The Computer Vision Workshop: Develop the skills you need to use computer vision algorithms in your own artificial intelligence projects

Description

Explore the potential of deep learning techniques in computer vision applications using the Python ecosystem, and build real-time systems for detecting human behavior Key Features Understand OpenCV and select the right algorithm to solve real-world problems Discover techniques for image and video processing Learn how to apply face recognition in videos to automatically extract key informationBook Description Computer Vision (CV) has become an important aspect of AI technology. From driverless cars to medical diagnostics and monitoring the health of crops to fraud detection in banking, computer vision is used across all domains to automate tasks. The Computer Vision Workshop will help you understand how computers master the art of processing digital images and videos to mimic human activities. Starting with an introduction to the OpenCV library, you'll learn how to write your first script using basic image processing operations. You'll then get to grips with essential image and video processing techniques such as histograms, contours, and face processing. As you progress, you'll become familiar with advanced computer vision and deep learning concepts, such as object detection, tracking, and recognition, and finally shift your focus from 2D to 3D visualization. This CV course will enable you to experiment with camera calibration and explore both passive and active canonical 3D reconstruction methods. By the end of this book, you'll have developed the practical skills necessary for building powerful applications to solve computer vision problems. What you will learn Access and manipulate pixels in OpenCV using BGR and grayscale images Create histograms to better understand image content Use contours for shape analysis, object detection, and recognition Track objects in videos using a variety of trackers available in OpenCV Discover how to apply face recognition tasks using computer vision techniques Visualize 3D objects in point clouds and polygon meshes using Open3DWho this book is for If you are a researcher, developer, or data scientist looking to automate everyday tasks using computer vision, this workshop is for you. A basic understanding of Python and deep learning will help you to get the most out of this workshop. Table of Contents Basics of Image Processing Common Operations When Working with Images Working with Histograms Working with Contours Face Processing in Image and Video Object Tracking Object Detection and Face Recognition OpenVINO with OpenCV Cover FM Copyright Table of Contents Preface Chapter 1: Basics ofImage Processing Introduction NumPy Arrays Exercise 1.01: Creating NumPy Arrays Pixels in Images Pixel Location – Image Coordinate System Image Properties Size of the Image Color Spaces and Channels Pixel Values Introduction to OpenCV Images in OpenCV Important OpenCV Functions Exercise 1.02: Reading, Processing, and Writing an Image Using Matplotlib to Display Images Accessing and Manipulating Pixels Exercise 1.03: Creating a Water Effect Activity 1.01: Mirror Effect with a Twist Summary Chapter 2: Common Operations When Working with Images Introduction Geometric Transformations Image Translation Exercise 2.01: Translation Using NumPy Image Rotation Finding the Rotation Matrix Finding the Size of the Output Image Image Resizing Affine Transformation Exercise 2.02: Working with Affine Transformation Perspective Transformation Exercise 2.03: Perspective Transformation Image Arithmetic Image Addition Exercise 2.04: Performing Image Addition Image Multiplication Exercise 2.05: Image Multiplication Binary Images Exercise 2.06: Converting an Image into a Binary Image Bitwise Operations on Images Exercise 2.07: Chess Pieces Masking Activity 2.01: Masking Using Binary Images Summary Chapter 3: Working with Histograms Introduction Introduction to Matplotlib Displaying Images with Matplotlib Plotting Histograms with Matplotlib Exercise 3.01: Plotting a Sample Image and Its Histogram with 256 bins Exercise 3.02: Plotting a