Reader small image

You're reading from  Hands-On Image Generation with TensorFlow

Product typeBook
Published inDec 2020
Reading LevelIntermediate
PublisherPackt
ISBN-139781838826789
Edition1st Edition
Languages
Right arrow
Author (1)
Soon Yau Cheong
Soon Yau Cheong
author image
Soon Yau Cheong

Soon Yau Cheong is an AI consultant and the founder of Sooner.ai Ltd. With a history of being associated with industry giants such as NVIDIA and Qualcomm, he provides consultation in the various domains of AI, such as deep learning, computer vision, natural language processing, and big data analytics. He was awarded a full scholarship to study for his PhD at the University of Bristol while working as a teaching assistant. He is also a mentor for AI courses with Udacity.
Read more about Soon Yau Cheong

Right arrow

Image processing

Out of all the things that image generative models can do, image processing is probably the one that produces the best results for commercial use. In our context, image processing refers to applying some transformation to existing images to produce new ones. We will look at the three applications of image processing in this section – image inpainting, image compression, and image super-resolution (ISR).

Image inpainting

Image inpainting is the process of filling in missing pixels of an image so that the result is visually realistic. It has practical applications in image editing, such as restoring a damaged image or removing obstructing objects. In the following example, you can see how image inpainting is used to remove people in the background. We first fill the people in with white pixels, then we use a generative model to fill in the pixels:

Figure 10.2 – Image inpainting using DeepFillv2 to remove people in the background...

lock icon
The rest of the page is locked
Previous PageNext Page
You have been reading a chapter from
Hands-On Image Generation with TensorFlow
Published in: Dec 2020Publisher: PacktISBN-13: 9781838826789

Author (1)

author image
Soon Yau Cheong

Soon Yau Cheong is an AI consultant and the founder of Sooner.ai Ltd. With a history of being associated with industry giants such as NVIDIA and Qualcomm, he provides consultation in the various domains of AI, such as deep learning, computer vision, natural language processing, and big data analytics. He was awarded a full scholarship to study for his PhD at the University of Bristol while working as a teaching assistant. He is also a mentor for AI courses with Udacity.
Read more about Soon Yau Cheong