Dive into the advanced concepts of OpenCV and Machine learning for techniques to detect and decode images in OpenCV.
What you'll learn
Grasp the advanced concepts of bootstrapping, boosting, voting, and bagging.
Discover hidden structures in your data using k-means clustering.
Encode, decode, and denoise images with autoencoders.
Understand the structure and function of neural networks and CNN/pooling.
Classify images with OpenCV using smart Deep Learning methods
Detect objects in images with You Only Look Once (YOLOv3)
Work with advanced imaging tools such as Deep Dream, Style Transfer, and Neural Doodle
See functionalities in OpenCV that can be used for Object detection and recognition through Deep Learning
Master use of OpenCV by practicing the creation of basic applications.
Requirements
Prior working knowledge of Python Programming and Computer Vision knowledge is assumed.
Description
Machine Learning and Deep learning techniques, in particular, are changing the way computers see and interact with the World. From augmented and mixed-reality applications to just gathering data, these new techniques are revolutionizing a lot of industries. OpenCV is a cross-platform library using which we can develop real-time computer vision applications. It mainly focuses on image processing, video capture, and analysis including features like face detection and object detection. This course is designed to give you a hands-on learning experience by going from the basic concepts to the most current in-depth Deep Learning methods for Computer Vision in use today.This comprehensive 3-in-1 course a step-by-step, project-based approach to skill up with techniques for detection and decoding of images with advanced concepts of Machine Learning and Deep Learning with OpenCV. Initially, you'll not only understand, perform, and experiment with Machine Learning techniques but also load, store and visualize data using OpenCV and Python. You'll also learn Deep Learning techniques commonly used for Computer Vision: from denoising to classification/similarity matching, image generation, and object detection. Finally, you'll explore functionalities in OpenCV that can be used for Object detection and recognition through Deep Learning as well as master use of OpenCV by practicing the development of basic applications.By the end of the course, you'll skill up with techniques for detection and decoding of images with advanced concepts of Machine Learning and Deep Learning with OpenCV.Contents and OverviewThis training program includes 3 complete courses, carefully chosen to give you the most comprehensive training possible.The first course, Machine Learning for OpenCV – Advanced Methods and Deep Learning, covers a practical introduction to the world of machine learning and image processing using OpenCV and Python. The course will also guide you through creating custom graphs and visualizations, and show you how to go from raw data to beautiful visualizations. By the end of this course, you will be ready to create your own ML system and will also be able to take on your own machine learning problems.The second course, Hands-On Deep Learning for Computer Vision, covers how to generate, detect, and classify images faster and more accurately. In this course, you will be introduced to the concept of deep learning and a variety of popular and effective techniques for image classification, detection, segmentation, and generation. You will learn to build your own neural network and classify images accordingly. You will be taken through popular techniques such as Deep Dream (to generate psychedelic, surreal images), Style Transfer (to transfer styles between images), and Neural Doodle, to generate an image that matches a doodled sketch. By the end of this course, you will be able to use computer vision and deep learning to encode, classify, detect, and style images for the real world.The third course, Object Detection and Recognition Using Deep Learning in OpenCV, covers OpenCV Object Recognition: Harness Deep Learning in OpenCV. This course teaches effective object recognition and its implementation with the powerful OpenCV libraries. You will learn how to enhance your OpenCV skills with deep learning. You will explore and master OpenCV for Object Recognition/Classification. The course explains all the necessary theory and concepts of computer vision, image processing, and machine learning. You also learn the practical application of OpenCV libraries. Its capabilities and functionality are shown along with a tutorial on how to set up a machine such that it's able to use OpenCV in codes. You will start by seeing how to work with images in OpenCV, enhancement, and filtering in OpenCV. You will then move on to building an application which is capable of object recognition and performing homography. You will then move on to object classification and recognizing text in an image. In the end, you will be able to use object recognition algorithm which will be used by you for practical application.By the end of the course, you'll learn techniques for detection and decoding of images with advanced concepts of Machine Learning and Deep Learning with OpenCV.About the AuthorsMichael Beyeler is a Postdoctoral Fellow at the University of Washington in Seattle. His work lies at the intersection of neuroscience, computer vision, and machine learning. Michael is the author of two Packt books: OpenCV with Python Blueprints (2015) and Machine Learning for OpenCV (2017). He is an active contributor to several open-source software projects and has professional programming experience in Python, C/C++, CUDA, MATLAB, and Android.Jakub Konczyk has enjoyed programming professionally since 1995. He is a Python and Django expert and has been involved in building complex systems since 2006. He loves to simplify and teach programming subjects and share his knowledge with others. He first discovered Machine Learning when he was trying to predict real estate prices in one of the early stage startups he was involved in. He failed miserably. Then he discovered a much more practical way to learn Machine Learning that he would like to share with you in this course. It boils down to the Keep it simple! mantra.Param Uttarwar has extensively worked in OpenCV and he has been in touch with OpenCV, ML and AI field. Previously, he worked on a similar kind of project where he developed software that aided users in learning image processing. It used OpenCV and Qt Libraries at its core and was deployed on the hardware. The author has worked out image processing algorithms on SBCs & FPGAs. The author has also taught these topics himself, so he is well acquainted with the practical problems faced during learning which are not written in books. He feels that he is the best suited for authoring this course.
