Digikam/GSoC2012/FaceRecognition: Difference between revisions

From KDE Community Wiki
(Created page with "== DESIGN PHASE == === Ideas list === - use SQLite instead XMLs - ... (waiting for the end of the exam session) === TODO list === - '''collect and specify all possible ideas...")
 
(→‎Ideas list: new ideas.)
Line 3: Line 3:
=== Ideas list ===
=== Ideas list ===
  - use SQLite instead XMLs
  - use SQLite instead XMLs
- different way of merging multiple faces together. Currently, in the interests of saving space, as new faces are added to a particular person, rather than keeping them all separate they are merged together using eigen projections.It is good bcause it does save space, loading time and memory in general it tends to lose precision. So a differentmethod of merging would great addition, or perhaps an altogether different approach.
- New algorithm for face recognition. Currently Eigenfaces is the working algorithm, however it is coloury and rotation variant. This obviously has an adverse effect on quality of recognition. Fisherfacesis much more tollerant to rotation and colour changes. Hidden Markov Model based approach is another possible way of doing it. There used to be good helper function in OpenCV, however they reside in legacy headers and sadly a lot of documentation has been lost so revere engineering will be required from source. Ultimately an entirely new approach would be equally interesting to consider e.g. recognition based neural maps(network). Ideally the projectis not to invent a new method, but rather implement already existing one from the literature.
  - ... (waiting for the end of the exam session)
  - ... (waiting for the end of the exam session)



Revision as of 10:40, 11 February 2012

DESIGN PHASE

Ideas list

- use SQLite instead XMLs
- different way of merging multiple faces together. Currently, in the interests of saving space, as new faces are added to a particular person, rather than keeping them all separate they are merged together using eigen projections.It is good bcause it does save space, loading time and memory in general it tends to lose precision. So a differentmethod of merging would great addition, or perhaps an altogether different approach.
- New algorithm for face recognition. Currently Eigenfaces is the working algorithm, however it is coloury and rotation variant. This obviously has an adverse effect on quality of recognition. Fisherfacesis much more tollerant to rotation and colour changes. Hidden Markov Model based approach is another possible way of doing it. There used to be good helper function in OpenCV, however they reside in legacy headers and sadly a lot of documentation has been lost so revere engineering will be required from source. Ultimately an entirely new approach would be equally interesting to consider e.g. recognition based neural maps(network). Ideally the projectis not to invent a new method, but rather implement already existing one from the literature.
- ... (waiting for the end of the exam session)

TODO list

- collect and specify all possible ideas
- design database schema