2 x 50-minute lectures weekly
1 x 50-minute computer lab weekly
1 x 30-hour project work per semester
Assumed knowledge
Mathematics and statistics background such as covered in ENGR2711, COMP2781, MATH3701 or STAT2702; scientific programming skills such as that attained in COMP1102 or COMP2711
Topic description
Selected modern pattern recognition techniques will be covered in depth, including segmentation techniques such as threshold-based methods or graph-based methods, feature description and extraction (intensity features, shape features, principle component analysis), feature selection techniques, classification methods and evaluation methodology such as ROC curve, sensitivity and specificity, Dice and Jaccard index.
Educational aims
This topic provides:

  1. An understanding of pattern recognition problems in digital images
  2. An introduction to computer methods for pattern recognition problems
  3. Experience in scientific computing
  4. Experience in applying different computer methods in solving a range of real-life examples of pattern recognition problems
  5. Skills necessary to analyse, solve and critically evaluate, using appropriate evidence, feasibility of various approaches to a wide range of pattern recognition problems
Expected learning outcomes
At the completion of this topic, students are expected to:

  1. Understand the foundations of selected pattern recognition techniques
  2. Understand the concept and theory behind a range of common techniques in solving a broad range of pattern recognition problems
  3. Be able to analyse and explain issues arising in real-life pattern recognition applications
  4. Be able to use software to solve new pattern recognition problems
  5. Be able to critically evaluate applicability of various techniques to new problems
  6. Be able to use appropriately sourced evidence to devise feasible solutions for complex image analysis tasks