delta.utilities

Click on the signatures below to get a complete description.

Module for utility functions and class definitions that are used in pipeline.py

A few functions are redundant from data.py, but we keep the files separate to minimize the risk of unforeseen bugs.

@author: jblugagne

Classes

Cell
CroppingBox
Lineage()	Class for cell lineages contained in each ROI
files_watcher(reader)	Daemon to watch experiment files and signal new ones (not functional yet)
xpreader([filename, channelnames, ...])	Class to read experiment files from bioformats-compatible files or from file sequences in folders

Functions

cell_area(contour)	Area of a single cell
cell_fluo(fluo_frames, mask[, roi_box])	Extract mean fluorescence level from mask
cell_perimeter(contour)	Get single cell perimeter
cell_width_length(contour)	Mesure width and length of single cell
create_windows(img[, target_size, min_overlap])	Crop input image into windows of set size.
cropbox(img, box)	Crop image
deskew(image)	Compute the rotation angle to apply to the image to remove its rotation.
division_poles(poles_cell1, poles_cell2, ...)	Identify which poles belong to the mother and which to the daughter
driftcorr(img[, template, box, drift])	Compute drift between current frame and the reference, and return corrected image
eucl(p1, p2)	Euclidean point to point distance
extract_poles(end_img, labels)	Extract poles per cell from ends image
extrema_poles(cellmask[, scaling])	A slower and more rudimentary version of poles finding but that is guaranteed to find exactly 2 poles
find_contours(mask)	wrapper for CV2's findContours() because it keeps changing signatures
findfirst(mylist)	Find first non-zero element of list
getAttributions(scores)	Get attribution matrix from tracking scores
getDriftTemplate(chamberboxes, img[, ...])	This function retrieves a region above the chambers to use as drift template
getROIBoxes(chambersmask)	Extract the bounding boxes of the chambers in the binary mask produced by the chambers identification unet
getTrackingScores(labels, outputs[, boxes])	Get overlap scores between input/target cells and tracking outputs
getcellsinframe(labels[, return_contours, ...])	Get numbers of cells present in frame, sorted along Y axis
getcentroid(contour)	Get centroid of cv2 contour
getpoles(seg[, labels, scaling])	Get cell poles
getrandomcolors(num_colors[, seed])	Pseudo-randomly generate list of random hsv colors.
getshiftvalues(shift, img_shape, cb)	Parameters
gettrackingboxes(cell[, frame_shape, ...])	Get a crop box and a fill box around a cell that fits the tracking target size
getxppathdialog([ask_folder])	Pop up window to select experiment file or folder.
image_edges(contour, image)	Identify if cell touches image borders
imrotate(frame, rotate)	Rotate image
label_seg(seg[, cellnumbers, ...])	Label cells in segmentation mask
loadmodels([toload])	Load models (as specified in config.py)
opencv_areafilt(I[, min_area, max_area])	Area filtering using openCV instead of skimage
rangescale(frame, rescale)	Rescale image values to be within range
roi_features(labels_frame[, features, ...])	Extract single-cell morphological and fluorescence features
singlecell_features(contour, mask[, ...])	Extract features for a single cell
skeleton_poles(skel)	This function was adapted from stackoverflow #https://stackoverflow.com/questions/26537313/how-can-i-find-endpoints-of-binary-skeleton-image-in-opencv
stitch_pic(results, loc_y, loc_x)	Stitch segmentation back together from the windows of create_windows()
track_poles(poles, prev_old, prev_new)	Track poles of a cell to the previous old and new poles
two_poles(poles)	Sometimes the skeleton produces more than 2 poles.
vidwrite(images, filename[, crf, verbose])	Write images stack to video file with h264 compression.