Page 147 - Microsoft Word - B.Tech. Course Structure (R20) WITH 163 CREDITS

JNTUA College of Engineering (Autonomous), Ananthapuramu
Department of Computer Science & Engineering
Pattern Recognition
Professional Elective Course–III
Course Code: Semester VII(R20) L T P C : 3 0 0 3
Course Objectives:
• To understandthePRimportance in various real time applications
• To understand the basic model and fundamental steps of PR system
• To understand the use of different classifiers/algorithms/tech
• To learn the different methods for combining classifiers.
• To provide an introduction to various clustering algorithms
Course Outcomes:
• Explain the paradigms for PR problems
• Classify the patterns using NN, Bayes, HMM, Decision trees and SVM classifiers
• Apply ensemble of classifiers for certain PR problems
• Differentiate between supervised and unsupervised classifiers.
• Design an application: Handwritten Digit Recognition

UNIT – I: IntroductiontoPatternRecognition

IntroductiontoPatternRecognition:DataSetsforPatternRecognition,DifferentParadigmsforPattern
Recognition,
PatternRepresentation:DataStructuresforPatternRepresentation,RepresentationofClusters,Proximity
Measures,SizeofPatterns,AbstractionsoftheDataSet,Feature,FeatureSelection,
EvaluationofClassifiers,EvaluationofClustering

UNIT – II: Classifier
Nearest Neighbour Based Classifiers: Nearest Neighbour Algorithm, Variants of the NNAlgorithm, Use
of the Nearest Neighbour Algorithm for Transaction Databases, EfficientAlgorithms,DataReduction,
PrototypeSelection,
Bayes Classifier: Bayes Theorem, Minimum error rate classifier, Estimation of
Probabilities,ComparisonwiththeNNC,NaiveBayesClassifier,BayesianBeliefNetwork.

UNIT – III: Pattern Recognition Models
HiddenMarkovModels:MarkovModelsforClassification,HiddenMarkovModels,ClassificationUsingHMM
s, ClassificationofTest Patterns.
DecisionTrees:Introduction,DecisionTreesforPatternClassification,ConstructionofDecision Trees, Splitting
at the Nodes, Over fitting and Pruning, Example of Decision TreeInduction.

UNIT – IV: SVM & Combination of Classifiers
SupportVectorMachines:Introduction,LinearDiscriminantFunctions,LearningtheLinear Discriminant
Function, Neural Networks, SVM for Classification, Linearly SeparableCase,Non-linearlySeparableCase.
CombinationofClassifiers:Introduction,MethodsforConstructingEnsemblesofClassifiers,Methodsfor
CombiningClassifiers,EvaluationofClassifiers,EvaluationofClustering.

UNIT – V: Clustering
Clustering: Clustering and its Importance, Hierarchical Algorithms, Partitional Clustering,ClusteringLarge

Mdv
Mdv