slide1 l.
Download
Skip this Video
Loading SlideShow in 5 Seconds..
Pattern Recognition Vidya Manian Dept. of Electrical and Computer Engineering University of Puerto Rico manian@ece.uprm. PowerPoint Presentation
Download Presentation
Pattern Recognition Vidya Manian Dept. of Electrical and Computer Engineering University of Puerto Rico manian@ece.uprm.

Loading in 2 Seconds...

play fullscreen
1 / 31

Pattern Recognition Vidya Manian Dept. of Electrical and Computer Engineering University of Puerto Rico manian@ece.uprm. - PowerPoint PPT Presentation


  • 133 Views
  • Uploaded on

Pattern Recognition Vidya Manian Dept. of Electrical and Computer Engineering University of Puerto Rico manian@ece.uprm.edu INEL 5046, Spring 2007. Human Perception.

loader
I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
capcha
Download Presentation

PowerPoint Slideshow about 'Pattern Recognition Vidya Manian Dept. of Electrical and Computer Engineering University of Puerto Rico manian@ece.uprm.' - ardelle


Download Now An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript
slide1

Pattern RecognitionVidya ManianDept. of Electrical and Computer EngineeringUniversity of Puerto Ricomanian@ece.uprm.eduINEL 5046, Spring 2007

human perception
Human Perception
  • Humans have developed highly sophisticated skills for sensing their environment and taking actions according to what they observe, e.g.,
    • Recognizing a face
    • Understanding spoken words
    • Reading handwriting
    • Distinguishing fresh food from its smell
  • We would like to give similar capabilities to machines
what is a pattern
What is a Pattern?
  • “A pattern is the opposite of a chaos; it is an entity vaguely defined, that could be given a name.” (Watanabe)
what is pattern recognition
What is Pattern Recognition?
  • A pattern is an entity, vaguely defined, that could be given a name, e.g.,

> Fingerprint image >speech signal

> handwritten word >DNA sequence

>human face >…

  • Pattern recognition is the study of how machines can
    • Observe the environment
    • Learn to distinguish patterns of interest
    • Make sound and reasonable decisions about the categories of the patterns
recognition

Category “A”

Category “B”

Classification

Recognition
  • Identification of a pattern as a member of a category we already know, or we are familiar with
    • Classification (known categories)
    • Clustering (creation of new categories)

Clustering

pattern recognition
Pattern Recognition
  • Given an input pattern, make a decision about the “category” or “class” of the pattern
  • Pattern recognition is a very broad subject with many applications
  • In this course we will study a variety of techniques to solve P.R. problems and discuss their relative strengths and weaknesses
pattern class
Pattern Class
  • A collection of “similar” (not necessarily identical) objects
  • A class is defined by class samples (paradigms, exemplars, prototypes)
  • Inter-class variability
  • Intra-class variability
pattern class model
Pattern Class Model
  • Different descriptions, which are typically mathematical in form for each class/population
  • Given a pattern, choose the best-fitting model for it and then assign it to class associated with the model
i ntra class and inter class variability
Intra-class and Inter-class Variability

The letter “T” in different typefaces

Same face under different expression, pose….

inter class similarity
Inter-class Similarity

Characters that look similar

Identical twins

pattern recognition11
Pattern Recognition
  • Having been shown a few positive examples (and perhaps a few negative examples) of a pattern class, the system “learns” to tell whether or not a new object belongs in this class (Watanabe)
  • COGNITION = Formation of new classes

RECOGNITION = known classes

pattern recognition applications
Pattern Recognition Applications
  • Speech recognition
  • Detection and diagnosis of disease
  • Remote sensing (terrain classification, tanks detection)
  • Character recognition
  • Identification and counting of cells
  • Fingerprint identification
  • Web search
  • Inspection (PC boards, IC masks, textiles)
fish classification
Fish Classification

Preprocessing will involve image enhancement, separating touching/occluding fishes and finding the boundary of the fish

length feature
Length Feature

Training (design or learning) Samples

lightness feature
Lightness Feature

Overlap in the histograms is small compared to length feature

two dimensional feature space representation
Two-dimensional Feature Space (Representation)

Cost of misclassification?

Two features together are better than individual features

complex decision boundary
Complex Decision Boundary

Issue of generalization

boundary with good generalization
Boundary With Good Generalization

Simplify the decision boundary!

models for pattern recognition
Models for Pattern Recognition
  • Template matching
  • Statistical (geometric)
  • Syntactic (structural)
  • Artificial neural network (biologically motivated?)
  • Hybrid approach
statistical pattern recognition
Statistical Pattern Recognition

pattern

Preprocessing

Feature extraction

Classification

Recognition

Training

Feature selection

Learning

Preprocessing

Patterns

+

Class labels

pattern representation using features

x2

x2

x1

x1

Pattern Representation using features
  • Each pattern is represented as a point in the d-dimensional feature space
  • Features are domain-specific and be invariant to translation, rotation and scale
  • Good representation  small intraclass variation, large interclass separation, simple decision rule
  • No redundant features, too many features and less samples-curse of dimensionality (Huges phenomena)
artificial neural networks
Artificial Neural Networks

Massive parallelism is essential for complex pattern recognition tasks (e.g., speech and image recognition)

Human take only a few hundred ms for most cognitive tasks; suggests parallel computation

Biological networks attempt to achieve good performance via dense interconnection of simple computational elements (neurons)

Number of neurons  1010 – 1012

Number of interconnections/neuron  103 – 104

Total number of interconnections  1014

artificial neural networks24
Artificial Neural Networks

Nodes in neural networks are nonlinear, typically analog

where is internal threshold or offset

x1

w1

x2

Y (output)

xd

wd

multilayer perceptron
Multilayer Perceptron
  • Feed-forward nets with one or more layers (hidden) between the input and output nodes
  • A three-layer net can generate arbitrary complex decision regions
  • These nets can be trained by back-propagation training algorithm

.

.

.

.

.

.

.

.

.

c outputs

d inputs

First hidden layer

NH1 input units

Second hidden layer

NH2 input units

statistical pattern recognition26
Statistical Pattern Recognition
  • Patterns represented in a feature space
  • Statistical model for pattern generation in feature space
  • Given training patterns from each class, goal is to partition the feature space.
image analysis and segmentation classification using texture features
Image Analysis and Segmentation (classification) using texture features

Classified using Logical operators

Aerial photograph of Anasco,PR

classification of color images using texture features
Classification of color images using texture features

Texture mosaic of 3 colored tiles

and canvas texture.

Classified image

classification of landsat image of san juan area pr using gabor texture features
Classification of Landsat image of San Juan area, PR using Gabor texture features

Classified image using R,G,B

Landsat image

7 bands (R, G, B, IR and Thermal)