Object Recognition Computer Vision CSE399b Spring 2007, Jianbo Shi.

Slides:



Advertisements
Similar presentations
Human Neuropsychology,
Advertisements

DISORDERS OF AUDITORY PROCESSING 1 DAY 20 – OCT 14, 2013 Brain & Language LING NSCI Harry Howard Tulane University.
Agenda Introduction Bag-of-words models Visual words with spatial location Part-based models Discriminative methods Segmentation and recognition Recognition-based.
(2) Face Recognition These notes are the second part of a two-part lecture roughly corresponding to (1) object recognition and (2) face recognition We'll.
Chapter 44 Visual Perception of Objects Copyright © 2014 Elsevier Inc. All rights reserved.
Are faces special?. Brain damage can produce problems in face recognition - even own reflection (Bodamer, 1947) Prosopagnosia usually results from localized.
Cortical Structure and Function
Perception Chapter 4.
Announcements Final Exam May 13th, 8 am (not my idea).
Computer Vision - A Modern Approach Set: Model-based Vision Slides by D.A. Forsyth Recognition by Hypothesize and Test General idea –Hypothesize object.
Announcement MIDTERM When: 2/ PM Where: 128 Dennison.
Evidence from Lesions: Agnosia Lesions (especially in the left hemisphere) of the inferior temporal cortex lead to disorders of memory for people and things.
Copyright © 2006 by Allyn and Bacon Chapter 7 Mechanisms of Perception, Conscious Awareness, and Attention How You Know the World This multimedia product.
Lecture 6 Image Segmentation
Dorsal and Ventral Pathways
I. Face Perception II. Visual Imagery. Is Face Recognition Special? Arguments have been made for both functional and neuroanatomical specialization for.
Visual Cognition II Object Perception. Theories of Object Recognition Template matching models Feature matching Models Recognition-by-components Configural.
WHAT, WHERE, & HOW SYSTEMS AGNOSIAS!. What, Where, & How Systems.
A Study of Approaches for Object Recognition
Vision. Vision 1: Filling-in, Color, Motion, Form Visual Paths Filling-In –Perceptual Completion –Conceptual Completion Color Motion Form –Agnosia –Prosopagnosia.
Cognitive Processes PSY 334 Chapter 2 – Perception June 30, 2003.
Deficits of vision What do visual deficits tell us about the structure of the visual system?
Automatic Image Alignment (feature-based) : Computational Photography Alexei Efros, CMU, Fall 2005 with a lot of slides stolen from Steve Seitz and.
Visual Cognition II Object Perception. Theories of Object Recognition Template matching models Feature matching Models Recognition-by-components Configural.
Stepan Obdrzalek Jirı Matas
Texture Reading: Chapter 9 (skip 9.4) Key issue: How do we represent texture? Topics: –Texture segmentation –Texture-based matching –Texture synthesis.
Object Recognition Using Geometric Hashing
Computational Vision Jitendra Malik University of California at Berkeley Jitendra Malik University of California at Berkeley.
CS292 Computational Vision and Language Visual Features - Colour and Texture.
PY202 Overview. Meta issue How do we internalise the world to enable recognition judgements to be made, visual thinking, and actions to be executed.
Recognition of object by finding correspondences between features of a model and an image. Alignment repeatedly hypothesize correspondences between minimal.
Dorsal and Ventral Pathways and What They Do. Dorsal and Ventral Pathways visual information arrives at V1 via the retinostriate pathway it is already.
Beyond the Striate Cortex. Extrastriate Pathways  Parallel processing of visual information from the striate cortex.  Three pathways: Color processing.
Cognitive Processes PSY 334 Chapter 2 – Perception.
M.S.: a case of autobiographical amnesia and visual memory loss (D.L Greenberg, M.J. Eacott, D. Brechin, and D.C. Rubin) By Christina Schulte.
The Brain.
Final Exam Review CS485/685 Computer Vision Prof. Bebis.
Perception and the Medial Temporal Lobe: Evaluating the Current Evidence Wendy Suzuki.
Object Recognition -Segregation of function -Visual hierarchy -What and where (ventral and dorsal streams) -Single cell coding and ensemble coding -Distributed.
Biases: An Example Non-accidental properties: Properties that appear in an image that are very unlikely to have been produced by chance, and therefore.
Perception Introduction Pattern Recognition Image Formation
September 23, 2014Computer Vision Lecture 5: Binary Image Processing 1 Binary Images Binary images are grayscale images with only two possible levels of.
Chapter 4: Object Recognition What do various disorders of shape recognition tell us about object recognition? What do various disorders of shape recognition.
MSRI workshop, January 2005 Object Recognition Collected databases of objects on uniform background (no occlusions, no clutter) Mostly focus on viewpoint.
Vision. 2 Brodmann Original Calcarine 17 Collateral Sulcus Fusiform Gyrus 18.
Announcement MIDTERM When: 2/ PM Where: 182 Dennison.
Agnosia and Perceptual Disturbances March 27, 2006.
Vision Overview  Like all AI: in its infancy  Many methods which work well in specific applications  No universal solution  Classic problem: Recognition.
Fundamentals of Sensation and Perception RECOGNIZING VISUAL OBJECTS ERIK CHEVRIER NOVEMBER 23, 2015.
Computer Vision Set: Object Recognition Slides by C.F. Olson 1 Object Recognition.
Visual Agnosias Specification: Theories of perceptual organisation
Part 4: combined segmentation and recognition Li Fei-Fei.
776 Computer Vision Jan-Michael Frahm Spring 2012.
Review session today after class
Image features and properties. Image content representation The simplest representation of an image pattern is to list image pixels, one after the other.
Chapter 4: Cortical Organization
Finding Clusters within a Class to Improve Classification Accuracy Literature Survey Yong Jae Lee 3/6/08.
Agnosia and Perceptual Disturbances March 17, 2008.
Processing visual information for Computer Vision
Blindsight Patients with scotomas could move eyes to the location of a light flash (Poppel et al., 1973). Case D.B. (Larry Weizkrantz) hemianopic with.
COGS 172 VISION CONTINUED Visual form agnosia
Cognitive Processes PSY 334
Perceptual Disorders Agnosias.
Paper Presentation: Shape and Matching
Perceiving and Recognizing Objects
Prosopagnosia.
Brief Review of Recognition + Context
On Symmetry, Illusory Contours and Visual Perception
Cognitive Processes PSY 334
Introduction to Perception: Visual Perception
Presentation transcript:

