CS332 Visual Processing - Computer Science

CS 332 Visual Processing in Computer
and Biological Vision Systems
Hodgepodge
CS332 Visual Processing
Department of Computer Science
Wellesley College
Artificial Neural Nets
Use feedforward
network to compute
output from inputs
Use back-propagation
algorithm to learn
weights from training
data (correct
input/output pairs)
1-2
Rowley, Baluja & Kanade:
face detection with neural nets
1-3
Analysis of color
Edwin Land’s
color mondrian
experiments
1-4
Land’s Retinex Theory of Color
L(x,y,) = I(x,y,) * R(x,y,)
L(x,y,): luminance
I(x,y,): illuminant
R(x,y,): surface
reflectance
Goal: recover surface
reflectance (color)
1-5
Measuring color by retinal cones
1-6
Principal components analysis
 Method for reducing the dimensionality of a
high-dimensional data set, allowing a more compact
representation of each element of the set
 Takes advantage of redundancy within a data set
 Expresses original data samples as a linear
combination of a set of components that capture
as much as possible of the data’s variance
 Mathematically, the principle components are the
eigenvectors of the covariance matrix of the
original data set
1-7
Troje: Using PCA to represent human gait
 Obtain motion capture data
from many human walkers
 Use PCA to construct a small
number of “eigenpostures”
 Express each posture in the
original motion sequence as a
weighted sum of eigenpostures
Troje walker demo
 Use pattern of changing
coefficients over time to recognize
movements, e.g. classify gender
1-8
Using eigenpostures to represent gaits
Each posture consists of (x,y,z)
coordinates of 15 locations
Each sequence consists of about 1400
postures (12 secs, 20 steps)
PCA analysis: first component captures
84% of variance in postures, first four
components capture 98% of variance
P = P0 + ΣciPi
P0: average posture
Pi: i-th principal component, i = 1..4
(four eigenpostures)
Ci: coefficient of i-th eigenposture
Pattern of coefficients over time is
approximately sinusoidal – demo varies
properties of sinusoids
1-9