Curated educational list for computer vision
Reference Books
| Book | Links |
|---|---|
| González, Rafael Corsino and Richard E. Woods. “Digital image processing, 4th Edition.” (2018). | goodreads |
| Prince, Simon. “Computer Vision: Models, Learning, and Inference.” (2012). | goodreads |
| Forsyth, David Alexander and Jean Ponce. “Computer Vision - A Modern Approach, Second Edition.” (2011). | goodreads |
| Szeliski, Richard. “Computer Vision - Algorithms and Applications.” Texts in Computer Science (2010). | goodreads |
| Bishop, Charles M.. “Pattern recognition and machine learning, 5th Edition.” Information science and statistics (2007). | goodreads |
| Harltey, Andrew and Andrew Zisserman. “Multiple view geometry in computer vision (2. ed.).” (2003). | goodreads |
| Stockman, George C. and Linda G. Shapiro. “Computer Vision.” (2001). | goodreads |
Online Courses
| Course | Tags | Platform |
|---|---|---|
| Introduction to Python Programming | Programming |
Udacity |
| Learning Python | Programming |
LinkedIn Learning |
| Intro to Data Science | Data Science |
Udacity |
| Intro to Data Analysis | Data Science |
Udacity |
| Python Data Analysis | Data Science |
LinkedIn Learning |
| Segmentation and Clustering | Data Science |
Udacity |
| Python for Data Science Essential Training Part 1 | Data Science |
LinkedIn Learning |
| Python for Data Science Essential Training Part 2 | Data Science |
LinkedIn Learning |
| Introduction to Machine Learning Course | Machine Learning |
Udacity |
| Machine Learning with Scikit-Learn | Machine Learning |
LinkedIn Learning |
| Intro to Deep Learning with PyTorch | Deep Learning |
Udacity |
| Introduction to Computer Vision | Computer Vision |
Udacity |
| OpenCV for Python Developers | Computer Vision |
LinkedIn Learning |
Uni Courses
| Course | Tags | University |
|---|---|---|
| Introduction to Computer Vision | Computer Vision |
Brown |
| Advances in Computer Vision | Computer Vision |
MIT |
| Deep Learning for Computer Vision | Computer Vision Deep Learning |
Stanford |
YouTube Playlists
| Course | Year | Instructor | University |
|---|---|---|---|
| Computer Vision | 2021 | Andreas Geiger | University of Tübingen |
| Computer Vision | 2021 | Yogesh S Rawat / Mubarak Shah | University of Central Florida |
| Advanced Computer Vision | 2021 | Mubarak Shah | University of Central Florida |
| Deep Learning for Computer Vision | 2020 | Justin Johnson | University of Michigan |
| Advanced Deep Learning for Computer Vision | 2020 | Laura Leal-Taixé / Matthias Niessner | Technical University of Munich |
| Introduction to Digital Image Processing | 2020 | Ahmadreza Baghaie | New York Institute of Technology |
| Quantitative Imaging | 2019 | Kevin Mader | ETH Zurich |
| Convolutional Neural Networks for Visual Recognition | 2017 | Fei-Fei Li | Stanford University |
| Introduction to Digital Image Processing | 2015 | Rich Radke | Rensselaer Polytechnic Institute |
| Machine Learning for Robotics and Computer Vision | 2014 | Rudolph Triebel | Technical University of Munich |
| Multiple View Geometry | 2013 | Daniel Cremers | Technical University of Munich |
| Variational Methods for Computer Vision | 2013 | Daniel Cremers | Technical University of Munich |
| Computer Vision | 2012 | Mubarak Shah | University of Central Florida |
| Image and video processing | - | Guillermo Sapiro | Duke University |
Libraries
| Library | Description |
|---|---|
| OpenCV | Open Source Computer Vision Library |
| Pillow | The friendly PIL fork (Python Imaging Library) |
| scikit-image | collection of algorithms for image processing |
| SciPy | open-source software for mathematics, science, and engineering |
| mmcv | OpenMMLab foundational library for computer vision research |
| imutils | A series of convenience functions to make basic image processing operations |
| pgmagick | python based wrapper for GraphicsMagick/ImageMagick |
| Mahotas | library of fast computer vision algorithms (last updated: 2021) |
| SimpleCV | The Open Source Framework for Machine Vision (last updated: 2015) |
Repos
Tags: Object Classification [ObjCls], Object Detection [ObjDet], Object Segmentation [ObjSeg], General Library [GenLib], Text Reading / Object Character Recognition [OCR], Action Recognition [ActRec], Object Tracking [ObjTrk], Data Augmentation [DatAug], Simultaneous Localization and Mapping [SLAM], Outlier/Anomaly/Novelty Detection [NvlDet], Content-based Image Retrieval [CBIR], Image Enhancement [ImgEnh], Aesthetic Assessment [AesAss], Explainable Artificial Intelligence [XAI], Text-to-Image Generation [TexImg], Pose Estimation [PosEst], Video Matting [VidMat]
