harm.quant(Coo, id = 1:Coo@coo.nb, smooth.it = 0, harm.range= seq(8, 32, 6),
scale = FALSE, center = TRUE, align = FALSE,
plot = TRUE, legend = TRUE, palette = col.summer, lineat.y=c(1, 5, 10))
harm.qual(Coo, id = 1, smooth.it = 0, harm.range= c(1, 2, 4, 8, 16, 32),
scale = FALSE, center = TRUE, align = FALSE, method = c("stack", "panel")[1],
legend = TRUE,
palette = col.summer, shp.col="#70809033", shp.border="#708090EE")
harm.pow(Coo, id=1:Coo@coo.nb, probs=c(0, 0.5, 1), nb.h = 24,
drop = 1, smooth.it = 0, plot = TRUE,
legend = TRUE, title="Fourier power spectrum",
lineat.x=seq(0, nb.h, by=6), lineat.y=c(0.9, 0.99), bw=0.1)Coo objectinteger. The id of the shape to display. A range of ids can be passed to harm.powvector of numeric, to define quantiles to calculate ; see quantileinteger. The number of smoothing iteration to perform.vector of integer giving the harmonic range to calculate. See nb.h for harm.pow.integer. The maximal number of harmonics to calculate.logical. Whether to scale or not the shape.logical. Whether to center or not the shape.logical. Whether to align or not the shape.logical. Whether to plot or not the shape. If FALSE, only the results are returned.harm.qual. If "stack" outlines are plotted on the same same, if "panel", separate reconstructions are plotted.logical. Whether to display a legend box.character. The title to add.logical. Whether to drop the first harmonic for plotting and power calculation.vector of numeric to specify where to plot dashed lines on the x-axis.vector of numeric to specify where to plot dashed lines on the y-axis.numeric. The width of horizontal segments drawn for each harmonic.harm.quant returns a matrix containing deviations for each harmonic and corresponding quantiles.
harm.pow returns a matrix containing cumulated harmonic power for each harmonic.harm.quant is based on euclidean distance between original and reconstructed outlines harm.pow returns and plot cumulated harmonic power. The power of a given harmonic $n$ is calculated as follows:
$$HarmonicPower_n= \frac{A^2_n+B^2_n+C^2_n+D^2_n}{2}$$data(bot)
harm.quant(bot)
harm.qual(bot)
harm.pow(bot)Run the code above in your browser using DataLab