Last updated 3/2019MP4 | Video: h264, 1280x720 | Audio: AAC, 44.1 KHzLanguage: English | Size: 3.02 GB | Duration: 7h 10m

Grasp the concepts of OpenCV 4 to build powerful machine learning systems and computer vision applications with OpenCV 4

What you'll learn

Build real- applications that deal with image and video processing

Build an Optical Character Recognition (OCR) ee from scratch

Get to know how to train face recognition system

Create your own real- object classifier

Build computer vision applications

Create DNN based Image Classifier

How to apply various Machine Learning algorithms to real-life problems

Explore Supervised Learning and Unsupervised Learning approaches in Computer Vision

Train your own custom image classifier using Convolutional Neural Networks

Requirements

Working knowledge of Python programming is required.

Description

The application of Machine Learning and Deep Learning is rapidly gaining significance in Computer Vision. OpenCV lies at the intersection of these topics, providing a comprehensive open-source library for classic as well as state-of-the-art Computer Vision and Machine Learning algorithms. If you wish to build systems that are smarter, faster, sophisticated, and more practical by combining the power of Computer Vision, Machine Learning, and Deep Learning with OpenCV 4, then you should surely go for this Learning Path.This hands-on course on OpenCV not only helps you learn computer vision and ML with OpenCV 4 but also enables you to apply these skills to your projects. You will firstly set up your development environment for building 5 interesting computer vision applications for Face and Eyes detection, Emotion recognition, and Fast QR code detection. You will then explore essential machine learning and deep learning concepts such as supervised learning, unsupervised learning, neural networks, and learn how to combine them with other OpenCV functionality for image processing and object detection. Along the way, you will also get some tips and tricks to work efficiently.Contents and OverviewThis training program includes 3 complete courses, carefully chosen to give you the most comprehensive training possible.The first course, Hands-On OpenCV 4 with Python, is designed for you to develop some real-world computer vision applications. You will b with setting up your environment. You will then build five exciting applications. You will also be introduced to all necessary concepts and then moving into the field of Artificial Intelligence (AI) and deep learning such as classification and object detection with OpenCV 4.The second course, OpenCV 4 Computer Vision with Python Recipes, starts off with an introduction to OpenCV 4 and familiarizes you with the advancements in this version. You will learn how to handle images, enhance, and transform them. You will also develop some cool applications including Face and Eyes detection, Emotion recognition, and Fast QR code detection & decoding which can be deployed anywhere.The third course, Hands-On Machine Learning with OpenCV 4, will immerse you in Machine Learning and Deep Learning, and you'll learn about key topics and concepts along the way.By the end of this course, you will be able to tackle increasingly challeg computer vision problems faced in day-to-day life and leverage the power of machine learning algorithms to build machine learning systems and computer vision applications that are smarter, faster, more complex, and more practical.Meet Your Expert(s):We have the best work of the following esteemed author(s) to ensure that your learning journey is smooth:Colibri Digital is a technology consultancy company founded in 2015 by James Cross and Ingrid Funie. The company works to help their clients navigate the rapidly chag and complex world of emeg technologies, with deep expertise in areas such as Big Data, Data Science, Machine Learning, and Cloud Computing. Over the past few years, they have worked with some of the world's largest and most prestigious companies, including a tier 1 investment bank, a leading management consultancy group, and one of the world's most popular soft drinks companies, helping each of them to better make sense of their data, and process it in more intelligent ways.The company lives by their motto: Data -> Intelligence -> Action.Sourav Johar has over two years of experience with OpenCV and over three years of experience coding in Python. He has also developed an open source library built on top of OpenCV. Along with this, he has developed several Deep Learning solutions, using OpenCV for video analysis. As a computer vision enthusiast, he completely understands what problems students face. He is very passionate about programming and enjoys making programming tutorials on YouTube. He is currently working for Colibri Digital (@colibri_digital) as an instructor.Muhammad Hamza Javed is a self-taught Machine Learning eeer, an entrepreneur and an author having over five years of industrial experience. He and his team has been working on several Computer Vision and Machine Learning international projects. He started working when he was 17 and kept learning new technologies and skills since then. His areas of expertise include Computer Vision, Machine Learning and Deep Learning. He learned skills own his own without a direct mentor - so he knows how troublesome it is for everyone to find to-the-point content that really improves one’s skill-set. He’s designed this course considering the challenges he faced when he learned and, in the projects, so you don’t have to spend too much on finding what’s best for you.

Overview

Section 1: Hands-On OpenCV 4 with Python

Lecture 1 The Course Overview

Lecture 2 Computer Vision with OpenCV 4

Lecture 3 Setting Up the Environment

Lecture 4 Preprocessing Video Input, Thresholding, and Blurring

Lecture 5 Calculating Image Differences

Lecture 6 Visualizing and Triggering Actions

Lecture 7 Understanding Histograms and Back Projection

Lecture 8 Implementing the Histogram Capture for Skin

Lecture 9 Implementing Back Projection on Input Video Feed

Lecture 10 Bounding the Hand – Contour Extraction

Lecture 11 Extracting Fingertips – Convexity Defects

Lecture 12 Air Writing – Translating Gestures to Controls

Lecture 13 Using Haar Cascades – Eye and Face Detection

Lecture 14 Extending Haar Cascades for Eye Detection

Lecture 15 GUI Automation – Interfacing the App with a Media Player

Lecture 16 Deep Learning – What and Why?

Lecture 17 Using the DNN Module with a Pre-Trained Model

Lecture 18 Digging Deeper – Feeding the Input Image to the Neural Network

Lecture 19 Running Object Detection on Videos

Lecture 20 Optical Character Recognition –What, Why, and How?

