On Measuring * the Ecological Validity of Local Figure-Ground Cues Charless Fowlkes, David Martin, Jitendra Malik Computer Science Division University.

Slides:



Advertisements
Similar presentations
Computer Vision Group UC Berkeley How should we combine high level and low level knowledge? Jitendra Malik UC Berkeley Recognition using regions is joint.
Advertisements

Recovering Human Body Configurations: Combining Segmentation and Recognition Greg Mori, Xiaofeng Ren, and Jitentendra Malik (UC Berkeley) Alexei A. Efros.
1 Perceptual Organization and Linear Algebra Charless Fowlkes Computer Science Dept. University of California at Berkeley.
Neurodynamics of figure-ground organization Dražen Domijan University of Rijeka, Rijeka, Croatia 8th Alps-Adria Psychology Conference.
Lecture 18 – Recognition 1. Visual Recognition 1)Contours 2)Objects 3)Faces 4)Scenes.
Qualifying Exam: Contour Grouping Vida Movahedi Supervisor: James Elder Supervisory Committee: Minas Spetsakis, Jeff Edmonds York University Summer 2009.
ADS lab NCKU1 Michael Maire, Pablo Arbelaez, Charless Fowlkes, and Jitendra Malik university of California, Berkeley – Berkeley university of California,
Gestalt Principles of Visual Perception
Computer Vision Group University of California Berkeley Ecological Statistics of Good Continuation: Multi-scale Markov Models for Contours Xiaofeng Ren.
1 Contours and Junctions in Natural Images Jitendra Malik University of California at Berkeley (with Jianbo Shi, Thomas Leung, Serge Belongie, Charless.
Sketch Tokens: A Learned Mid-level Representation for Contour and Object Detection CVPR2013 POSTER.
Unsupervised Learning of Categorical Segments in Image Collections *California Institute of Technology **Technion Marco Andreetto*, Lihi Zelnik-Manor**,
Computer Vision Group University of California Berkeley 1 Learning Scale-Invariant Contour Completion Xiaofeng Ren, Charless Fowlkes and Jitendra Malik.
Learning to Detect Natural Image Boundaries Using Local Brightness, Color, and Texture Cues David R. Martin Charless C. Fowlkes Jitendra Malik.
Understanding Gestalt Cues and Ecological Statistics using a Database of Human Segmented Images Charless Fowlkes, David Martin and Jitendra Malik Department.
Abstract We present a model of curvilinear grouping using piecewise linear representations of contours and a conditional random field to capture continuity.
Measuring the Ecological Statistics of Figure-Ground Charless Fowlkes, David Martin, Jitendra Malik.
1 Learning to Detect Natural Image Boundaries David Martin, Charless Fowlkes, Jitendra Malik Computer Science Division University of California at Berkeley.
CVR05 University of California Berkeley 1 Familiar Configuration Enables Figure/Ground Assignment in Natural Scenes Xiaofeng Ren, Charless Fowlkes, Jitendra.
Berkeley Vision GroupNIPS Vancouver Learning to Detect Natural Image Boundaries Using Local Brightness,
CVR05 University of California Berkeley 1 Cue Integration in Figure/Ground Labeling Xiaofeng Ren, Charless Fowlkes, Jitendra Malik.
Measuring the Ecological Statistics of Figure-Ground Charless Fowlkes, David Martin, Jitendra Malik.
A Database of Human Segmented Natural Images and Two Applications David Martin, Charless Fowlkes, Doron Tal, Jitendra Malik UC Berkeley
1 The Ecological Statistics of Grouping by Similarity Charless Fowlkes, David Martin, Jitendra Malik Computer Science Division University of California.
Computer Vision Group University of California Berkeley 1 Scale-Invariant Random Fields for Mid-level Vision Xiaofeng Ren, Charless Fowlkes and Jitendra.
Visual Grouping and Recognition David Martin UC Berkeley David Martin UC Berkeley.
Computational Vision Jitendra Malik University of California at Berkeley Jitendra Malik University of California at Berkeley.
1 Occlusions – the world is flat without them! : Learning-Based Methods in Vision A. Efros, CMU, Spring 2009.
1 How do ideas from perceptual organization relate to natural scenes?
1 Ecological Statistics and Perceptual Organization Charless Fowlkes work with David Martin and Jitendra Malik at University of California at Berkeley.
Computer Vision Group University of California Berkeley 1 Cue Integration in Figure/Ground Labeling Xiaofeng Ren, Charless Fowlkes and Jitendra Malik.
Cue Integration in Figure/Ground Labeling Xiaofeng Ren, Charless Fowlkes and Jitendra Malik, U.C. Berkeley We present a model of edge and region grouping.
Heather Dunlop : Advanced Perception January 25, 2006
Performance Evaluation of Grouping Algorithms Vida Movahedi Elder Lab - Centre for Vision Research York University Spring 2009.
1. An Overview of the Data Analysis and Probability Standard for School Mathematics? 2.
1 Contours and Junctions in Natural Images Jitendra Malik University of California at Berkeley (with Jianbo Shi, Thomas Leung, Serge Belongie, Charless.
Lecture 2 Sampling design Analysis of data. 1. Sampling design, - the what, the where, and the how.. It is never possible to compile a complete data set,
Visual Grouping and Recognition Jitendra Malik University of California at Berkeley Jitendra Malik University of California at Berkeley.
Chapter 5: Spatial Vision & Form Perception
1 Epidemiologic studies that are concerned with characterizing the amount and distribution of health and disease within a population. Descriptive Epidemiology.
Supervised Learning of Edges and Object Boundaries Piotr Dollár Zhuowen Tu Serge Belongie.
‘rules’ that we apply to visual information  to assist our organization and interpretation of the information in consistent meaningful ways.
Physics I Significant Figures. Measurement necessary for science “I often say that when you can measure what you are speaking about, and express it in.
Information: Perception and Representation Lecture #7 Part A.
Chapter 36 Image Formation.
CS 3300 FALL 2015 Software Metrics. Some Quotes When you can measure what you are speaking about and express it in numbers, you know something about it;
CHAPTER 4 – RESEARCH METHODS Psychology 110. How Do We Know What We Know? You can know something because a friend told you You can know something because.
Inductive Reasoning 1-2A What do you think are basic geometry figures?
Introduction to Measurement. According to Lord Kelvin “When you can measure what you are speaking about and express it in numbers, you know something.
Context-based vision system for place and object recognition Antonio Torralba Kevin Murphy Bill Freeman Mark Rubin Presented by David Lee Some slides borrowed.
CSCI 102: Introduction to Computational Modeling Chapter 1: The Modeling Process.
Constructs AKA... AKA... Latent variables Latent variables Unmeasured variables Unmeasured variables Factors Factors Unobserved variables Unobserved variables.
Category Independent Region Proposals Ian Endres and Derek Hoiem University of Illinois at Urbana-Champaign.
Fundamentals of Sensation and Perception RECOGNIZING VISUAL OBJECTS ERIK CHEVRIER NOVEMBER 23, 2015.
The Scientific Method. The scientific method is the only scientific way accepted to back up a theory or idea.
Computational Vision Jitendra Malik University of California, Berkeley.
In: Pattern Analysis and Machine Intelligence, IEEE Transactions on, Vol. 30, Nr. 1 (2008), p Group of Adjacent Contour Segments for Object Detection.
Modeling Perspective Effects in Photographic Composition Zihan Zhou, Siqiong He, Jia Li, and James Z. Wang The Pennsylvania State University.
9/30/ Cognitive Robotics1 Gestalt Perception Cognitive Robotics David S. Touretzky & Ethan Tira-Thompson Carnegie Mellon Spring 2006.
Gestalt Perception Cognitive Robotics David S. Touretzky &
The Invisible Surface that Glows
The User Lecture 2 DeSiaMore
Enhanced-alignment Measure for Binary Foreground Map Evaluation
Outline Perceptual organization, grouping, and segmentation
The Nature of Probability and Statistics
Perceiving and Recognizing Objects
Contours and Junctions in Natural Images
CSc4730/6730 Scientific Visualization
Artifacts of Adversarial Examples
Learning complex visual concepts
Presentation transcript:

