-
摘要: 提出一种鲁棒的特征描述符MSALJS (Multi-Scale Autoconvolution on Local Jet Structure),该描述符对仿射变换具有近似不变性. MSALJS是一种全局图像特征描述符,它基于描述图像局部结构的微分进行多尺度自卷积矩计算. 实验结果表明,MSALJS能适用于目标识别实际应用时图像发生部分遮挡、视角变化等变形情形.
-
关键词:
- 多尺度自卷积 /
- 仿射变换 /
- Local Jet结构 /
- 不变量
Abstract: This article presents a novel and robust feature descriptor called the multi-scale autoconvolution on local jet structure (MSALJS), which is quasi-invariant to affine transformation. The MSALJS, a global image feature descriptor, is based on the derivatives that describe the image local structure to compute the multi-scale autoconvolution moment. Experimental data demonstrate that the MSALJS can be used in practical applications in which the object is deformed in various ways, such as particular occlusion, view angle change, and so on. -
[1] Hu M. Visual pattern recognition by moment invariants. IEEE Transactions on Information Theory, 1962, 8(2): 179-187 [2] [2] Farokhi S, Shamsuddin S M, Flusser J, Sheikh U U, Khansari M, Jafari-Khouzani K. Rotation and noise invariant near-infrared face recognition by means of Zernike moments and spectral regression discriminant analysis. Journal of Electronic Imaging, 2013, 22(1): 1-11 [3] [3] Flusser J. Pattern recognition by affine moment invariants. Pattern Recognition, 1993, 26(1): 167-174 [4] [4] Tomas S, Flusser J. Affine moment invariants generated by graph method. Pattern Recognition, 2011, 44(9): 2047-2056 [5] [5] Tomas S, Flusser J. Combined blur and affine moment invariants and their use in pattern recognition. Pattern Recognition, 2003, 36(12): 2895-2907 [6] [6] Rahtu E, Salo M, Heikkila J. Affine invariant pattern recognition using multi-scale autoconvolution. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(6): 908-918 [7] [7] Lindeberg T. Scale selection properties of generalized scale-space interest point detectors. Journal of Mathematical Imaging and Vision, 2013, 46(2): 177-210 [8] [8] Baumberg A. Reliable feature matching across widely separated views. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Hilton Head Island, South Carolina, USA: IEEE, 2000. 774-781 [9] [9] Mikolajczyk K, Schmid C. Scale affine invariant interest point detectors. International Journal of Computer Vision, 2004, 60(1): 63-86 [10] Lan R, Yang Jian-Wei, Jiang Yong, Song Zhan, Tang Yuan-Yan. An affine invariant discriminate analysis with canonical correlation analysis. Neurocomputing, 2012, 86(1): 184-192 [11] Morel JM, Yu Guo-Shen. ASIFT: a new framework for fully affine invariant image comparison. SIAM Journal on Imaging Sciences, 2009, 2(2): 438-469 [12] Cui Chun-Hui, Ngan K N. Scale-and affine-invariant fan feature. IEEE Transactions on Image Processing, 2011, 20(6): 1627-1640 [13] Ferraz L, Binefa X. A sparse curvature-based detector of affine invariant blobs. Journal of Computer Vision and Image Understanding, 2012, 116(4): 524-537 [14] Koenderink J J. The structure of images. Biological Cybernetics, 1984, 50(5): 363-370 [15] Koenderink J J, van Doorn A J. Representation of local geometry in the visual system. Biological Cybernetics, 1987, 55(6): 367-375 [16] Florack L M J, Romeny B M, Koenderink J J, Viergever M. General intensity transformations and differential invariants. Journal of Mathematical Imaging and Vision, 1994, 4(2): 171-187 [17] Koenderink J J, van Doorn A. The structure of visual spaces. Journal of Math Imaging Vision, 2008, 31(2-3): 171-187 [18] Lowe D G. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 2004, 60(2): 91-110 [19] Kadyrov A, Petrou M. The trace transform and its applications. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(8): 811-828 [20] Geusebroek J M, Burghouts G J, Smeulders A W M. The Amsterdam library of object images. International Journal of Computer Vision, 2005, 61(1): 103-112
点击查看大图
计量
- 文章访问数: 1975
- HTML全文浏览量: 78
- PDF下载量: 739
- 被引次数: 0