Back to Module List

CMPSMI16 - COMPUTER VISION (FOR DIGITAL PHOTOGRAPHY)

Module Code:
CMPSMI16
Department:
Computing Sciences
Credit Value:
20
Level:
M
Organiser:
Dr. Michal Mackiewicz
This module covers the various stages in processing the image recorded at the sensor level in a camera so that the output is an attractive photographic image. The first half of the course will cover topics including demosaicking, denoising, white point correction, dynamic range compression and image rendering. The second half will look at higher level functions such as finding faces in images, content recognition (including face recognition) and facial coding in images. The last topic is particularly interesting in the context of mobile phone applications.
  • One lab demonstrator for two hours per week.
  • One lab with Matlab 2009b installed

Required reading:

Sonka, M., Hlavac, V. and Boyle, R.(2007) Image processing, analysis and machine vision, ITP

A reading list is handed-out at the start of the module.


Submission:

Written coursework should be submitted by following the standard CMP practice. Students are advised to refer to the Guidelines and Hints on Written Work in CMP.

Deadlines:

If coursework is handed in after the deadline day or an agreed extension:

Work submitted Marks deducted
After 15:00 on the due date and before 15:00 on the day following the due date 10 marks
After 15:00 on the second day after the due date and before 15:00 on the third day after the due date 20 marks
After 15:00 on the third day after the due date and before 15:00 on the 20th day after the due date.  All the marks the work merits if submitted on time (ie no marks awarded) 
After 20 working days Work will not be marked and a mark of zero will be entered


Saturdays and Sundays will NOT be taken into account for the purposes of calculation of marks deducted.

All extension requests will be managed through the LTS Hub. A request for an extension to a deadline for the submission of work for assessment should be submitted by the student to the appropriate Learning and Teaching Service Hub, prior to the deadline, on a University Extension Request Form accompanied by appropriate evidence. Extension requests will be considered by the appropriate Learning and Teaching Service Manager in those instances where (a) acceptable extenuating circumstances exist and (b) the request is submitted before the deadline. All other cases will be considered by a Coursework Coordinator in CMP.

For more details, including how to apply for an extension due to extenuating circumstances download Submission for Work Assessment (PDF, 39KB)
 

Plagiarism:

Plagiarism is the copying or close paraphrasing of published or unpublished work, including    the work of another student; without due acknowledgement. Plagiarism is regarded a serious offence by the University, and all cases will be investigated. Possible consequences of plagiarism include deduction of marks and disciplinary action, as detailed by UEA's Policy on Plagiarism and Collusion.


Module specific:

  • To gain an overall understanding of modern vision and photographic systems
  • To be able to critically compare vision algorithms
  • To understand the importance of evaluation in computer vision

Transferable skills:

  • Matlab programming and hence program design
  • The use of statistical techniques for data analysis
  • Report writing

On completion of the unit students should be able to:

  • Be able to describe a restricted range of vision algorithms
  • Be able to compare specified algorithms from the point of view of their complexity, robustness and modularity
  • Understand the role of colour, shape and segmentation
  • Write simple Matlab programs to manipulate images

Total Hours: 38

Lectures: 20; Hours 20; Content (with provisional weekly schedule)

  1. What is computer vision? Why do it?
  2. The physics of vison: light to CCD image
  3. Image data: coding and computing with images
  4. Light and colour: models and representations
  5. Image formation (demosaicing)
  6. Image denoising
  7. White point estimation
  8. Colour correction
  9. Dynamic range compression (I)
  10. Dynamic range compression (II)
  11. Image segmentation (I)
  12. Image segmentation (II)
  13. Chain codes and differential chain codes
  14. Active Contours (Snakes)
  15. Point Distribution Models
  16. Active Shape Models I
  17. Active Shape Models II
  18. Appearance Models
  19. Active Appearance Models 
  20. Applications

Worskhops: 0 hours

Laboratory work: 30 hours; Content:

  • Introduction to Matlab
  • Using Matlab to manipulate images
  • Building systems with Matlab
  • Image segmentation
  • Active contours
  • Active appearance models
  • Assignment work

Examination with Coursework or Project