| Repo | Tags | Description |
|---|---|---|
| computervision-recipes | [GenLib] |
Microsoft, Best Practices, code samples, and documentation for Computer Vision |
| FastAI | [GenLib] |
FastAI, Library over PyTorch used for learning and practicing machine learning and deep learning |
| pytorch-lightning | [GenLib] |
PyTorchLightning, Lightweight PyTorch wrapper for high-performance AI research |
| ignite | [GenLib] |
PyTorch, High-level library to help with training and evaluating neural networks in PyTorch flexibly and transparently |
| pytorch_geometric | [GenLib] |
Graph Neural Network Library for PyTorch |
| kornia | [GenLib] |
Open Source Differentiable Computer Vision Library |
| ncnn | [GenLib] |
Tencent, High-performance neural network inference framework optimized for the mobile platform |
| MediaPipe | [ObjDet] [ObjSeg] [ObjTrk] [GenLib] |
Google, iOS - Andriod - C++ - Python - Coral, Face Detection - Face Mesh - Iris - Hands - Pose - Holistic - Hair Segmentation - Object Detection - Box Tracking - Instant Motion Tracking - Objectron - KNIFT (Similar to SIFT) |
| PyTorch image models | [ObjCls] |
rwightman, PyTorch image classification models, scripts, pretrained weights |
| mmclassification | [ObjCls] |
OpenMMLab, Image Classification Toolbox and Benchmark |
| vit-pytorch | [ObjCls] |
SOTA for vision transformers |
| face_classification | [ObjCls] [ObjDet] |
Real-time face detection and emotion/gender classification |
| mmdetection | [ObjDet] |
OpenMMLab, Image Detection Toolbox and Benchmark |
| detectron2 | [ObjDet] [ObjSeg] |
Facebook, FAIR's next-generation platform for object detection, segmentation and other visual recognition tasks |
| detr | [ObjDet] |
Facebook, End-to-End Object Detection with Transformers |
| libfacedetection | [ObjDet] |
An open source library for face detection in images, speed: ~1000FPS |
| FaceDetection-DSFD | [ObjDet] |
Tencent, SOTA face detector |
| object-Detection-Metrics | [ObjDet] |
Most popular metrics used to evaluate object detection algorithms |
| SAHI | [ObjDet] [ObjSeg] |
A lightweight vision library for performing large scale object detection/ instance segmentation |
| yolov5 | [ObjDet] |
ultralytics |
| AlexeyAB/darknet pjreddie/darknet | [ObjDet] |
YOLOv4 / Scaled-YOLOv4 / YOLOv3 / YOLOv2 |
| U-2-Net | [ObjDet] |
ultralytics U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection |
| segmentation_models.pytorch | [ObjSeg] |
qubvel, PyTorch segmentation models with pretrained backbones |
| mmsegmentation | [ObjSeg] |
OpenMMLab, Semantic Segmentation Toolbox and Benchmark |
| mmocr | [OCR] |
OpenMMLab, Text Detection, Recognition and Understanding Toolbox |
| pytesseract | [OCR] |
A Python wrapper for Google Tesseract |
| EasyOCR | [OCR] |
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc |
| mmtracking | [ObjTrk] |
OpenMMLab, Video Perception Toolbox for object detection and tracking |
| mmaction | [ActRec] |
OpenMMLab, An open-source toolbox for action understanding based on PyTorch |
| albumentations | [DatAug] |
Fast image augmentation library and an easy-to-use wrapper around other libraries |
| ORB_SLAM2 | [SLAM] |
Real-Time SLAM for Monocular, Stereo and RGB-D Cameras, with Loop Detection and Relocalization Capabilities |
| pyod | [NvlDet] |
Python Toolbox for Scalable Outlier Detection (Anomaly Detection) |
| imagededup | [CBIR] |
Image retrieval, CBIR, Find duplicate images made easy! |
| image-match | [CBIR] |
Image retrieval, CBIR, Quickly search over billions of images |
| Bringing-Old-Photos-Back-to-Life | [ImgEnh] |
Microsoft, Bringing Old Photo Back to Life (CVPR 2020 oral) |
| image-quality-assessment | [AesAss] |
Idealo, Image Aesthetic, NIMA model to predict the aesthetic and technical quality of images |
| aesthetics | [AesAss] |
Image Aesthetics Toolkit using Fisher Vectors |
| pytorch-cnn-visualizations | [XAI] |
Pytorch implementation of convolutional neural network visualization techniques |
| DALLE2-pytorch | [TexImg] |
Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch |
| imagen-pytorch | [TexImg] |
Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch |
| openpose | [PosEst] |
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation |
| RobustVideoMatting | [VidMat] |
Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML! |
Dataset Collections
- PyTorch - CV Datasets, Meta
- Tensorflow - CV Datasets, Google
- CVonline: Image Databases, Edinburgh University, Thanks to Robert Fisher!
