matchShapes computes the difference between two shapes
using the Hu invariants.
Arguments
- x1
Either a Nx2 matrix of the X-Y coordinates of a polygon (e.g., a contour produced by
findContours), or a single-channelImageobject.- x2
Either a Nx2 matrix of the X-Y coordinates of a polygon (e.g., a contour produced by
findContours), or a single-channelImageobject.- method
The comparison method to compute the difference between the two shapes (see Notes; default: "I1").
Note
The available shape matching methods are defined as follows:
\(I_1(A,B) = \sum _{i=1...7} \left | \frac{1}{m^A_i} - \frac{1}{m^B_i} \right |\)
\(I_2(A,B) = \sum _{i=1...7} \left | m^A_i - m^B_i \right |\)
\(I_3(A,B) = \max _{i=1...7} \frac{ \left| m^A_i - m^B_i \right| }{ \left| m^A_i \right| }\)
where
\(A\) denotes x1, \(B\) denotes x2.
\(m^A_i = \mathrm{sign} (h^A_i) \cdot \log{h^A_i}\)
\(m^B_i = \mathrm{sign} (h^B_i) \cdot \log{h^B_i}\)
and \(h^A_i, h^B_i\) are the Hu invariants of \(A\) and \(B\), respectively.
Author
Simon Garnier, garnier@njit.edu
Examples
dots <- image(system.file("sample_img/dots.jpg", package = "Rvision"))
dots_gray <- changeColorSpace(dots, "GRAY")
dots_bin <- dots_gray < 200
contours <- findContours(dots_bin)
contour0 <- contours$contours[contours$contours[, 1] == 0, 2:3]
contour1 <- contours$contours[contours$contours[, 1] == 1, 2:3]
matchShapes(contour0, contour1)
#> [1] 0.1503717