Abstract | ||
---|---|---|
We propose a method for recognizing the ID tags of "objects" in the real world that uses the image capture capabilities of conventional cell phone cameras. The method offers robustness with regard to view-direction and view-distance. Instead of using projective transformation for geometric calibration and multi-view data, we use five colored rectangles to establish the "geometric invariants of five coplanar points". We can use the low-quality images common in the mobile environment because we use feature extraction through color calibration based on RGB values of the "Visual- Tag" background and color segmentation based on the hue information of the colored squares. Tests show that the method can yield effective ID-recognition systems. |
Year | DOI | Venue |
---|---|---|
2003 | 10.1109/ICIP.2003.1247305 | Image Processing, 2003. ICIP 2003. Proceedings. 2003 International Conference |
Keywords | Field | DocType |
cameras,feature extraction,image colour analysis,image recognition,mobile handsets,cell phone camera,color calibration,color segmentation,feature extraction,geometric calibration,image capture capabilities,multiview data,view-direction,view-distance,visual-tag reader | Camera phone,Computer vision,Colored,Pattern recognition,Color calibration,Computer science,Hue,Feature extraction,Homography,RGB color model,Artificial intelligence,Color image | Conference |
Volume | ISSN | ISBN |
3 | 1522-4880 | 0-7803-7750-8 |
Citations | PageRank | References |
3 | 0.50 | 2 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Toshiki Iso | 1 | 62 | 6.49 |
Shoji Kurakake | 2 | 181 | 17.16 |
Toshiaki Sugimura | 3 | 125 | 18.47 |