Title :
Object recognition from 3D blurred images
Author :
Boucher, Alain ; Thonnat, Monique
Author_Institution :
INRIA, Sophia-Antipolis, France
Abstract :
This paper presents a novel approach for 3D object recognition and classification. The originality of this approach is the combination of statistical reasoning, feature learning and expertise knowledge from the application. It is based on 2D processing of images alternating with 3D validation of class characteristics for recognition. Classification is based on iterative refinement of hypotheses. An application is presented for pollen grain observed with light microscopy for allergy prevention.
Keywords :
biological techniques; biology computing; image recognition; inference mechanisms; object recognition; optical microscopy; 3D blurred images; allergy prevention; class characteristics; expertise knowledge; feature learning; iterative refinement; light microscopy; object classification; object recognition; pollen grain; statistical reasoning; Biomedical equipment; Character recognition; Humans; Image analysis; Image recognition; Medical services; Microscopy; Object recognition; Optical refraction; Statistics;
Conference_Titel :
Pattern Recognition, 2002. Proceedings. 16th International Conference on
Print_ISBN :
0-7695-1695-X
DOI :
10.1109/ICPR.2002.1044880
