Abstract
We provide a generalized image normalization technique which basically solved all problems in image normalization. The orientation of any image can be uniquely defined by at most three non-zero generalized complex (GC) moments. The correctness of our method is demonstrated theoretically as well as in practice by applying them to a number of "degenerate" images which have failed other previously reported techniques for image normalization.
| Original language | English |
|---|---|
| Pages (from-to) | 431-440 |
| Number of pages | 10 |
| Journal | IEEE Transactions on Pattern Analysis and Machine Intelligence |
| Volume | 19 |
| Issue number | 5 |
| DOIs | |
| Publication status | Published - 1997 |
Keywords
- Complex moment
- Fold detection
- Image normalization
- Image orientation
- Invariant image matching
- Rotationally symmetric image
- Symmetry detection
ASJC Scopus subject areas
- Software
- Computer Vision and Pattern Recognition
- Computational Theory and Mathematics
- Artificial Intelligence
- Applied Mathematics
Fingerprint Dive into the research topics of 'Generalized affine invariant image normalization'. Together they form a unique fingerprint.
Cite this
Shen, D., & Ip, H. H. S. (1997). Generalized affine invariant image normalization. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(5), 431-440. https://doi.org/10.1109/34.589203