Getting Started
Session 1
Computer Vision Group
IIT Madras
December 1, 2014
(Computer Vision Group)
Getting Started
December 1, 2014
1 / 18
Outline
Installation OpenCV
Windows
Ubuntu
Concepts in Image Processing
Pixels
Image Processing
Image Transformation
Feature Extraction
What are features?
Some feature extraction tools
(Computer Vision Group)
Getting Started
December 1, 2014
2 / 18
Installing OpenCV
Windows 7/8
Install Anaconda 2.0.1
Download OpenCV 2.4.9 and extract to a convenient location
Go to opencv/build/python/2.7 folder
Copy cv2.pyd to INSTALL DIRECTORY/Python/lib/site-packages
Open IPython QT console.
import cv2
If you dont get any errors, its a success.
(Computer Vision Group)
Getting Started
December 1, 2014
3 / 18
Installing OpenCV
Ubuntu
Using the apt-get tool
# sudo apt-get install python-opencv
Installs an older version of OpenCV. Build from source to get the latest
version.
(Computer Vision Group)
Getting Started
December 1, 2014
4 / 18
Pixels
Recap
Basic building blocks of an image
Color represented as a tuple (R, G, B)
(Computer Vision Group)
Getting Started
December 1, 2014
5 / 18
Image Processing
Recap
Thresholding
Erosion
Dilation
(Computer Vision Group)
Getting Started
December 1, 2014
6 / 18
Thresholding
Image Processing
(Computer Vision Group)
Getting Started
December 1, 2014
7 / 18
Erosion
Image Processing
(Computer Vision Group)
Getting Started
December 1, 2014
8 / 18
Dilation
Image Processing
(Computer Vision Group)
Getting Started
December 1, 2014
9 / 18
Image Transformation
Fairly Simple
Rotation
Translation
Cropping
Warping
(Computer Vision Group)
Getting Started
December 1, 2014
10 / 18
Rotation
Image Transformation
(Computer Vision Group)
Getting Started
December 1, 2014
11 / 18
Translation
Image Transformation
(Computer Vision Group)
Getting Started
December 1, 2014
12 / 18
Warping
Image Transformation
(Computer Vision Group)
Getting Started
December 1, 2014
13 / 18
Feature Extraction
What are features?
Feature Extraction in Images
Transforming rich content of images into a set of values. Feature
extraction is a crucial part in Machine Learning.
(Computer Vision Group)
Getting Started
December 1, 2014
14 / 18
Feature Extraction
What are features?
Feature Extraction in Images
Transforming rich content of images into a set of values. Feature
extraction is a crucial part in Machine Learning.
Example
Histograms are commonly used for extracting set of features. More feature
extraction techniques coming up.
(Computer Vision Group)
Getting Started
December 1, 2014
14 / 18
Feature Extraction
What are features?
Feature Extraction in Images
Transforming rich content of images into a set of values. Feature
extraction is a crucial part in Machine Learning.
Example
Histograms are commonly used for extracting set of features. More feature
extraction techniques coming up.
Digit Recognizer
Well be using Machine Learning to build a digit recognizer in tomorrows
session.
(Computer Vision Group)
Getting Started
December 1, 2014
14 / 18
Feature Extraction Tools
There are many more available
Binarized pixel values
Intensity histogram
Histogram of Oriented gradients
SIFT
(Computer Vision Group)
Getting Started
December 1, 2014
15 / 18
Intensity Histogram
Feature Extraction
(Computer Vision Group)
Getting Started
December 1, 2014
16 / 18
Histogram of Oriented Gradients
Feature Extraction
(Computer Vision Group)
Getting Started
December 1, 2014
17 / 18
Summary
Todays session
Image processing/transformations
Feature Extraction
Tomorrows session
Machine Learning Basics
Training a classifier for handwritten digit recognition
(Computer Vision Group)
Getting Started
December 1, 2014
18 / 18