Change search
ReferencesLink to record
Permanent link

Direct link
Face Alignment using Boosted Appeareance Model (Discriminative Appearance Model)
Blekinge Institute of Technology, School of Engineering.
2009 (English)Independent thesis Advanced level (degree of Master (Two Years))Student thesis
Abstract [en]

This thesis explores decriminative face alignment using Boosted Appearance Model (BAM). In this method face alignment is done by maximizing the score of the trained two classifier which learns both correct and incorrect alignment and is able to distinguish correct and incorrect alignment so that the correct alignment gets maximum positve score. During the training stage we trained Point Distribution Model (PDM) which acts as shape model and a boosting based classifier based on Haar like Rectangular Features which we call as Boosted Appearance Model (BAM). This algorithm iteratively updates the shape parameters of the PDM by the well known optimization method known as gradient ascent, such that the classification score is maximized. When we test our algorithm on the images the initial parameters will likely have a negative score and these parameters are updated so that the final parameters will have the maximum positive score this will indicates alignment is finalized. The main applications are tracking, Medical Image Interpretation, Industrial Inspection etc.

Place, publisher, year, edition, pages
2009. , 61 p.
Keyword [en]
Discrminative Appearance Model, Boosted Appearance Model, Image alignment, tracking, object detection
National Category
Signal Processing Media and Communications
URN: urn:nbn:se:bth-4137Local ID: diva2:831460
Social and Behavioural Science, Law
C/o Sandeep Karanamsetty Västanågatan 26, Linköping-58235 phone no: +46704936869Available from: 2015-04-22 Created: 2009-12-02 Last updated: 2015-06-30Bibliographically approved

Open Access in DiVA

fulltext(3134 kB)31 downloads
File information
File name FULLTEXT01.pdfFile size 3134 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Other links$file/satya_presentationslides_PHILIPS.pptx
By organisation
School of Engineering
Signal ProcessingMedia and Communications

Search outside of DiVA

GoogleGoogle Scholar
Total: 31 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 30 hits
ReferencesLink to record
Permanent link

Direct link