Scribd
Upload
2 views

Lecture-1 CV

The lecture on Computer Vision, presented by Dr. Yin Win Chit, explores the nature and objectives of computer vision, comparing it to human vision and discussing its challenges. Key topics include the process of interpreting images, various applications such as 3D modeling and face detection, and the difficulties in achieving human-like vision due to the complexity of visual data. The lecture concludes with a preview of real-world applications of computer vision, including medical imaging and automotive safety.

Uploaded by

Thet Hsu
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
2 views

Lecture-1 CV

The lecture on Computer Vision, presented by Dr. Yin Win Chit, explores the nature and objectives of computer vision, comparing it to human vision and discussing its challenges. Key topics include the process of interpreting images, various applications such as 3D modeling and face detection, and the difficulties in achieving human-like vision due to the complexity of visual data. The lecture concludes with a preview of real-world applications of computer vision, including medical imaging and automotive safety.

Uploaded by

Thet Hsu
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 18

Computer Vision

Overview of Computer Vision

Lecture - 1

Presented By
Dr. Yin Win Chit
Associate Professor
Reference

Computer Vision– Algorithms and Applications


by Richard Szeliski
2011.
Lecture Topics
 Human Vision

 What is Computer Vision?

 Overview of Computer Vision

 Computer Vision vs. Human Vision

 Goal of Computer Vision

 Why study Computer Vision?

 Why is vision so difficult?

 The challenge of making systems human-like


Lecture Objective

To understand the nature and basis of Computer Vision


Human Vision
 Perceive the three-dimensional (3D) structure of the world.

 No problem interpreting the subtle variations in translucency and shading in this


photo and correctly segmenting the object from its background.
Computer Vision vs. Human Vision
Overview of Computer Vision
 Make computers understand images and video.

What kind of scene?

Where are the cars?

How far is the building?


What is Computer Vision?

 Computer Vision is the process whereby a machine, usually a digital


computer, automatically processes an image and reports “what is in the
image.”

 In Computer Vision a camera (or several cameras) is linked to a computer.

 The computer interprets images of a real scene to obtain information useful


for tasks such as navigation, manipulation and recognition.
What is Computer Vision? –Cont’d
 Stitching: turning overlapping photos into a single seamlessly stitched
panorama

 Exposure bracketing: merging multiple exposures taken under challenging


lighting conditions (strong sunlight and shadows) into a single perfectly
exposed image

 Morphing: turning a picture of one of your friends into another, using a


seamless morph transition

 3D modeling: converting one or more snapshots into a 3D model of the object


or person you are photographing
What is Computer Vision? –Cont’d
 Video match move and stabilization: inserting 2D pictures or 3D models into your
videos by automatically tracking nearby reference points 3 or using motion estimates to
remove shake from your videos

 Photo-based walkthroughs: navigating a large collection of photographs, such as the


interior of your house, by flying between different photos in 3D

 Face detection: for improved camera focusing as well as more relevant image searching;

 Visual authentication: automatically logging family members onto your home computer
as they sit down in front of the webcam
Goal of Computer Vision
 The goal of computer vision is to enable computers to analyze and understand visual data in much
the same way that human brains and eyes do.
 To bridge the gap between pixels and “meaning”

 Goal of computer vision is to write the computer programs that can interpret images.

What we see? What a computer sees?


Why study Computer Vision?

 Images and movies have become ubiquitous in both production and


consumption.

 Therefore, applications to manipulate images become core.

 As the system extract the information from imagery


 Surveillance

 Building 3D representations

 Motion capture assisted….


Why is vision so difficult? (Some common optical illusions)
(a) Hermann Grid

(b) (c)
Do you see the gray spots How many red X’s are there?
at the intersections?
Why is vision so difficult? (Some common optical illusions)

 The “white” square B in the shadow and the “black” square A in the light actually

have the same absolute intensity value.


The challenge of making systems human-like

 The core problem of computer vision is object recognition.

 One reason is that we don’t have a strong grasp of how human vision works still
learning exactly how human vision works.

 Another reason why it is such a challenging problem is because of the complexity


inherent in the visual world.

 A given object may be seen from any orientation, in any lighting conditions, with any
type of occlusion from other objects, and so on.
Let's summarize

 Extracting descriptions of the world from pictures or sequences of pictures.

 The construction of explicit meaningful description of physical objects from


images.

 There are many challenges of Computer Vision.

 Researchers in computer vision have been developing many techniques for


recovering the three-dimensional shape and appearance of objects in imagery.
Next Lecture Applications of Computer Vision
 Computer Vision is being used today in a wide variety of real-world applications, which
include:
 Optical character recognition (OCR)

 3D model building (photogrammetry)

 Medical imaging

 Automotive safety

 Matchmove

 Motion capture

 Surveillance

 Fingerprint recognition and biometrics


Lecture End!

You might also like