Apparatus and method for partial component facial recognition
A method and system for identifying a human being or verifying two human beings by partial component(s) of their face. A probe human face image is identified from the gallery database by detecting and segmenting a plurality of partial face components from the probe human face image; creating a probe template for each of the partial face components from the probe human face image, comparing first and second probe templates against first and second categories of templates in the gallery database to generate similarity scores between the probe templates and templates in the gallery database; generating a plurality of sub-lists of candidate images having partial face component templates with the highest similarity scores over a first preset threshold; generating for each candidate image from each sub-list a combined similarity score; and generating a final list of candidates from said candidates of combined similarity scores over a second preset threshold.
1. A method for face identification of a probe human face image from a plurality of human face images in a gallery database having a plurality of templates, each template corresponding to a partial face component and said templates in said gallery database being grouped into categories, comprising the steps of:
detecting and segmenting a plurality of partial face components from said probe human face image;
creating a probe template for each of said partial face components from said probe human face image;
comparing a first probe template against a first category of templates in said gallery database and a second probe template against a second category of templates in said gallery database to generate similarity scores between said first and second probe templates and said first and second templates in said gallery database;
generating a first list of candidate images whose first template in said gallery database has a similarity score with said first probe template over a preset threshold and a second list of candidate images whose second template in said gallery database have a similarity score with said second template over said preset threshold.
2. A method for face recognition according to claim 1 further comprising the steps of:
generating a combined similarity score for each candidate image on said first and second lists;
comparing each combined similarity score with a second threshold; and
generating a final list of candidate images having the highest combined similarity scores over said second threshold.
3. A method for face identification of a probe human face image from a plurality of human face images in a gallery database having a plurality of templates, each template corresponding to a partial face component and said templates in said gallery database being grouped into categories, comprising the steps of:
detecting and segmenting a plurality of partial face components from said probe human face image;
creating a probe template for each of said partial face components from said probe human face image;
comparing each of said probe templates against a category of templates in said gallery database to generate similarity scores between said probe templates and templates in said gallery database;
generating a plurality of sub-lists of candidate images having partial face component templates with the highest similarity scores over a first preset threshold;
generating for each candidate image from each said sub-list a combined similarity score; and
generating a final list of candidates having combined similarity scores over a second preset threshold.