Best Computer Vision Courses on Udemy

Python for Computer Vision with OpenCV and Deep Learning

This course is your best resource for learning how to use the Python programming language for Computer Vision.

We’ll be exploring how to use Python and the OpenCV (Open Computer Vision) library to analyze images and video data.

In this course we’ll teach you everything you need to know to become an expert in computer vision! This $20 billion dollar industry will be one of the most important job markets in the years to come.

We’ll start the course by learning about numerical processing with the NumPy library and how to open and manipulate images with NumPy. Then will move on to using the OpenCV library to open and work with image basics. Then we’ll start to understand how to process images and apply a variety of effects, including color mappings, blending, thresholds, gradients, and more.

Then we’ll move on to understanding video basics with OpenCV, including working with streaming video from a webcam.  Afterwards we’ll learn about direct video topics, such as optical flow and object detection. Including face detection and object tracking.

Then we’ll move on to an entire section of the course devoted to the latest deep learning topics, including image recognition and custom image classifications. We’ll even cover the latest deep learning networks, including the YOLO (you only look once) deep learning network.

• NumPy
• Images with NumPy
• Image and Video Basics with NumPy
• Color Mappings
• Blending and Pasting Images
• Image Thresholding
• Blurring and Smoothing
• Morphological Operators
• Gradients
• Histograms
• Streaming video with OpenCV
• Object Detection
• Template Matching
• Corner, Edge, and Grid Detection
• Contour Detection
• Feature Matching
• WaterShed Algorithm
• Face Detection
• Object Tracking
• Optical Flow
• Deep Learning with Keras
• Keras and Convolutional Networks
• Customized Deep Learning Networks
• State of the Art YOLO Networks

Python Developers interested in Computer Vision and Deep Learning. This course is not for complete python beginners.

• Understand basics of NumPy
• Manipulate and open Images with NumPy
• Use OpenCV to work with image files
• Use Python and OpenCV to draw shapes on images and videos
• Perform image manipulation with OpenCV, including smoothing, blurring, thresholding, and morphological operations.
• Create Color Histograms with OpenCV
• Open and Stream video with Python and OpenCV
• Detect Objects, including corner, edge, and grid detection techniques with OpenCV and Python
• Create Face Detection Software
• Segment Images with the Watershed Algorithm
• Track Objects in Video
• Use Python and Deep Learning to build image classifiers
• Work with Tensorflow, Keras, and Python to train on your own custom images.

Modern Computer Vision GPT, PyTorch, Keras, OpenCV4

In this course, you will learn the essential very foundations of Computer Vision, Classical Computer Vision (using OpenCV) I then move on to Deep Learning where we build our foundational knowledge of CNNs and learn all about the following topics:

Computer vision applications involving Deep Learning are booming!

Having Machines that can see will change our world and revolutionize almost every industry out there. Machines or robots that can see will be able to:

• Perform surgery and accurately analyze and diagnose you from medical scans.
• Enable self-driving cars
• Radically change robots allowing us to build robots that can cook, clean, and assist us with almost any task
• Understand what’s being seen in CCTV surveillance videos thus performing security, traffic management, and a host of other services
• Create Art with amazing Neural Style Transfers and other innovative types of image generation
• Simulate many tasks such as Aging faces, modifying live video feeds, and realistically replacing actors in films

This is a comprehensive course, is broken up into two (2) main sections. This first is a detailed OpenCV (Classical Computer Vision tutorial) and the second is a detailed Deep Learning

This course is filled with fun and cool projects including these Classical Computer Vision Projects:

1. Sorting contours by size, location, using them for shape matching
2. Finding Waldo
3. Perspective Transforms (CamScanner)
4. Image Similarity
5. K-Means clustering for image colors
6. Motion tracking with MeanShift and CAMShift
7. Optical Flow
8. Facial Landmark Detection with Dlib
9. Face Swaps
10. QR Code and Barcode Reaching
11. Background removal
12. Text Detection
13. OCR with PyTesseract and EasyOCR
14. Colourize Black and White Photos
15. Computational Photography with inpainting and Noise Removal
16. Create a Sketch of yourself using Edge Detection
17. RTSP and IP Streams
18. Capturing Screenshots as video
19. Import Youtube videos directly

Deep Learning Computer Vision Projects:

