Last updated 10/2018MP4 | Video: h264, 1280x720 | Audio: AAC, 44.1 KHzLanguage: English | Size: 1.73 GB | Duration: 3h 49m

Dive deep into computer vision concepts for image processing with Python 3

What you'll learn

Work with open source libraries such Pillow, Scikit-image, and OpenCV

Perform basic to advanced image and video stream processing with OpenCV Python APIs

Write programs for edge detection, color processing, image feature extraction, and more

Implement feature detection algorithms such as LBP and ORB

Understand convolutional neural networks to learn patterns in images

Work with human faces and perform identification and orientation estimation

Discover deep learning methods that can be applied to a wide variety of problems in computer vision

Requirements

Basic knowledge of Python is expected.

Description

Python comes with many freely available powerful modules for handling images, mathematical computing, and data mining which makes it an ideal language for rapidly prototyping and developing production-grade codes for image processing and computer vision. If you wish to build computer vision applications that are smarter, faster, more complex, and more practical with Python 3, then you should surely go for this Learning Path. This comprehensive 2-in-1 course aims to equip you to build Computer Vision applications that are capable of working in real-world scenarios effectively. Some of the applications that you will learn in this course are Optical Character Recognition, Object Tracking and building a Computer Vision as a Service platform that works over the internet. You will also learn state-of-the-art techniques to classify images, and to find and identify humans within videos. This learning path will give you a versatile range of computer vision techniques with Python 3, which you will put to work in building your own computer vision applications. This training program includes 2 complete courses, carefully chosen to give you the most comprehensive training possible. The first course, Python 3.x for Computer Vision, starts off with an introduction to image processing. You will then learn features and filters in computer vision. You will also implement feature detection algorithms such as LBP and ORB. Finally, you will understand convolutional neural networks to learn patterns in images. Throughout this course, three image processing libraries: Pillow, Scikit-Image, and OpenCV are used to implement different computer vision algorithms. The second course, Computer Vision Projects with Python 3, starts off by showing you how to set up Anaconda Python for the major OSes with cutting-edge third-party libraries for computer vision. You will then learn state-of-the-art techniques to classify images and find and identify humans within videos. Next, you will learn to augment Python with the powerful vision and machine learning tools such as OpenCV and TensorFlow. Finally, you will learn to detect facial features and develop a general image classifier.By the end of this Learning Path, you will be able to build computer vision applications that are capable of working in real-world scenarios effectively.About the Authors : Saurabh Kapur is a computer science student at Indraprastha Institute of Information Technology, Delhi. His interests are in computer vision, numerical analysis, and algorithm design. He often spends -solving competitive programming questions. Saurabh also enjoys working on IoT applications and tinkering with hardware. He likes to spend his free playing or watching cricket.Matthew Rever is an image processing and computer vision eeer at a major national laboratory. He has years of experience automating the analysis of complex scientific data, as well as the control of sophisticated instruments. He has applied computer vision technology to save a great many hours of valuable human labor. He is also enthusiastic about making the latest developments in computer vision accessible to developers of all backgrounds.

Overview

Section 1: Python 3.x for Computer Vision

Lecture 1 The Course Overview

Lecture 2 Image Processing and Its Applications

Lecture 3 Image Processing Libraries - Pillow

Lecture 4 Geometrical Transformation - Pillow

Lecture 5 Introduction to scikit-image

Lecture 6 Image Derivatives

Lecture 7 Understanding Image Filters

Lecture 8 Custom Filters and Image Thresholding

Lecture 9 Edge Detection

Lecture 10 Harris Corner Detection

Lecture 11 Local Binary Patterns

Lecture 12 Oriented FAST and Rotated BRIEF (ORB)

Lecture 13 Image Stitching

Lecture 14 Contour Detection and the Watershed Algorithm

Lecture 15 Superpixels and Normalized Graph Cut

Lecture 16 Introduction to Machine Learning

Lecture 17 Logistic Regression

Lecture 18 Support Vector Machines

Lecture 19 K-means Clustering

Lecture 20 Introduction to Neural Network

Lecture 21 MNIST Digit Classification Using Neural Networks

Lecture 22 Convolutional Neural Networks

Section 2: Computer Vision Projects with Python 3

Lecture 23 The Course Overview

Lecture 24 ing and Installing Python 3/Anaconda

Lecture 25 Installing Additional Libraries

Lecture 26 Exploring the Jupyter Notebook

Lecture 27 Acquiring and Processing MNIST Digit Data

Lecture 28 Creating and Training a Support Vector Machine

Lecture 29 Applying the Support Vector Machine to New Data

Lecture 30 Introducing TensorFlow with Digit Classification

Lecture 31 Evaluating the Results

Lecture 32 Introducing dlib

Lecture 33 What Are Facial Landmarks?

Lecture 34 Example One – Finding 68 Facial Landmarks in Images

Lecture 35 Example Two – Faces in Videos

Lecture 36 Example Three – Facial Recognition

Lecture 37 A Deeper Introduction to TensorFlow

Lecture 38 Using a Pre-Trained Model (Inception) for Image Classification

Lecture 39 Retraining with Our Own Images

Lecture 40 Speeding Up Computations with GPUs

This learning path is for developers who want to explore the field of computer vision to design and develop computer vision applications with Python.

HomePage:

gfxtra__Python_Com.part1.rar.html

gfxtra__Python_Com.part2.rar.html