Computer Vision Theory and Projects in Python for Beginners

Video description

The high-quality content of the Mastering Computer Vision from the Absolute Beginning Using Python course presents you with a great opportunity to learn and become an expert. You will learn the core concepts of the CV field. This course will also help you understand the digital imaging process and identify the key application areas of CV. The course is easy to understand, descriptive, comprehensive, practical with live coding, and rich with state-of-the-art and updated knowledge of this field.

Although this course is a compilation of all the basic concepts of CV, you are encouraged to step up and experience more than what you learn. Your understanding of every concept is tested at the end of each section. The homework assignments/tasks/activities/quizzes along with solutions will assess your learning. Several of these activities are focused on coding so that you are ready to run with implementations.

The two hands-on projects in the last section—Change Detection in CCTV Cameras (Real-Time) and Smart DVRs (Real-Time)—make up the most important learning element of this course. They will help you sharpen your practical skills. Successful completion of these two projects will help you enrich your portfolio and kick-start your career in the CV field.

By the end of the course, you will have a strong understanding of Computer Vision concepts and will be ready to apply them in your future projects.

What You Will Learn

  • Learn the concept of colored and black and white images with practice
  • Know the theory and implementation of panoramic images
  • Learn image filtering with implementation in Python
  • Implement any project from scratch that requires Computer Vision knowledge
  • Apply edge detection, shape detection, and corner detection
  • Develop a project to make a very intelligent and efficient DVR using Python


This course is useful for data scientists, machine learning experts, and learners who are absolute beginners and know nothing about Computer Vision, and for people who want to learn Computer Vision with real data along with its implementation in realistic projects.

About The Author

AI Sciences: AI Sciences are experts, PhDs, and artificial intelligence practitioners, including computer science, machine learning, and Statistics. Some work in big companies such as Amazon, Google, Facebook, Microsoft, KPMG, BCG, and IBM.

AI sciences produce a series of courses dedicated to beginners and newcomers on techniques and methods of machine learning, statistics, artificial intelligence, and data science. They aim to help those who wish to understand techniques more easily and start with less theory and less extended reading. Today, they publish more comprehensive courses on specific topics for wider audiences.

Their courses have successfully helped more than 100,000 students master AI and data science.

