Book Image

Hands-On Image Processing with Python

By : Sandipan Dey
Book Image

Hands-On Image Processing with Python

By: Sandipan Dey

Overview of this book

Image processing plays an important role in our daily lives with various applications such as in social media (face detection), medical imaging (X-ray, CT-scan), security (fingerprint recognition) to robotics & space. This book will touch the core of image processing, from concepts to code using Python. The book will start from the classical image processing techniques and explore the evolution of image processing algorithms up to the recent advances in image processing or computer vision with deep learning. We will learn how to use image processing libraries such as PIL, scikit-mage, and scipy ndimage in Python. This book will enable us to write code snippets in Python 3 and quickly implement complex image processing algorithms such as image enhancement, filtering, segmentation, object detection, and classification. We will be able to use machine learning models using the scikit-learn library and later explore deep CNN, such as VGG-19 with Keras, and we will also use an end-to-end deep learning model called YOLO for object detection. We will also cover a few advanced problems, such as image inpainting, gradient blending, variational denoising, seam carving, quilting, and morphing. By the end of this book, we will have learned to implement various algorithms for efficient image processing.
Table of Contents (20 chapters)
Title Page
Copyright and Credits
Dedication
About Packt
Contributors
Preface
Index

Image pyramids (Gaussian and Laplacian) – blending images


We can construct the Gaussian pyramid of an image by starting with the original image and creating smaller images iteratively, first by smoothing (with a Gaussian filter to avoid anti-aliasing), and then by subsampling (collectively called reducing) from the previous level's image at each iteration until a minimum resolution is reached. The image pyramid created in this way is called a Gaussian pyramid. These are good for searching over scale (for instance, template-matching), precomputation, and image processing tasks by editing frequency bands separately (for instance, image blending). Similarly, a Laplacian pyramid for the image can be constructed by starting from the smallest sized image in the Gaussian pyramid and then by expanding (up-sampling plus smoothing) the image from that level and subtracting it from the image from the next level of the Gaussian pyramid, and repeating this process iteratively until the original image...