The ‘Master Computer Vision™ OpenCV4 in Python with Deep Learning Course’ is a hands-on training program where students will learn how to master computer vision using the latest version of OpenCV4 in Python. Computer vision is a part of the AI that focuses on ways that computer-based algorithms decipher images.
The course covers key concepts of computer vision and OpenCV4, image manipulation, feature detection, object detection, facial recognition, motion analysis, object tracking, etc. Students will also work on a total of 21 projects based on applications of OpenCV4 and Deep Learning. The course is usually available for INR 2,499 on Udemy but students can click on the link and get the ‘Master Computer Vision™ OpenCV4 in Python with Deep Learning Course’ for INR 449.
Who all can opt for this course?
- Beginners curious to learn about computer vision
- College students looking for an introductory course on computer vision
- Anybody interested to learn about computer vision using deep learning
- Entrepreneurs looking to implement business ideas for computer vision
- Making a fantastic computer vision prototype as a hobby
- Software engineers and developers who desire to hone their computer vision skills
Course Highlights
| Key Highlights | Details |
|---|---|
| Registration Link | Apply Now! |
| Price | INR 449 ( |
| Duration | 10.5 hours |
| Rating | 4.2/5 |
| Student Enrollment | 21,135 students |
| Instructor | Rajeev D. Ratan https://www.linkedin.com/in/rajeevd.ratan |
| Topics Covered | Key concepts of computer vision, OpenCV4, image manipulation, image segmentation, facial recognition, deep learning, computational photography, etc. |
| Course Level | Beginner |
| Total Student Reviews | 3,597 |
Learning Outcomes
- Learn and use OpenCV4 in Python
- How to utilise deep learning using Keras and TensorFlow in Python
- With DLIB, make your own sophisticated face swaps and face detectors
- Motion analysis, object tracking, and object detection
- Make apps for augmented reality
- Fundamentals of Numpy and Python
- How to implement innovative company concepts using computer vision
- Learn about neural networks and convolutional networks
- Learn how to create straightforward Python image classifiers
- Build a credit card OCR reader by learning how to do it
- Learn to use OpenCV for Neural Style Transfer
- Discover how to use SSDs for multi-object detection in OpenCV (up to 90 Objects!) (Single Shot Detector)
- Learn how to use Caffe to transform grayscale images into colour
- Develop an automatic number plate (licence plate) recognition system (ALPR)
- Study the fundamentals of image processing and computer vision
Course Content
| S.No. | Module (Duration) | Topics |
|---|---|---|
| 1. | Course Introduction and Setup (30 minutes) | Introduction |
| Introduction to Computer Vision and OpenCV | ||
| About this course | ||
| READ THIS – Guide to installing and setting up your OpenCV4.0.1 Virtual Machine | ||
| Recommended – Setup your OpenCV4.0.1 Virtual Machine | ||
| Installation of OpenCV & Python on Windows | ||
| Installation of OpenCV & Python on Mac | ||
| Installation of OpenCV & Python on Linux | ||
| Set up course materials (DOWNLOAD LINK BELOW) – Not needed if using the new VM | ||
| 2. | Basics of Computer Vision and OpenCV (43 minutes) | What are Images? |
| How are Images Formed? | ||
| Storing Images on Computers | ||
| Getting Started with OpenCV – A Brief OpenCV Intro | ||
| Grayscaling – Converting Color Images To Shades of Gray | ||
| Understanding Color Spaces – The Many Ways Color Images Are Stored Digitally | ||
| Histogram representation of Images – Visualizing the Components of Images | ||
| Creating Images & Drawing on Images – Make Squares, Circles, Polygons & Add Text | ||
| 3. | Image Manipulations & Processing (01 hour 01 minutes) | Transformations, Affine And Non-Affine – The Many Ways We Can Change Images |
| Image Translations – Moving Images Up, Down. Left And Right | ||
| Rotations – How To Spin Your Image Around And Do Horizontal Flipping | ||
| Scaling, Re-sizing and Interpolations – Understand How Re-Sizing Affects Quality | ||
| Image Pyramids – Another Way of Re-Sizing | ||
| Cropping – Cut Out The Image The Regions You Want or Don’t Want | ||
| Arithmetic Operations – Brightening and Darkening Images | ||
| Bitwise Operations – How Image Masking Works | ||
| Blurring – The Many Ways We Can Blur Images & Why It’s Important | ||
| Sharpening – Reverse Your Images Blurs | ||
| Thresholding (Binarization) – Making Certain Images Areas Black or White | ||
