Book Image

Learning OpenCV 3 Computer Vision with Python (Update)

Book Image

Learning OpenCV 3 Computer Vision with Python (Update)

Overview of this book

Table of Contents (16 chapters)
Learning OpenCV 3 Computer Vision with Python Second Edition
Credits
About the Authors
About the Reviewers
www.PacktPub.com
Preface
6
Retrieving Images and Searching Using Image Descriptors
Index

Handwritten digit recognition with ANNs


The world of Machine Learning is vast and mostly unexplored, and ANNs are but one of the many concepts related to Machine Learning, which is one of the many subdisciplines of Artificial Intelligence. For the purpose of this chapter, we will only be exploring the concept of ANNs in the context of OpenCV. It is by no means an exhaustive treatise on the subject of Artificial Intelligence.

Ultimately, we're interested in seeing ANNs work in the real world. So let's go ahead and make it happen.

MNIST – the handwritten digit database

One of the most popular resources on the Web for the training of classifiers dealing with OCR and handwritten character recognition is the MNIST database, publicly available at http://yann.lecun.com/exdb/mnist/.

This particular database is a freely available resource to kick-start the creation of a program that utilizes ANNs to recognize handwritten digits.

Customized training data

It is always possible to build your own training...