Object Recognition Computer Vision CSE399b Spring 2007, Jianbo Shi

Human vision: recognition Slides taken from Bart Rypma

“ What & Where” Visual Pathways Established with electophysiology, lesion, neuropsychology and neuroimaging data

Monkey Lesion Data Two types of Delayed Response Task Monkeys trained to criterion on one of these tasks Then task was reversed After learning, either temporal or parietal lobe lesioned Landmark Discrimination Task Object Discrimination Task

Effects of Lesion on Landmark Task Unoperated monkeys show no impairment Temporal-lobe lesion monkeys show minimal impairment Parietal-lobe lesion monkeys show much impairment

Effects of Lesion on Object Task Temporal-lobe lesion monkeys show much impairment Parietal-lobe lesion monkeys show minimal impairment

Monkey Lesion Data Subsequent lesion work supports the “what- where” distinction Object discrimination: Ventral lesion deficits restricted to visual modality Posterior/Anterior Ventral Lobe distinction: –Posterior: Visual discrimination –Anterior: Visual memory

The What-Where Distinction: Human Neuroimaging Data indicate evidence for what-where distinction Object task: Same objects? Spatial Task” Same locations?

Human Neuropsychological Data Agnosia Term coined by Sigmund Freud From the Greek word for “lack of knowledge” The inability to recognize objects when using a given sense, even though that sense is basically intact (Nolte, 1999)

Agnosia Usually involves damage to the occipito-parietal pathway

Patient GS Sensory abilities intact Language normal Unable to name objects

Agnosia Two Types Apperceptive –Object recognition failure due to perceptual processing Associative –Perceptual processing intact but subject cannot use information to recognize objects

Agnosia Depends on the availability of the object representation to consciousness Apperceptive Associative

Apperceptive Agnosias (also known as visual space agnosias) refer to a condition in which a person fails to recognize objects due to a functional impairment of the occipito-temporal vision areas of the brain. Other elementary visual functions such as acuity, colour vision, and brightness discrimination are still intact. Apperceptive agnosics are unable to distinguish visual shapes and so have trouble recognizing, copying, or discriminating between different visual stimuli. When patients are able to identify objects, they do so based on inferences using colour, size, texture and/or reflective cues to piece it together. For example, in the image below, an apperceptive patient may not be able to distinguish a poker chip from a scrabble tile despite their clear difference in shape and surface features.

