Blobs#

class Blobs(image: Any = None, kulpa: bool = True, binaryImage: bool = False, **kwargs: Any)[source]#

Find blobs and compute their attributes

Parameters:

image (Image, optional) – image to use, defaults to None
kulpa (bool, optional) – apply Kulpa’s correction factor to circularity, defaults to True
binaryImage (bool, optional) – if True, the input image is treated as a binary image for the purpose of moment calculation, otherwise greyscale moments are computed, defaults to False

Uses OpenCV functions findContours to find a hierarchy of regions represented by their contours, and boundingRect, moments to compute moments, perimeters, centroids etc.

A region is defined as a connected group of non-zero pixels, the particular values do not matter.

This class behaves like a list and each element of the list is a blob represented by a Blob instance

>>> from machinevisiontoolbox import Image
>>> img = Image.Read('sharks.png')
>>> blobs = img.blobs()
>>> len(blobs)
4
>>> blobs[0]
Blobs(nblobs=1)
>>> blobs.area
array([18465.5,  7509.5,  7523. , 14356. ])

The list can be indexed, sliced or used as an iterator in a for loop or comprehension, for example:

for blob in blobs:
    # do a thing
    pass

areas = [blob.area for blob in blobs]

However the last line can also be written as:

areas = blobs.area

since all methods return a scalar if applied to a single blob:

blobs[1].area

or a list if applied to multiple blobs:

blobs.area

A blob has many attributes:

Geometric attributes

Property	Description
`area`	The area of the blob.
`bbox`	The bounding box of the blob.
`umin`, `umax`	The horizontal extent of the bounding box.
`vmin`, `vmax`	The vertical extent of the bounding box.
`touch`	True if the blob touches the border of the image.
`fillfactor`	Ratio of blob area to bounding box area.
`bboxarea`	Area of the bounding box.

Moment attributes

Property	Description
`u`, `v`	The centroid (center of mass) of the blob.
`orientation`	Orientation of the equivalent ellipse.
`a, b`	The equivalent ellipse radii.
`aligned_box`	A rotated bounding box with sides parallel to the axes of the equivalent ellipse.
`moments`	The moments of the blob including central and normalised values up to 3rd order.
`humoments`	Seven Hu moment invariants (invariant to position, orientation and scale).

Boundary and shape attributes

Property	Description
`contour_point`	A point on the contour of the blob.
`perimeter`	A 2xN array of points on the perimeter of the blob.
`perimeter_length`	The perimeter length of the blob.
`circularity`	The circularity of the blob.
`perimeter_approx`	A polygonal approximation to the perimeter.
`perimeter_hull`	The convex hull of the perimeter.
`MEC`	The minimum enclosing circle.
`MER`	The minimum enclosing rectangle.

Hierarchy and region attributes

Property	Description
`color`	The value of pixels within the blob.
`children`	A list of references to child `Blob` instances.
`parent`	A reference to the parent `Blob` instance, or None if no parent.
`level`	The depth of the blob in the region tree.
`dotfile`	Write a GraphViz dot file representing the blob hierarchy.

Note

findContours can give surprising results for small images:

The perimeter length is computed between the mid points of the pixels, and the OpenCV function arcLength seems to underestimate the perimeter even more. The perimeter length is not the same as the number of pixels in the contour.
The area will be less than the number of pixels in the blob, because the area is computed from the moments of the blob, which are computed from the contour, see above.

References:

P. Corke, Robotics, Vision & Control for Python, Springer, 2023, Section 12.1.2.1.

Seealso:

filter sort opencv.moments, opencv.boundingRect, opencv.findContours

Methods

`aligned_box`(**kwargs)	Compute rectangle aligned with ellipse axes for blobs
`append`(item)	S.append(value) -- append value to the end of the sequence
`blob_frame`()	Transformation from blob coordinate frame to image frame
`clear`()
`copy`()
`count`(value)
`dotfile`([filename, direction, show])	Create a GraphViz dot file
`extend`(other)	S.extend(iterable) -- extend sequence by appending elements from the iterable
`filter`([area, circularity, color, touch, aspect])	Filter blobs
`humoments`(**kwargs)	Hu image moment invariants of blobs
`index`(value, [start, [stop]])	Raises ValueError if the value is not present.
`insert`(i, item)	S.insert(index, value) -- insert value before index
`label_image`([image])	Create label image from blobs
`perimeter_approx`(**kwargs)	Approximate perimeter of blob
`perimeter_hull`(**kwargs)	Convex hull of blob's perimeter
`plot_aligned_box`(args, *kwargs)	Plot aligned rectangles of blobs using Matplotlib
`plot_axes`(args, *kwargs)	Plot equivalent ellipse axes of blobs using Matplotlib
`plot_box`(args, *kwargs)	Plot a bounding box for the blob using Matplotlib
`plot_centroid`(*args[, label])	Plot the centroid of blobs using Matplotlib
`plot_ellipse`(args, *kwargs)	Plot the equivalent ellipses of blobs using Matplotlib
`plot_labelbox`([fmt, label])	Plot a labelled bounding box of blobs using Matplotlib
`plot_MEC`(args, *kwargs)	Plot minimum enclosing circles of blobs using Matplotlib
`plot_MER`(args, *kwargs)	Plot minimum enclosing rectangles of blobs using Matplotlib
`plot_perimeter`(*args[, show, epsilon, clockwise])	Plot the perimeter of blobs using Matplotlib
`polar`(**kwargs)	Boundary in polar coordinate form
`polarmatch`(target)	Compare polar profiles
`pop`([index])	Raise IndexError if list is empty or index is out of range.
`remove`(item)	S.remove(value) -- remove first occurrence of value.
`reverse`()	S.reverse() -- reverse IN PLACE
`sort`([by, reverse])	Sort blobs

Properties

`a`	Radius of equivalent ellipse
`area`	Area of the blob
`aspect`	Blob aspect ratio
`b`	Radius of equivalent ellipse
`bbox`	Bounding box
`bboxarea`	Area of the bounding box
`centroid`	Centroid of blob
`children`	Child blobs
`circularity`	Blob circularity
`color`	Blob color
`fillfactor`	Fill factor, ratio of area to bounding box area
`id`	Blob id number
`level`	Blob level in hierarchy
`MEC`	Minimum enclosing circle of blob
`MER`	Minimum enclosing rectangle of blob
`moments`	Moments of blobs
`orientation`	Blob orientation
`p`	Centroid point of blob
`parent`	Parent blob
`perimeter`	Perimeter of the blob
`perimeter_length`	Perimeter length of the blob
`touch`	Blob edge touch status
`uc`	u-coordinate of the blob centroid
`umax`	Maximum u-axis extent
`umin`	Minimum u-axis extent
`vc`	v-coordinate of the blob centroid
`vmax`	Minimum v-axis extent
`vmin`	Maximum v-axis extent