Tag: Computer Vision

Course content

• Introduction
• DCGAN and WGAN
• cGAN – Pix2Pix and CycleGAN
• SRGAN and ESRGAN
• StyleGAN
• VQGAN + CLIP – text to image
• Other types of GANs
• Additional content 1: Artificial neural networks
• Additional content 2: Convolution neural networks
• Final remarks

Course content

• Introduction and Getting Started
• About DLIB
• Building a Drowsiness Detection System
• Project Files and Code

Course content

• Introduction
• Camera in ADAS & Autonomous Driving Application
• Camera Image Formation and Calibration
• Image classfication, Localization, segmentation and Object detection
• Concept of Multi Object Tracking for camera images
• Wrap up

Course content

• Introduction
• OCR with Tesseract
• Techniques for image pre-processing
• OCR with EAST for natural scenes
• Training a custom OCR
• Natural scenarios with EasyOCR
• OCR in videos
• Project 1: Searching for specific terms
• Project 2: Scanner + OCR
• Project 3: License plate reading
• Extra content 1: artificial neural networks
• Extra content 2: convolutional neural networks
• Final remarks

Course content

• Introduction
• Intro to Computer Vision & Deep Learning
• Installation Guide
• Handwriting Recognition
• OpenCV Tutorial – Learn Classic Computer Vision & Face Detection (OPTIONAL)
• Neural Networks Explained
• Convolutional Neural Networks (CNNs) Explained
• Build CNNs in Python using Keras
• What CNNs ‘see’ – Filter Visualizations, Heatmaps and Salience Maps
• Data Augmentation: Cats vs Dogs
• Assessing Model Performance
• Optimizers, Learning Rates & Callbacks with Fruit Classification
• Batch Normalization & LeNet, AlexNet: Clothing Classifier
• Advanced Image Classiers – ImageNet in Keras (VGG16/19, InceptionV3, ResNet50)
• Transfer Learning: Build a Flower & Monkey Breed Classifier
• Design Your Own CNN – LittleVGG: A Simpsons Classifier
• Advanced Activation Functions & Initializations
• Facial Applications – Emotion, Age & Gender Recognition
• Medical Imaging – Image Segmentation with U-Net
• Principles of Object Detection
• TensorFlow Object Detection API
• Object Detection with YOLO & Darkflow: Build a London Underground Sign Detector
• DeepDream & Neural Style Transfers: Make A1 Generated Art
• Generative Adversarial Networks (GANs): Simulate Aging Faces
• Face Recognition with VGGFace
• The Computer Vision World
• BONUS – Build a Credit Card Number Reader
• BONUS – Use Cloud GPUs on PaperSpace
• BONUS – Create a Computer Vision API & Web App Using Flask and AWS

Course content

• Introduction
• Installation
• Python Crash Course (Optional)
• NumPy Crash Course (Optional)
• Computer Vision: Finding Lane Lines
• The Perceptron
• Keras
• Deep Neural Networks
• Multiclass Classification
• MN 1ST Image Recognition
• Convolutional Neural Networks
• Classifying Road Symbols
• Polynomial Regression
• Behavioural Cloning

Course content

• Introduction
• Deep Learning and TensorFlow Fundamentals
• Neural network regression with TensorFlow
• Neural network classification in TensorFlow
• Computer Vision and Convolutional Neural Networks in TensorFlow
• Transfer Learning in TensorFlow Part 1: Feature extraction
• Transfer Learning in TensorFlow Part 2: Fine tuning
• Transfer Learning with TensorFlow Part 3: Scaling Up
• Milestone Project 1: Food Vision Big
• NLP Fundamentals in TensorFlow
• Milestone Project 2: SkimLit
• Time Series fundamentals in TensorFIow + Milestone Project 3: BitPredict
• Passing the TensorFlow Developer Certificate Exam
• Where To Go From Here?
• Appendix: Machine Learning Primer
• Appendix: Machine Learning and Data Science Framework
• Appendix: Pandas for Data Analysis
• Appendix: NumPy
• BONUS SECTION

Duration

28 hours (usually 4 days including breaks)

Requirements

One of the following:

• C++
• Java
• Python
• MATLAB
• CUDA
• OpenCL

And basic knowledge of machine learning. Knowledge of linear algebra, statistics, probability are helpful.

