Search icon CANCEL
Arrow left icon
Explore Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Conferences
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
Data Science  with Python

You're reading from   Data Science with Python Combine Python with machine learning principles to discover hidden patterns in raw data

Arrow left icon
Product type Paperback
Published in Jul 2019
Publisher Packt
ISBN-13 9781838552862
Length 426 pages
Edition 1st Edition
Languages
Tools
Arrow right icon
Authors (3):
Arrow left icon
Rohan Chopra Rohan Chopra
Author Profile Icon Rohan Chopra
Rohan Chopra
Mohamed Noordeen Alaudeen Mohamed Noordeen Alaudeen
Author Profile Icon Mohamed Noordeen Alaudeen
Mohamed Noordeen Alaudeen
Aaron England Aaron England
Author Profile Icon Aaron England
Aaron England
Arrow right icon
View More author details
Toc

Table of Contents (10) Chapters Close

About the Book 1. Introduction to Data Science and Data Pre-Processing FREE CHAPTER 2. Data Visualization 3. Introduction to Machine Learning via Scikit-Learn 4. Dimensionality Reduction and Unsupervised Learning 5. Mastering Structured Data 6. Decoding Images 7. Processing Human Language 8. Tips and Tricks of the Trade 1. Appendix

Image Data Preprocessing

In this section, we go over a few techniques that you can use as a data scientist to preprocess images. First, we look at image normalization, and then we learn how we can convert a color image into a greyscale image. Finally, we look at ways in which we can bring all images in a dataset to the same dimensions. Preprocessing images is needed because datasets do not contain images that are the same size; we need to convert them into a standard size to train machine learning models on them. Some image preprocessing techniques help by reducing the model's training time by either making the important features easier to identify for the model or by reducing the dimensions as in the case of a greyscale image.

Normalization

In the case of images, the scale of the pixels is of the same order and in the range 0 to 255. Therefore, this normalization step is optional, but it might help speed up the learning process. To reiterate, centering the data and scaling it to the...

lock icon The rest of the chapter is locked
Register for a free Packt account to unlock a world of extra content!
A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.
Unlock this book and the full library FREE for 7 days
Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of
Renews at $19.99/month. Cancel anytime