Title: Object Recognition using Boosted Discriminants Shyjan Mahamud, Martial Hebert, and Jianbo Shi
1Object Recognition using Boosted Discriminants
Shyjan Mahamud, Martial Hebert, and Jianbo Shi
- Presented by Chang Jia
- As for Pattern Recognition
- Instructor Prof. George Bebis
2Outline
- Introduction
- Review of basic concepts
- Object discrimination method
- The Loss Function
- Boosting Discriminants
- Learning an Efficient Code
- Experimental results
- Conclusions and future work
3Object Recognition
- Recognize object class/ Identify individual
object in given images - Face detection, recognizing animals, cars, etc.
- Possible for both instances or object classes (
Mona Lisa vs. faces or Beetle vs. cars)
4Object Recognition
- The hard part the same object can look
incredibly different in different images due to
differences in view points - A robust recognizer must be tolerant to changes
in pose, expression, illumination, and occlusion
etc.
5COIL Object Database
6Code Space for Objects
7Boosting Algorithm
- Boosting - is an algorithm for constructing a
strong classifier out of a linear combination - of simple weak classifiers It
provides a method of choosing the weak
classifiers and setting the weights
8Example combination of linear classifiers
9Correlation Function
- Distance Measure in code space
- Related to the Hamming distance when the weight
all set to 1 - Given an input image the class label
corresponding to the training image that has the
highest correlation with the input image is
reported.
10Proposed Method
- Idea
- Various candidate discriminants are constructed
by optimizing a pair-wise formulation of a
generalization of the Fisher criteria. - The candidate discriminant that reduces the total
loss the most is chosen. - The discriminants chosen so far are weighted and
combined to give the final correlation function
to be used at run-time.
11The Loss Function
- The exponential loss function
- The logistic cost function
- To simplify the presentation, use the first one
12Boosting Discriminants
- Goal Learning a good code. It requires finding
good discriminants hk and the associated weights - Assume that we are given a continuous feature
space. - For example, the pixel intensities in a localized
m x m window around a given location in an input
image lies in the continuous feature space R. - We would like to find a discriminant in the
feature space that satisfies some specific
criteria.
13Finding Good Discriminants
- Criteria for good discriminants
- focus on pairs of training images that have been
difficult to classify so far (high )
- pairs of training images from the same object
class (i.e., yij 1) should be put in the same
partition induced by the discriminant, while
pairs of training images from different object
classes (i.e., yij -1) should be put in
different partitions
- the training images are partitioned into two
well- separate groups, each of which is tightly
clustered
14Discriminant Function
Between-classes scatter
Fisher Linear Discriminant
Within-classes scatter
Distance Function (a Kernel)
Indicator variables
Final Fisher Discriminant Function
15Iterative Optimization
- Maximizing J keeping l fixed solve for s in
continuous interval -1, 1 instead of binary
values -1, 1 - Maximizing J keeping s fixed return a value in
-1, 1
16Pseudo-code for finding optimal discriminants
- Alternate between maximizing J w.r.t. s and l by
solving for the corresponding eigenvector
problems, until convergence.
17Illustration on a synthetic example in a
continuous 2D feature space
18Choosing Threshold
- Finding the optimal threshold ? is a one
dimensional problem along the discriminant
hyperplane l - Use a simple brute-force search
- The optimal value for ? is that which minimizes
the total loss - Determine ? as follows sort the projections onto
the optimal l of all the vis, find the total
loss for each value of that are mid-points (for
robustness at run-time) between successive sorted
projections, and choose the that gives the
minimum.
19Learning an Efficient Code
- Composing Discriminants
- Compose discriminants in a tree Tk to be more
powerful in practice - Partition function
- Corresponding loss function
if Tk maps both images xi and xj to the same
partition (i.e. same leaf node of Tk)
if Tk maps both images xi and xj to the same
partition (i.e. same leaf node of Tk)
20Composing Discriminants
- Composing simple discriminants into a tree of
discriminants.
21Optimizing Parameter
- Optimizing
- Smoothing in practice
- due to limited training data the optimal estimate
can be large in value - Introduce
W is the total loss of all pairs of training
examples that were correctly classified, while W-
is the total loss of all incorrectly classified
pairs by the kth discriminant.
22Overall Scheme
23Experimental Data
- FERET database
- Training Data
- Pairs of frontal images of 41 individuals
- Test Data
- Also pairs of frontal images of the same
individuals but taken around a month apart from
the training images with differences in hair,
lighting and expressions. - Faces are rigidly aligned
24Results
Used the prominent regions around the eyes, nose
and mouth as features
25Results
- Use eigenspace based method
- Both training and testing data were projected
onto the first 50 PCA components - a search for the nearest training image for each
testing image was performed - The resulting recognition rate was 92.6.
- Use presented method
- After training, we classified a test image by
finding the training image that was most
correlated with the test image using the
correlation function output. In other words, we
found the nearest neighbor in code-space. - The resulting recognition rate was 95.2.
26Results
- Parameters to be set
- total number of discriminants ( set as twice the
number of discriminants that gives a training
error of 0) - a regularization constant of ? 1 was used to
smooth the weights - Time
- The training time for our approach was around 6
hours, while the run-time was around 2 seconds.
27Conclusions and Future Work
- Presented an approach to learning good
discriminators that can be thought of as that of
learning good codes. - Good discriminators are determined sequentially
that focus on the currently hard to classify
training images. - Such discriminators are weighted and combined in
an energy minimization scheme - Can explore feature spaces in which distance
measures can be non-linear by using more powerful
non-linear kernels
28Thank you!