\n![Example: several results](./iciar2020/pic4.png)\n\n# Papers:\n\n- [./iciar2020/](./iciar2020)  -  Code, slides and paper for the **Pixel Color Amplification paper** from ICIAR 2020.\n\n\u003c!-- It also contains the code used for the Pixel Color Amplification paper: --\u003e\n\u003c!-- todo --\u003e\n\u003c!-- [code](./iciar2020)  [paper: Pixel Color Amplification](TODO) --\u003e\n\n# Code:\n\n- `ietk.util` - methods to separate the fundus from the black background,\nas well as crop the image to minimize background.\n- `ietk.methods` - a set of enhancement methods, mostly based on pixel\ncolor amplification for brightening, darkening and sharpening.\n- `ietk.data` - access to the images in the IDRiD dataset for R\u0026D\n  (assuming you already downloaded the dataset)\n\n\n# Usage\n\n```\npip install ietk-ret\n```\n\n\n### Example usage:\n```\nfrom matplotlib import pyplot as plt\nfrom ietk import methods\nfrom ietk import util\nfrom ietk.data import IDRiD\n\n# load a fundus image, normalized into 0-1 range (not 0-255)\n# such as one from the IDRiD dataset  (assuming you already have it on disk)\ndset = IDRiD('./data/IDRiD_segmentation')\nimg_id, img, labels = dset.sample()\nprint(\"using image\", img_id)\n\n\n# crop fundus image and get a focus region  (a very useful function!)\nI = img.copy()\nI, fg = util.center_crop_and_get_foreground_mask(I)\n\n# enhance the image with an enhancement method from the ICIAR 2020 paper\n# (any combination of letters A,B,C,D,W,X,Y,Z and sA,sB,sC,... are supported)\nenhanced_img = methods.brighten_darken(I, 'A+B+X', focus_region=fg)\nenhanced_img2 = methods.sharpen(enhanced_img, bg=~fg)\n\n# plot results\nf, (ax1, ax2, ax3) = plt.subplots(1, 3)\nax1.imshow(img)\nax2.imshow(enhanced_img)\nax3.imshow(enhanced_img2)\nf.tight_layout()\n```\n\n# Disclaimer\n\nThis code, including the API and methods, may not be backwards\ncompatible between releases.  If you use it, fix the version, git tag or\ngit commit used in your requirements.txt file.\n\nI am not responsible or liable for your use of this code or methods.\nPlease *carefully* verify and ensure safety of its use in any production or\ndecision-making or clinical or other contexts.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fadgaudio%2Fietk-ret","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fadgaudio%2Fietk-ret","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fadgaudio%2Fietk-ret/lists"}