Overview

OpenCV (Open Source Computer Vision Library: http://opencv.org) is an open-source BSD-licensed library that includes several hundreds of computer vision algorithms.

Audience

This course is directed at engineers and architects seeking to utilize OpenCV for computer vision projects

Course Outline

Introduction

• Setting up OpenCV
• API concepts

Main Modules

• The Core Functionality(Core Module)
• Image Processing(Imgproc Module)
• High Level GUI and Media (highgui module)
• Image Input and Output (imgcodecs module)
• Video Input and Output (videoio module)
• Camera calibration and 3D reconstruction (calib3d module)
• 2D Features framework (feature2d module)
• Video analysis (video module)
• Object Detection (objdetect module)
• Machine Learning (ml module)
• Computational photography (photo module)
• OpenCV Viz

Bonus topics

• GPU-Accelerated Computer Vision (cuda module)
• OpenCV iOS

Bonus topics are not available as a part of a remote course. They can be delivered during classroom-based courses, but only by prior agreement, and only if both the trainer and all participants have laptops with supported NVIDIA GPUs (for the CUDA module) or MacBooks, Apple developer accounts and iOS-based mobile devices (for the iOS topic). NobleProg cannot guarantee the availability of trainers with the required hardware.

Duration

14 hours (usually 2 days including breaks)

Requirements

• Programming experience with Python

Overview

Computer Vision is a field that involves automatically extracting, analyzing, and understanding useful information from digital media. Python is a high-level programming language famous for its clear syntax and code readibility.

In this instructor-led, live training, participants will learn the basics of Computer Vision as they step through the creation of set of simple Computer Vision application using Python.

By the end of this training, participants will be able to:

• Understand the basics of Computer Vision
• Use Python to implement Computer Vision tasks
• Build their own face, object, and motion detection systems

Audience

• Python programmers interested in Computer Vision

Format of the course

• Part lecture, part discussion, exercises and heavy hands-on practice

Course Outline

Introduction

Understanding Computer Vision Basics

Installing OpenCV with Python Wrappers

Introduction to Using OpenCV

Using Media with Python

• Loading Images
• Converting Color to Grayscale
• Using Metadata

Applying Image Theory with Python

• Understanding Images as Multidimensional Arrays
• Understanding the Color Space
• Overview of Pixels and Coordinates
• Accessing Pixels
• Changing Pixels in Images
• Drawing Lines and Shapes
• Applying Text on Images
• Resizing Images
• Cropping Images

Exploring Common Computer Vision Algorithms and Methods

• Thresholding
• Finding Contours
• Background Subtraction
• Using Detectors

Implementing Feature Extraction with Python

• Using Feature Vectors
• Understanding the Color-mean Features Theory
• Extracting Histogram Features
• Extracting Grayscale Histogram Features
• Extracting Texture Features

Implementing an App to Detect Image Similarity

Implementing a Reverse Image Search Engine

Creating an Object Detection App Using Template Matching

Creating a Face Detection App Using Haar Cascade

Implementing an Object Detection App Using Keypoints

Capturing and Processing Video through a WebCam

Creating a Motion Detection System

Troubleshooting

Summary and Conclusion

Duration

14 hours (usually 2 days including breaks)

Requirements

Knowlege of the following languages:

• Python

Overview

SimpleCV is an open source framework — meaning that it is a collection of libraries and software that you can use to develop vision applications. It lets you work with the images or video streams that come from webcams, Kinects, FireWire and IP cameras, or mobile phones. It’s helps you build software to make your various technologies not only see the world, but understand it too.

Audience

This course is directed at engineers and developers seeking to develop computer vision applications with SimpleCV.

Course Outline

Getting Started

• Installation

Tutorials & Examples

• SimpleCV Shell
• SimpleCV Basics
• The Hello World program
• Interacting with the Display
• Loading a Directory of Images
• Macro’s
• Kinect
• Timing
• Detecting a Car
• Segmenting the Image and Morphology
• Image Arithmetic
  • Exceptions in Image Math
  • Histograms
  • Color Space
  • Using Hue Peaks
  • Creating a Motion Blur Effect
  • Simulating Long Exposure
  • Chroma Key (Green Screen)
• Drawing on Images in SimpleCV
  • Layers
  • Marking up the Image
  • Text and Fonts
  • Making a Custom Display Object