OMR Checker: Grade exams with scanner🖨 or phone 🤳 Robust. Fast. Free.

🎯 OMR Checker : What can it do for me? Just configure for your OMR layout once, then throw images of the sheets at it, you'll get back the graded responses in an excel sheet! See what kind of images it can support in attached images. 🎯 Features A full-fledged OMR checking software that can read and evaluate OMR sheets scanned at any angle and having any color. Support is also provided for a customisable marking scheme with section-wise marking, bonus questions, etc. 💯 Accurate - nearly 100% accurate on good quality scans. About 90% accurate on mobile images. 💪🏿 Robust - Please see attached images for a better feel of the robustness. ⏩ Fast - Current processing speed without any optimization : 200 Sheets/min. ✅ Extensible - Easily apply to different OMR layouts, surveys, etc. 📊 Visually Rich Outputs - get insights to debug and configure easily 🎈 Lightweight - Size is just 500 KB 📄 Simple Structure - inputs and outputs style. 👩🏿‍💻 Dev Friendly - Well documented repository based on python and openCV. 💁🏿‍♂️ User Friendly - You Decide! 💡 How do I give a review? We'd love to hear your inputs. Help us improve by doing the following. Non-Devs : See the code-in-action gifs above, or forward us your OMR images on discord (link on github). Live demo on Google Colab coming soon :) Devs : You can clone and run this project in less than 20 minutes(See guide on github). Please leave a star on github if you liked it! 🎯 Why is this software free? After seeing it work fabulously at large scale on scanned OMR sheets at Technothlon, we have decided to roll out mobile based scanning this year. The feedback from you all will be extremely valuable to make this initiative a success. Also, we want to take things to the next level! Motto: ✨ Don't reinvent the wheel, use good wheels to make great vehicles! ✨ 🏁 Project Progress 🏁 🥅__₂₀__⚽️_____₈₀______ 🏃‍♂️ Scope for improvement- 🚩 Faster Speeds : parallelization 🚩 Higher Robustness 🚩 Making a Testing Benchmark (Dataset coming very soon!) ✨ Note: Interesting work available in all tiers of challenges(Beginner to Advanced). We are looking for 🐱‍💻 computer vision enthusiasts to take it to the next level! ✨ 🎯 What can contributors learn from this project? In order of beginner to expert level: 🔰 Great learning experience to up your game in computer vision. 🔰 Intro to Opensource, Working with github 🔰 Visually rich outputs - for learning easily what is happening under the hood. 🔰 Working on large code base with well documented code 🔰 Dedicated Discord channel for doubts as well as open discussions 🔰 Get access to the Android OMR helper application 🔰 Learn Basics like developing an app like camscanner 🔰 Structured way of presenting the working via images. 🔰 Edge detection using OpenCV (used in self-driving vehicles/robot vision) 🔰 Working with contours (OCR/self-driving vehicles) 🔰 If your PR is accepted, this is a good project to add to your CV. 🔰 Out of the box use cases of popular techniques : morphology, adaptive threshold, outlier detection, reverse perspective transform, etc. 🔰 Example of when ML cannot easily bring solution to your table, CV never fails to impress! 💡 Can I use this code in my work? OMRChecker is an open source software published under GNU GPLv3 license which is just to give a heads up to disclose its usage in your code. OMRChecker can be forked and modified. We encourage you to play with it and would love to see your own projects in action! ⭐ Help us reach 550 stars to become #1 on the "OMR" tag on github!