VISUAL INFORMATION SYSTEMS
CSE4VIS
2015
Credit points: 15
Subject outline
This subject covers an overview of visual information access, image representation, feature extraction, image recognition and understanding, and content-based image retrieval techniques. Design issues on facial image recognition and content-based image retrieval systems for image database management will be addressed, which contain eigenface technology, image feature extraction, indexing, similarity measure, lower-bounding lemma and performance evaluation. Practice on facial image recognition (FIR) will be offered in Labs.
School: School Engineering&Mathematical Sciences
Credit points: 15
Subject Co-ordinator: Justin Wang
Available to Study Abroad Students: Yes
Subject year level: Year Level 4 - UG/Hons/1st Yr PG
Exchange Students: Yes
Subject particulars
Subject rules
Prerequisites: CSE2ICE or equivalent AND Enrolment in one of the following courses: SMIT, SMICT, SMCSC, SMBBS, SGBBS, SGIT or SGCS.
Co-requisites: N/A
Incompatible subjects: CSE3VIS AND Students in the following courses are not permitted to enrol: SBCS, SBIT, SBCSGT, SVCSE, SZCSC, SBITP and SBBIY.
Equivalent subjects: N/A
Special conditions: N/A
Learning resources
Readings
| Resource Type | Title | Resource Requirement | Author and Year | Publisher |
|---|---|---|---|---|
| Readings | Content-based image and video retrieval | Recommended | Marques, O and Furht, B 2002 | 1ST ED, SPRINGER |
| Readings | Image recognition and classification: algorithms, systems and applications | Recommended | Javidi, B 2002 | 1ST EN, CRC PRESS |
Graduate capabilities & intended learning outcomes
01. Define the technologies used in visual information systems.
- Activities:
- Students are required to complete the questions related to the specific information and knowledge in the exam papers. Lecture topic 1 on the introduction of visual information systems.
- Related graduate capabilities and elements:
- Discipline-specific GCs(Discipline-specific GCs)
- Writing(Writing)
02. Evaluate the major issues in visual data recognition, content-based image database management, and describe how to effectively represent visual data for visual information processing.
- Activities:
- Students are required to complete all questions related to the specific techniques for visual data modelling, image database management and visual information retrieval in the exam papers. Lectures 2, 3, 4, 5, 6, 7 are on visual data representation, features and similarity, Facial Image Recognition, retrieval systems fundamentals.
- Related graduate capabilities and elements:
- Inquiry/ Research(Inquiry/ Research)
- Discipline-specific GCs(Discipline-specific GCs)
- Creative Problem-solving(Creative Problem-solving)
- Quantitative Literacy/ Numeracy(Quantitative Literacy/ Numeracy)
- Critical Thinking(Critical Thinking)
03. Research and implementation of Facial Image Recognition (FIR) systems.
- Activities:
- One assignment on facial image recognition and 8 laboratories exercises, plus one group assignment on forensic image recognition. Lab 1 to Lab 8 are on FIR system implementation. MATLAB will be used to implement the FIR system.
- Related graduate capabilities and elements:
- Teamwork(Teamwork)
- Creative Problem-solving(Creative Problem-solving)
- Critical Thinking(Critical Thinking)
- Quantitative Literacy/ Numeracy(Quantitative Literacy/ Numeracy)
04. Evaluate the significance of image recognition techniques for real world applications.
- Activities:
- Students are required to complete some questions related to the specific techniques for image recognition and its applications in the exam papers. Lectures 8, 9, 10, 11 are on Recognition Systems Fundamentals, Feature-based Classifiers, Handwritten Numeral Recognition, and Face Image Recognition.
- Related graduate capabilities and elements:
- Discipline-specific GCs(Discipline-specific GCs)
- Writing(Writing)
- Critical Thinking(Critical Thinking)
Melbourne, 2015, Semester 1, Day
Overview
Online enrolment: Yes
Maximum enrolment size: N/A
Enrolment information:
Subject Instance Co-ordinator: Justin Wang
Class requirements
Laboratory Class
One 2.0 hours laboratory class per week and delivered via face-to-face.
Lecture
One 2.0 hours lecture per week and delivered via face-to-face.
Assessments
| Assessment element | Comments | % | ILO* |
|---|---|---|---|
| Assignment 2 - Forensic Image recognition techniques (Group project | 20 | 03 | |
| Assignment 1 - Facial image recognition system design | 20 | 03 | |
| Exam | 60 | 01, 02, 04 |