Eingang zum Volltext in PsyDok
Lizenz
Report (Bericht) zugänglich unter
Representation of human faces
URN: urn:nbn:de:bsz:291-psydok-9315
URL: http://psydok.sulb.uni-saarland.de/volltexte/2007/931/
pdf-Format:
Dokument 1.pdf (77 KB)
Freie Schlagwörter (Englisch):
pixel-based representations , human faces , pixel-by-pixel correspondence
Institut:
Max-Planck-Institut für biologische Kybernetik
DDC-Sachgruppe:
Psychologie
Dokumentart:
Report (Bericht)
Sprache:
Englisch
Erstellungsjahr:
1996
Publikationsdatum:
14.03.2007
Kurzfassung auf Englisch:
Several models for parameterized face representations have been proposed in the last years. A simple coding scheme treats the image of a face as a long vector with each entry coding for the intensity of one single pixel in the image. (e.g. Sirovich & Kirby 1987). Although simple and straitforward, such pixel-based representations have several disadvantages. We propose a representation for images of faces that separates texture and 2D shape by exploiting pixel-by-pixel correspondence between the images. The advantages of this representation compared to pixel-based representations are demonstrated by means of the quality of low-dimensional reconstructions derived from principal component analysis and by means of the performance that simple linear classifier can achieve for sex classification.
Lizenz:
Standard-Veröffentlichungsvertrag