Upload
stephanie-tate
View
222
Download
3
Embed Size (px)
Citation preview
EE 4780: Introduction to Computer Vision
Introduction
Bahadir K. Gunturk 2
EE 4780
Instructor: Bahadir K. Gunturk Office: EE 225 Email: [email protected] Tel: 8-5621 Office Hours: MW 10:00 – 12:00
Bahadir K. Gunturk 3
EE 4780
We will learn the fundamentals of digital image processing and computer vision.
Lecture slides, problems sets, solutions, study materials, etc. will be posted on the class website. [www.ece.lsu.edu/gunturk/EE4780]
Textbook is not required. References:
Gonzalez/Woods, Digital Image Processing, Prentice-Hall, 2/e. Forsyth/Ponce, Computer Vision: A Modern Approach, Prentice-Hall. Duda, Hart, and Stork, “Pattern Classification,” John Wiley&Sons, 2001. Shapiro/Stockman, Computer Vision, Prentice-Hall. Horn, “Robot Vision,” MIT Press, 1986.
Bahadir K. Gunturk 4
Grading Policy
Your grade will be based on Problem Sets: 30% Midterm: 30% Final: 40%
Problem Sets Mini projects: Theoretical problems and MATLAB assignments 4-5 Problem Sets Individually or in two-person teams
Bahadir K. Gunturk 5
Digital Image AcquisitionSensor array
When photons strike, electron-hole pairs are generated on sensor sites.
Electrons generated are collected over a certain period of time.
The number of electrons are converted to pixel values. (Pixel is short for picture element.)
Bahadir K. Gunturk 6
Digital Image Acquisition
Two types of quantization:1. There are finite number of
pixels. (Spatial resolution)2. The amplitude of pixel is
represented by a finite number of bits. (Gray-scale resolution)
Bahadir K. Gunturk 7
Digital Image Acquisition
Take a look at this cross section
Bahadir K. Gunturk 8
Digital Image Acquisition• 256x256 - Found on very cheap
cameras, this resolution is so low that the picture quality is almost always unacceptable. This is 65,000 total pixels.
• 640x480 - This is the low end on most "real" cameras. This resolution is ideal for e-mailing pictures or posting pictures on a Web site.
• 1216x912 - This is a "megapixel" image size -- 1,109,000 total pixels -- good for printing pictures.
• 1600x1200 - With almost 2 million total pixels, this is "high resolution." You can print a 4x5 inch print taken at this resolution with the same quality that you would get from a photo lab.
• 2240x1680 - Found on 4 megapixel cameras -- the current standard -- this allows even larger printed photos, with good quality for prints up to 16x20 inches.
• 4064x2704 - A top-of-the-line digital camera with 11.1 megapixels takes pictures at this resolution. At this setting, you can create 13.5x9 inch prints with no loss of picture quality.
Bahadir K. Gunturk 9
Image Resolution
Don’t confuse image size and resolution.
Bahadir K. Gunturk 10
Bit Depth – Grayscale Resolution
8 bits 7 bits
6 bits 5 bits
Bahadir K. Gunturk 11
Bit Depth – Grayscale Resolution
4 bits 3 bits2 bits 1 bit
Bahadir K. Gunturk 12
Matrix Representation of Images A digital image can be written as a matrix
1 2
[0,0] [0,1] [0, 1]
[1,0] [1,1] [1, 1][ , ]
[ 1,0] [ 1, 1]MxN
x x x N
x x x Nx n n
x M x M N
35 45 20
43 64 52
10 29 39
Bahadir K. Gunturk 13
Digital Color Images
1 2[ , ]Rx n n
1 2[ , ]Gx n n
1 2[ , ]Bx n n
Bahadir K. Gunturk 14
Color Displays
CRT
LCD
Polarize to control the amount of light passed.
Bahadir K. Gunturk 15
Video
= vertical position
= horizontal position
= frame number
1 2 3[ , , ]x n n n
1n
2n
3n
~24 frames per second.
Bahadir K. Gunturk 16
Why do we process images?
