h1. MSER

h2. OpenCV functions for MSER extraction

(From the source code: src/cv/cvmser.cpp):

# there are two different implementation of MSER: one for grey image, one for color image

# the grey image algorithm is taken from: Linear Time Maximally Stable Extremal Regions; the paper claims to be faster than union-find method; it actually get 1.5~2m/s on my centrino L7200 1.2GHz laptop.

# the color image algorithm is taken from: Maximally Stable Colour Regions for Recognition and Match; it should be much slower than grey image method ( 3~4 times ); the chi_table.h file is taken directly from paper's source code which is distributed under GPL.

# though the name is *contours*, the result actually is a list of point set.

h2. Parameters description

(From the source code: features2d/features2d.hpp):

<pre>

int delta; //! delta, in the code, it compares (size_{i}-size_{i-delta})/size_{i-delta}

int maxArea; //! prune the area which bigger than maxArea

int minArea; //! prune the area which smaller than minArea

float maxVariation; //! prune the area have simliar size to its children

float minDiversity; //! trace back to cut off mser with diversity < min_diversity

The next few params for MSER of color image:

int maxEvolution; //! for color image, the evolution steps

double areaThreshold; //! the area threshold to cause re-initialize

double minMargin; //! ignore too small margin

int edgeBlurSize; //! the aperture size for edge blur

</pre>