Python for Computer Vision with OpenCV and Deep Learning course is the finest resource for learning how to programme in Python for computer vision. Students will learn how to analyse image and video data using Python and the OpenCV (Open Computer Vision) package.
The course will begin with an introduction to the NumPy library, numerical processing, and opening and manipulating images. The OpenCV library will then be used to open and manipulate basic image data after that. Then, Instructor will teach how to edit pictures and use a range of effects, such as gradients, thresholds, colour blending, and more. Currently, udemy is offering Python for Computer Vision with OpenCV and Deep Learning for up to 85% off i.e. INR 455 (INR 2,799)
Who all can opt for this course?
- Python programmers with a deep learning and computer vision interest
- Python beginners should not take this course
Course Highlights
| Key Highlights | Details |
|---|---|
| Registration Link | Apply Now! |
| Price | INR 455 ( |
| Duration | 14 Hours |
| Rating | 4.5/5 |
| Student Enrollment | 49,915 students |
| Instructor | Jose Portilla https://www.linkedin.com/in/joseportilla |
| Topics Covered | NumPy, Color mapping, Deep learning with keras, Face detection, watershed algorithm and more |
| Course Level | Intermediate |
| Total Student Reviews | 9,195 |
Learning Outcomes
- learn the fundamentals of NumPy
- Use NumPy to manipulate and open images
- To work with picture files, use OpenCV
- To add shapes to photos and videos, use Python and OpenCV
- Use OpenCV to manipulate images, including morphological operations, thresholding, blurring, and smoothing
- Use OpenCV to create colour histograms
- Python and OpenCV are used to open and stream video
- Using OpenCV and Python, detect objects using corner, edge, and grid detection methods
- Make software that can detect faces
- Use the Watershed Algorithm to segment images
- Object tracking in video
- Create image classifiers using Python and deep learning
- To train on your own unique photos, use Python, Keras, and Tensorflow
Course Content
| S.No. | Module (Duration) | Topics |
|---|---|---|
| 1. | Course Overview and Introduction (23 minutes) | Course Overview |
| FAQ – Frequently Asked Questions | ||
| Course Curriculum Overview | ||
| Getting Set-Up for the Course Content | ||
| 2. | NumPy and Image Basics (47 minutes) | Introduction to Numpy and Image Section |
| NumPy Arrays | ||
| What is an image? | ||
| Images and NumPy | ||
| NumPy and Image Assessment Test | ||
| NumPy and Image Assessment Test – Solutions | ||
| 3. | Image Basics with OpenCV (01 hour 32 minutes) | Introduction to Images and OpenCV Basics |
| Opening Image files in a notebook | ||
| Opening Image files with OpenCV | ||
| Drawing on Images – Part One – Basic Shapes | ||
| Drawing on Images Part Two – Text and Polygons | ||
| Direct Drawing on Images with a mouse – Part One | ||
| Direct Drawing on Images with a mouse – Part Two | ||
| Direct Drawing on Images with a mouse – Part Three | ||
| Image Basics Assessment | ||
| Image Basics Assessment Solutions | ||
| 4. | Image Processing (02 hours 36 minutes) | Introduction to Image Processing |
| Color Mappings | ||
| Blending and Pasting Images | ||
| Blending and Pasting Images Part Two – Masks | ||
| Image Thresholding | ||
| Blurring and Smoothing | ||
| Blurring and Smoothing – Part Two | ||
| Morphological Operators | ||
| Gradients | ||
| Histograms – Part One | ||
| Histograms – Part Two – Histogram Eqaulization | ||
| Histograms Part Three – Histogram Equalization | ||
| Image Processing Assessment | ||
| Image Processing Assessment Solutions | ||
| 5. | Video Basics with Python and OpenCV (45 minutes) | Introduction to Video Basics |
| Connecting to Camera | ||
| Using Video Files | ||
| Drawing on Live Camera | ||
| Video Basics Assessment | ||
| Video Basics Assessment Solutions | ||
| 6. | Object Detection with OpenCV and Python (03 hours 05 minutes) | Introduction to Object Detection |
| Template Matching | ||
| Corner Detection – Part One – Harris Corner Detection | ||
| Corner Detection – Part Two – Shi-Tomasi Detection | ||
| Edge Detection | ||
| Grid Detection | ||
| Contour Detection | ||
| Feature Matching – Part One | ||
| Feature Matching – Part Two | ||
| Watershed Algorithm – Part One | ||
| Watershed Algorithm – Part Two | ||
| Custom Seeds with Watershed Algorithm | ||
| Introduction to Face Detection | ||
| Face Detection with OpenCV | ||
| Detection Assessment | ||
| Detection Assessment Solutions | ||
| 7. | Object Tracking (01 hour 09 minutes) | Introduction to Object Tracking |
| Optical Flow | ||
| Optical Flow Coding with OpenCV – Part One | ||
| Optical Flow Coding with OpenCV – Part Two | ||
