Vision Recognition

jabgoldfishAI and Robotics

Oct 19, 2013 (3 years and 7 months ago)

97 views

Vision Recognition

Neil Agarwal

Bailey Zhang

Zack Sorenson

Ben Schneider

What is Computer Vision?


Definition


Computational Vision


Attempts to understand visual perception and
understanding


Machine Vision


Attempts to create practical application for
computer vision



Vision Recognition & AI


Creating useful autonomous agents


Human/computer interfacing


Gesture recognition


Handwriting recognition


Passive observation & analysis


Understanding biological vision


Honda’s
ASIMO


GRACE the Robot

Converting handwritten figures
into figures usable by a computer



Current Implementation

Optical Character Recognition (OCR)

Types of OCR

Character
-
based word recognition

Segmentation
-
based word recognition

Word
-
shape recognition

Current Limitations of OCR



Underlines in text



‘I’

and
‘i’

confusions



Distortion of
‘e’


Examples of OCR software



Calera Wordscan Plus 1.0




Caere Omnipage Professional 3.0




Xerox Imaging Systems AccuText 3.0


Current Implementation (cont.)





Scarecrow



Floating, autonomous robot platform powered
by solar panels


Searches for birds using its vision system


Goes around, when its senses birds, bumps
them or shoots water at them


Floats in catfish ponds to protect the stock
which is frequently depleted by hungry birds

Successes in
Computer/Machine

Vision


Machine Vision, the name for Computer
Vision that is applied specifically to robots
or machines, is extremely relevant in
industry.


Most Computer Vision technology that
affects you is in fact Machine Vision.

Machine Vision and You


Machine Vision is being developed to control the quality
of products, detecting defects automatically


The technology is reaching a point where people can be
tracked in 3D, leading to more robust security systems.


And for your entertainment, Machine vision is being
developed to track actual movements, for more realistic
and exciting games

Other Machine Vision Fields


Agriculture, Architecture, Character
Recognition, Cultural, Forensic, Medical,
Image Processing, Reverse Engineering,
Military, Navigation, Remote Sensing,
Safety, Sports

Successes in Computer Vision


Computer Vision is broader than
Machine Vision.


There are many successes in Computer
Vision; many, many, many successes

Development/Successes in
Computer Vision Technology


SUCCESSOR


General Successes


Marr’s Theory: shape info from images.

Marr’s Theory


The geometry


The reflectance of the visible surfaces


The illumination


The viewpoint

More Marr

Problems & Setbacks


Finding 3D objects in 2D images


Making raster images usable for a computer





Incomplete understanding of human vision


What’s Currently Being Done


Penn State Computer Vision Lab


Berkeley Group


Penn State


Hand gesture
recognition as
supplement to speech
recognition.


Text recognition and
clarification in video.



Text Clarification


Possible example need for technology


Berkeley

Automatic detection of
human nudes

Image content
recognition

Image Content Analysis

Future of Vision Recognition

PC’s Recognizing Users (Microsoft Project)


When a user sits in front of the computer, it will
bring up his work, etc.


PC equipped with a camera on top


Long term: aiming for a system that can
recognize eye movements, so that software
could be controlled by eye movement


Only a couple years from reaching mass market?

Future of Vision Recognition (cont.)

Augmented Reality


Real world







Augmented world

Any Questions?