To facilitate their storage and transmission To prepare them for display or printing To enhance or restore them To extract information from them To hide information in them
Bahadir K. Gunturk 17
Image Processing Example
Image Restoration
Original image Blurred Restored by Wiener filter
Bahadir K. Gunturk 18
Image Processing Example
Noise Removal
Noisy image Denoised by Median filter
Bahadir K. Gunturk 19
Image Processing Example
Image Enhancement
Histogram equalization
Bahadir K. Gunturk 20
Image Processing Example Artifact Reduction in Digital Cameras
Original scene Captured by a digital camera
Processed to reduce artifacts
Bahadir K. Gunturk 21
Image Processing Example
Image Compression
Original image 64 KB
JPEG compressed 15 KB
JPEG compressed 9
KB
Bahadir K. Gunturk 22
Image Processing Example
Object Segmentation
“Rice” image Edges detected using Canny filter
Bahadir K. Gunturk 23
Image Processing Example
Resolution Enhancement
Bahadir K. Gunturk 24
Image Processing Example
Watermarking
Original image
Hidden message
Generate watermark
Watermarked image
Secret key
Bahadir K. Gunturk 25
Image Processing Example
Face Recognition
Surveillance video
Search in the database
Bahadir K. Gunturk 26
Image Processing Example
Fingerprint Matching
Bahadir K. Gunturk 27
Image Processing Example
Segmentation
Bahadir K. Gunturk 28
Image Processing Example
Texture Analysis and Synthesis
Pattern repeated Computer generated
Photo
Bahadir K. Gunturk 29
Image Processing Example
Face detection and tracking
http://www-2.cs.cmu.edu/~har/faces.html
Bahadir K. Gunturk 30
Image Processing Example
Face Tracking
Bahadir K. Gunturk 31
Image Processing Example
Object Tracking
Bahadir K. Gunturk 32
Image Processing Example
Virtual Controls
Bahadir K. Gunturk 33
Image Processing Example
Visually Guided Surgery
Bahadir K. Gunturk 34
Cameras
First camera was invented in 16th century. It used a pinhole to focus light rays onto a wall or
translucent plate.
Take a box, prick a small hole in one of its sides with a pin, and then replace the opposite side with a translucent plate.
Place a candle on the pinhole side, you will see an inverted image of the candle on the translucent plate.
Bahadir K. Gunturk 35
Perspective Projection
Perspective projection equations
' ' 'x y z
x y z
Bahadir K. Gunturk 36
Pinhole Camera Model If the pinhole were really reduced to a point, exactly one light ray would
pass through each point in the image plane. In reality, each point in the image place collects light from a cone of rays.
Bahadir K. Gunturk 37
Pinhole Cameras
Pinhole too big - many directions are averaged, blurring the image Pinhole too small - diffraction effects blur the image
Bahadir K. Gunturk 38
Cameras With Lenses
Most cameras are equipped with lenses. There are two main reasons for this:
To gather light. For an ideal pinhole, a single light ray would reach each point the image plane. Real pinholes have a finite size, so each point in the image plane is illuminated by a cone of light rays. The larger the hole, the wider the cone and the brighter the image => blurry pictures. Shrinking the pinhole produces sharper images, but reduces the amount of light and may introduce diffraction effects.
To keep the picture in sharp focus while gathering light from a large area.
Bahadir K. Gunturk 39
Compound Lens Systems
Bahadir K. Gunturk 40
Real Lenses
Rays may not focus at a single point.
Spherical aberration
Spherical aberration can be eliminated completely by designing aspherical lenses.
Bahadir K. Gunturk 41
Real Lenses
Chromatic aberration
The index of refraction is a function of wavelength. Light at different wavelengths follow different paths.
Bahadir K. Gunturk 42
Real Lenses
Chromatic Aberration
Bahadir K. Gunturk 43
Real Lenses Special lens systems using two or more pieces of glass with different
refractive indeces can reduce or eliminate this problem. However, not even these lens systems are completely perfect and still can lead to visible chromatic aberrations.
Bahadir K. Gunturk 44
Real Lenses Barrel Distortion & Pincushion Distortion
Stop (Aperture)
Causes of distortion
(normal)
Chief ray
Bahadir K. Gunturk 45
Real Lenses Barrel Distortion & Pincushion Distortion
Distorted Corrected
http://www.vanwalree.com/optics/distortion.htmlhttp://www.dpreview.com/learn/?/Image_Techniques/Barrel_Distortion_Correction_01.htm
Bahadir K. Gunturk 46
Real Lenses
Vignetting effect in a two-lens system. The shaded part of the beam never reaches the second lens. The brightness drop in the image perimeter.
