+ All Categories
Home > Documents > High level vision.

High level vision.

Date post: 18-Jan-2018
Category:
Upload: noel-walton
View: 238 times
Download: 0 times
Share this document with a friend
Description:
High level vision Models of object recognition Top down influences Navigation/Movement
63
High level vision
Transcript
Page 1: High level vision.

High level vision

Page 2: High level vision.

High level vision

• Models of object recognition• Top down influences• Navigation/Movement

Page 3: High level vision.

Last Time. . ..

We spent a lot of time focusing on lines; how you get them, why you would want them, and so on.

We need to move from lines to objects. How do you recognize an object from an organization of lines?How does perception connect to memory?

Page 4: High level vision.

Models of object recognition

• Template• Feature• “New wave” of feature models (3D

features)

Page 5: High level vision.

Template model

Page 6: High level vision.

Template--problems

Problems: Size

Orientation

Need too many templates

Page 7: High level vision.

Feature model--pandemonium

Page 8: High level vision.

Feature modelsGood: visual input does seem to be decomposed into features

Good: Physiological evidence about simple features from Hubel & Wiesel

Problems: orientation missing features

natural objects

Page 9: High level vision.

Natural objects: What are the features of a dog?

• Nose • Ear • Front Leg• Tail• Back Leg

Page 10: High level vision.

Principle from Gestalt Psych

A

B

C

D

Good continuation

Page 11: High level vision.

Good continuation can be used to find the parts of objects

Page 12: High level vision.

“new wave” of feature models

These models use three-dimensional features.

Page 13: High level vision.

Biederman’s geon model

You usually only need to see the edges of a geonGeons have properties that are invariant to rotations

Geons

Simple objects

Page 14: High level vision.

Experiment

Which can be better identifiedat a very briefexposure?

Page 15: High level vision.
Page 16: High level vision.

Problems with Geons

• Do geons really represent all shapes?• How are relationships among geons coded?

Page 17: High level vision.

An alternative: Local viewpoints

Note that you can identify objects from many different orientations. Templates & Feature

models couldn’t account for this—geons can.BUT how good are you at doing this really?

Page 18: High level vision.
Page 19: High level vision.
Page 20: High level vision.
Page 21: High level vision.
Page 22: High level vision.
Page 23: High level vision.
Page 24: High level vision.
Page 25: High level vision.
Page 26: High level vision.
Page 27: High level vision.

AlternativeSome researchers have suggested that object representations are NOT viewpoint independent. Rather, we store views of objects the way we see them.

HUH? Isn’t that the template theory?

The difference is that you do some “fixing” (size, rotation) of the image to fit the template

Page 28: High level vision.

Tarr’s local view experimentsO° 45° 90° O° 45° 90°

Page 29: High level vision.

Tarr Results

Page 30: High level vision.

Problems with local view

• Chicken & egg: how do you know how to rotate the image before you can identify it?

• What is stored is clearly not literal pictures…but what is it?

• How is what you see and what is in memory matched?

Page 31: High level vision.

Chicken & egg problem. . .

Bottom up processing refers to beginning with relatively raw, unprocessed sensory information, and building towards more conceptual representations. Top-down processing refers to conceptual knowledge influencing the processing or interpretation of lower-level perceptual processes

Page 32: High level vision.

NOTE--we’ve been acting as though all processing were

bottom up.

Page 33: High level vision.

Example: ambiguous figures

Page 34: High level vision.

Example

Page 35: High level vision.

Example:

Page 36: High level vision.

It appears that in top down processing you use conceptual information to generate hypotheses about what the stimulus might be, then test these hypotheses

Page 37: High level vision.

More formal work

Watch for the object appearing

Page 38: High level vision.
Page 39: High level vision.
Page 40: High level vision.
Page 41: High level vision.
Page 42: High level vision.
Page 43: High level vision.

The Parsing Paradox

If perceptual organization is a matter of mapping sensations onto structural schema, which happens first: interpreting the whole or interpreting the parts? How can someone recognize a face until he has first recognized the eyes, nose, mouth and ears? Then again, how can you recognize the parts until you know that they are part of a face?

--Stephen Palmer

Page 44: High level vision.
Page 45: High level vision.

Question: do you process the top-down information atthe same time as the bottom-up info?

You’ll see a circle--try to identify the objectthat appears in the circle.

Page 46: High level vision.
Page 47: High level vision.
Page 48: High level vision.
Page 49: High level vision.
Page 50: High level vision.
Page 51: High level vision.
Page 52: High level vision.
Page 53: High level vision.

The result: people are better at identifying the objectwhen the scene makes sense, compared to when it’s jumbled

Page 54: High level vision.

How is this possible?

Word superiority effectIt is easier to recognize a letter in a

word than in isolation.

Page 55: High level vision.

Identify the letter that will appear in the circle

Page 56: High level vision.

TAKE

Page 57: High level vision.

WOLP

Page 58: High level vision.

Word superiority effect

Faster and more reliable in identifying a letter when it’s part of a

word than a non-word.

Isn’t there the same chicken-egg problem? Don’t you need to know the letters to identify the word? So then how is the word helping to identify the letters (which you already know?)

Page 59: High level vision.

Model of word identification

Page 60: High level vision.

Navigation vs. Object identification

There is increasing evidence that spatial information that helps us get around is independent of the information that helps us identify objects.

Page 61: High level vision.

Mishkin & Ungerlieder

Page 62: High level vision.

Mishkin & Ungerlieger

Page 63: High level vision.

Mishkin & Ungerliedger

Object

Spatial


Recommended