| Dilation, Erosion, Opening/Closing – Importance of Thickening/Thinning Lines | ||
| Edge Detection using Image Gradients & Canny Edge Detection | ||
| Perspective & Affine Transforms – Take An Off Angle Shot & Make It Look Top Down | ||
| Mini Project 1 – Live Sketch App – Turn your Webcam Feed Into A Pencil Drawing | ||
| 4. | Image Segmentation & Contours (57 minutes) | Segmentation and Contours – Extract Defined Shapes In Your Image |
| Sorting Contours – Sort Those Shapes By Size | ||
| Approximating Contours & Finding Their Convex Hull – Clean Up Messy Contours | ||
| Matching Contour Shapes – Match Shapes In Images Even When Distorted | ||
| Mini Project 2 – Identify Shapes (Square, Rectangle, Circle, Triangle & Stars) | ||
| Line Detection – Detect Straight Lines E.g. The Lines On A Sudoku Game | ||
| Circle Detection | ||
| Blob Detection – Detect The Center of Flowers | ||
| Mini Project 3 – Counting Circles and Ellipses | ||
| 5. | Object Detection in OpenCV (50 minutes) | Object Detection Overview |
| Mini Project # 4 – Finding Waldo (Quickly Find A Specific Pattern In An Image) | ||
| Feature Description Theory – How We Digitally Represent Objects | ||
| Finding Corners – Why Corners In Images Are Important to Object Detection | ||
| SIFT, SURF, FAST, BRIEF & ORB – Learn The Different Ways To Get Image Features | ||
| Mini Project 5 – Object Detection – Detect A Specific Object Using Your Webcam | ||
| Histogram of Oriented Gradients – Another Novel Way Of Representing Images | ||
| 6. | Object Detection – Build a Face, People and Car/Vehicle Detectors (22 minutes) | HAAR Cascade Classifiers – Learn How Classifiers Work And Why They’re Amazing |
| Face and Eye Detection – Detect Human Faces and Eyes In Any Image | ||
| Mini Project 6 – Car and Pedestrian Detection in Videos | ||
| 7. | Augmented Reality (AR) – Facial Landmark Identification (Face Swaps) (35 minutes) | Face Analysis and Filtering – Identify Face Outline, Lips, Eyes Even Eyebrows |
| Merging Faces (Face Swaps) – Combine Two Faces For Fun & Sometimes Scary Results | ||
| Mini Project 7 – Live Face Swapper (like MSQRD & Snapchat filters!!!) | ||
| Mini Project 8 – Yawn Detector and Counter | ||
| 8. | Simple Machine Learning using OpenCV (41 minutes) | Machine Learning Overview – What Is It & Why It’s Important to Computer Vision |
| Mini Project 9 – Handwritten Digit Classification | ||
| Mini Project # 10 – Facial Recognition – Make Your Computer Recognize You | ||
| 9. | Object Tracking & Motion Analysis (34 minutes) | Filtering by Color |
| Background Subtraction and Foreground Subtraction | ||
| Using Meanshift for Object Tracking | ||
| Using CAMshift for Object Tracking | ||
| Optical Flow – Track Moving Objects In Videos | ||
| Mini Project # 11 – Ball Tracking | ||
| 10. | Computational Photography & Make a License Plate Reader (06 minutes) | Mini Project # 12 – Photo-Restoration |
| Mini Project # 13 – Automatic Number-Plate Recognition (ALPR) | ||
| 11. | Conclusion (09 minutes) | Course Summary and how to become an Expert |
| Latest Advances, 12 Startup Ideas & Implementing Computer VIsion in Mobile Apps | ||
| 12. | BONUS – Deep Learning Computer Vision 1 – Setup a Deep Learning Virtual Machine (19 minutes) | Setup your Deep Learning Virtual Machine |
| Intro to Handwritten Digit Classification (MNIST) | ||
| Intro to Multiple Image Classification (CIFAR10) | ||
| 13. | BONUS – Deep Learning Computer Vision 2 – Introduction to Neural Networks (01 hour 34 minutes) | Neural Networks Chapter Overview |
| Machine Learning Overview | ||
| Neural Networks Explained | ||
| Forward Propagation | ||
| Activation Functions | ||
| Training Part 1 – Loss Functions | ||
| Training Part 2 – Backpropagation and Gradient Descent | ||
| Backpropagation & Learning Rates – A Worked Example | ||
| Regularization, Overfitting, Generalization and Test Datasets | ||
| Epochs, Iterations and Batch Sizes | ||
| Measuring Performance and the Confusion Matrix | ||
| Review and Best Practices | ||
| 14. | BONUS – Deep Learning Computer Vision 3 – Convolutional Neural Networks (CNNs) (42 minutes) | Convolutional Neural Networks Chapter Overview |
| Introduction to Convolutional Neural Networks (CNNs) | ||
| Convolutions & Image Features | ||
| Depth, Stride and Padding | ||
| ReLU | ||
| Pooling | ||
| The Fully Connected Layer | ||
| Training CNNs | ||
| Designing Your Own CNN | ||
| 15. | BONUS – Deep Learning Computer Vision 4 – Build CNNs in Python using Keras (52 minutes) | Introduction to Keras & Tensorflow |
| Building a CNN in Keras | ||
