introduction what is “image processing and computer vision”? image representation

41
Introduction What is “image processing and computer vision”? Image Representation

Upload: alfred-cannon

Post on 21-Dec-2015

245 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Introduction What is “image processing and computer vision”? Image Representation

Introduction

What is “image processing and computer vision”?Image Representation

Page 2: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 2

What is “Image Processing and Computer Vision”?

Image Processingmanipulate image datagenerate another image

Computer Visionprocess image data

generate symbolic data

Page 3: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 3

Computer Vision Reconstruction

Recover 3D information from data Recognition

Detect and identify objects Understanding

What is happening in the scene?

Page 4: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 4

Historical overview 1920s

Coding images for transmission by telegraph (3 hours)

1960s Computers powerful enough to store

images and process in realistic times Space program

Page 5: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 5

1960s - 1970s Applications

Medical imaging Remote sensing Astronomy

Page 6: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 6

Today DTV Image interpretation Biometry GIS Human genome project

Page 7: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 7

Example images (1)

Page 8: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 8

Example images (2)

Page 9: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 9

Sample applications Character recognition (OCR)

Printed text, Hand-printed text, Cursive text

Biometry GIS

Page 10: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 10

Printed Text Characteristics

Regular shape Regular orientation Good contrast

Can compare characters with a prototype

Page 11: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 11

0

20

40

60

80

100

1201

26

51

76

101

126

151

176

201

226

251

276

301

326

351

376

401

426

Position

No

n-N

orm

alis

ed

Co

rre

lati

on

Template

Input Output

Page 12: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 12

Hand Printed Text Characteristics

Less regularity Must examine components of

character

Page 13: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 13

Cursive Text Totally irregular Careful analysis of strokes

Page 14: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 14

Biometry Using personal characteristics to

identify a person Fingerprints Face Iris DNA Gait etc

Page 15: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 15

Iris Scan Striations on iris are individually

unique Obvious applications:

Security PIN

Page 16: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 16

} fixed number of samples

Locate the eye in the head image

Radial resampling of iris

Numerical descriptionAnalysis

Page 17: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 17

GIS Earth/Planetary Observation

Monitoring Exploration

Page 18: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 18

Examples

Page 19: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 19

System Overview

Enhancement

Feature Extraction

Feature Recognition

Image Recognition

Captured data

Labels

Page 20: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 20

Image Representation Image capture Image quality measurements Image resolution Colour representation Camera calibration Parallels with human visual system

Page 21: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 21

Image Capture Many sources

Consider requirements of system Resolution

Type of data Transducer

Page 22: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 22

Representation Sampled data

Spatial Amplitude

On a rectangular array

Page 23: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 23

Image Resolution How many pixels

Spatial resolution How many shades of grey/colours

Amplitude resolution How many frames per second

Temporal resolution

Nyquist’s theorem

Page 24: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 24

Nyquist’s Theorem A periodic signal can be

reconstructed if the sampling interval is half the period

An object can be detected if two samples span its smallest dimension

Page 25: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 25

Spatial Resolution

n, n/2, n/4, n/8, n/16 and n/32 pixels on a side.

Page 26: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 26

Amplitude Resolution Humans can see:

About 40 shades of brightness About 7.5 million shades of colour

Cameras can see: Depends on signal to noise ratio 40 dB equates to about 20 shades

Images captured: 256 shades

Page 27: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 27

Shades of Grey

256, 16, 4 and 2 shades.

Page 28: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 28

Temporal Resolution Nyquist’s theorem for temporal

data How much does an object move

between frames? Can motion be understood

unambiguously?

Page 29: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 29

Colour Representation Newton

White light composed of seven colours

red, orange, yellow, green, blue, indigo, violet

Three primaries could approximate many colours

red, green, blue

Page 30: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 30

CIE Colour Diagram

Page 31: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 31

Other Colour Models YMCK IHS YCrCb etc

Page 32: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 32

Camera Calibration Link image co-ordinates and world

co-ordinates Extrinsic parameters

Location and orientation of camera with respect to a co-ordinate frame

Intrinsic parameters Relate pixel co-ordinates with camera

reference frame co-ordinates

Page 33: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 33

Extrinsic Parameters Camera’s

Location Orientation

With respect to world origin

Page 34: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 34

World frame

Camera frame

translate androtate

Page 35: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 35

Intrinsic Parameters Characterise

Optical Geometric Digital

properties of camera Relate

Image co-ordinates to camera co-ordinates

Page 36: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 36

Pinhole Camera

Image

ObjectOpticalcentre

Image and centre, object and centre are similar triangles.

f Z

Z

Yfy

Z

Xfx

Page 37: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 37

Distortionless If

no distortions uniform sampling

Co-ordinates linearly related offset and scale

s yo yyimy

sxoxximx

Page 38: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 38

Distorted Periphery is distorted

k2 = 0 is good enough

yxr

rkrkydy

rkrkxdx

222

42

211

42

211

Page 39: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 39

Parallels With Human Visual System Image capture

Retina Focussing

Cornea and lens Exposure

Iris and retina

Page 40: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 40

Summary Historical overview Sample applications Resolution Colour models Camera calibration

Page 41: Introduction What is “image processing and computer vision”? Image Representation

Image Processing and Computer Vision: 1 41

640k ought to be enough for anybodyBill Gates, 1981