Lecture 21 Training a Digit Classifier on the MNIST Dataset

Lecture 22 Developing the OCR Ee Functions

Lecture 23 Developing the OCR Ee Functions (Continued)

Lecture 24 OCR Square Calculator

Section 2: OpenCV 4 Computer Vision with Python Recipes

Lecture 25 The Course Overview

Lecture 26 Installation and Setup

Lecture 27 Reading Images from Files

Lecture 28 Simple Image Transformations

Lecture 29 Saving the Images

Lecture 30 Showing the Images

Lecture 31 Drawing 2D Primitives

Lecture 32 Handling User Input from a Keyboard

Lecture 33 Handling User Input from a Mouse

Lecture 34 Capturing and Showing Frames from a Camera

Lecture 35 Playing Frame Stream from Video

Lecture 36 Manipulating Matrices-Creating, Filling, Accessing Elements, and ROIs

Lecture 37 Converting between Different Data Types and Scaling Values

Lecture 38 Non-Image Data Persistence Using NumPy

Lecture 39 Manipulating Image Channels

Lecture 40 Converting Images from One Color Space to Another

Lecture 41 Computing Image Histograms

Lecture 42 Removing Noise Using Gaussian, Median, and Bilateral Filters

Lecture 43 Creating and Applying Your Own Filter

Lecture 44 Processing Images with Different Thresholds

Lecture 45 Morphological Operators

Lecture 46 Image Masks and Binary Operations

Lecture 47 Binarization of Grayscale Images Using the Otsu Algorithm

Lecture 48 Finding External and Internal Contours in a Binary Image

Lecture 49 Extracting Connected Components from a Binary Image

Lecture 50 Fitting Lines and Circles into Two-Dimensional Point Sets

Lecture 51 Calculating Image Moments

Lecture 52 Checking Whether a Point is Within a Contour

Lecture 53 Computing Distance Maps

Lecture 54 Image Sntation Using the k-Means Algorithm

Lecture 55 Warping an Image Using Affine and Perspective Transformations

Lecture 56 Stitching Many Images into Panorama

Lecture 57 Removing Defects from a Photo with Image Inpainting

Lecture 58 Finding Corners in an Image – Harris and FAST

Lecture 59 Computing Descriptors for Image Key Points Using ORB

Lecture 60 Obtaining an Object Mask Using the GrabCut Algorithm

Lecture 61 Finding Edges Using the Canny Algorithm

Lecture 62 Detecting Lines and Circles Using the Hough Transform

Lecture 63 Finding Objects via Template Matching

Lecture 64 Medial Flow Tracker

Lecture 65 Tracking Objects Using Different Algorithms via the Tracking API

Lecture 66 Computing the Dense Optical Flow between Two Frames

Lecture 67 Detecting Chessboard and Circle Grid Patterns

Lecture 68 Simple Pedestrian Detector Using the SVM Model

Lecture 69 Optical Character Recognition Using Different Machine Learning Models

Lecture 70 Detecting Faces Using Haar Cascades

Lecture 71 Fast QR Code Detector and Decoder

Lecture 72 Representing Images as Tensors/Blobs

Lecture 73 Loading Deep Learning Models Using OpenCV | Caffe, Torch and TensorFlow

Lecture 74 Preprocessing Images and Inference in Convolutional Networks

Lecture 75 Dataset Collection from ImageNet

Lecture 76 Dataset Annotation with LabelImg

Lecture 77 Dataset Augmentation

Lecture 78 Classifying Images with GoogleNet/Inception and ResNet Models

Lecture 79 Detecting Objects with the Single Shot Detection (SSD) Model

Lecture 80 Snting a Scene Using the Fully Convolutional Network (FCN) Model

Lecture 81 Introduction to Open Model Zoo

Lecture 82 ONNX (Open Neural Network Exchange)

Lecture 83 G-API (Graph API)

Lecture 84 Age and Gender Recognition

Lecture 85 Face Detection and Emotion Recognition

Lecture 86 Human Detection

Lecture 87 Advanced Applications with OpenVINO

Section 3: Hands-On Machine Learning with OpenCV 4

Lecture 88 The Course Overview

Lecture 89 Introduction to Machine Learning in Computer Vision

Lecture 90 Setting Up the Development Environment

Lecture 91 Reading Images and Video Feeds

Lecture 92 Manipulating Image Properties — Color Spaces, Thresholding

Lecture 93 Exploring the Drawing Functions of OpenCV

Lecture 94 Understanding Supervised Learning

Lecture 95 A Quick Comparison – KNN versus SVM

Lecture 96 Visualizing the Quick, Draw! Dataset and Establishing the ML Pipeline

Lecture 97 Classifying Hand-Made Sketches Using KNN and SVM

Lecture 98 How Unsupervised Learning Is Different

Lecture 99 Clustering and the K- Means Algorithms

Lecture 100 Using K-Means to Cluster the Quick, Draw! Dataset

Lecture 101 Understanding Histograms and Backprojection

Lecture 102 Detecting Objects in Real Using Colour

Lecture 103 Understanding What a Haar Cascade is

Lecture 104 Detecting Objects in Real Using Haar Cascades

Lecture 105 CNNs - What the Hype Is About

Lecture 106 Using a Pre-Trained Caffe Model for Object Detection

Lecture 107 Using the TensorFlow Object Detection API

Lecture 108 Gathering the Dataset and Annotating the Images

Lecture 109 Generate TFRecords and Train

Lecture 110 Export the Inference Graph and Test the Model

This course is intended for Python developers, computer vision developers, and enthusiasts who want to learn machine learning algorithms and implement them with OpenCV 4 for building computer vision applications.

HomePage:

gfxtra__Computer_V.part1.rar.html

gfxtra__Computer_V.part2.rar.html

gfxtra__Computer_V.part3.rar.html

gfxtra__Computer_V.part4.rar.html