You're reading from Mastering OpenCV Android Application Programming Master the art of implementing computer vision algorithms on Android platforms to build robust and efficient applications

Product type Paperback

Published in Jul 2015

Publisher

ISBN-13 9781783988204

Length 216 pages

Edition 1st Edition

Languages

Java

Tools

OpenCV

Concepts

Android Development

Table of Contents (11) Chapters

Preface

1. Applying Effects to Images FREE CHAPTER

2. Detecting Basic Features in Images

3. Detecting Objects

4. Drilling Deeper into Object Detection – Using Cascade Classifiers

5. Tracking Objects in Videos

6. Working with Image Alignment and Stitching

7. Bringing Your Apps to Life with OpenCV Machine Learning

8. Troubleshooting and Best Practices

9. Developing a Document Scanning App

Index

Scale Invariant Feature Transform

Scale Invariant Feature Transform (SIFT) is one of the most widely recognized feature detection algorithms. It was proposed by David Lowe in 2004.

Note

Link to the paper: http://www.cs.ubc.ca/~lowe/papers/ijcv04.pdf

Some of the properties of SIFT are as follows:

It is invariant to scaling and rotation changes in objects
It is also partially invariant to 3D viewpoint and illumination changes
A large number of keypoints (features) can be extracted from a single image

Understanding how SIFT works

SIFT follows a strategy of matching robust local features. It is divided into four parts:

Scale-space extrema detection
Keypoint localization
Orientation assignment
Keypoint descriptor

Scale-space extrema detection

In this step, an image is progressively blurred out using Gaussian blur to get rid of some details in the images. It has been mathematically proven (under reasonable assumptions) that performing Gaussian blur is the only way to carry this out effectively.

Images of...

The rest of the chapter is locked