Abstract | ||
---|---|---|
We propose a data structure that captures global geometric properties in images: Histogram of Mirror Symmetry Coefficients. We compute such a coefficient for every pair of pixels, and group them in a 6-dimensional histogram. By marginalizing the HMSC in various ways, we develop algorithms for a range of applications: detection of nearly-circular cells, location of the main axis of reflection symmetry, detection of cell-division in movies of developing embryos, detection of worm-tips and indirect cell-counting via supervised classification. Our approach generalizes a series of histogram-related methods, and the proposed algorithms perform with state-of-the-art accuracy. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/CVPR.2014.381 | CVPR |
Keywords | Field | DocType |
image classification,object detection,6-dimensional histogram,HMSC,cell-division detection,data structure,global geometric properties,histogram-related methods,mirror symmetry coefficient histograms,nearly-circular cell detection,reflection symmetry,supervised classification,worm-tips detection,biology,cell,circle fitting,geometric representation,histogram,hough transform,mirror symmetry | Reflection symmetry,Histogram,Data structure,Computer vision,Pattern recognition,Computer science,Histogram matching,Hough transform,Mirror symmetry,Artificial intelligence,Pixel,Image histogram | Conference |
ISSN | Citations | PageRank |
1063-6919 | 6 | 0.47 |
References | Authors | |
21 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Marcelo Cicconet | 1 | 28 | 7.08 |
Davi Geiger | 2 | 1050 | 353.66 |
Kristin C. Gunsalus | 3 | 9 | 1.19 |
M. Werman | 4 | 343 | 112.04 |