Table of contents

  1. Chapter 1 : Introduction to Course and Instructor
    1. Introduction to the Course
    2. Introduction to Instructor
    3. About AI Sciences
    4. Course Outline (Optional)
    5. Computer Vision Applications
    6. Final Project
  2. Chapter 2 : Introduction to Images
    1. Grayscale Image
    2. Quiz (Grayscale Image)
    3. Solution (Grayscale Image)
    4. Grayscale Spectrum
    5. Reading, Manipulating, and Saving Grayscale Image using Matplotlib Python
    6. Quiz (Reading, Manipulating, and Saving Grayscale Image using Matplotlib Python)
    7. Solution (Reading, Manipulating, and Saving Grayscale Image using Matplotlib Python)
    8. Reading, Manipulating, and Saving Grayscale Image using OpenCV Python
    9. Introduction to RGB Images
    10. Quiz (Introduction to RGB Images)
    11. Solution (Introduction to RGB Images)
    12. RGB Color Images Matplotlib and OpenCV
    13. Quiz (RGB Color Images Matplotlib and OpenCV)
    14. Solution (RGB Color Images Matplotlib and OpenCV)
    15. RGB to HSV theory and Algorithm
    16. RGB to HSV Algorithm Implementation using Python
    17. Quiz (RGB to HSV Algorithm Implementation using Python)
    18. Solution (RGB to HSV Algorithm Implementation using Python)
    19. Red Rose Extraction or Segmentation using HSV Python
    20. Quiz (Red Rose Extraction or Segmentation using HSV Python)
    21. Solution (Red Rose Extraction or Segmentation using HSV Python)
    22. Hyper Spectral Images
  3. Chapter 3 : 2D Scaling Transformations
    1. Introduction to Geometric Transformations
    2. Scaling Example in OpenCV
    3. Quiz (Scaling Example in OpenCV)
    4. Solution (Scaling Example in OpenCV)
    5. Scaling in Real Space
    6. Quiz (Scaling in Real Space)
    7. Solution (Scaling in Real Space)
    8. Linear Transformation Explained
    9. Scaling is a Linear Transformation
    10. Scaling as a Matrix Multiplication Example Python
    11. Quiz (Scaling as a Matrix Multiplication Example Python)
    12. Solution (Scaling as a Matrix Multiplication Example Python)
    13. Image Coordinate System
    14. Image Copy and Flipping Vertically
    15. Quiz 01 (Image Copy and Flipping Vertically)
    16. Solution 01 (Image Copy and Flipping Vertically)
    17. Quiz 02 (Image Copy and Flipping Vertically)
    18. Solution 02 (Image Copy and Flipping Vertically)
    19. Continuous Coordinates
    20. Saturations and Holes
    21. Image Doubling and Holes using Python
    22. Inverse Scaling and Quiz
    23. Solution and Nearest Neighbor Interpolation
    24. Inverse Scaling Python
    25. Quiz 01 (Inverse Scaling Python)
    26. Solution 01 (Inverse Scaling Python)
    27. Quiz 02 (Inverse Scaling Python)
    28. Solution 02 (Inverse Scaling Python)
    29. Nearest Neighbor Interpolation
    30. Weighted Average Versus Simple Average
    31. Bilinear Interpolation
    32. Bilinear Interpolation Implementation in Python
    33. Scaling Transformation with Bilinear Interpolation Implementation
    34. Scaling Transformation Algorithm(Recap)
    35. Exam
    36. Exam Solution 01
    37. Exam Solution 02
  4. Chapter 4 : 2D Geometric Transformations
    1. Rotation Introduction
    2. Optional Rotation is Linear Transform Proof
    3. Rotation can Result Negative Coordinates (Problem)
    4. Rotation Computing Width and Hight of Resultant Image(Solution)
    5. Rotation Index Shifting
    6. Quiz (Rotation Index Shifting)
    7. Solution (Rotation Index Shifting)
    8. Rotation Implementation Complete
    9. Quiz (Rotation Implementation Complete)
    10. Solution (Rotation Implementation Complete)
    11. Rotation Implementation (Good Coding Practice)
    12. Quiz: Rotation Implementation (Good Coding Practice)
    13. Solution: Rotation Implementation (Good Coding Practice)
    14. Reflection Introduction
    15. Quiz (Reflection Introduction)
    16. Solution (Reflection Introduction)
    17. Reflection Implementation
    18. Quiz 01 (Reflection Implementation)
    19. Solution 01 (Reflection Implementation)
    20. Quiz 02 (Reflection Implementation)
    21. Solution 02 (Reflection Implementation)
    22. Shear Introduction
    23. Shear Implementation and Quiz
    24. Translation and its Nonlinearity (Problem)
    25. Homogeneous Coordinates
    26. Translation as a Matrix (Solution)
    27. Homogeneous Representations of All Transformations
    28. Affine Transformation Implementation
    29. Quiz (Affine Transformation Implementation)
    30. Rotation about Any Point Theory
    31. Rotation about Any Point Implementation
    32. Reflection about a Line Quiz
    33. Solution (Reflection about a Line)
    34. Transformation Matrix Properties
    35. Transformation Matrix Properties Implementation
    36. Affine Transformation Hierarchy
    37. Optional Affine Transformation SVD
    38. Projective Transformation Homography