Sample Image and Its Histogram with 10 bins Histograms with OpenCV User-Selected ROI Exercise 3.03: Creating a Mask Image Using a User-Selected ROI A Comparison of Some Sample Histograms What Is Histogram Equalization? Exercise 3.04: Histogram Equalization of a Grayscale Image Contrast Limited Adaptive Histogram Equalization (CLAHE) Exercise 3.05: Application of CLAHE on a Grayscale Image Activity 3.01: Enhancing Images Using Histogram Equalization and CLAHE Exercise 3.06: Histogram Equalization in the BGR Color Space The Histogram Equalization of Color Images Using the HSV and LAB Color Spaces Exercise 3.07: Histogram Equalization in the HSV Color Space Exercise 3.08: Histogram Equalization in the LAB Color Space Activity 3.02: Image Enhancement in a User-Defined ROI Summary Chapter 4: Working with contours Introduction Contours – Basic Detection and Plotting Exercise 4.01: Detecting Shapes and Displaying Them on BGR Images Exercise 4.02: Detecting Shapes and Displaying Them on Black and White Images Exercise 4.03: Displaying Different Contours with Different Colors and Thicknesses Drawing a Bounding Box around a Contour Area of a Contour Difference between Contour Detection and Edge Detection Hierarchy Exercise 4.04: Detecting a Bolt and a Nut Exercise 4.05: Detecting a Basketball Net in an Image Contour Matching Exercise 4.06: Detecting Fruits in an Image Exercise 4.07: Identifying Bananas from the Image of Fruits Exercise 4.08: Detecting an Upright Banana from the Image of Fruits Activity 4.01: Identifying a Character on a Mirrored Document Summary Chapter 5: Face Processing in Image and Video Introduction Introduction to Haar Cascades Using Haar Cascades for Face Detection Exercise 5.01: Face Detection Using Haar Cascades Detecting Parts of the Face Exercise 5.02: Eye Detection Using Cascades Clubbing Cascades for Multiple Object Detection Activity 5.01: Eye Detection Using Multiple Cascades Activity 5.02: Smile Detection Using Haar Cascades GrabCut Technique Exercise 5.03: Human Body Segmentation Using GrabCut with Rectangular Mask Exercise 5.04: Human Body Segmentation Using Mask and ROI Activity 5.03: Skin Segmentation Using GrabCut Activity 5.04: Emoji Filter Summary Chapter 6: Object Tracking Introduction Naïve Tracker Exercise 6.01: Object Tracking Using Basic Image Processing Non-Deep Learning-Based Object Trackers Kalman Filter – Predict and Update Meanshift – Density Seeking Filter CAMshift – Continuously Adaptive Meanshift The OpenCV Object Tracking API Object Tracker Summary Exercise 6.02: Object Tracking Using the Median Flow and MIL Trackers Installing Dlib Object Tracking Using Dlib Exercise 6.03: Object Tracking Using Dlib Activity 6.01: Implementing Autofocus Using Object Tracking Summary Chapter 7: Object Detection and Face Recognition Introduction Face Recognition Face Recognition Using Eigenfaces Principal Component Analysis Eigenfaces Exercise 7.01: Facial Recognition Using Eigenfaces Limitations of the Eigenface Method Fisherface Exercise 7.02: Facial Recognition Using the Fisherface Method Local Binary Patterns Histograms Exercise 7.03: Facial Recognition Using the LBPH Method Object Detection Single Shot Detector MobileNet Exercise 7.04: Object Detection Using MobileNet SSD Object Detection Using the LBPH Method Exercise 7.05: Object Detection Using the LBPH Method Haar Cascades Exercise 7.06: Object Detection Using Haar-Based Features Activity 7.01: Object Detection in a Video Using MobileNet SSD Activity 7.02: Real-Time Facial Recognition Using LBPH Summary Chapter 8: OpenVINO with OpenCV Introduction Exploring the OpenVINO Toolkit Components of the OpenVINO Toolkit Installing OpenVINO for Ubuntu OpenVINO as a Backend in OpenCV The Need for Pre-Trained Models OpenVINO Model Zoo Exercise 8.01: Downloading the Pedestrian and Vehicle Detection Model Model Specifications Image Transforms Using OpenCV Exercise 8.02: Image Preprocessing Using OpenCV Model Conversion Using Model Optimizer Introduction to OpenVINO's Inference Engine Exercise 8.03: Vehicle and Pedestrian Detection Activity 8.01: Face Detection Using OpenVINO and OpenCV Summary Appendix Index