|
|
|
| Edge-enhanced maximally stable color regions |
| PAN Neng-jie, YU Hui-min |
| Department of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China |
|
|
|
Abstract The proposed edge-enhanced MSCR (EMSCR) integrated image edge information which had strong image blur robustness to enhance the detection of stable extremal regions. The edge information was got by the idea of assigning a probability of boundary for every pixel. Then the edge information was utilized by strengthening the differences between edge pixel and region interior pixel and weakening the differences between the region interior pixels. Stable color regions were detected at the Opponent color space which had better illumination invariance. Experimental results show that EMSCR improves the invariance of MSCR in almost all image transformations when holding the advantage of more corresponding region features. EMSCR improves the invariance of MSER in some image transformations, especially for image blur. The corresponding region features detected by EMSCR are also more than that detected by MSER．
|
|
Published: 04 August 2014
|
|
|
边缘加强型的彩色空间最稳极值区域
缘加强型的彩色空间最稳极值区域(EMSCR)利用对模糊变化具有较好鲁棒性的边缘信息来约束稳定极值区域的检测,通过加强边缘处像素点之间的差异性,减小区域内部像素点之间的差异性,从而提高模糊不变性；EMSCR采用具有良好光照不变性的Opponent颜色空间,使区域特征具有更好的光照不变性.实验表明,与MSCR相比,EMSCR在保持其具有丰富相关区域特征这一优点的同时,全面提高了其不变性,与MSER相比,EMSCR提高了部分不变性,尤其是对于图像模糊,不变性有大幅度的提高,且EMSCR所获得的相关区域特征明显多于MSER.
|
|
| 1］ MATAS J, CHUM O, URBAN M, et al. Robust wide baseline stereo from maximally stable extremal regions ［J］. Image and Vision Computing, 2004, 22(10): 761-767．
［2］ TUYTELAARS T, VAN GOOL L. Wide baseline stereo matching based on local, affinely invariant regions ［C］∥Proceedings of the 11th British Machine Vision Conference. Bristol: ［s.n.］, 2000: 412-425.
［3］ SCHMID C, MOHR R. Local grayvalue invariants for image retrieval ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(5): 530-535．
［4］ TUYTELAARS T, VAN GOOL L. Content-based image retrieval based on local affinely invariant regions ［C］∥ Proceedings of the 3rd International Conference on Visual Information and Information Systems. London: ［s.n.］, 1999: 493-500．
［5］ SCHAFFALITZKY F, ZISSERMAN A. Multi-view matching for unordered image sets, or “How do I organize my holiday snaps？” ［C］∥Proceedings of the 7th European Conference on Computer Vision. Copenhagen: ［s.n.］, 2002: 414-431．
［6］ MIKOLAJCZYK K, SCHMID C. Indexing based on scale invariant interest points ［C］∥Proceedings of the 8th International Conference on Computer Vision. Vancouver: ［s.n.］, 2001: 525-531．
［7］ MIKOLAJCZYK K, SCHMID C. Scale and affine invariant interest point detectors ［J］. International Journal of Computer Vision, 2004, 60(1): 63-68．
［8］ MIKOLAJCZYK K, TUYTELAARS T, SCHMID C, et al. A comparison of affine region detectors ［J］. International Journal of Computer Vision, 2005, 65(1/2): 43-72．
［9］ FORSSEN P E. Maximally stable color region for recognition and matching ［C］∥IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis: IEEE, 2007: 18．
［10］ PERDOCH M, MATAS J, OBDRZALEK S. Stable affine frame on Isophotes ［C］∥Proceedings of the 11th International Conference on Computer Vision. Rio de Janeiro: ［s.n.］, 2007: 18．
［11］ CHEN Hui-zhong, TSAI S S, SCHROTH G, et al. Robust text detection in natural images with edge-enhanced maximally stable extremal regions ［C］∥Proceedings of the 18th International Conference on Image Processing. Brussels: ［s.n.］, 2011: 2609-2612．
［12］ KIMMEL R, ZHANG Cui-ping, BRONSTEIN A M, et al. Are MSER features really interesting？ ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(11): 2316-2320．
［13］ MAIRE M, ARBELAEZ P, FOWLKES C, et al. Using contours to detect and localize junctions in natural images ［C］∥IEEE Conference on Computer Vision and Pattern Recognition. Anchorage: IEEE, 2008: 18．
［14］ FELZENSZWALB P F, HUTTENLOCHER D P. Distance transforms of sampled functions ［R］. USA: Cornell University, 2004．
［15］ VEDALDI A, FULKERSON B. VLFeat: an open and portable library of computer vision algorithms ［EB/OL］.\[2013-01-05\]. http:∥www.vlfeat.org/．
［16］ VAN DE SANDE K, GEVERS T, SNOEK C. Evaluating color descriptors for object and scene recognition ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(9): 1582-1596．
［17］ VGG, LEUVEN, INRIA, et al. Affine covariant features ［EB/OL］. \[2013-01-05\]. http:∥www.robots.ox.ac.uk/～vgg/research/affine/. |
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
| |
Shared |
|
|
|
|
| |
Discussed |
|
|
|
|
