Analysis and Segmentation of Face Images using Point Annotations and Linear Subspace Techniques

Mikkel B. Stegmann

AbstractThis report provides an analysis of 37 annotated frontal face images. All results presented have been obtained using our freely available Active Appearance Model (AAM) implementation. To ensure the reproducibility of the presented experiments, the data set has also been made available. As such, the data and this report may serve as a point of reference to compare other AAM implementations against.
In addition, we address the problem of AAM model truncation using parallel analysis along with a comparable study of the two prevalent AAM learning methods; principal component regression and estimation of fixed Jacobian matrices.
To assess applicability and efficiency, timings for model building, warping and optimisation are given together with a description of how to exploit the warping capabilities of contemporary consumer-level graphics hardware.
Keywordsshape analysis, generative modelling, face recognition, active shape models, active appearance models, annotated image data set
TypeTechnical report
Year2002    Month August    pp. 25
PublisherInformatics and Mathematical Modelling, Technical University of Denmark, DTU
AddressRichard Petersens Plads, Building 321, DK-2800 Kgs. Lyngby
IMM no.IMM-REP-2002-22
NoteSee the publication link for the images and the annotations.
Electronic version(s)[pdf]
Publication linkhttp://www.imm.dtu.dk/~aam/datasets/face_data.zip
BibTeX data [bibtex]
IMM Group(s)Image Analysis & Computer Graphics


Back  ::  IMM Publications