    39. Projective Transformation Implementation
    40. Projective Warping Algorithm
  5. Chapter 5 : Geometric Transformation Estimation (Panorama)
    1. Goal
    2. Affine Transformation Estimation Introduction
    3. Quiz (Affine Transformation Estimation Introduction)
    4. Solution (Affine Transformation Estimation Introduction)
    5. Affine Transformation Estimation Points Correspondences
    6. Estimation Points Marking using Python and Quiz
    7. Affine Transformation Min Number of Points Needed
    8. Affine Transformation Estimation using Python
    9. Affine Transformation Estimation Verification using Python
    10. Affine Transformation Estimation with More Than Three Points
    11. Quiz (Affine Transformation Estimation with More Than Three Points)
    12. Solution (Affine Transformation Estimation with More Than Three Points)
    13. Affine Transformation Estimation with More Than Three Points Implementation
    14. Quiz (Affine Transformation Estimation with More Than Three Points Implementation)
    15. Solution (Affine Transformation Estimation with More Than Three Points Implementation)
    16. Optional Affine Transformation Estimation with LeastSquared
    17. Projective Transformation Estimation Introduction
    18. Projective Transformation Estimation First Implementation having Bug
    19. Projective Transformation Estimation Reason of the Bug
    20. Projective Transformation Estimation Removing Scale Factor
    21. Projective Transformation Estimation DLT
    22. Projective Transformation Estimation DLT Nullspace and Why Four Points
    23. Projective Transformation Estimation DLT Nullspace Implementation
    24. DLT Implementation
    25. Quiz (DLT Implementation)
    26. Panorama Stitching
    27. Panorama Stitching Implementation in OpenCV
    28. How Projective Transformation Helps in Panorama
  6. Chapter 6 : Binary Morphology
    1. Binary Images Theory
    2. Binary Images Python
    3. Structuring Element Kernel and Sliding Window Theory
    4. Structuring Element Python
    5. Erosion Theory
    6. Quiz 01 (Erosion Theory)
    7. Solution 01 (Erosion Theory)
    8. Quiz 02 (Erosion Theory)
    9. Solution 02 (Erosion Theory)
    10. Erosion Python
    11. Dilation Theory
    12. Quiz 01 (Dilation Theory)
    13. Solution 01 (Dilation Theory)
    14. Quiz 02 (Dilation Theory)
    15. Solution 02 (Dilation Theory)
    16. Dilation Python
    17. Opening Theory
    18. Opening Python
    19. Closing Theory
    20. Closing Python
    21. Gradient Morphology
    22. Gradient Morphology Python
    23. Top Hat and Black Hat
  7. Chapter 7 : Image Filtering
    1. Image Blurring 01
    2. Image Blurring 02
    3. General Image Filtering
    4. Convolution
    5. Naive Edge Detection
    6. Image Sharpening
    7. Quiz (Image Sharpening)
    8. Solution (Image Sharpening)
    9. Implementation of Image Blurring, Edge Detection, and Image Sharpening in Python
    10. Low Pass, High Pass, and Band Pass Filters
  8. Chapter 8 : Canny Edge Detector
    1. Canny Edge Detector Algorithm Introduction
    2. Canny Edge Detector OpenCV
    3. Quiz (Canny Edge Detector OpenCV)
    4. Solution (Canny Edge Detector OpenCV)
    5. Gaussian Filter Introduction
    6. Gaussian Filter to Mask Computation
    7. Gaussian Filter Window Size
    8. Gaussian Filter Implementation
    9. Quiz (Gaussian Filter Implementation)
    10. Solution (Gaussian Filter Implementation)
    11. Gaussian Filter Smoothing Implementation
    12. Quiz (Gaussian Filter Smoothing Implementation)
    13. Solution (Gaussian Filter Smoothing Implementation)
    14. Image Gradients Theory
    15. Image Gradients Implementation
    16. Image Gradients Implementation Datatype Bug
    17. Derivative of Gaussian
    18. Derivative of Gaussian Expression
    19. Derivative of Gaussian Implementation
    20. Applying DOG Filters
    21. Gradient Vector
    22. Gradient Magnitude and Gradient Direction
    23. Non-Maxima Suppression
    24. Gradient Direction Quantization
    25. Quiz (Gradient Direction Quantization)
    26. Solution (Gradient Direction Quantization)
    27. Gradient Direction Quantization Implementation
    28. Gradient Direction Quantization Implementation Better Way
    29. NMS Implementation
    30. Quiz 01 (NMS Implementation)
    31. Solution 01 (NMS Implementation)
    32. Quiz 02 (NMS Implementation)
    33. Solution 02 (NMS Implementation)
    34. Last Step Thresholding
    35. Hysteresis Thresholding
    36. Hysteresis Thresholding Implementation
  9. Chapter 9 : Shape Detection
    1. Shape Detection Introduction
    2. Why Edge Detection is not Enough
    3. RANSAC Introduction
    4. RANSAC For Lines Coordinate Arrays
    5. RANSAC for Lines Sampling Points Randomly Implementation
    6. Quiz (RANSAC for Lines Sampling Points Randomly Implementation)