Bahadir K. Gunturk 47
Real Lenses
Optical vignetting example. Left: f/1.4. Right: f/5.6.
f-number
focal length to diameter ratio
Bahadir K. Gunturk 48
Real Lenses
Long exposure time
Short exposure time
Bahadir K. Gunturk 49
Real Lenses
Flare
Hood may prevent flares
Bahadir K. Gunturk 50
Real Lenses
Flare
Bahadir K. Gunturk 51
Compound Lens Systems
http://www.dpreview.com/learn/?/glossary/http://www.cartage.org.lb/en/themes/Sciences/Physics/Optics/Optical/Lens/Lens.htmhttp://www.vanwalree.com/optics.html
Bahadir K. Gunturk 52
Digital Camera Pipeline
Auto-exposure algorithms measure brightness over discrete scene regions to compensate for overexposed or underexposed areas by manipulating shutter speed and/or aperture size. The net goals here are to maintain relative contrast between different regions in the image and to achieve a good overall quality.
(from Katz and Gentile)
Bahadir K. Gunturk 53
Digital Camera Pipeline
Auto-focus algorithms divide into two categories. Active methods use infrared or ultrasonic emitters/receivers to estimate the distance between the camera and the object being photographed. Passive methods, on the other hand, make focusing decisions based on the received image in the camera.
Bahadir K. Gunturk 54
Digital Camera Pipeline
Lens distortion correctionThis set of algorithms accounts for the physical properties of lenses that warp the output image compared to the actual scene the user is viewing. Different lenses can cause different distortions; for instance, wide-angle lenses create a "barrel distortion", while telephoto lenses create a "pincushion distortion“.
Bahadir K. Gunturk 55
Digital Camera Pipeline
Vignetting (shading distortion) reduces image brightness in the area around the lens. Chromatic aberration causes color fringes around an image. The media processor needs to mathematically transform the image in order to correct for these distortions.
Bahadir K. Gunturk 56
Digital Camera Pipeline
Sensor's output needs to be gamma-corrected to account for eventual display, as well as to compensate for nonlinearities in the sensor's capture response.
Bahadir K. Gunturk 57
Digital Camera Pipeline
Image stability compensation, or hand-shaking correction is another area of preprocessing. Here, the processor adjusts for the translational motion of the received image, often with the help of external transducers that relate the real-time motion profile of the sensor.
Bahadir K. Gunturk 58
Digital Camera Pipeline
White balance is another important stage of preprocessing. When we look at a scene, regardless of lighting conditions, our eyes tend to normalize everything to the same set of natural colors. For instance, an apple looks deep red to us whether we're indoors under fluorescent lighting, or outside in sunny weather. However, an image sensor's "perception" of color depends largely on lighting conditions, so it needs to map its acquired image to appear natural in its final output. This mapping can be done either manually or automatically.
Bahadir K. Gunturk 59
Digital Camera Pipeline
Demosaicking (Bayer interpolation) estimates missing color samples in single-chip cameras.
Bahadir K. Gunturk 60
Digital Camera Pipeline
In this stage, the interpolated RGB image is transformed to the targeted output color space (if not already in the right space). For compression or display to a television, this will usually involve an RGBYCbCr matrix transformation, often with another gamma correction stage to accommodate the target display. The YCbCr outputs may also be chroma subsampled at this stage to the standard 4:2:2 format for color bandwidth reduction with little visual impact.
Bahadir K. Gunturk 61
Digital Camera Pipeline
PostprocessingIn this phase, the image is perfected via a variety of filtering operations before being sent to the display and/or storage media. For instance, edge enhancement, pixel thresholding for noise reduction, and color-artifact removal are all common at this stage.
Bahadir K. Gunturk 62
Digital Camera Pipeline
Display / Compress / StoreOnce the image itself is ready for viewing, the image pipe branches off in two different directions. In the first, the postprocessed image is output to the target display, usually an integrated LCD screen (but sometimes an NTSC/PAL television monitor, in certain camera modes). In the second, the image is sent to the media processor's compression algorithm, where industry-standard compression techniques (JPEG, for instance) are applied before the picture is stored locally in some storage medium (e.g., Flash memory card).