September 2, 2014 Computer Vision Lecture 1: Human 1 Welcome to CS 675 – Computer Vision Fall 2014 Instructor: Marc Pomplun
Dec 31, 2015
September 2, 2014 Computer Vision Lecture 1: Human Vision
1
Welcome to
CS 675 – Computer Vision
Fall 2014
Instructor: Marc Pomplun
September 2, 2014 Computer Vision Lecture 1: Human Vision
2
Instructor – Marc PomplunOffice: S-3-171
Lab: S-3-135
Office Hours: Tuesdays 3:30-4:00, 5:15–7:00 Thursdays 5:15– 6:00
Phone: 287-6443 (office) 287-6485 (lab)
E-Mail: [email protected]
Website: http://www.cs.umb.edu/~marc/cs675/
September 2, 2014 Computer Vision Lecture 1: Human Vision
3
The Visual Attention Lab
Cognitive Science, esp. eye movements
September 2, 2014 Computer Vision Lecture 1: Human Vision
4
A poor guinea pig:
September 2, 2014 Computer Vision Lecture 1: Human Vision
5
Computer Vision:
September 2, 2014 Computer Vision Lecture 1: Human Vision
6
Modeling of Brain Functions
September 2, 2014 Computer Vision Lecture 1: Human Vision
7
Modeling of Brain Functionsunit and connectionin the interpretive network
unit and connectionin the gating network
unit and connectionin the top-down bias network
layer l +1
layer l -1
layer l
September 2, 2014 Computer Vision Lecture 1: Human Vision
8
Example: Distribution of Visual Attention
September 2, 2014 Computer Vision Lecture 1: Human Vision
9
Selectivity in Complex Scenes
September 2, 2014 Computer Vision Lecture 1: Human Vision
10
Selectivity in Complex Scenes
September 2, 2014 Computer Vision Lecture 1: Human Vision
11
Selectivity in Complex Scenes
September 2, 2014 Computer Vision Lecture 1: Human Vision
12
Selectivity in Complex Scenes
September 2, 2014 Computer Vision Lecture 1: Human Vision
13
Selectivity in Complex Scenes
September 2, 2014 Computer Vision Lecture 1: Human Vision
14
Selectivity in Complex Scenes
September 2, 2014 Computer Vision Lecture 1: Human Vision
15
Human-Computer Interfaces:
September 2, 2014 Computer Vision Lecture 1: Human Vision
16
Your Evaluation
• 4 sets of exercises (individual work)
o paper-and-pencil questions: 10%
o programming tasks: 30%
• midterm (75 minutes) 25%
• final exam (2.5 hours) 35%
September 2, 2014 Computer Vision Lecture 1: Human Vision
17
Grading
95%: A 90%: A-
74%: C+ 70%: C 66%: C-
86%: B+ 82%: B 78%: B-
62%: D+ 56%: D 50%: D-
50%: F
For the assignments, exams and your course grade, the following scheme will be used to convert percentages into letter grades:
September 2, 2014 Computer Vision Lecture 1: Human Vision
18
Complaints about Grading
If you think that the grading of your assignment or exam was unfair,
• write down your complaint (handwriting is OK),• attach it to the assignment or exam, • and give it to me or put it in my mailbox.
I will re-grade the exam/assignment and return it to you in class.
September 2, 2014 Computer Vision Lecture 1: Human Vision
19
Computer VisionComputer Vision is the science of building systems that can extract certain task-relevant information from a visual scene.
Such systems can be used for applications such as optical character recognition, analysis of satellite and microscopic images, magnetic resonance imaging, surveillance, identity verification, quality control in manufacturing etc.
September 2, 2014 Computer Vision Lecture 1: Human Vision
20
Computer VisionIn a way, Computer Vision can be considered the inversion of Computer Graphics.
A computer graphics systems receives as its input the formal description of a visual scene, and its output is a visualization of that scene.
A computer vision system receives as its input a visual scene, and its output is a formal description of that scene with regard to the system’s task.
Unfortunately, while a computer graphics task only allows one solution, computer vision tasks are often ambiguous, and it is unclear what the correct output should be.
September 2, 2014 Computer Vision Lecture 1: Human Vision
21
Computer VisionDigital Images
Binary Image Processing
Color
Image Filtering
Basic Image Transformation
Edge Detection
Image Segmentation
Shape Representation
Texture
Depth
Motion
Object Recognition
Image Understanding
Visible light is just a part of the electromagnetic spectrum
September 2, 2014 Computer Vision Lecture 1: Human Vision
2222
Cross Section of the Human Eye
September 2, 2014 Computer Vision Lecture 1: Human Vision
2323
24September 2, 2014 Computer Vision Lecture 1: Human Vision
25
Photoreceptor
Bipolar
Ganglion
September 2, 2014 Computer Vision Lecture 1: Human Vision
26
Major Cell Types of the Retina
September 2, 2014 Computer Vision Lecture 1: Human Vision
27
Receptive Fields
September 2, 2014 Computer Vision Lecture 1: Human Vision
28
Coding of Visual Information in the Retina Photoreceptors: Trichromatic Coding
Peak wavelength sensitivities of the three cones:Blue cone: Short- Blue-violet (420 nm) Green cone: Medium- Green (530 nm)Red Cone: Long- Yellow-green (560nm)
September 2, 2014 Computer Vision Lecture 1: Human Vision
29September 2, 2014 Computer Vision Lecture 1: Human Vision
30
Coding of Visual Information in the Retina Retinal Ganglion Cells:
Opponent-Process Coding
Negative afterimage: The image seen after a portion of the retina is exposed to an
intense visual stimulus; consists of colors complimentary to those of the physical stimulus.
Complimentary colors: Colors that make white or gray when mixed together.
September 2, 2014 Computer Vision Lecture 1: Human Vision
31September 2, 2014 Computer Vision Lecture 1: Human Vision
32September 2, 2014 Computer Vision Lecture 1: Human Vision