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 Dec 1 |
| Externally published | Yes |
Fingerprint
Keywords
- Complex moment
- Fold detection
- Image normalization
- Image orientation
- Invariant image matching
- Rotationally symmetric image
- Symmetry detection
ASJC Scopus subject areas
- Control and Systems Engineering
- Electrical and Electronic Engineering
- Artificial Intelligence
- Computer Vision and Pattern Recognition
Cite this
Generalized affine invariant image normalization. / Shen, Dinggang; Ip, Horace H S.
In: IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 19, No. 5, 01.12.1997, p. 431-440.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Generalized affine invariant image normalization
AU - Shen, Dinggang
AU - Ip, Horace H S
PY - 1997/12/1
Y1 - 1997/12/1
N2 - 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.
AB - 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.
KW - Complex moment
KW - Fold detection
KW - Image normalization
KW - Image orientation
KW - Invariant image matching
KW - Rotationally symmetric image
KW - Symmetry detection
UR - http://www.scopus.com/inward/record.url?scp=0031146742&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0031146742&partnerID=8YFLogxK
U2 - 10.1109/34.589203
DO - 10.1109/34.589203
M3 - Article
VL - 19
SP - 431
EP - 440
JO - IEEE Transactions on Pattern Analysis and Machine Intelligence
JF - IEEE Transactions on Pattern Analysis and Machine Intelligence
SN - 0162-8828
IS - 5
ER -