Robust recognition of facial expressions on noise degraded facial images

Simple item page
dc.contributor.advisorConnan, James
dc.contributor.authorSheikh, Munaf
dc.contributor.otherDept. of Computer Science
dc.contributor.otherFaculty of Science
dc.date.accessioned2014-01-21T14:01:01Z
dc.date.accessioned2024-10-30T14:00:41Z
dc.date.available2011/05/31 09:46
dc.date.available2011/05/31
dc.date.available2014-01-21T14:01:01Z
dc.date.available2024-10-30T14:00:41Z
dc.date.issued2011
dc.descriptionMagister Scientiae - MScen_US
dc.description.abstractWe investigate the use of noise degraded facial images in the application of facial expression recognition. In particular, we trained Gabor+SVMclassifiers to recognize facial expressions images with various types of noise. We applied Gaussian noise, Poisson noise, varying levels of salt and pepper noise, and speckle noise to noiseless facial images. Classifiers were trained with images without noise and then tested on the images with noise. Next, the classifiers were trained using images with noise, and then on tested both images that had noise, and images that were noiseless. Finally, classifiers were tested on images while increasing the levels of salt and pepper in the test set. Our results reflected distinct degradation of recognition accuracy. We also discovered that certain types of noise, particularly Gaussian and Poisson noise, boost recognition rates to levels greater than would be achieved by normal, noiseless images. We attribute this effect to the Gaussian envelope component of Gabor filters being sympathetic to Gaussian-like noise, which is similar in variance to that of the Gabor filters. Finally, using linear regression, we mapped a mathematical model to this degradation and used it to suggest how recognition rates would degrade further should more noise be added to the images.en_US
dc.description.countrySouth Africa
dc.identifier.urihttps://hdl.handle.net/10566/16929
dc.language.isoenen_US
dc.publisherUniversity of the Western Capeen_US
dc.rights.holderUniversity of the Western Capeen_US
dc.subjectFacial expression recognitionen_US
dc.subjectFacial action unitsen_US
dc.subjectNoiseen_US
dc.subjectGaboren_US
dc.subjectSupport vector machinesen_US
dc.subjectMachine learningen_US
dc.subjectPoisson probability distributionen_US
dc.subjectGaussian normal distributionen_US
dc.subjectSalt and pepperen_US
dc.subjectSpeckleen_US
dc.titleRobust recognition of facial expressions on noise degraded facial imagesen_US
dc.typeThesisen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Sheikh_MSC_2011.pdf
Size:
3.78 MB
Format:
Adobe Portable Document Format
Download

Collections

Magister Scientiae - MSc (Computer Science)