Human vision Jitendra Malik U.C. Berkeley. Visual Areas.

Slides:



Advertisements
Similar presentations
Chapter 4: The Visual Cortex and Beyond
Advertisements

What do we know about Primary Visual Cortex (V1)
Chapter 2.
Visual Sensation & Perception How do we see?. Structure of the eye.
Object recognition and scene “understanding”
What is vision Aristotle - vision is knowing what is where by looking.
HMAX Models Architecture Jim Mutch March 31, 2010.
Chapter 6 The Visual System
Neuron Neurons Purkinje cells from cerebellum, dendrites showing calcium concentration.
MENTAL REPRESENATIONS Neur 3680 Midterm I review.
Blue= rods Green = Cones Pathways from the Retina In the brain, retinal ganglion axons travel to… –the hypothalamus: control bodily rhythms.
1 Biological Neural Networks Example: The Visual System.
Introduction to Cognitive Science Lecture 2: Vision in Humans and Machines 1 Vision in Humans and Machines September 10, 2009.
Unrelated vs. Related Color Unrelated color: color perceived to belong to an area in isolation (CIE 17.4) Related color: color perceived to belong to.
The Human Visual System Short Overview. Terms: LGN, cortex, primary visual cortex, V1.
Front-end computations in human vision Jitendra Malik U.C. Berkeley References: DeValois & DeValois,Hubel, Palmer, Spillman &Werner, Wandell Jitendra Malik.
Levels in Computational Neuroscience Reasonably good understanding (for our purposes!) Poor understanding Poorer understanding Very poorer understanding.
Visual Sensation & Perception How do we see?. Structure of the eye.
Components of the visual system. The individual neuron.
ניורוביולוגיה ומדעי המח חלק 2 – מערכת הראייה Introduction to Neurobiology Part 2 – The Visual System Shaul Hochstein.
Human Sensing: The eye and visual processing Physiology and Function Martin Jagersand.
The Human Visual System Vision Class The main topics covered here were: photoreceptors and ganglion cells in the retina. The photoreceptors are.
Ch 31 Sensation & Perception Ch. 3: Vision © Takashi Yamauchi (Dept. of Psychology, Texas A&M University) Main topics –convergence –Inhibition, lateral.
Chapter 10 The Central Visual System. Introduction Neurons in the visual system –Neural processing results in perception Parallel pathway serving conscious.
The visual system Lecture 1: Structure of the eye
Computational Vision Jitendra Malik, UC Berkeley.
Copyright © 2007 Wolters Kluwer Health | Lippincott Williams & Wilkins Neuroscience: Exploring the Brain, 3e Chapter 10: The Central Visual System.
University Studies 15A: Consciousness I The Neurobiology of Vision.
1B50 – Percepts and Concepts Daniel J Hulme. Outline Cognitive Vision –Why do we want computers to see? –Why can’t computers see? –Introducing percepts.
Convolutional Neural Networks for Image Processing with Applications in Mobile Robotics By, Sruthi Moola.
Physiology of Vision: a swift overview Pixels to Percepts A. Efros, CMU, Spring 2011 Some figures from Steve Palmer.
Neural Information in the Visual System By Paul Ruvolo Bryn Mawr College Fall 2012.
Explorations in Neural Networks Tianhui Cai Period 3.
Low Level Visual Processing. Information Maximization in the Retina Hypothesis: ganglion cells try to transmit as much information as possible about the.
1 Computational Vision CSCI 363, Fall 2012 Lecture 3 Neurons Central Visual Pathways See Reading Assignment on "Assignments page"
THE VISUAL SYSTEM: EYE TO CORTEX Outline 1. The Eyes a. Structure b. Accommodation c. Binocular Disparity 2. The Retina a. Structure b. Completion c. Cone.
Slide 1 Neuroscience: Exploring the Brain, 3rd Ed, Bear, Connors, and Paradiso Copyright © 2007 Lippincott Williams & Wilkins Bear: Neuroscience: Exploring.
Occipital Lobe Videos: –Brain modules 8,9,10, 11 –Consciousness- Blindsight.
15 1 Grossberg Network Biological Motivation: Vision Eyeball and Retina.
Ch 31 Sensation & Perception Ch. 3: Vision © Takashi Yamauchi (Dept. of Psychology, Texas A&M University) Main topics –convergence –Inhibition, lateral.
Visual Recognition: The Big Picture Jitendra Malik University of California at Berkeley.
Why is this hard to read. Unrelated vs. Related Color Unrelated color: color perceived to belong to an area in isolation (CIE 17.4) Related color: color.
The primate visual systemHelmuth Radrich, The primate visual system 1.Structure of the eye 2.Neural responses to light 3.Brightness perception.
Visual Neuroscience Visual pathways Retina Photoreceptors Rods Cones Spacing and density ON and OFF pathways Ganglion cells Retinal projections SCN Pretectum.
Computer Vision Group University of California Berkeley On Visual Recognition Jitendra Malik UC Berkeley.
1B50 – Visual System Daniel J Hulme. Errata Phylogenetic – genetic history of the species Ontogenetic – experience of the individual It was Kepler who.
Keith Clements Introduction to Neuroscience
Sensory Receptor Cells of the Eye Sensory Neural Systems 22 January 2008 Rachel L. Leon.
Understanding Psychophysics: Spatial Frequency & Contrast
The Human Visual System Background on Vision Human vision – the best system around Deep network models.
1 Computational Vision CSCI 363, Fall 2012 Lecture 12 Review for Exam 1.
1 Perception and VR MONT 104S, Spring 2008 Lecture 3 Central Visual Pathways.
Biological Image Processing Physiology and Function C428/615 Martin Jagersand With illustrations from: Tutis Vilis Talia Konkle and others as cited.
Processing visual information - pathways
Psychology 304: Brain and Behaviour Lecture 28
Visual Computation and Learning Lab
Non-linear classifiers Neural networks
Computer Vision James Hays
Early Processing in Biological Vision
Smoothing the intensities
Physiology of Photoreceptors Vertebrate photoreceptors hyperpolarize and produce graded potentials Photoreceptors use glutamate as transmitter.
Spatial Vision (continued)
Grossberg Network.
CSC 578 Neural Networks and Deep Learning
Orientation tuning: strongest response to one orientation
Neural Networks and Neuroscience-Inspired Computer Vision
Human vision: physical apparatus
From Functional Architecture to Functional Connectomics
Week 14: Neurobiology of Vision Part 2
Edge Detection via Lateral Inhibition
Presentation transcript:

