Download presentation
Presentation is loading. Please wait.
Published byEmily Lane Modified over 9 years ago
1
An Introduction to Computer Vision George J. Grevera, Ph.D.
2
The science of analyzing images and videos in order to recognize or just model 3D objects, persons, and environments. Computer Vision
3
How does the Sony AIBO dog find its way “home” (to its charging stations)? Computer Vision
4
How does the yellow, virtual first-down line work? Computer Vision
5
How do cameras perform (digital) image stabilization? In this class, we study the underlying principles and produce working examples. Computer Vision
6
Visualization includes… Computer graphics Computer / Machine vision Image understanding Database and communications Computer games Medical imaging Image processing Pattern recognition
7
Computer graphics/games vs. computer vision Computer graphics/games creates a 2D image from a 3D world/model. 3D to 2D
8
Computer graphics/games vs. computer vision Computer vision estimates a 3D world/model from a 2D image. 2D to 3D
9
Examples gray (b&w) and color
10
Ansel Adams: El Capitan
11
Bill Brandt: Lambeth Walk
12
Lewis Hine
14
George Grevera: Horse Fishing
16
#1 Major problems in Computer Vision: Segmentation
17
Segmentation Recognition: Is a t-shirt present? Delineation: Can you accurately outline the t-shirt (what size is it)?
18
Segmentation tasks: 1. Recognition Human is typically better. more qualitative 2. Delineation Computer is typically better. more quantitative
19
Model building
20
Models from CT (Computed Tomography) head data
21
3D visualization of CT head data
23
MRI Diffusion Tensor Imaging
24
#2 Major problem in Computer Vision: Registration
25
Registration A.K.A.: alignment warping mosaicing morphing fusion
26
Simple MRI Example (rigid)
27
Deformable
28
Thirion’s “Demons” algorithm applied to pre- and post-contrast MRI of the breast. excellent results Deformable registration example pre post (no reg) post (after Thirion’s Demons registration) diff diff (after reg)
29
Thirion’s “Demons” algorithm applied to PET chest emission and transmission images. poor results PET transmission image PET emission image PET emission warped to match transmission Deformable registration example
30
NON-MEDICAL VISUALIZATION
31
Red eye reduction
32
What is a distance transform? Input:a binary image Output:a grey image for all points... assign the minimum distance from that particular point to the nearest point on the border of an object
33
Applications of distance transforms: skeletonization/medial axis transform interpolation registration efficient ray tracing classification of plant cells measuring cell walls characterize spinal cord atrophy
34
Experimental Results binary input image distance transform result
36
Application areas: Object recognition Tracking Registration Fusion Intelligence, industrial and medical projects FBI Automatic Fingerprint Identification System FOCUS: Monitor change in satellite images FBI Facial Reconstruction Software: Target Junior Image Understanding
41
Textbook L.G. Shapiro, G.C. Stockman, Computer Vision, Prentice-Hall, 2001.
42
Topics Imaging and image representation Sensors Problems (including noise) Image file formats Color representation and shading Binary image analysis Connected components Morphology Region properties
43
Topics Pattern recognition concepts Classifiers and classification Filtering (enhancing) images Segmentation Registration (matching)
44
Topics Registration Texture representation and segmentation Motion from sequences of 2D images
45
Homework #1 Read chapter 1. Hand in 1.1, 1.2, and 1.3.
46
Survey questions… 1. Do you have access to a digital camera?
47
2. Write a function that, given a 2D array, returns a 1D array where each entry is the sum of the corresponding row in the 2D array. (So result[0] contains the sum of values in m for row 0, result[1] contains the sum of values in m for row 1, etc.) Java: int[] sumOfRows ( int m[][], int rows, int cols ) { …}
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.