Module Catalogues, Xi'an Jiaotong-Liverpool University   
 
Module Code: EEE344
Module Title: Pattern Recognition in Computer Vision
Module Level: Level 3
Module Credits: 5.00
Academic Year: 2019/20
Semester: SEM2
Originating Department: Electrical and Electronic Engineering
Pre-requisites: N/A
   
Aims
To introduce the basic concept of pattern recognition in computer vision.

To develop the necessary skills to carry out and report simple experiments of pattern recognition in computer vision
Learning outcomes 
Students completing the module successfully should be able to:

Knowledge and Understanding

A. understand basic principles of pattern recognition in computer vision.

B. have knowledge in the areas of applications for various techniques of pattern recognition in computer vision.

Intellectual Abilities

C. formulate and define computer vision problems and to use pattern recognition methodologies to analyse and solve engineering problems.

D. design simple pattern recognition systems to achieve the specified objectives on performance, cost, etc.

Practical Skills

E. apply relevant pattern recognition techniques to a given problem.

F. develop basic image recognition software.

General Transferable Skills

G. independent learning, problem solving and design skills.
Method of teaching and learning 
This module will be delivered through a combination of formal lectures and supervised laboratory sessions. There are totally five coursework that will be assigned across the semester.
Syllabus 
1- Introduction

Example of typical pattern recognition system in computer vision ;

Overview of techniques in pattern recognition

History of pattern recognition


2 Statistical Pattern Recognition

Bayesian decision theory, Parametric /non- Parametric, Gaussian Classifiers,
Maximum Likelihood Estimation, Expectation-Maximisation (EM), Clustering, Loss function, Regularization;


3 Feature Extraction and Selection

Linear Discriminant Analysis (LDA);

Primary Component Analysis (PCA);

Forward feature selection;

Typical Features, e.g., Scale-invariant feature transform (SIFT);


4 Statistical Classifiers

Linear Classifiers, naïve bayes classifier;

Support Vector Machine (SVM);

Neural Network;


5 Ensemble Learning

Tree classifier

Random Forest

Bagging

Boosting


6 Structural Patten Recognition

Syntactic parsing,

String matching,

Graph matching,

Hidden Markov Model (HMM),

Markov random field (MRF), Conditional Random Field (CRF);


7 Deep Learning

Basic introduction,

Auto-Encode/Decode,

Convolutional neural network.


8 Object Detection

Coarse-to-Fine and Boosted Classifiers,

Dictionary Based,

Deformable Part-Based Model,

Deep learning based,

Example of scene text localisation;

Delivery Hours  
Lectures Seminars Tutorials Lab/Prcaticals Fieldwork / Placement Other(Private study) Total
Hours/Semester 26      24    100  150 

Assessment

Sequence Method % of Final Mark
1 Continuous Assessments 15.00
2 Continuous Assessments 15.00
3 Continuous Assessments 20.00
4 Continuous Assessments 25.00
5 Continuous Assessments 25.00

Module Catalogue generated from SITS CUT-OFF: 8/20/2019 6:26:58 PM