Human vision Jitendra Malik U.C. Berkeley

Visual Areas

Mathematical Abstraction

The photoreceptor mosaic: rods and cones are the eye’s pixels

Cones and Rods After dark adaptation, a single rod can respond to a single photon

The three cone types have different spectral sensitivity functions

ON and OFF cells in retinal ganglia

Figure 6.16 Receptive fields The receptive field of a receptor is simply the area of the visual field from which light strikes that receptor. For any other cell in the visual system, the receptive field is determined by which receptors connect to the cell in question. Receptive Fields

The receptive field of a retinal ganglion cell can be modeled as a “Difference of Gaussians”

Convolving an image with a filter

Each output unit gets the weighted sum of image pixels

Each output unit gets the weighted sum of input units We can think of this weighting function as the receptive field of the output unit

Visual Processing Areas

Macaque Visual Areas

Orientation Selectivity in V1

Receptive fields of simple cells (discovered by Hubel & Wiesel)

The 1D Gaussian and its derivatives

Oriented Gaussian Derivatives in 2D

Oriented Gaussian First and Second Derivatives

Modeling simple cells Elongated directional Gaussian derivatives Gabor filters could be used instead Multiple orientations, scales

Receptive fields of complex cells

Orientation Energy Can be used to model complex cells, as this is insensitive to phase Multiple scales

Hypercolumns in visual cortex

Macaque Visual Areas

Rolls et al (2000) model of ventral stream

Object Detection can be very fast On a task of judging animal vs no animal, humans can make mostly correct saccades in 150 ms (Kirchner & Thorpe, 2006) – Comparable to synaptic delay in the retina, LGN, V1, V2, V4, IT pathway. – Doesn’t rule out feed back but shows feed forward only is very powerful Detection and categorization are practically simultaneous (Grill-Spector & Kanwisher, 2005)

Feed-forward model of the ventral stream

Intrinsic & Extrinsic Connectivity of the Ventral Stream (Kravitz, Saleem, Baker, Ungerleinder, Mishkin, TICS, 2013)

What can we learn? Neurons show increasing specificity higher in the visual pathway V1 simple and complex cells are orientation-tuned Convolution with a linear kernel followed by simple non-linearities is a good model for computation in retina, LGN and V1, but beyond that we do not have satisfactory computational models Good designs of visual systems are likely to be hierarchical and “mostly” feedforward

Neuroscience & Computer Vision Features Hubel & Wiesel’s finding of orientation selective simple and complex cells in V1 inspired features such as SIFT and HOG. A feed-forward view of processing in the ventral stream with layers of simple and complex cells led to the neocognitron and subsequently convolutional networks. We now know that the ventral stream is much more complicated with bidirectional as well as feedback connections. So far this has not been exploited much in computer vision

Convolutional Neural Networks (LeCun et al)

Training multi-layer networks