    7. Solution (RANSAC for Lines Sampling Points Randomly Implementation)
    8. RANSAC for Lines - Fitting Line with Two Points
    9. RANSAC for Lines - Fitting Line with Two Points Implementation
    10. Quiz (RANSAC for Lines Fitting Line with Two Points Implementation)
    11. Solution (RANSAC for Lines Fitting Line with Two Points Implementation)
    12. RANSAC for Lines Computing Consistency Score
    13. RANSAC For Lines Computing Consistency Score Implementation
    14. RANSAC for Lines Implementation
    15. RANSAC for Lines Implementation Test on Real Image
    16. Drawback
    17. RANSAC for Lines Implementation Test on Real Image Drawing and Quiz
    18. RANSAC for Circles
    19. RANSAC for Circles Consistency Score
    20. RANSAC for Circles Implementation
    21. RANSAC for Circles Implementation Real Image
    22. Drawback
    23. RANSAC for Circles Implementation Real Image Drawing
    24. RANSAC General
    25. RANSAC Quiz
    26. RANSAC Quiz Solution
  10. Chapter 10 : Shape Detection Hough Transform
    1. Hough Transform Introduction
    2. Hough Transform as Voting
    3. Hough Transform as Voting Loop
    4. Hough Transform Polar Representation
    5. Hough Transform Polar Representation Benefits
    6. Hough Transform Polar Representation Implementation
    7. Hough Transform Lines Implementation Real Image
    8. Hough Transform Lines Parameters Conversion
    9. Hough Transform Lines Drawing
    10. Solution (Hough Transform Lines Drawing)
    11. Hough Transform Fast Version
    12. Hough Transform Circles
    13. Hough Transform Circles Implementation
    14. Hough Transform Circles Implementation Drawing
    15. Solution (Hough Transform Circles Implementation Drawing)
  11. Chapter 11 : Corner Detection
    1. Corner Definition
    2. Why Corner
    3. Corner Measure
    4. SSD
    5. Why SSD to be Muted Somewhere
    6. Corner Detection Implementation 01
    7. Corner Detection Implementation 02
    8. Corner Detection Implementation 03
    9. Moravec Corner Detector
    10. Scale Space
    11. Infinite Directions Towards Harris Corner Detector
    12. Harris Corner Detector 01
    13. Harris Corner Detector 02
    14. Harris Corner Detector 03
    15. Harris Corner Detector 04 Structure Tensor
    16. Harris Corner Detector 05 Final Expression
    17. Harris Corner Detector Implementation Speedup Convolution
    18. Harris Corner Detector Implementation 01
    19. Harris Corner Detector Implementation 02
    20. Harris Corner Detector as Edge Detector
  12. Chapter 12 : Automatic Panorama SIFT
    1. Point Correspondence Introduction
    2. Point Drawing Implementation
    3. Scale and Orientation Alignment
    4. SIFT and HOG
    5. Points Matching
  13. Chapter 13 : Object Detection
    1. Introduction to Object Detection
    2. Classification Pipeline
    3. Sliding Window Implementation
    4. Shift Scale Rotation Invariance
    5. Person Detection
    6. HOG Features
    7. Hand Engineering Versus CNNs
    8. Implementation
    9. Activity
  14. Chapter 14 : YOLO Object Detector
    1. CNNS Introduction
    2. Face Detection Implementation
    3. YOLO Implementation
    4. YOLO Image Classification Revisited
    5. YOLO Sliding Window Object Localization
    6. YOLO Sliding Window Efficient Implementation
    7. YOLO Introduction
    8. YOLO Training Data Generation
    9. YOLO Anchor Boxes
    10. YOLO Algorithm
    11. YOLO Non-Maxima Suppression
    12. YOLO RCNN
  15. Chapter 15 : Motion
    1. Optical Flow
    2. BC Assumption
    3. Optical Flow Derivation
  16. Chapter 16 : Object Tracking
    1. Tracking by Detection
    2. Tracking by Detection Motion Model Assumption
    3. Tracking KLT TLD
    4. Single Object Tracking
    5. Multiple Object Tracking
    6. WebCam and Saving Annotations of Multiple Object Tracking
  17. Chapter 17 : 3D Reconstruction
    1. 3d Reconstruction Introduction
    2. 3d Motion Capture
    3. Camera
    4. Camera Matrix
    5. Triangulation
    6. Camera Matrix Estimation
    7. Mocap Revisited
  18. Chapter 18 : Smart CCTV Project
    1. Introduction to the Project
    2. Introduction to Data
    3. Reading a Video File
    4. Change Detection Frame Differencing
    5. Change Detection Frame Differencing Implementation
    6. Change Detection Background Subtraction
    7. Change Detection Background Subtraction MOG
    8. Denoising using Morphology
    9. Connected Components
    10. Connected Components Filtering
    11. Tracking Change
    12. Saving Segments
    13. Saving and Viewing Segments
    14. Saving and Viewing Segments with Object Detection
    15. Applications

Product information

  • Title: Computer Vision Theory and Projects in Python for Beginners
  • Author(s): AI Sciences
  • Release date: September 2021
  • Publisher(s): Packt Publishing
  • ISBN: 9781801815949