| Building a Handwriting Recognition CNN | ||
| Loading Our Data | ||
| Getting our data in ‘Shape’ | ||
| Hot One Encoding | ||
| Building & Compiling Our Model | ||
| Training Our Classifier | ||
| Plotting Loss and Accuracy Charts | ||
| Saving and Loading Your Model | ||
| Displaying Your Model Visually | ||
| Building a Simple Image Classifier using CIFAR10 | ||
| 16. | BONUS – Deep Learning Computer Vision 5 – Build a Cats vs Dogs Classifier (25 minutes) | Data Augmentation Chapter Overview |
| Splitting Data into Test and Training Datasets | ||
| Train a Cats vs. Dogs Classifier | ||
| Boosting Accuracy with Data Augmentation | ||
| Types of Data Augmentation | ||
| 17. | BONUS – Build a Credit Card Number Reader (12 minutes) | Step 1 – Creating a Credit Card Number Dataset |
| Step 2 – Training Our Model | ||
| Step 3 – Extracting A Credit Card from the Background | ||
| Step 4 – Use our Model to Identify the Digits & Display it onto our Credit Card | ||
| 18. | BONUS – Neural Style Transfer with OpenCV (01 minute) | Perform Neural Style Transfer Using OpenCV4 |
| 19. | BONUS – Object Detection – Use SSDs (Single Shot Detector) for Detecting Objects (03 minutes) | Using an SSD In OpenCV |
| 20. | BONUS – Colorize Black and White Images (01 minute) | Colorizing Black and White Images Using Caffe |
Resources Required
- Basic programming knowledge is helpful but is not absolutely necessary
- A macOS, Windows 10, or Ubuntu computer
- A webcam for some of the smaller tasks
Featured Review
Alexander Baker (5/5): Concise, and informative. Excellent course to get a handle on the computer vision capabilities of Python. (As the description reads) it’s not a from scratch course though. Learn the basics of machine learning and Python in a different course before this one.
Pros
- Abhijit Debnath (5/5): This is an excellent course for someone to get started with Computer Vision using Python OpenCV.
- Pedro Sousa (5/5): Giving us the source code in Jupyter Notebooks is just awesome!
- Andrew Norris (5/5): 5++ starts! One of the best investments I’ve ever made here at Udemy.
- Darshan Iyer (5/5): Rajeev did a brilliant job in putting a great open CV course together.
Cons
- Abdulsamad Gobir (1/5): I am really disappointed at why I have to go to another site to get instructions to install and even at that the pyimage search sites do use anaconda in their installation process.
- Alain Seux-Bos (1/5): And a guy that ask to run 2 times the code to see graphs from matplotlib beacuse he don’t know #matplotlib inline is a really bad teacher.
- Stevaras (2/5): Even wrong comments in some parts of the code and errors in presentations ( like erosion/dilation ) 6) Errors when trying to execute his code.
- Stephan Bernstorf (1/5): the instructor just talks about random image manipulation topics without any context, provides VM that doesnt seem to work.
About the Author
The instructor of this course is Rajeev D. Ratan who is a Data Scientist, Computer Vision Expert & Electrical Engineer. With a 4.4 instructor rating and 9,177 reviews on Udemy, he offers 7 courses and has taught 61,761 students so far.
- He graduated from the University of Edinburgh with a BSc in Computer & Electrical Engineering and an MSc in Artificial Intelligence degree. He gained in-depth expertise in machine learning, computer vision, and intelligent robotics.
- Rajiv was a member of a team that won a robotics competition at the University of Edinburgh.
- His research on using data-driven methods for probabilistic stochastic modelling for public transportation has been published.
- In order to use deep learning in education, he founded his own computer vision startup.
- Since then, he has worked with two other companies in the computer vision space as well as a large international company in data science.
- He has spent over 8 years working for two of the biggest telecom companies in the Caribbean, where he developed skills in technical staff management and the deployment of challenging telecom projects.
Comparison Table
| Parameters | Master Computer Vision™ OpenCV4 in Python with Deep Learning | Artificial Intelligence: Reinforcement Learning in Python | Advanced AI: Deep Reinforcement Learning in Python |
|---|---|---|---|
| Offers | INR 449 ( | INR 455 ( | INR 455 ( |
| Duration | 10.5 hours | 14.5 hours | 10.5 hours |
| Rating | 4.2/5 | 4.8 /5 | 4.6 /5 |
| Student Enrollments | 21,135 | 43,647 | 36,737 |
| Instructors | Rajeev D. Ratan | Lazy Programmer Team | Lazy Programmer Team |
| Register Here | Apply Now! | Apply Now! | Apply Now! |
Leave feedback about this