This would be problem for apperceptive agnosia patient: They also have trouble with object constancy by view changes Right hemisphere lesions

Associative Agnosias are also known as visual object agnosias. Although they can present with a variety of symptoms, the main impairment is failure to recognize visually presented objects despite having intact perception of that object. A patient with an associative agnosia may be able to replicate a drawing of the object but still fail to recognize it. Errors in misidentifying an object as one that looks similar are common. Three specific criteria are associated with a diagnosis of associative agnosia (Farah,1990): 1) Difficulty recognizing a variety of visually presented objects (e.g., naming or grouping objects together according to their semantic categories). 2) Normal recognition of objects from a verbal description of it or when using a sense other than vision such as touch, smell, or taste. 3) Elementary visual perception intact sufficient to copy an object, as exemplified in original and copied picture below. Overall, this loss can be thought of as "recognition without meaning".

Prosopagnosia Specific inability to recognize faces Are faces and other objects in the world represented in fundamentally different ways in memory? Does face-memory depend on fundamentally different brain systems?

Are Faces Special? Subjects presented with a face and asked to represent a face-part Subjects presented with a house and asked to represent a house-part

Are Faces Special? Houses represented in parts Faces represented as wholes

Are Faces Special? Objects represented in parts and holistically Faces represented holistically

Object Recognition, Computer Vision Three distinct Approaches: 1)Alignment, prototype, 2)Part-based classification, 3)Invariance, geometrical & photometrical, hashing

Hypothesis-Test: Alignment Method

Recognition by Hypothesize and Test General idea –Hypothesize object identity and pose –Render object in camera –Compare to image Issues –where do the hypotheses come from? –How do we compare to image (verification)?

Step 1: correspondence

What are the features? They have to project like points –Lines –Conics –Other fitted curves –Regions (particularly the center of a region, etc.)

Step 2: Shape deformation and matching

Pose consistency Strategy: –Generate hypotheses using small numbers of correspondences (e.g. triples of points for a calibrated perspective camera, etc., etc.) –Backproject and verify Appropriate groups are “frame groups”

Figure from “Object recognition using alignment,” D.P. Huttenlocher and S. Ullman, Proc. Int. Conf. Computer Vision, 1986, copyright IEEE, 1986

Models Body Recognition G. Mori, X. Ren, A. Efros, and J. Malik, Recovering Human Body Configurations: Combining Segmentation and Recognition, IEEE Computer Vision and Pattern Recognition, 2004.

Example 1: View-point variations, many examples are needed Problem with Alignment algorithm: T. Sebastian

Example 2: Partial occlusion T. Sebastian

Part-based Object Recognition

Binford ‘78

Shocks (or medial axis or skeleton) are locus of centers of maximal circles that are bitangent to shape boundary Shape boundary Shocks Computing part-decomposition T. Sebastian

Complexity-increasing shape deformation paths are not optimal Represent a deformation path by a pair of simplifying deformation paths from A, B to a simpler shape C T. Sebastian

Shock graph edit operation transforms a shape to adjacent transition shape T. Sebastian

Edit-distance is defined as the sum of the cost of edits in optimal edit sequence T. Sebastian

Shock graphs represents object parts and part hierarchy Edit-distance is robust in presence of part-based changes T. Sebastian

Invariance + hashing

Figure from “Efficient model library access by projectively invariant indexing functions,” by C.A. Rothwell et al., Proc. Computer Vision and Pattern Recognition, 1992, copyright 1992, IEEE

Invariant Local Features Image content is transformed into local feature coordinates that are invariant to translation, rotation, scale, and other imaging parameters SIFT Features David Lowe