CGCI-SIFT: A More Efficient and Compact Representation of Local Descriptor

Su, Dongliang; Wu, Jian; Cui, Zhiming; Sheng, Victor S.; Gong, Shengrong

doi:10.2478/msr-2013-0022

Abstract

This paper proposes a novel invariant local descriptor, a combination of gradient histograms with contrast intensity (CGCI), for image matching and object recognition. Considering the different contributions of sub-regions inside a local interest region to an interest point, we divide the local interest region around the interest point into two main sub-regions: an inner region and a peripheral region. Then we describe the divided regions with gradient histogram information for the inner region and contrast intensity information for the peripheral region respectively. The contrast intensity information is defined as intensity difference between an interest point and other pixels in the local region. Our experimental results demonstrate that the proposed descriptor performs better than SIFT and its variants PCA-SIFT and SURF with various optical and geometric transformations. It also has better matching efficiency than SIFT and its variants PCA-SIFT and SURF, and has the potential to be used in a variety of realtime applications.

References

[1] Lowe, D.G. (2004). Distinctive image features from scale-invariant keypoints. International Journal ofComputer Vision, 60 (2), 91-110.10.1023/B:VISI.0000029664.99615.94
Search in Google Scholar
[2] Strecha, Ch., Bronstein, A.M. (2012). LDAHash: Improved matching with smaller descriptors. IEEETransactions on Pattern Analysis and MachineIntelligence, 34 (1), 66-78.10.1109/TPAMI.2011.10321576750
Search in Google Scholar
[3] Senchenko, E.S., Chugui, Yu.V. (2011). Shadow inspection of 3D objects in partially coherent light. Measurement Science Review, 11 (4), 104-107.10.2478/v10048-011-0018-x
Search in Google Scholar
[4] Jin Guofeng, Zhang Wei, Yang Zhengwei et al. (2012). Image segmentation of thermal waving inspection based on particle swarm optimization fuzzy clustering algorithm. Measurement Science Review, 12 (6), 296-301.10.2478/v10048-012-0041-6
Search in Google Scholar
[5] Harris, Ch., Stephens, M. (1988). A combined corner and edge detector. In Proceedings of the 4th AlveyVision Conference, 147-151.10.5244/C.2.23
Search in Google Scholar
[6] Mikolajczyk, K., Schmid, C. (2005). A performance evaluation of local descriptors. IEEE Transactions onPattern Analysis and Machine Intelligence, 27 (10), 1615-1630.10.1109/TPAMI.2005.18816237996
Search in Google Scholar
[7] Bay, H., Ess, A., Tuytelaars, T., Gool, L.V. (2008). SURF: Speeded up robust features. Computer Visionand Image Understanding, 10 (3), 346-359.10.1016/j.cviu.2007.09.014
Search in Google Scholar
[8] Yan Ke, Sukthankar, R. (2004). PCA-SIFT: A more distinctive representation for local image descriptors. In Computer Vision and Pattern Recognition (CVPR2004), 27 June- 2 July 2004. IEEE, Vol. 2, 506-513.
Search in Google Scholar
[9] Mortensen, E.N., Deng Hongli, Shapiro, L. (2005). A SIFT descriptor with global context. In ComputerVision and Pattern Recognition (CVPR 2005), 20-25 June 2005. IEEE, Vol. 1, 184-190.
Search in Google Scholar
[10] Tola, E., Lepetit, V., Fua, P. (2010). Daisy: An efficient dense descriptor applied to wide baseline stereo. IEEETransactions on Pattern Analysis and MachineIntelligence, 32 (5), 815-830.10.1109/TPAMI.2009.7720299707
Search in Google Scholar
[11] Yang Duanduan, Sluzek, A. (2010). A lowdimensional local descriptor incorporating TPS warping for image matching. Image & VisionComputing, 28 (8), 1184-1195.
Search in Google Scholar
[12] Tuytelaars, T., Mikolajczyk, K. (2008). Local invariant feature detectors: A survey. Computer Graphics andVision, 3 (3), 177-280.
Search in Google Scholar
[13] Rabbani, H. (2011). Statistical modeling of low SNR magnetic resonance images in wavelet domain using laplacian prior and two-sided rayleigh noise for visual quality improvement. Measurement Science Review, 11 (4), 125-130.10.2478/v10048-011-0023-0
Search in Google Scholar
[14] Xianqing Lei, Chunyang Zhang, Yujun Xue, Jishun Li. (2011). Roundness error evaluation algorithm based on polar coordinate transform. Measurement, 44 (2), 345-350.10.1016/j.measurement.2010.10.007
Search in Google Scholar
[15] Bai Cong, Kpalma Kidiyo, Ronsin Joseph. (2011). Analysis of histogram descriptor for image retrieval in DCT domain. In Intelligent Interactive MultimediaSystems and Services. Springer, Vol. 11, 227-235.
Search in Google Scholar
[16] Huang, C.R., Chen, C.R., Chung, P.C. (2008). Contrast context histogram an efcient discriminating local descriptor for object recognition and image matching. Pattern Recognition, 41 (10), 3071-3077.10.1016/j.patcog.2008.03.013
Search in Google Scholar
[17] Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A. (2005). A comparison of affine region detectors. International Journal of Computer Vision, 65 (1/2), 43-72.10.1007/s11263-005-3848-x
Search in Google Scholar

CGCI-SIFT: A More Efficient and Compact Representation of Local Descriptor

Abstract

Paradigm

My account