1 / 38

Visual Cognition II Object Perception

Visual Cognition II Object Perception. Theories of Object Recognition. Template matching models Feature matching Models Recognition-by-components Configural models. Template matching. TEST INSTANCE. “J” TEMPLATE. “T” TEMPLATE.

hedva
Download Presentation

Visual Cognition II Object Perception

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Visual Cognition IIObject Perception

  2. Theories of Object Recognition • Template matching models • Feature matching Models • Recognition-by-components • Configural models

  3. Template matching TEST INSTANCE “J” TEMPLATE “T” TEMPLATE Detect patterns by matching visual input with a set of templates stored in memory – see if any template matches. match

  4. Problem: what if the object differs slightly from the template? E.g., it is rotated or scaled differently? Solution: use a set of transformations to best align the object with a template (using translation, rotation, scaling) TEST INSTANCE rotation “J” TEMPLATE “T” TEMPLATE match

  5. Template-matching works well in constrained environments

  6. Figure 2-15 (p. 58)Examples of the letter M. Problem: template matching is not powerful enough for general object recognition

  7. Feature Theories • Detect objects by the presence of features • Each object is broken down into features • E.g. A = + +

  8. Problem • Many objects consist of the same collection of features • Need to also know how the features relate to each other  structural theories • One theory is recognition by components Different objects, similar sets of features

  9. Recognition by Components (RBC) • Biederman (1987): Complex objects are made up of arrangements of basic, component parts: geons. • “Alphabet” of 24 geons • Recognition involves recognizing object elements (geons) and their configuration

  10. Why these geons? • Choice of shape vocabulary seems a bit arbitrary • However, choice of geons was based on non-accidental properties. The same geon can be recognized across a variety of different perspectives: except for a few “accidental” views:

  11. Viewpoint Invariance • Viewpoint invariance is possible except for a few accidental viewpoints, where geons cannot be uniquely identified

  12. Deleting line segments Deleting vertices Prediction Object • Recognition is easier when geons can be recovered • Disrupting vertices disrupts geon processing more than just deleting parts of lines

  13. Evidence from priming experiments

  14. Problem for RBC • Theory does not say how color, texture and small details are processed. These are often important to tell apart specific exemplars or similar objects. E.g.:

  15. Configural models of recognition • Individual instances are not stored; what is stored is an “exemplar” or representative element of a category • Recognition based on “distance” between perceived item and prototype prototype match no match “Face space”

  16. Prediction: Caricatures might be better recognized than original face average female face caricature of B “veridical” face from: Face Recognition by Humans: 20 Results all Computer Vision Researchers Should Know About. Sinha et al. (2005).

  17. Do these faces have anything in common? • no, nothing • same mouth • same nose • same eyes

  18. How about these ones? By disrupting holistic (configural) processing, it becomes easier to process the individual parts

  19. Face Inversion • Configural effects often disappear when stimulus is inverted

  20. Top-down and Context Effects in Object Recognition

  21. Slide from Rob Goldstone

  22. Context can often help in identification of an object Later identification of objects is more accurate when object is embedded in coherent context

  23. Context can alter the interpretation of an object

  24. Context Effects in Letter Perception The word superiority effect: discriminating between letters is easier in the context of a word than as letters alone or in the context of a nonword string. DEMO:http://psiexp.ss.uci.edu/research/teachingP140C/demos/demo_wordsuperiorityeffect.ppt (Reicher, 1969)

  25. Interactive Activation Model • Word superiority effect suggests that information at the word level might affect interpretation at the letter level • Interactive activation model: neural network model for how different information processing levels interact • Levels interact • bottom up: how letters combine to form words • top-down: how words affect detectability of letters

  26. Three levels: feature, letter, and word level Nodes represent features, letters and words; each has an activation level Connections between nodes are excitatory or inhibitory Activation flows from feature to letter to word level and back to letter level The Interactive Activation Model (McClelland & Rumelhart, 1981)

  27. Bottom-up: feature to word level Top-down: word to letter level Model predicts word superiority effect because of top-down processing The Interactive Activation Model (McClelland & Rumelhart, 1981)

  28. Predictions of the IA model – stimulus is “WORK” WORK WORD WEAR • At word level, evidence for “WORK” accumulates over time • Small initial increase for “WORD”

  29. Why does the letter “K” get activated? because of (partial) activation from feature level because of activation from word level back to feature level both a) and b) Predictions of the IA model – stimulus is “WORK” K R D

  30. Why does the letter “R” get partially activated? because of (partial) activation from feature level because of activation from word level back to feature level both a) and b) Predictions of the IA model – stimulus is “WORK” K R D

  31. For a demo of the IA model, see: http://www.itee.uq.edu.au/~cogs2010/cmc/chapters/LetterPerception/

  32. “Mind reading”

  33. Predicting What Somebody is Seeing (“mind reading”) bold response bold response Viewing a Bottle Viewing a Shoe If the brain response is different for different kinds of stimuli, can we predict what somebody is thinking of solely based on the brain’s response?

  34. Pattern Classification Method • Acquire brain data for different stimuli (e.g. bottles and shoes) • Train a classifier (such as the neural network on right) to discriminate between bottle voxel patterns and shoe voxel patterns • Test classifier on novel images bottle shoe Output layer (categories) Input Layer (voxels) (slide from Ken Norman)

  35. Haxby et al. (2001)can predict with 96% accuracy stimuli from 8 categories Faces Cats Scissors Chairs Houses Bottles Shoes Scrambled Pictures slides courtesy of Jim Haxby

  36. Reconstructing the Mental Image • If we can predict what somebody is looking at, can we also reconstruct what somebody might be looking at from just the brain’s response? Mathematical Model Reconstructed image Brain’s response Image

  37. Reconstructing simple patterns from fMRIMiyawaki et al. (2008) from: Miyawaki et al. (2008). Neuron, 60(5), pp. 915-929. movie at: http://psiexp.ss.uci.edu/research/teachingP140C/demos/mmc2.mpg

  38. Brain Computer Interfaces • ATR Laboratories in Japan developed a • robotic hand that can be controlled • using fMRI Rainer Goebel’s team had two patients play mental ping-pong in fMRI machines

More Related