Description
In this course, you will :
- Learn the fundamentals of working with image data represented as multidimensional arrays.
- Learn how to manipulate images with the NumPy package, extract features with block view and pooling techniques, detect edges and lines in images, and find contours in images.
- Investigate various object and feature detection techniques, such as using the DAISY and HOG algorithms to extract image features and morphological reconstruction to fill holes and find peaks in your images.
- By exploring the Regional Adjacency Graph data structure to represent image segments, you'll delve into image processing techniques that allow you to segment similar regions in your images and apply complex transformations.
Syllabus :
1. Working with Image Data
- Prerequisites and Course Outline
- Introducing scikit-image
- Working with Images as NumPy Arrays
- Masking Images Using Array Manipulation
- Masking Color Images
- Introducing Block Views and Pooling
- Block Views and Pooling Operations
- Contours
- Convex Hull
- Edge Detection
- Roberts and Sobel Edge Detection
- Canny Edge Detection
2. Object and Feature Detection
- Feature Detection and Image Descriptors
- Visualizing Daisy Descriptors on Images
- Visualizing Hog Feature Descriptors
- Corner Detection
- Introducing Denoising Filters
- Applying Denoising Filters
- Morphological Reconstruction
- Filling Holes and Finding Peaks Using Erosion and Dilation
3. Segmentation and Transformation
- Introducing Thresholding
- Applying Global and Local Thresholding Algorithms
- Image Segmentation and Region Adjacency Graphs
- Segmentation and Merging Segments Using Rags
- Introducing Watershed Algorithms for Segmentation
- Segmentation Using Classic and Compact Watershed
- Applying Image Transformations
- Introducing the MSE and SSIM as Distance Measures
- Comparing Images Using MSE and SSIM