|
|
|
Professor Hager |
|
http://www.cs.jhu.edu/~hager |
|
|
|
|
Outline and Organization of the course |
|
|
|
What is Computer Vision |
|
|
|
Some Applications of Computer Vision |
|
|
|
|
|
|
|
Trucco and Verri |
|
computing properties of the 3D world from one or
more digital image |
|
|
|
Stockman and Shapiro |
|
To make useful decisions about real physical
objects and scenes based on sensed images |
|
|
|
Ballard and Brown |
|
The construction of explicit, meaningful
description of physical objects from images |
|
|
|
|
|
|
|
|
|
|
|
|
|
Image processing: the study of the properties of operators that produce images
from other images |
|
we will touch on image filtering and related
operators from image processing |
|
|
|
Machine Vision: a somewhat outdated term which
now tends to refer to industrial vision applications where (usually) a
single camera is used to solve a structured inspection task |
|
|
|
(demonstration of NI Vision Builder example) |
|
|
|
Pattern Recognition: typically refers to the
recognition of structures in 2D images (usually without reference to any
underlying 3D information). |
|
|
|
Photogrammetry: the science of measurement
though non-contact sensing, e.g. terrain maps from satellite images. Usually is more focussed on accuracy issues. |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Computer Graphics |
|
Produce “plausible” images |
|
You choose the models, conditions, imaging
parameters, etc. |
|
|
|
Computer Vision |
|
Given real images with noise, sampling artifacts
… |
|
Estimate physically quantities |
|
Ill-posed ---- what is the minimum world
knowledge we need? |
|
|
|
|
|
|
|
|
|
|
|
|
Image Processing |
|
Mostly concerned with image-to-image
transformations |
|
Filtering |
|
Enhancement |
|
Compression |
|
|
|
Computer Vision |
|
Concerned with how images reflect the 3D world |
|
Filtering for feature extraction |
|
Enhancement for recognition/detection |
|
Compression that preserves geometric information
in images |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
The goal of computer vision: to produce a “2 ½
D” sketch |
|
Shape from stereo |
|
Shape from shading |
|
Shape from motion |
|
. |
|
. |
|
. |
|
. |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Face recognition |
|
|
|
Iris scanning |
|
|
|
Fingerprint recognition |
|
|
|
Activity recognition |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Use the course WEB site |
|
|
|
http://www.ugrad.cs.jhu.edu/~cs461 |
|
|
|
|
|
For information on this course |
|
|
|
|
Professor Hager |
|
http://www.cs.jhu.edu/~hager |
|
|
|
|
|
|
|
|
Basic process: |
|
photons hit a detector |
|
the detector becomes charged |
|
the charge is read out as brightness |
|
|
|
Sensor types: |
|
CCD (charge-coupled device) |
|
most common |
|
high sensitivity |
|
high power |
|
cannot be individually addressed |
|
blooming |
|
CMOS |
|
simple to fabricate (cheap) |
|
lower sensitivity, lower power |
|
can be individually addressed |
|
|
|
|
|
|
|
|
The “diameter” d of a pixel determines the
highest frequency representable in an image |
|
|
|
|
|
|
|
Real scenes may contain higher frequencies
resulting in aliasing of the signal. |
|
|
|
In practice, this effect is often dominated by
other digitization artifacts. |
|
|
|
One problem in particular is differing sampling
rates between digitizer and camera readout of a row. |
|
|
|
|
|
|
Non-lossy schemes |
|
pbm/pgm/ppm/pnm |
|
code for file type, size, number of bands, and
maximum brightness |
|
tif (lossless and lossy versions) |
|
bmp |
|
gif |
|
|
|
Lossy schemes |
|
jpg |
|
uses Y Cb Cr color representation; subsamples
the color |
|
Uses DCT on result |
|
Uses the fact the human system is less sensitive
to color than spatial detail |
|
|
|
|
|
GIF (Graphics Interchange Format) |
|
Limited to 8 bits/pixel for both color and
gray-scale. |
|
|
|
|
|
|
TIFF (Tagged Image File Format) |
|
More general than GIF |
|
Allows 24 bits/pixel |
|
Supports 5 types of image compression including: |
|
RLE (Run
length encoding) |
|
LZW (Lempel-Ziv-Welch) |
|
JPEG (Joint Photographic Experts Group) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 CCD cameras |
|
A Bayer pattern is placed in front of the CCD |
|
A Demosaicing process reads the pixels in a
region and computes color and intensity |
|
|
|
3 CCD camera use a beam splitter and 3 separate
CCDs |
|
higher color fidelity |
|
needs lots of light |
|
requires careful alignment of ccds |
|
|
|
|
|
|
|
|
|
|
Two different Spectral Energy Distributions with
the same RED, GREEN, BLUE response are termed metamers. |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Notes