| MeanShift and CamShift Tracking Theory | ||
| MeanShift and CamShift Tracking with OpenCV | ||
| Overview of various Tracking API Methods | ||
| Tracking APIs with OpenCV | ||
| 8. | Deep Learning for Computer Vision (03 hours 03 minutes) | Introduction to Deep Learning for Computer Vision |
| Machine Learning Basics | ||
| Understanding Classification Metrics | ||
| Introduction to Deep Learning Topics | ||
| Understanding a Neuron | ||
| Understanding a Neural Network | ||
| Cost Functions | ||
| Gradient Descent and Back Propagation | ||
| Keras Basics | ||
| MNIST Data Overview | ||
| Convolutional Neural Networks Overview – Part One | ||
| Convolutional Neural Networks Overview – Part Two | ||
| Keras Convolutional Neural Networks with MNIST | ||
| Keras Convolutional Neural Networks with CIFAR-10 | ||
| LINK FOR CATS AND DOGS ZIP | ||
| Deep Learning on Custom Images – Part One | ||
| Deep Learning on Custom Images – Part Two | ||
| Deep Learning and Convolutional Neural Networks Assessment | ||
| Deep Learning and Convolutional Neural Networks Assessment Solutions | ||
| Introduction to YOLO v3 | ||
| YOLO Weights Download | ||
| YOLO v3 with Python | ||
| 9. | Capstone Project (41 minutes) | Introduction to CapStone Project |
| Capstone Part One – Variables and Background function | ||
| Capstone Part Two – Segmentation | ||
| Capstone Part Three – Counting and ConvexHull | ||
| Capstone Part Four – Bringing it all together | ||
| 10. | BONUS SECTION: THANK YOU! (10 seconds) | BONUS LECTURE |
Resources Required
- Basic knowledge of Python is required
- Ubuntu, Windows 10, or Mac OS
- Must have Computer Install Permissions
- If you want to learn about the video streaming material, use a webcam
Featured Review
Mah Kaiquan (5/5) : Good introduction to OpenCV, CNN and image processing concepts with lecture videos, readings and Jupyter notebook exercises. Jose and different teaching assistants such as Yau were helpful in answering conceptual and code-related questions I had usually within a day. The quick response was refreshing for an online course.
Pros
- Lei Deng (5/5) : He is always to the point and provides an excellent context of how the code fits in.
- Helge Plehn (5/5) : I had some difficulties with the Jupyter notebooks at the start, but after that everything worked perfectly.
- Saurav Banerjee (5/5) : This is an awesome course for a beginner like me in the Computer Vision field.
- Shalini Shukla (5/5) : I’m really happy with the content of the course which is well explained!
Cons
- Anonymized User (2/5) : The linux .yml file is broken and seemingly has been for some time.
- Ça?atay (2/5) : Also I hate how you are told to use certain parameters without any explanation on why we used them.
- Vy Dinh (1/5) : After few hours, I decided to manually install them without Conda
- Chirag Rao (1/5) : The Capstone Project is a mess , he hardly explains lines properly and he thinks that we already have a lot of experience with OpenCV.
About the Author
The instructor of this course is Jose Portilla who is a Head of Data Science at Pierian Training. With 4.6 Instructor Rating and 1,022,766 Reviews on Udemy, he/she offers 60 Courses and has taught 3,292,376 Students so far.
- Jose Marcial Portilla holds degrees in mechanical engineering from Santa Clara University (BS and MS), and he has years of experience working as a qualified instructor and trainer for Python programming, machine learning, and data science
- He has written articles and received patents in a number of disciplines, including data science, materials science, and microfluidics
- He has acquired a set of abilities for data analysis throughout the course of his career, and he wants to combine both his teaching and data science knowledge to educate others the power of programming, how to analyse data, and how to display the data in attractive visualisations
- He currently serves as the Head of Data Science for Pierian Training, where he trains people at prestigious organisations like General Electric, Cigna, The New York Times, Credit Suisse, McKinsey, and others in data science and python programming on-site
- Please click the website link to learn more about the available training options
Comparison Table
| Parameters | Python for Computer Vision with OpenCV and Deep Learning | NLP – Natural Language Processing with Python | Interactive Python Dashboards with Plotly and Dash |
|---|---|---|---|
| Offers | INR 455 ( | INR 455 ( | INR 455 ( |
| Duration | 14 hours | 11.5 hours | 9.5 hours |
| Rating | 4.5 /5 | 4.6 /5 | 4.6 /5 |
| Student Enrollments | 49,910 | 68,426 | 44,688 |
| Instructors | Jose Portilla | Jose Portilla | Jose Portilla |
| Register Here | Apply Now! | Apply Now! | Apply Now! |
Leave feedback about this