1. PyTorch & Keras CNN Tutorial MNIST
2. PyTorch & Keras Misclassifications and Model Performance Analysis
3. PyTorch & Keras Fashion-MNIST with and without Regularisation
4. CNN Visualisation – Filter and Filter Activation Visualisation
5. CNN Visualisation Filter and Class Maximisation
6. CNN Visualisation GradCAM GradCAMplusplus and FasterScoreCAM
7. Replicating LeNet and AlexNet in Tensorflow2.0 using Keras
8. PyTorch & Keras Pretrained Models – 1 – VGG16, ResNet, Inceptionv3, MobileNetv2, SqueezeNet, WideResNet, DenseNet201, MobileMNASNet, EfficientNet and MNASNet
9. Rank-1 and Rank-5 Accuracy
10. PyTorch and Keras Cats vs Dogs PyTorch – Train with your own data
11. PyTorch Lightning Tutorial – Batch and LR Selection, Tensorboards, Callbacks, mGPU, TPU and more
12. PyTorch Lightning – Transfer Learning
13. PyTorch and Keras Transfer Learning and Fine Tuning
14. PyTorch & Keras Using CNN’s as a Feature Extractor
15. PyTorch & Keras – Google Deep Dream
16. PyTorch Keras – Neural Style Transfer + TF-HUB Models
17. PyTorch & Keras Autoencoders using the Fashion-MNIST Dataset
18. PyTorch & Keras – Generative Adversarial Networks – DCGAN – MNIST
19. Keras – Super Resolution SRGAN
20. Project – Generate_Anime_with_StyleGAN
21. CycleGAN – Turn Horses into Zebras
22. ArcaneGAN inference
23. PyTorch & Keras Siamese Networks
24. Facial Recognition with VGGFace in Keras
25. PyTorch Facial Similarity with FaceNet
26. DeepFace – Age, Gender, Expression, Headpose and Recognition
27. Object Detection – Gun, Pistol Detector – Scaled-YOLOv4
28. Object Detection – Mask Detection – TensorFlow Object Detection – MobileNetV2 SSD
29. Object Detection  – Sign Language Detection – TFODAPI – EfficientDetD0-D7
30. Object Detection – Pot Hole Detection with TinyYOLOv4
31. Object Detection – Mushroom Type Object Detection – Detectron 2
32. Object Detection – Website Screenshot Region Detection – YOLOv4-Darknet
33. Object Detection – Drone Maritime Detector – Tensorflow Object Detection Faster R-CNN
34. Object Detection – Chess Pieces Detection – YOLOv3 PyTorch
35. Object Detection – Hardhat Detection for Construction sites – EfficientDet-v2
36. Object DetectionBlood Cell Object Detection – YOLOv5
37. Object DetectionPlant Doctor Object Detection – YOLOv5
38. Image Segmentation – Keras, U-Net and SegNet
39. DeepLabV3 – PyTorch_Vision_Deeplabv3
40. Mask R-CNN Demo
41. Detectron2 – Mask R-CNN
42. Train a Mask R-CNN – Shapes
43. Yolov5 DeepSort Pytorch tutorial
44. DeepFakes – first-order-model-demo
45. Vision Transformer Tutorial PyTorch
46. Vision Transformer Classifier in Keras
47. Image Classification using BigTransfer (BiT)
48. Depth Estimation with Keras
49. Image Similarity Search using Metric Learning with Keras
50. Image Captioning with Keras
51. Video Classification with a CNN-RNN Architecture with Keras
52. Video Classification with Transformers with Keras
53. Point Cloud Classification – PointNet
54. Point Cloud Segmentation with PointNet
55. 3D Image Classification CT-Scan
56. X-ray Pneumonia Classification using TPUs
57. Low Light Image Enhancement using MIRNet
58. Captcha OCR Cracker
59. Flask Rest API – Server and Flask Web App
60. Detectron2 – BodyPose

Computer Vision Masterclass

In this course you will learn everything you need to know in order to get in this world. You will learn the step-by-step implementation of the 14 (fourteen) main computer vision techniques. If you have never heard about computer vision, at the end of this course you will have a practical overview of all areas. Below you can see some of the content you will implement:

• Detect faces in images and videos using OpenCV and Dlib libraries
• Learn how to train the LBPH algorithm to recognize faces, also using OpenCV and Dlib libraries
• Track objects in videos using KCF and CSRT algorithms
• Learn the whole theory behind artificial neural networks and implement them to classify images
• Implement convolutional neural networks to classify images
• Use transfer learning and fine tuning to improve the results of convolutional neural networks
• Detect emotions in images and videos using neural networks
• Compress images using autoencoders and TensorFlow
• Detect objects using YOLO, one of the most powerful techniques for this task
• Recognize gestures and actions in videos using OpenCV
• Create hallucinogenic images using the Deep Dream technique
• Combine style of images using style transfer
• Create images that don’t exist in the real world with GANs (Generative Adversarial Networks)
• Extract useful information from images using image segmentation

Deep Learning: Advanced Computer Vision (GANs, SSD, +More!)

This is one of the most exciting courses I’ve done and it really shows how fast and how far deep learning has come over the years.

this course is so entirely different from the previous one, you will be impressed at just how much material we have to cover.

In this course, you’ll see how we can turn a CNN into an object detection system, that not only classifies images but can locate each object in an image and predict its label.

You can imagine that such a task is a basic prerequisite for self-driving vehicles. (It must be able to detect cars, pedestrians, bicycles, traffic lights, etc. in real-time)

We’ll be looking at a state-of-the-art algorithm called SSD which is both faster and more accurate than its predecessors.

Another very popular computer vision task that makes use of CNNs is called neural style transfer.

