最大穩定極值區域
外觀
特徵檢測 |
---|
邊緣檢測 |
角檢測 |
斑點檢測 |
脊檢測 |
霍夫變換 |
結構張量 |
仿射不變特徵檢測 |
特徵描述 |
尺度空間 |
最大穩定極值區域(Maximally Stable Extremal Regions,簡稱MSER)是在計算機視覺領域中一種用於在圖像中進行斑點檢測的方法。這個方法由Matas等人[1]提出,用於在兩個不同視角的圖片中尋找對應關係。這種方法從圖像中提取全面的元素對應關係,有助於寬基線匹配(wide-baseline matching),以及更好的立體匹配和物體識別算法。
其他應用
[編輯]- Shape Descriptors for Maximally Stable Extremal Regions (頁面存檔備份,存於互聯網檔案館)
- Efficient Maximally Stable Extremal Region (MSER) Tracking (頁面存檔備份,存於互聯網檔案館)
- N-tree Disjoint-Set Forests for Maximally Stable Extremal Regions (頁面存檔備份,存於互聯網檔案館)
- Video Google and Object Level Grouping for Video Shots
- Real-Time Extraction of Maximally Stable Extremal Regions on an FPGA (頁面存檔備份,存於互聯網檔案館)
- Maximally Stable Colour Regions for Recognition and Matching
參見
[編輯]外部連結
[編輯]- VLFeat (頁面存檔備份,存於互聯網檔案館), an open source computer vision library in C (with a MEX interface to MATLAB), including an implementation of MSER
- OpenCV, an open source computer vision library in C/C++, including an implementation of Linear Time MSER
- Detector Repeatabilty Study, Kristian Mikolajczyk Binaries (Win/Linux to compute MSER/HarrisAffine... . Binary used in his repeatability study.
參考文獻
[編輯]- ^ J. Matas, O. Chum, M. Urban, and T. Pajdla. "Robust wide baseline stereo from maximally stable extremal regions." (頁面存檔備份,存於互聯網檔案館) Proc. of British Machine Vision Conference, pages 384-396, 2002.