JOURNAL BROWSE
Search
Advanced SearchSearch Tips
Performance Analysis of Brightness-Combined LLAH
facebook(new window)  Pirnt(new window) E-mail(new window) Excel Download
 Title & Authors
Performance Analysis of Brightness-Combined LLAH
Park, Hanhoon; Moon, Kwang-Seok;
  PDF(new window)
 Abstract
LLAH(Locally Likely Arrangement Hashing) is a method which describes image features by exploiting the geometric relationship between their neighbors. Inherently, it is more robust to large view change and poor scene texture than conventional texture-based feature description methods. However, LLAH strongly requires that image features should be detected with high repeatability. The problem is that such requirement is difficult to satisfy in real applications. To alleviate the problem, this paper proposes a method that improves the matching rate of LLAH by exploiting together the brightness of features. Then, it is verified that the matching rate is increased by about 5% in experiments with synthetic images in the presence of Gaussian noise.
 Keywords
LLAH;Feature Description;Feature Brightness;Gaussian Noise;
 Language
Korean
 Cited by
 References
1.
D. Lowe, “Distinctive Image Features from Scale-Invariant Keypoints”, International Journal of Computer Vision, Vol. 60, No. 2, pp. 91-110, 2004. crossref(new window)

2.
T. Nakai, K. Kise, and M. Iwamura. "Use of Affine Invariants in Locally Likely Arrangement Hashing for Camera-Based Document Image Retrieval," Proceeding of International Workshop on Document Analysis Systems, pp. 541-552, 2006.

3.
H. Uchiyama and H. Saito, "Random Dot Markers," Proceeding of IEEE Virtual Reality, pp. 35-38, 2011.

4.
B.K. Seo, H. Uchiyama, and J.I. Park, "stAR: Visualizing Constellations with Star Retrieval," Proceeding of SIGGRAPH ASIA, 2011.

5.
H. Uchiyama and E. Marchand, "Toward Augmenting Everything: Detecting and Tracking Geometrical Features on Planar Objects," Proceeding of IEEE International Symposium on Mixed and Augmented Reality, pp. 17-25, 2011.

6.
H. Park, “Performance Optimization of LLAH for Tracking Random Dots Under Gaussian Noise,” Journal of Broadcast Engineering, Vol. 20, No. 6, pp. 912-920, 2015. crossref(new window)

7.
H. Park and K.S. Moon, “Performance Analysis of Feature Detection Methods for Topology- Based Feature Description,” Journal of the Institute of Signal Processing and Systems, Vol. 16, No. 2, pp. 44-49, 2015.

8.
H. Ryu and H. Park, “Performance Analysis of Modified LLAH Algorithm Under Gaussian Noise,” Journal of Korea Multimedia Society, Vol. 18, No. 8, pp. 901-908, 2015. crossref(new window)