Abstract
This paper proposes a novel family of local feature descriptors, a variant of the speed up robust features (SURF) descriptor, which is capable of demonstrably better performance. The conventional SURF descriptor is an efficient implementation of the SIFT descriptor. Although the SURF descriptor can represent the nature of the underlying image pattern, it is still sensitive to more complicated deformations such as large viewpoint and rotation changes. To solve this problem, our family of descriptors, called MDGHM-SURF, is based on the modified discrete Gaussian-Hermite moment (MDGHM), which devises a movable mask to represent the local feature information of non-square images. Whereas conventional SURF uses first-order derivatives, MDGHM-SURF uses MDGHM, which offers more feature information than first-order derivative-based local descriptors such as SURF and SIFT. Consequently, by redefining the conventional SURF descriptor using MDGHM, MDGHM-SURF can extract more distinctive features than conventional SURF. The results of evaluations conducted with six types of deformations indicate that our proposed method outperforms the matching accuracy of other SURF related algorithms.
| Original language | English |
|---|---|
| Pages (from-to) | 670-684 |
| Number of pages | 15 |
| Journal | Pattern Recognition |
| Volume | 48 |
| Issue number | 3 |
| DOIs | |
| Publication status | Published - 2014 Jan 1 |
Fingerprint
ASJC Scopus subject areas
- Software
- Artificial Intelligence
- Computer Vision and Pattern Recognition
- Signal Processing
Cite this
MDGHM-SURF : A robust local image descriptor based on modified discrete Gaussian-Hermite moment. / Kang, Tae Koo; Choi, In Hwan; Lim, Myo Taeg.
In: Pattern Recognition, Vol. 48, No. 3, 01.01.2014, p. 670-684.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - MDGHM-SURF
T2 - A robust local image descriptor based on modified discrete Gaussian-Hermite moment
AU - Kang, Tae Koo
AU - Choi, In Hwan
AU - Lim, Myo Taeg
PY - 2014/1/1
Y1 - 2014/1/1
N2 - This paper proposes a novel family of local feature descriptors, a variant of the speed up robust features (SURF) descriptor, which is capable of demonstrably better performance. The conventional SURF descriptor is an efficient implementation of the SIFT descriptor. Although the SURF descriptor can represent the nature of the underlying image pattern, it is still sensitive to more complicated deformations such as large viewpoint and rotation changes. To solve this problem, our family of descriptors, called MDGHM-SURF, is based on the modified discrete Gaussian-Hermite moment (MDGHM), which devises a movable mask to represent the local feature information of non-square images. Whereas conventional SURF uses first-order derivatives, MDGHM-SURF uses MDGHM, which offers more feature information than first-order derivative-based local descriptors such as SURF and SIFT. Consequently, by redefining the conventional SURF descriptor using MDGHM, MDGHM-SURF can extract more distinctive features than conventional SURF. The results of evaluations conducted with six types of deformations indicate that our proposed method outperforms the matching accuracy of other SURF related algorithms.
AB - This paper proposes a novel family of local feature descriptors, a variant of the speed up robust features (SURF) descriptor, which is capable of demonstrably better performance. The conventional SURF descriptor is an efficient implementation of the SIFT descriptor. Although the SURF descriptor can represent the nature of the underlying image pattern, it is still sensitive to more complicated deformations such as large viewpoint and rotation changes. To solve this problem, our family of descriptors, called MDGHM-SURF, is based on the modified discrete Gaussian-Hermite moment (MDGHM), which devises a movable mask to represent the local feature information of non-square images. Whereas conventional SURF uses first-order derivatives, MDGHM-SURF uses MDGHM, which offers more feature information than first-order derivative-based local descriptors such as SURF and SIFT. Consequently, by redefining the conventional SURF descriptor using MDGHM, MDGHM-SURF can extract more distinctive features than conventional SURF. The results of evaluations conducted with six types of deformations indicate that our proposed method outperforms the matching accuracy of other SURF related algorithms.
KW - Local feature extraction
KW - Modified discrete Gaussian-Hermite moment
KW - SURF algorithm
UR - http://www.scopus.com/inward/record.url?scp=84916937436&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84916937436&partnerID=8YFLogxK
U2 - 10.1016/j.patcog.2014.06.022
DO - 10.1016/j.patcog.2014.06.022
M3 - Article
AN - SCOPUS:84916937436
VL - 48
SP - 670
EP - 684
JO - Pattern Recognition
JF - Pattern Recognition
SN - 0031-3203
IS - 3
ER -