Computer Vision

1
Computer Vision Overview

• Hanyang University
• Jong-Il Park

2
Digital Image Processing

• Sampling Quantization
• Image Enhancement
• Image Restoration
• Image Coding( or Image Data Compression)
• Image Understanding( or Computer Vision)

3
Image formation
4
Sampling Quantization
5
(No Transcript)
6
Subsampling aliasing
aliasing
7
Sub-Nyquist sampling
Circular Zone Plate
H ½, v ½
Org.
aliasing
8
Image Enhancement

• Goal
• to accentuate certain image features for
  subsequent analysis or for image display

Input image
Output image
9
(No Transcript)
10
(No Transcript)
11
Image Enhancement

• Techniques
• contrast/edge enhancement
• histogram equalization
• pseudo coloring
• noise filtering
• edge sharpening
• smoothing
• Applications
• processing of remote-sensed image via satellite
• radar, SAR, Ultrasonic image processing

12
Image Restoration

• Goal
• to remove or minimize known/unknown degradations
  in image

13
(No Transcript)
14
Blur model

• ? estimate or recover f(x,y) from g(x,y)
• ? deconvolution problem

15
Enhancement by integration
16
Image Restoration

• Techniques
• deblurring
• noise filtering
• correction of geometric distortion
• inverse filtering
• Least mean square(Wiener) filtering
• Applications
• remote-sensed image processing
• noise cancellation

17
Image Data Compression

• Goal
• to reduce the amount of data required to
  represent images

Input image
Output bit-stream data
010100101100110101001 . . . .
moving image 1,000?1,000?8(bits/sample)?3?30
frame/sec 72?107 bit/sec
18
2-D Image Compression, JPEG

• Image quality by JPEG

(a) 27.9 dB at 0.125 bpp
(b) 31.5 dB at 0.25 bpp
(c) 34.8 dB at 0.5 bpp
19
(No Transcript)
20
(No Transcript)
21
3D Mesh Compression
Model of Vertex of Triangle Original (byte) Compressed (byte) Compressed (byte) Compressed (byte)
Model of Vertex of Triangle Original (byte) 12 bpc 10 bpc 8 bpc
Bunny 34835 69473 2,879,786 57,952 37,642 24,842
Compression ratio Compression ratio Compression ratio Compression ratio 50 1 77 1 116 1
Original Bunny
12 bpc
8 bpc
10 bpc
22
Image Data Compression

• Techniques
• Error-free coding( or lossless coding)
• Lossy compression
• Image Compression Standard
• JPEG, H.261, H.263, MPEG-1,2,4 etc
• Applications
• Transmission
• teleconferencing ,TV system, remote sensing via
  satellite
• Storage
• VOD(video on demand), Video CD, DVD(digital video
  disk), medical imaging, educational and business
  documents

23
Image Coding Standards
24
MPEG

• MPEG-1
• 1992
• Video CD
• Includes Audio Layer III (MP3)
• MPEG-4
• Part 1 1998
• Part 2 1999 (addition still under development)
• Audio visual object
• Mobile telephony (IMT-2000)
• Interactivity
• Content Based Interactivity

25

• MPEG-7
• 2001 (addition still under development)
• Content Description Interface
• Metadata language and schemes for search
  retrieval

26
Content-based Image Retrieval

• Image retrieval
• Find similar images from image database
• Used features
• Color
• Texture
• Shape

Query
Retrieved
27
(No Transcript)
28
Content-based Video Retrieval

• Video retrieval
• Scene change detection and key frame extraction
• Extracted key frame from a movie clip

29
Content-based Video Retrieval

• Video retrieval
• Automatic indexing
• Index from a news sequence

30
Media Framework Tech.

• MPEG-21
• All electronic creation, delivery and trade of
  digital multimedia content
• Transparent usage of various content types on
  various devices connected through various network

31
Watermarking

• the process of embedding information into a host
  signal without changing perceived characteristics
  of the host

32
Image Understanding

• Goal
• to interpret or describe the meaning contained in
  the image

Input image
Output interpretation(description)
KAISION
circle
33
(No Transcript)
34
(No Transcript)
35
Stereo Vision (disparity map)
?? ??(?)
?? ??(?)
?? ?? ??(??? ????)
?? ? ?(??? ????)
36
Scene Matching (1)
Scene matching result
37
Scene Matching (2)
38
Fruit Classifier

• Apple
• Orange
• Water Mellon

??, ???
39

• color

40
Edge Detection
41
Segmentation
(a) Aerial Original Image
(b) Segmented Image
42
(No Transcript)
43

• There are a lot of interesting topics to explore
  in image processing and computer vision.