最大稳定极值区域（Maximally Stable Extremal Regions，簡稱MSER）是在计算机视觉领域中一种用于在图像中进行斑点检测的方法。这个方法由Matas等人提出，用于在两个不同视角的图片中寻找对应关系。这种方法从图像中提取全面的元素对应关系，有助于宽基线匹配（wide-baseline matching），以及更好的立体匹配和物体识别算法。
其他应用
- [http://www.cs.ubc.ca/~lowe/papers/07forssen.pdf Shape Descriptors for Maximally Stable Extremal Regions]
- [http://www.icg.tugraz.at/pub/pubobjects/docvpr2006 Efficient Maximally Stable Extremal Region (MSER) Tracking]
- [http://www.bmva.org/bmvc/2006/papers/276.pdf N-tree Disjoint-Set Forests for Maximally Stable Extremal Regions]
- [http://www.cs.ucsd.edu/classes/fa05/cse252c/hewitt-2.pdf Video Google and Object Level Grouping for Video Shots]
- [http://www.eecg.toronto.edu/~maclean/9501292851/iscas2007-Kristensen.pdf Real-Time Extraction of Maximally Stable Extremal Regions on an FPGA]
- [https://web.archive.org/web/20110610230652/http://www.cs.ubc.ca/~perfo/papers/forssen_cvpr07.pdf Maximally Stable Colour Regions for Recognition and Matching]
参见
*斑点检测
*特征检测
外部链接
- [http://www.vlfeat.org/ VLFeat] , an open source computer vision library in C (with a MEX interface to MATLAB), including an implementation of MSER
- [https://web.archive.org/web/20091029150308/http://opencv.willowgarage.com/wiki/ OpenCV], an open source computer vision library in C/C++, including an implementation of Linear Time MSER
- [https://web.archive.org/web/20110726051203/http://www.featurespace.org/code.htm Detector Repeatabilty Study], Kristian Mikolajczyk Binaries (Win/Linux to compute MSER/HarrisAffine... . Binary used in his repeatability study.
参考文献
评论 (0)