Building Features from Image Data
This course covers conceptual and practical aspects of pre-processing images to maximize the efficacy of image processing algorithms, as well as implementing feature extraction, dimensionality reduction, and latent factor identification.
What you'll learn
From machine-generated art to visualizations of black holes, some of the hottest applications of ML and AI these days are to data in image form.
In this course, Building Features from Image Data, you will gain the ability to structure image data in a manner ideal for use in ML models.
First, you will learn how to pre-process images using operations such as making the aspect ratio uniform, normalizing pixel magnitudes, and cropping images to be square in shape. Next, you will discover how to implement denoising techniques such as ZCA whitening and batch normalization to remove variations.
Finally, you will explore how to identify points and blobs of interest and calculate image descriptors using algorithms such as Histogram of Oriented Gradients and Scale Invariant Feature Transform.
You will round out the course by implementing dimensionality reduction using dictionary learning, feature extraction using convolutional kernels, and latent factor identification using autoencoders.
When you’re finished with this course, you will have the skills and knowledge to move on to pre-process images in conceptually and practically sound ways to extract features from such data for use in machine learning models.
Table of contents
- Version Check 0m
- Module Overview 1m
- Prerequisites and Course Outline 1m
- Representing Images for Machine Learning 5m
- Image Preprocessing to Build Robust Models 6m
- Working with Images as Arrays 5m
- Representing Pixels in Images 3m
- Working with Color and Color Spaces 5m
- Resizing, Rescaling, Rotating, and Flipping Images 5m
- Block Views and Pooling 3m
- Denoising Images 5m
- Normalization and ZCA Whitening 6m
- Image Augmentation Using Weather Transforms 2m
- Module Summary 1m
- Module Overview 1m
- Feature Detection and Its Importance 4m
- Key Points and Descriptors 6m
- Applying Keypoint Preserving Transformations 6m
- Scale Invariant Feature Transform (SIFT), DAISY, and Histogram of Oriented Gradients (HOG) 5m
- Feature Detection and Extraction Using SIFT 7m
- Feature Detection Using DAISY Descriptors 2m
- Feature Detection Using Histogram of Oriented Gradients 6m
- Optical Character Recognition Using Tesseract 6m
- Module Summary 1m