Templates, Image Pyramids, and Filter Banks
Computer Vision
Docsity.com
Prepare for your exams
Study with the several resources on Docsity
Earn points to download
Earn points by helping other students or get them with a premium plan
Guidelines and tips
Prepare for your exams
Study with the several resources on Docsity
Earn points to download
Earn points by helping other students or get them with a premium plan
Templates - Introduction to Computer Version - Lecture Sli, Lecture notes of Computer Science
These are the Lecture Slides of Introduction to Computer Version which includes Machine Learning, Framework, Prediction Function, Feature Representation, Image, Desired Output, Prediction Function, Prediction Error, Predicted Value etc. Key important points are: Templates, Image Pyramids, Filter Banks, Spatial Domain Image, Fourier Magnitude Image, Template Matching, Image Pyramids, Filter Banks and Texture, Denoising, Compression
Typology: Lecture notes
2012/2013
1 / 44
This page cannot be seen from the preview
Don't miss anything!
Related documents
Partial preview of the text
Download Templates - Introduction to Computer Version - Lecture Sli and more Lecture notes Computer Science in PDF only on Docsity!
Templates, Image Pyramids, and Filter Banks
Computer Vision Docsity.com
Review
1. Match the spatial domain image to the
Fourier magnitude image
(^1 )
A
(^23)
C
B
D
E
Slide: HoiemDocsity.com
Today’s class
- Template matching
- Image Pyramids
- Filter banks and texture
- Denoising, Compression
Docsity.com
Template matching
- Goal: find in image
- Main challenge: What is a good similarity or distance measure between two patches? - Correlation - Zero-mean correlation - Sum Square Difference - Normalized Cross Correlation
Slide: HoiemDocsity.com
Slide: Hoiem
Matching with filters
- Goal: find in image
- Method 1: filter the image with zero-mean eye
Input Filtered Image (scaled)^ Thresholded Image
[ , ] ( [ , ] )( [ , ])
,
h m n f k l f g m k n l k l
True detections
False detections
mean of f
Docsity.com
Slide: Hoiem
Matching with filters
- Goal: find in image
- Method 2: SSD
Input 1- sqrt(SSD)^ Thresholded Image
2 ,
h [ m , n ] ( g [ k , l ] f [ m k , n l ] ) k l
True detections
Docsity.com
Matching with filters
- Goal: find in image
- Method 3: Normalized cross-correlation
- 5
,
2 , ,
2
, ,
( [ , ] ) ( [ , ] )
( [ , ] )( [ , ] )
[ , ]
k l
mn k l
mn k l
g k l g f m k n l f
g k l g f m k n l f
h m n
Matlab: normxcorr2(template, im)
mean template mean image patch
Slide: HoiemDocsity.com
Slide: Hoiem
Matching with filters
- Goal: find in image
- Method 3: Normalized cross-correlation
Input (^) Normalized X-Correlation Thresholded Image
True detections
Docsity.com
Q: What is the best method to use?
A: Depends
- SSD: faster, sensitive to overall intensity
- Normalized cross-correlation: slower, invariant
to local average intensity and contrast
Docsity.com
Q: What if we want to find larger or smaller eyes?
A: Image Pyramid
Docsity.com
Gaussian pyramid
Source: ForsythDocsity.com
Template Matching with Image Pyramids
Input: Image, Template
- Match template at current scale
- Downsample image
- Repeat 1-2 until image is very small
- Take responses above some threshold, perhaps with non-maxima suppression
Slide: HoiemDocsity.com
Laplacian filter
unit impulse (^) Gaussian Laplacian of Gaussian
Source: LazebnikDocsity.com
2D edge detection filters
is the Laplacian operator:
Laplacian of Gaussian
Gaussian derivative of Gaussian
Docsity.com