Name
Abstract | ||
|---|---|---|
The correspondence problem in computer vision is basically a matching task between two or more sets of features. In this paper, we introduce a vectorized image representation, which is a feature-based representation where correspondence has been established with respect to a reference image. The representation consists of two image measurements made at the feature points: shape and texture. Feature geometry, or shape, is represented using the (x, y) locations of features relative to the some standard reference shape. Image grey levels, or texture, are represented by mapping image grey levels onto the standard reference shape. Computing this representation is essentially a correspondence task, and in this paper we explore an automatic technique for "vectorizing" face images. Our face vectorizer alternates back and forth between computation steps for shape and texture, and a key idea is to structure the two computations so that each one uses the output of the other. In addition to describing the vectorizer, an application to the problem of facial feature detection will be presented. |
Year | DOI | Venue |
|---|---|---|
1996 | 10.1109/CVPR.1996.517181 | CVPR |
Keywords | Field | DocType |
image grey level,face image,feature correspondence,interleaving shape,texture computations,correspondence task,vectorized image representation,mapping image grey level,correspondence problem,image measurement,feature-based representation,reference image,standard reference shape,feature extraction,artificial intelligence,geometry,face recognition,image texture,computer vision,face detection,image analysis | Computer vision,Feature detection (computer vision),Pattern recognition,Computer science,Feature (computer vision),Image texture,Edge detection,Pyramid (image processing),Scale space,Feature extraction,Artificial intelligence,Correspondence problem | Conference |
Volume | Issue | ISSN |
1996 | 1 | 1063-6919 |
ISBN | Citations | PageRank |
0-8186-7258-7 | 15 | 6.58 |
References | Authors | |
10 | 1 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Beymer David | 1 | 420 | 87.32 |