Transcript 슬라이드 1 - Vision & Media Research LAB

Computer Vision
Introduction to Computer
Vision
2/03/2015
Hyunki Hong
School of Integrative Engineering
Contents
• Class & Grading
• Introduction to Computer Vision
Introduction
• Computer vision is
- the analysis of digital images by a computer.
- computing properties of the 3-D world from one or
more digital images:
1. Geometric (shape and position of solid objects)
2. Dynamic (object velocities)
• The tools of Computer Vision
: H/W for acquiring & storing digital images, processing
the images, and communicating results to users or other
automated systems.
Introduction
• Image processing
- Main target : image properties and image-to-image
transformations
cf. CV : the 3-D world
- Preliminary process for 3-D vision
1. Enhancement : computing an image of better quality than
original one
2. Compression : devising compact representations for digital
images, typically for transmission process
3. Restoration : eliminating the effect of known degradations
4. Feature extraction : locating special image elements like
contours, or textured areas
Introduction
• Pattern recognition : recognizing and classifying
objects using digital images
• The goals of this course are to understand many
core algorithms in computer vision
– cameras and projection models,
– low-level image processing methods such as filtering and
edge detection
– mid-level vision topics such as segmentation and clustering,
shape reconstruction from stereo
– high-level vision tasks such as scene and object recognition
Class & Grading
• Textbooks
- E. Trucco and A. Verri, Introductory Techniques for 3-D
Computer Vision, Prentice Hall, 1998.
- D. Kang and J. Ha, Digital Image Processing, Infinity Books,
2010.
- R. Laganiere, OpenCV2 Computer Vision Application
Programming Cookbook, Packt Publishing, 2011.
• Course assessment includes a term project,
homework programming assignments, and two
exams - midterm and final.
• The final grade has four components: class
attendance (10%), term project (20%), midterm exam
score (30%), and final exam score (40%).
Connections to other disciplines
Artificial Intelligence
Robotics
Machine Learning
Computer Vision
Cognitive science
Neuroscience
Computer Graphics
Image Processing
Digital Image Terminology
0
0
0
0
0
0
0
•
•
•
•
•
•
0
0
1
0
0
1
0
0
1
95
92
93
92
94
0
1
96
93
93
93
95
1
1
94
93
94
93
95
0
0
93
92
92
93
96
0
0
92
92
93
93
95
binary image
gray-scale (or gray-tone) image
color image
multi-spectral image
range image
labeled image
pixel (with value 94)
its 3x3 neighborhood
region of medium
intensity
resolution (7x7)
Three Stages of Computer Vision
• low-level
image
image
• mid-level
image
features
• high-level
features
analysis