Overview
Section 1: Machine Learning for OpenCV - Advanced Methods and Deep Learning
Lecture 1 The Course Overview
Lecture 2 Understanding and Implementing Bayesian Classifier
Lecture 3 Classifying Emails Using Naive Bayes Classifier
Lecture 4 Understanding Unsupervised Learning and k-means Clustering
Lecture 5 Understanding Expectation-Maximization
Lecture 6 Compressing Color Spaces Using k-means
Lecture 7 Classifying Handwritten Digits Using k-means
Lecture 8 Organizing Clusters as a Hierarchical Tree
Lecture 9 Understanding and Implementing Perceptron
Lecture 10 Understanding and Implementing Multilayer Perceptrons
Lecture 11 Getting Acquainted with Deep Learning
Lecture 12 Classifying Handwritten Digits
Lecture 13 Understanding Ensemble Methods
Lecture 14 Combining Decision Trees into a Random Forest
Lecture 15 Using Random Forests for Face Recognition
Lecture 16 Implementing AdaBoost
Lecture 17 Combining Different Models into a Voting Classifier
Lecture 18 Evaluating a Model
Lecture 19 Understanding Cross-Validation
Lecture 20 Estimating Robustness Using Bootstrapping
Lecture 21 Assessing the Significance of Our Results
Lecture 22 Tuning Hyperparameters with Grid Search
Lecture 23 Chaining Algorithms Together to Form a Pipeline
Section 2: Hands-On Deep Learning for Computer Vision
Lecture 24 The Course Overview
Lecture 25 A High-Level Overview of Deep Learning
Lecture 26 Installing Keras and TensorFlow
Lecture 27 Building a CNN Based Autoencoder to Denoise Images
Lecture 28 Summary
Lecture 29 An Introduction to ImageNet Dataset and VGG Model
Lecture 30 Using a Pre-Trained VGG Model
Lecture 31 Summary and What's Next?
Lecture 32 Introduction to GANs
Lecture 33 Building GANs to Learn MNIST Dataset
Lecture 34 Summary and What's Next?
Lecture 35 An Introduction to Object Detection and YOLO
Lecture 36 Installing and Setting Up Keras Implementation of YOLO
Lecture 37 Using a Pre-Trained YOLO Model for Object Detection
Lecture 38 Summary and What's Next?
Lecture 39 An Introduction to Neural Style Transfer
Lecture 40 Using Keras Implementation of Neural Style Transfer
Lecture 41 Summary
Section 3: Object Detection and Recognition Using Deep Learning in OpenCV
Lecture 42 The Course Overview
Lecture 43 How to Work with Images in OpenCV?
Lecture 44 Enhancement and Filtering Operations in OpenCV
Lecture 45 Saving Images, Accessing Camera
Lecture 46 Image Transformations
Lecture 47 Computer Vision Algorithms
Lecture 48 Working with Object Recognition
Lecture 49 Features and Descriptors
Lecture 50 Feature Matching and Homography
Lecture 51 Building an Application
Lecture 52 Getting Started with Neural Networks
Lecture 53 Architecture of a Convolutional Neural Network (CNN)
Lecture 54 Starting with Caffe
Lecture 55 Implementing Deep Learning Using OpenCV and Caffe
Lecture 56 Defining Problem Statement
Lecture 57 Designing an Algorithm for the Problem
Lecture 58 Training the Network Using Labeled Data
Lecture 59 Classification Problem
Lecture 60 Problem Definition and Gathering Dataset
Lecture 61 Modeling Appropriate Algorithm
Lecture 62 Moving from Algorithm to Code
Lecture 63 Results and Analysis
This course is perfect for:,Python Developers who are already familiar with OpenCV and want to perform Machine Learning and Deep Learning with OpenCV will find this Course very helpful.
Screenshots