Segmentation methods

The module rois has a collection of functions to segment and find regions of interest in audio and spectrograms.

Temporal (1D)

find_rois_cwt(s, fs, flims, tlen[, th, ...])

Find region of interest using known estimates of signal length and frequency limits.

Spectro-temporal (2D)

create_mask(im[, mode_bin, verbose, ...])	Binarize an image based on a double threshold.
select_rois(im_bin[, min_roi, max_roi, ...])	Select regions of interest based on its dimensions.
rois_to_imblobs(im_zeros, rois)	Take a matrix full of zeros and add ones in delimited regions defined by rois.
template_matching(Sxx, Sxx_template, tn, ...)	Use normalized spectrogram cross-correlation to detect the occurrence of a template sound in a target audio.
spectrogram_local_max(Sxx, tn, fn, ext, ...)	Find peaks on spectrogram as coordinate list in time and frequency