Data processing apparatus, data processing method and recording medium
AssigneeSony Corporation
InventorsTetsujiro Kondo, Junichi Ishibashi
Life of this patent
Estimating the term…
Abstract
A group of input image data is determined based on the distance between images of a number of representative faces, prepared from plural templates, and the input image data (correlative values C1 to C5). The number of representative faces is smaller than the number of the templates. An angle of the input image is calculated based on the so-determined group.
Claims9
1-34. (canceled)
An apparatus for generating a plurality of facial image templates for a plurality of face classes, said apparatus comprising:
- means for receiving an input facial image and a plurality of facial image templates, each facial image template of said plurality of facial image templates previously generated for each face class of said plurality of face classes;
- means for determining correlation between said input facial image and said each facial image template;
- means for classifying said input facial image into one of said plurality of face classes based on the determined correlation between said input facial image and said each facial image template;
- and
- means for generating said plurality of facial image templates representing orientations of said input facial images.
A method for generating a plurality of facial image templates for a plurality of face classes, said method comprising:
- receiving an input facial image and a plurality of facial image templates, each facial image template of said plurality of facial image templates previously generated for each face class of said plurality of face classes;
- determining correlation between said input facial image and said each facial image template;
- classifying said input facial image into one of said plurality of face classes based on the determined correlation between said input facial image and said each facial image template;
- and
- generating said plurality of facial image templates representing orientations of said input facial images.
Dependencies are inferred from the claim text.