Book Image

Python Image Processing Cookbook

By : Sandipan Dey
Book Image

Python Image Processing Cookbook

By: Sandipan Dey

Overview of this book

With the advancements in wireless devices and mobile technology, there's increasing demand for people with digital image processing skills in order to extract useful information from the ever-growing volume of images. This book provides comprehensive coverage of the relevant tools and algorithms, and guides you through analysis and visualization for image processing. With the help of over 60 cutting-edge recipes, you'll address common challenges in image processing and learn how to perform complex tasks such as object detection, image segmentation, and image reconstruction using large hybrid datasets. Dedicated sections will also take you through implementing various image enhancement and image restoration techniques, such as cartooning, gradient blending, and sparse dictionary learning. As you advance, you'll get to grips with face morphing and image segmentation techniques. With an emphasis on practical solutions, this book will help you apply deep learning techniques such as transfer learning and fine-tuning to solve real-world problems. By the end of this book, you'll be proficient in utilizing the capabilities of the Python ecosystem to implement various image processing techniques effectively.

Related Content you might be interested in

Current Title:

Small book image
Python Image Processing Cookbook
Sandipan Dey
Apr, 2020 | 438 pages
No titles found
Table of Contents (11 chapters)
Preface
Preface
Who this book is for
What this book covers
To get the most out of this book
Sections
Get in touch
1
Image Manipulation and Transformation
Image Manipulation and Transformation
Technical requirements
Transforming color space (RGB → Lab)
Applying affine transformation
Applying perspective transformation and homography
Creating pencil sketches from images
Creating cartoonish images
Simulating light art/long exposure
Object detection using color in HSV
Free Chapter
2
Image Enhancement
Image Enhancement
Applying filters to denoise different types of noise in an image
Image denoising with a denoising autoencoder
Image denoising with PCA/DFT/DWT
Image denoising with anisotropic diffusion
Improving image contrast with histogram equalization
Implementing histogram matching
Performing gradient blending
Edge detection with Canny, LoG/zero-crossing, and wavelets
3
Image Restoration
Image Restoration
Restoring an image with the Wiener filter
Restoring an image with the constrained least squares filter 
Image restoration with a Markov random field
Image inpainting
Image completion with inpainting using deep learning
Image restoration with dictionary learning
Compressing an image using wavelets
Using steganography and steganalysis
4
Binary Image Processing
Binary Image Processing
Applying morphological operators to a binary image
Applying Morphological filters
Morphological pattern matching
Segmenting images with morphology
Counting objects
5
Image Registration
Image Registration
Medical image registration with SimpleITK
Image alignment with ECC algorithm and warping 
Face alignment with dlib
Robust matching and homography with the RANSAC algorithm
Image mosaicing (panorama)
Face morphing
Implementing an image search engine
6
Image Segmentation
Image Segmentation
Thresholding with Otsu and Riddler–Calvard
Image segmentation with self-organizing maps
RandomWalk segmentation with scikit-image
Human skin segmentation with the GMM-EM algorithm
Medical image segmentation
Deep semantic segmentation
Deep instance segmentation
7
Image Classification
Image Classification
Classifying images with scikit-learn (HOG and logistic regression)
Classifying textures with Gabor filter banks
Classifying images with VGG19/Inception V3/MobileNet/ResNet101 (with PyTorch)
Fine-tuning (with transfer learning) for image classification
Classifying traffic signs using a deep learning model (with PyTorch)
Estimating a human pose using a deep learning model
8
Object Detection in Images
Object Detection in Images
Object detection with HOG/SVM
Object detection with Yolo V3
Object detection with Faster R-CNN
Object detection with Mask R-CNN
Multiple object tracking with Python-OpenCV
Text detection/recognition in images with EAST/Tesseract
Face detection with Viola-Jones/Haar-like features
9
Face Recognition, Image Captioning, and More
Face Recognition, Image Captioning, and More
Face recognition using FaceNet
Age, gender, and emotion recognition using deep learning models
Image colorization with deep learning
Automatic image captioning with a CNN and an LSTM
Image generation with a GAN
Using a variational autoencoder to reconstruct and generate images
Using a restricted Boltzmann machine to reconstruct Bangla MNIST images
10
Other Books You May Enjoy
Other Books You May Enjoy
Leave a review - let other readers know what you think

Object detection with Mask R-CNN

The Mask R-CNN algorithm (2017), by Girshick et al., includes a number of improvements compared with the Faster R-CNN algorithm for region-based object detection, with the following two primary contributions:

  • ROI Pooling is replaced with an ROI Align module (which is more accurate).
  • An additional branch is inserted (which receives the output from ROI Align, subsequently feeding it into two successive convolution layers. Output from the last convolutional layer forms the object mask) at the output of the ROI Align module.

The RoIAlign module provides a more precise correspondence between the regions of the feature map selected and those of the input image. Much more fine-grained alignment is needed for pixel-level segmentation, rather than just computing the bounding boxes. The following screenshot shows the architecture of Mask R-CNN:

In...

Previous Section
End of Section 5
Next Section