Abstract
Feature matching is a basic process of many computer vision applications such as object detection or image stitching. A lot of state of the art technologies of feature extraction are focusing on the internal features of object. They perform great matching result but some of them spend extensive computational time to extract and match the features. In this paper, we propose a robust method for keypoint detection, description, and matching. The proposed algorithm is based on the point that people can recognize the object through the silhouette, firstly. We use object’s contour to extract their features. We can see that the proposed scheme can reduce much time to extract features through experiments.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Dalal, N., Triggs, B.: Histogram of Oriented Gradients for Human Detecting. Computer Vision and Pattern Recognition, 886–893 (2005)
Lowe, G.G.: Distinctive Image Feature from Scale-Invariant Keypoints. International Journal of Computer Vision 60, 91–110 (2004)
Rosten, E., Drummond, T.: Machine learning for high-speed corner detection In: European Conference on Computer Vision, vol. 3951, pp. 430–443 (2006)
Bay, H., Tuytelaars, T., Gool, L.V.: SURF: speeded up robust features. In: European Conference on Computer Vision, vol. 3951, pp. 404–417 (2006)
Rublee, E., Rabaud, V., Konolige, K., Bradski, G.: ORB: an efficient alternative to SIFT or SURF. In: International Conference on Computer Vision, pp. 2264–2571 (2011)
Leutenegger, S., Chil, M., Siegwart, R.Y.: BRISK: binary robust invariant scalable keypoints. In: International Conference on Computer Vision, pp. 2548–2555 (2011)
Mikolajczyk, K., Schmid, C.: A Performance Evaluation of Local Descriptors. Pattern Analysis and Machine Intelligence 27, 1615–1630 (2005)
Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories. Computer Vision and Image Understanding 106, 59–70 (2007)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer Science+Business Media Singapore
About this paper
Cite this paper
Hu, W., Koo, Ms., Nam, JH., Kim, BG., Kim, SK. (2015). Robust Feature Design for Object Detection. In: Park, DS., Chao, HC., Jeong, YS., Park, J. (eds) Advances in Computer Science and Ubiquitous Computing. Lecture Notes in Electrical Engineering, vol 373. Springer, Singapore. https://doi.org/10.1007/978-981-10-0281-6_17
Download citation
DOI: https://doi.org/10.1007/978-981-10-0281-6_17
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-0280-9
Online ISBN: 978-981-10-0281-6
eBook Packages: Computer ScienceComputer Science (R0)