- Yet Another Computer Vision Index To Datasets (YACVID), Thanks to Hayko Riemenschneider!
- Kaggle
- PaperWithCode, Meta
- RoboFlow
- VisualData
- CUHK Computer Vision
- VGG - University of Oxford
Task Management Tools
- MLflow, Platform to manage the ML lifecycle, including experimentation, reproducibility, deployment, and a central model registry
- Apache Airflow, Apache/AirBnB, Platform created by the community to programmatically author, schedule and monitor workflows
- Ploomber, fastest way to build data pipelines.
Annotation Tools
- VoTT, Microsoft, Visual Object Tagging Tool: An electron app for building end to end Object Detection Models from Images and Videos
- labelme, Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation)
- labelImg, Graphical image annotation tool and label object bounding boxes in images
- VIA, VGG Oxford, HTML-based standalone manual annotation software for image, audio and video
- FiftyOne, open-source tool for building high-quality datasets and computer vision models
Awesome Lists
- anomaly-detection-resources, Anomaly detection related books, papers, videos, and toolboxes
- awesome-satellite-imagery-datasets List of satellite image training datasets with annotations for computer vision and deep learning
- awesome-Face_Recognition, Computer vision papers about faces.
- the-incredible-pytorch, Curated list of tutorials, papers, projects, communities and more relating to PyTorch
Misc
- How to build a good poster - [Link1] [Link2] [Link3]
- How to report a good report - [Link1] [link2]
- The "Python Machine Learning (3rd edition)" book code repository
- Multithreading with OpenCV-Python to improve video processing performance
- Computer Vision Zone - Videos and implementations for computer vision projects
- MadeWithML, Learn how to responsibly deliver value with ML
- d2l-en, Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 200 universities
- Writing Pet Peeves, writing guide for correctness, references, and style
- Hitchhiker's Guide to Python, Python best practices guidebook, written for humans
- python-fire, Google, a library for automatically generating command line interfaces (CLIs) from absolutely any Python object.
- shotcut, a free, open source, cross-platform video editor.
- PyTorch Computer Vision Cookbook, PyTorch Computer Vision Cookbook, Published by Packt.
- Machine Learning Mastery - Blogs, Blogs written by Jason Brownlee about machine learning.
- PyImageSearch - Blogs, Blogs written by Adrian Rosebrock about computer vision.
- jetson-inference, guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.
Conferences in Computer Vision
- CORE Rank A (ICCV, CVPR, ECCV, WACV, ICASSP, MICCAI, IROS, ACMMM)
- CORE Rank B (ACCV, VCIP, ICIP, CAIP, BMVC, VISAPP, ICPR, ACIVS, EUSIPCO, ICRA)
- CORE Rank C (ICIAP, ICISP, ICIAR, ICVS)
- CORE Unranked (MIUA, CVCS, EUVIP, CIC, EI)
Journals in Computer Vision
- Tier 1 (IEEE TPAMI, IEEE TIP, IEEE TCSVT, Springer IJCV, Elsevier Pattern Recognition, Elsevier CVIU, Elsevier Expert Systems with Applications, Elsevier Neurocomputing, Springer Neural Computing and Applications)
- Tier 2 (Elsevier Image and Vision Computing, Elsevier Pattern Recognition Letters, Elsevier Journal of Visual Communication and Image Representation, Springer Journal of Mathematical Imaging and Vision, SPIE Journal of Electronic Imaging, IET Image Processing, Springer Pattern Analysis and Applications, Springer Machine Vision and Applications, IET Computer Vision)
- Open Access (IEEE Access, MDPI Journal of Imaging)
Summer Schools in Computer Vision
- International Computer Vision Summer School (IVCSS) [2007-Present], Sicily, Italy [2022]
- Machine Intelligence and Visual Computing Summer School (VISUM) [2013-Present], Porto, Portugal [2022]
- BMVA British Computer Vision Summer School (CVSS) [2013-2020], UK [Website]