Abstract | ||
---|---|---|
This paper presents a method that matches interest point features detected on two images taken from different view points. A new multi-scale Plessey corner detector(MPCD) is used to detect the interest points. The geometric constraint between two images is exploited as in [2]: the fundamental matrix is derived using least median of squares(LMedS) from an initial set of matches, then it is used to guide new matches. However, we propose a new energy function that can approximate affine transformation in a more effective way. Then, the initial set of matches are derived by minimizing the energy function. As a result, our method can perform well even when the pose variation is large between the two images. We compare our method using the proposed MPCD against two standard corner detectors on image matching. Also we evaluate our proposed matching criterion against Zhang's. Our method gave better results in both experiments on real face images. |
Year | DOI | Venue |
---|---|---|
2004 | 10.1109/ICARCV.2004.1469076 | 2004 8TH INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION, ROBOTICS AND VISION, VOLS 1-3 |
Keywords | Field | DocType |
affine transformation,fundamental matrix,feature detection | Affine transformation,Pattern recognition,Computer science,Image matching,Least median of squares,Artificial intelligence,Feature based,Detector,Fundamental matrix (computer vision),Corner detector | Conference |
ISSN | Citations | PageRank |
2474-2953 | 0 | 0.34 |
References | Authors | |
6 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Wenbo Zhang | 1 | 88 | 26.13 |
Xinting Gao | 2 | 119 | 10.60 |
Eric Sung | 3 | 346 | 20.86 |
Farook Sattar | 4 | 371 | 41.95 |
Ronda Venkateswarlu | 5 | 255 | 17.03 |