On Measuring * the Ecological Validity of Local Figure-Ground Cues Charless Fowlkes, David Martin, Jitendra Malik Computer Science Division University of California at Berkeley * "When you can measure what you are speaking about and express it in numbers, you know something about it; but when you cannot measure it, when you cannot express it in numbers, your knowledge is of the meager and unsatisfactory kind." --Lord Kelvin

2 Cues to Figure-Ground Assignment Size Surroundedness Convexity Lower-Region Symmetry Parallelism Meaningfulness Photo by Wei-Chung Lee

3 Ecological Statistics of Figure-Ground Cues Hypothesis: Perceptual organization reflects the statistics of the natural world in which the visual system evolved. In the context of grouping, this has been explored by: –Brunswik/Kamiya 1953 : proximity of similars –Geisler et. al : good continuation –Martin/Fowlkes/Malik 2001 : proximity, similarity in color/texture In this work we measure, in a probabilistic sense, the power of size, convexity and lower-region in determining figure-ground assignment

4 1.Human observers assign figure-ground labels to every boundary in a collection of natural images. 2.The cues of size, convexity, and lower-region are measured locally at each boundary point. 3.The extent to which these local cues are able to predict the ground-truth labeling is quantified. Overview

5 Berkeley Segmentation Dataset 1000 images each segmented by 10 different subjects

6 Figure-Ground Labeling segmented images of natural scenes - boundaries labeled by at least 2 different human subjects - subjects agree on 88% of contours labeled

7 Size(p) = log(Area F / Area G ) Size and Surroundedness [Rubin 1921] G F p

8 Convexity(p) = log(Conv F / Conv G ) Convexity [Metzger 1953, Kanizsa and Gerbino 1976] Conv G = percentage of straight lines that lie completely within region G p G F

9 LowerRegion(p) = θ G Lower Region [Vecera, Vogel & Woodman 2002] θ p center of mass

10 sizeconvexitylower region -Sample 350,000 boundary points from 200 images -Intersect with circular window of chosen radius r -Compute size, convexity and lower-region cues and compare to ground truth labeling

11 Figural regions tend to be smaller mean is zero with p <

12 Figural regions tend to be convex mean is zero with p = (less at other radii)

13 Figural regions tend to lie below ground regions mean is 90 with p <

14 Power of cue depends on support of the analysis window.

15 Conclusion Figural regions are smaller, more convex and below ground regions in natural images