Explore mathematical computations and algorithms for image processing using popular Python tools and frameworks
Key Features
- Gain practical knowledge of every image processing task with popular Python libraries
- Explore topics such as pseudo-coloring, noise smoothing, and computing image descriptors
- Cover popular machine learning and deep learning techniques for complex image processing tasks
Book Description
Image processing plays an important role in our daily lives with various applications in social media (face detection), medical imaging (X-rays and CT scans), and security (fingerprint recognition). This book is designed to help you learn the core aspects of image processing, from essential concepts to code using the Python programming language.
The book starts by covering classical image processing techniques. You'll then go on to explore the evolution of image processing algorithms, right up to the recent advancements in image processing and computer vision with deep learning. As you progress, you'll learn how to use image processing libraries such as PIL, scikit-image, and scipy ndimage in Python. The book will further enable you to write code snippets in Python 3 and implement complex image processing algorithms such as image enhancement, filtering, segmentation, object detection, and classification. You'll gradually be able to implement machine learning models using the Python library, scikit-learn. In addition to this, you'll explore deep convolutional neural networks (CNNs), such as VGG-19 with Keras, before progressing to use an end-to-end deep learning model called YOLO for object detection. Later chapters will take you through a few advanced problems, such as image inpainting, gradient blending, variational denoising, seam carving, quilting, and morphing.
By the end of this book, you'll have learned how to implement various algorithms for efficient image processing.
What you will learn
- Perform basic data pre-processing tasks such as image denoising and spatial filtering in Python
- Implement Fast Fourier Transform (FFT) and Frequency Domain Filters such as Weiner in Python
- Perform morphological image processing and segment images with different algorithms
- Get to grips with techniques for extracting features from images and matching images
- Write Python code to implement supervised machine learning and unsupervised machine learning algorithms for image processing
- Use deep learning models for image classification, segmentation, object detection and style transfer
Who this book is for
This image processing handbook is for computer vision engineers and machine learning developers who are well-versed in Python programming and want to delve into the various aspects and complexities of image processing. No prior knowledge of image processing techniques is required.
Table of Contents
- Getting started with Image Processing
- Sampling Fourier Transform
- Convolution and Frequency domain Filtering
- Image Enhancement
- Image Enhancement using Derivatives
- Morphological Image Processing
- Extracting Image Features and Descriptors
- Image Segmentation
- Classical Machine Learning Methods
- Learning in Image Processing - Image Classification with CNN
- Object Detection, Deep Segmentation and Transfer Learning
- Additional Problems in Image Processing
Sandipan Dey is a data scientist with a wide range of interests, covering topics such as machine learning, deep learning, image processing, and computer vision. He has worked in numerous data science fields, working with recommender systems, predictive models for the events industry, sensor localization models, sentiment analysis, and device prognostics. He earned his master's degree in computer science from the University of Maryland, Baltimore County, and has published in a few IEEE Data Mining conferences and journals. He has earned certifications from 100+ MOOCs on data science, machine learning, deep learning, image processing, and related courses/specializations. He is a regular blogger on his blog (sandipanweb) and is a machine learning education enthusiast.
