Scribd
Upload
23 views

Intro

The document provides an overview of computer vision, including what it is, where images come from, and various applications such as medical imaging, robotics, image databases, and object recognition. It also discusses the goals of image analysis and the three stages of computer vision - low-level, mid-level, and high-level processing. Computer vision is challenging as there are many visual tasks humans can perform easily that current computer vision systems struggle with.

Uploaded by

mehari kiros
Copyright
© © All Rights Reserved
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
23 views

Intro

The document provides an overview of computer vision, including what it is, where images come from, and various applications such as medical imaging, robotics, image databases, and object recognition. It also discusses the goals of image analysis and the three stages of computer vision - low-level, mid-level, and high-level processing. Computer vision is challenging as there are many visual tasks humans can perform easily that current computer vision systems struggle with.

Uploaded by

mehari kiros
Copyright
© © All Rights Reserved
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 23

Introduction

• What IS computer vision?

the analysis of digital images by a computer

• Where do images come from?

1
Applications
• Medical Imaging

CT image of a
patient’s abdomen
liver

kidney
kidney

2
Visible Man Slice Through Lung

3
3D Reconstruction of the Blood Vessel Tree

4
Slice of a Chicken Embryo’s Inner Ear

5
CBIR of Mouse Eye Images for Genetic Studies

6
Robotics
• 2D Gray-tone or Color Images

“Mars” rover

• 3D Range Images

What am I?

7
Image Databases:

Images from my Ground-Truth collection.

What categories of image databases exist today?

8
Abstract Regions for Object Recognition

Original Images Color Regions Texture Regions Line Clusters

9
Documents:

10
11
Insect Recognition for Ecology

12
Surveillance: Event Recognition in Aerial Videos

Original Video Frame Structure Regions

13
Color Regions Color-Merge Regions
Vision for Graphics:

Recent work of Steve Seitz (CSE) and Aaron Hertzman


on Computing the Geometry of Objects from Images.

14
Some Applications from WACV
• Face Detection / Skin Detection
• Face Recognition
• Gesture Recognition
• Eye Gaze Estimation
• Gender Classification
• People Tracking
• Group Behavior Recognition
• Visual Navigation
• Real-Time Precrash Vehicle Detection
• Augmented Reality
• Vehicle Inspection
• Video de-Abstraction (save money on wedding videos)
• Analysis of Auroral Appearance over Canada
• Video Endoscopy
15
Digital Image Terminology:

0 0 0 0 1 0 0
pixel (with value 94)
0 0 1 1 1 0 0
0 1 95 96 94 93 92 its 3x3 neighborhood
0 0 92 93 93 92 92
0 0 93 93 94 92 93 region of medium
0 1 92 93 93 93 93 intensity
0 0 94 95 95 96 95
resolution (7x7)

• binary image
• gray-scale (or gray-tone) image
• color image
• multi-spectral image
• range image
• labeled image 16
Goals of Image Analysis

• Segment the image into useful regions

• Perform measurements on certain areas

• Determine what object(s) are in the scene

• Calculate the precise location(s) of objects

• Visually inspect a manufactured object

• Construct a 3D model of the imaged object 17


•The Three Stages of Computer Vision

• low-level

image image

• mid-level

image features

• high-level

features analysis

18
Low-Level

sharpening

blurring

19
Low-Level

Canny

original image edge image


Mid-Level

ORT

data
structure
circular arcs and line segments 20
edge image
Mid-level

K-means
clustering
(followed by
connected
component
analysis)

original color image regions of homogeneous color

data
structure
21
Low- to High-Level

low-level
edge image

mid-level

consistent
high-level line clusters

Building Recognition
22
Difficulty of Computer Vision

• Computer vision is far from completely solved.

• There have been many successful systems used in


real applications.

Like what?

• There are lots of things that humans can do for


which vision programs don’t come close to success.

Can you name some?

23

You might also like