0% found this document useful (0 votes)
163 views30 pages

Object Recognition

Object recognition is the process by which computers can identify and detect objects in digital images and videos. The summary discusses the key components of an object recognition system including a model database, feature detector, hypothesizer, and hypothesis verifier. It also outlines some of the tools and techniques used in object recognition like object representation, feature extraction, and feature-model matching. Finally, it notes some of the complexities involved in object recognition like scene constancy, the number of objects, and the possibility of occlusion.
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
163 views30 pages

Object Recognition

Object recognition is the process by which computers can identify and detect objects in digital images and videos. The summary discusses the key components of an object recognition system including a model database, feature detector, hypothesizer, and hypothesis verifier. It also outlines some of the tools and techniques used in object recognition like object representation, feature extraction, and feature-model matching. Finally, it notes some of the complexities involved in object recognition like scene constancy, the number of objects, and the possibility of occlusion.
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 30

Object Recognition

Outline
• Introduction
• Human Vision Vs Computer Vision
' I •( '~

• Object Recognition
• What is Object
Recognition?
• System Components
• Tools and Techniques
• Complexities Involved

• New Innovations
in Object Recognition
Human Vision
Vision is the process of discovering what is present
in the world and where it is by looking

Scene Image Perception


Eye - Brain

Image Acquisition Image Interpretation

5
Computer Vision
Computer Vision is the study of analysis of pictures and
videos in order to achieve results similar to those as by
humans

Scene Image Perception


Camera Compute
Computer .
.
Image Acquisition Image Inte
Interpretation

6
Human Vision VS Computer Vision

What we see What a computer sees


7
Main Goal of Computer Vision

Every picture tells a story!!


* write computer programs that can interpret images
*

8
Significance of Computer Vision

Safety Health Security

- .. -- ,-i

Fun
9
What is Digital Image Processing?

•The continuum from image processing to


computer vision can be broken up into low-,
mid- and high-level processes
Low Level Process Mid Level Process High Level Process
Input: Image Input: Image Input: Attributes
Output: Image Output: Attributes Output: Understanding
Examples: Noise Examples: Object Examples: Scene
removal, image recognition, understanding,
sharpening segmentation autonomous navigation

11
Key Stages in Digital Image Processing

Image Morphological
Restoration Processing

Image
Segmentation
Enhancement

Image Object
Acquisition Recognition

Representation
Problem Domain & Description

12
What is Object Recognition?
• Last step in image processing

• It is a computer vision technique for finding and identifying objects


in an image or a video sequence using object models

Like human understanding, it includes :

• Detection – of separate objects


• Description – of their geometry and positions
• Classification – as being one of a known class
• Identification – of the particular instance
• Understanding – of relationships between objects
22
System Components
• Model Data Base

• Feature Detector

• Hypothesizer

• Hypothesis Verifier

Different components of an object recognition system are shown


Tools & Techniques
• An object recognition system must select appropriate
tools and techniques in order to achieve the desired goals.

• The central issues considered in designing an object


recognition system are:

• Object or Model Representation


• Feature Extraction
• Feature-Model Matching
• Hypothesis Formation
• Hypothesis Verification
Complexity of Object Recognition

• Scene Constancy

• Image Models spaces

• Number of objects in Model Database

• Number of objects in an image and possibility of Occlusion


So what does object recognition involve?
Detection: are there people?
Verification: is that a lamp?
Identification: is that a Palace?
Object Categorization

mountain

tree
building
banner

street lamp

vendor
people
Scene and context categorization/Understanding

• outdoor
• city
•…

Slide credit Fei-Fei, Fergus, Torralba CVPR07 Short


Supermarket scanner recognizes objects without
barcodes

87
The Object Recognition
Scanner recognize items
based on color and pattern
88
Supermarket scanner recognizes objects without barcodes

Uses object recognition to identify foods at the supermarket checkout line.

The technology uses a camera that compares the food that is being scanned to a
large, expandable database of products.

That camera filters out background "noise" in its picture, so that it only sees
objects held close to its lens against a neutral black background.

The technology recognizes supermarket items at check out without requiring a


bar code...making bar codes obsolete for check out purposes.

It uses pattern recognition technology and claims it can operate at


high speeds.

This object recognition system requires a database that contains the information
about the items in the supermarket.

This system claims to be able to make very precise identification of produce.

89
Google patents new object recognition technology

90
Google patents new object recognition technology

It’s known as “automatic large scale video object recognition.”

It can actually recognize the difference between a variety of


objects, not just human faces.

After recognizing an object it then labels it with certain tags. If you


are wondering how it does this, there is a special object name
repository involved.

This database would hold at least 50,000 object names,


information and shapes that would allow for easy identification.
91
92
88
SELF-PARKING CAR

No humans Here
96
- -

.
References

• http://arxiv.org/ftp/arxiv/papers/1001/1001.4186.pdf
• http://www4.comp.polyu.edu.hk/~csajaykr/myhome/teaching/biometrics/final_re
port.pdf
• http://www.google.com.lb/ Fingerprint Analysis and Representation.ppt
• http://www.academia.edu/2537762/Fingerprint_Matching_using_Ridge-
End_and_Bifurcation_Points
• http://ai.pku.edu.cn/aiwebsite/research.files/collected%20papers%20-
%20fingerprint/Minutiae%20detection%20algorithm%20for%20fingerprint%20reco
gnition.pdf
• http://en.wikipedia.org/wiki/Computer_vision

98
THANK YOU

99

You might also like