Search icon
Arrow left icon
All Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Newsletters
Free Learning
Arrow right icon
Neural Network Projects with Python

You're reading from  Neural Network Projects with Python

Product type Book
Published in Feb 2019
Publisher Packt
ISBN-13 9781789138900
Pages 308 pages
Edition 1st Edition
Languages
Author (1):
James Loy James Loy
Profile icon James Loy

Table of Contents (10) Chapters

Preface Machine Learning and Neural Networks 101 Predicting Diabetes with Multilayer Perceptrons Predicting Taxi Fares with Deep Feedforward Networks Cats Versus Dogs - Image Classification Using CNNs Removing Noise from Images Using Autoencoders Sentiment Analysis of Movie Reviews Using LSTM Implementing a Facial Recognition System with Neural Networks What's Next? Other Books You May Enjoy

The faces dataset

Let's now look at the faces dataset that we will be using for this project. There are numerous publicly available faces dataset for use, as consolidated at http://www.face-rec.org/databases/.

While there are many face datasets that we can use, the most appropriate dataset for training a facial recognition system should contain photos of different subjects, with each subject having multiple photos taken from different angles. It should also ideally contain photos of the subject wearing different expressions (eyes closed and so on), as such photos are commonly encountered by facial recognition systems.

With these considerations in mind, the dataset that we have chosen is the Database of Faces, created by AT&T Laboratories, Cambridge. The database contains photos of 40 subjects, with 10 photos of each subject. The photos of each subject were taken under...

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 $15.99/month. Cancel anytime}