This is where you take one image called the content image, and another image called the style image, and you combine these to make an entirely new image, that is as if you hired a painter to paint the content of the first image with the style of the other. Unlike a human painter, this can be done in a matter of seconds.

You will also introduce you to the now-famous GAN architecture (Generative Adversarial Networks), where you will learn some of the technology behind how neural networks are used to generate state-of-the-art, photo-realistic images.

• Understand and apply transfer learning
• Understand and use state-of-the-art convolutional neural nets such as VGG, ResNet and Inception
• Understand and use object detection algorithms like SSD
• Understand and apply neural style transfer
• Understand state-of-the-art computer vision topics
• Class Activation Maps
• GANs (Generative Adversarial Networks)
• Object Localization Implementation Project
• Understand important foundations for OpenAI ChatGPT, GPT-4, DALL-E, Midjourney, and Stable Diffusion

PyTorch for Deep Learning Bootcamp

By enrolling today, you’ll also get to join our exclusive live online community classroom to learn alongside thousands of students, alumni, mentors, TAs and Instructors.

Most importantly, you will be learning PyTorch from a professional machine learning engineer, with real-world experience, and who is one of the best teachers around!

What will this PyTorch course be like?

This PyTorch course is very hands-on and project based. You won’t just be staring at your screen. We’ll leave that for other PyTorch tutorials and courses.

In this course you’ll actually be:

• Running experiments
• Completing exercises to test your skills
• Building real-world deep learning models and projects to mimic real life scenarios

By the end of it all, you’ll have the skillset needed to identify and develop modern deep learning solutions that Big Tech companies encounter.

• Everything from getting started with using PyTorch to building your own real-world models
• Understand how to integrate Deep Learning into tools and applications
• Build and deploy your own custom trained PyTorch neural network accessible to the public
• Master deep learning and become a top candidate for recruiters seeking Deep Learning Engineers
• The skills you need to become a Deep Learning Engineer and get hired with a chance of making US$100,000+ / year
• Why PyTorch is a fantastic way to start working in machine learning
• Create and utilize machine learning algorithms just like you would write a Python program
• How to take data, build a ML algorithm to find patterns, and then use that algorithm as an AI to enhance your applications
• To expand your Machine Learning and Deep Learning skills and toolkit

Master Computer Vision OpenCV4 in Python with Deep Learning

 this course to teach you all the key concepts without the heavy mathematical theory while using the most up to date methods. 

If you’re an academic or college student I still point you in the right direction if you wish to learn more by linking the research papers of techniques we use. 

So if you want to get an excellent foundation in Computer Vision, look no further.In this course, you will discover the power of OpenCV in Python, and obtain skills to dramatically increase your career prospects as a Computer Vision developer.

• Understand and use OpenCV4 in Python
• How to use Deep Learning using Keras & TensorFlow in Python
• Create Face Detectors & Recognizers and create your own advanced face swaps using DLIB
• Object Detection, Tracking and Motion Analysis
• Create Augmented Reality Apps
• Programming skills such as basic Python and Numpy
• How to use Computer Vision in executing cool startup ideas
• Understand Neural and Convolutional Neural Networks
• Learn to build simple Image Classifiers in Python
• Learn to build an OCR Reader for Credit Cards
• Learn to Perform Neural Style Transfer Using OpenCV
• Learn how to do Multi Object Detection in OpenCV (up to 90 Objects!) using SSDs (Single Shot Detector)
• Learn how to convert black and white Images to color using Caffe
• Learn to build an Automatic Number (License) Plate Recognition (ALPR)
• Learn the Basics of Computer Vision and Image Processing

At the end of the course, you will be able to build 12 Awesome Computer Vision Apps using OpenCV in Python.

PyTorch for Deep Learning and Computer Vision

Deep Learning jobs command some of the highest salaries in the development world. This course is meant to take you from the complete basics, to building state-of-the art Deep Learning and Computer Vision applications with PyTorch.

Learn & Master Deep Learning with PyTorch in this fun and exciting course with top instructor Rayan Slim. With over 44000 students, Rayan is a highly rated and experienced instructor who has followed a “learn by doing” style to create this amazing course.

You’ll go from beginner to Deep Learning expert and your instructor will complete each task with you step by step on screen.

By the end of the course, you will have built state-of-the art Deep Learning and Computer Vision applications with PyTorch. The projects built in this course will impress even the most senior developers and ensure you have hands on skills that you can bring to any project or company.

• Learn how to work with the tensor data structure
• Implement Machine and Deep Learning applications with PyTorch
• Build neural networks from scratch
• Build complex models through the applied theme of advanced imagery and Computer Vision
• Learn to solve complex problems in Computer Vision by harnessing highly sophisticated pre-trained models
• Use style transfer to build sophisticated AI applications that are able to seamlessly recompose images in the style of other images.
• Implement Machine and Deep Learning applications with PyTorch
• Build Neural Networks from scratch
• Build complex models through the applied theme of Advanced Imagery and Computer Vision
• Solve complex problems in Computer Vision by harnessing highly sophisticated pre-trained models
• Use style transfer to build sophisticated AI applications