Classify Objects classifies objects into different classes according to the value of measurements you choose.
This module classifies objects into a number of different bins according to the value of a measurement (e.g., by size, intensity, shape). It reports how many objects fall into each class as well as the percentage of objects that fall into each class. The module asks you to select the measurement feature to be used to classify your objects and specify the bins to use. It also requires you to have run a measurement or
CalculateMath previous to this module in the pipeline so that the measurement values can be used to classify the objects.
There are two flavors of classification:
- The first classifies each object according to the measurements you choose and assigns each object to one class per measurement. You may specify more than two classification bins per measurement.
- The second classifies each object according to two measurements and two threshold values. The module classifies each object once per measurement resulting in four possible object classes. The module then stores one measurement per object, based on the object's class.
Note that objects without a measurement are not counted as belonging in a classification bin and will not show up in the output image (shown in the module display window); in the object classification they will have a value of False for all bins. However, they are still counted in the total number of objects and hence are reflected in the classification percentages.
Available measurements
- Image measurements:
- NumObjectsPerBin: The number of objects that are classified into each bin.
- PctObjectsPerBin: The percentage of total objects that are classified into each bin.
- Object measurements:
- Single measurement: Classification (true/false) of the Nth bin for the Mth measurement.
- Two measurement: Classification (true/false) of the 1st measurement versus the 2nd measurement binned into bins above ("high") and below ("low") the cutoff.
See also CalculateMath and any of the modules in the Measure category.
Settings:
Make each classification decision on how many measurements?
This setting controls how many measurements are used to make a classifications decision
for each object:
- Single measurement: Classifies each object based on a single measurement.
- Pair of measurements: Classifies each object based on a pair of measurements taken
together (that is, an object must meet two criteria to belong to a class).
Select the object to be classified
The name of the objects to be classified. You can
choose from objects created by any previous module. See
IdentifyPrimaryObjects, IdentifySecondaryObjects, or
IdentifyTertiaryObjects.
Select the measurement to classify by
Select a measurement made by a previous module. The objects
will be classified according to their values for this
measurement.
Select bin spacing
You can either specify bins of equal size, bounded by
upper and lower limits, or you can specify custom values that
define the edges of each bin with a threshold.
Note: If you would like two bins, choose Custom-defined bins and then provide a single threshold when asked.
Evenly spaced bins creates the indicated number of bins
at evenly spaced intervals between the low and high threshold.
You also have the option to create bins for objects that fall below
or above the low and high threhsold
Number of bins
This is the number of bins that will be created between
the low and high threshold
Lower threshold
(Used only if Evenly spaced bins selected)
This is the threshold that separates the lowest bin from the
others. The lower threshold, upper threshold, and number of bins
define the thresholds of bins between the lowest and highest.
Use a bin for objects below the threshold?
Select Yes if you want to create a bin for objects
whose values fall below the low threshold. Select No
if you do not want a bin for these objects.
Upper threshold
(Used only if Evenly spaced bins selected)
This is the threshold that separates the last bin from
the others.
Note: If you would like two bins, choose Custom-defined bins.
Use a bin for objects above the threshold?
Select Yes if you want to create a bin for objects
whose values are above the high threshold.
Select No if you do not want a bin for these objects.
Enter the custom thresholds separating the values between bins
(Used only if Custom thresholds selected)
This setting establishes the threshold values for the
bins. You should enter one threshold between each bin, separating
thresholds with commas (for example, 0.3, 1.5, 2.1 for four bins).
The module will create one more bin than there are thresholds.
Give each bin a name?
Select
Yes to assign custom names to bins you have
specified.
Select No for the module to automatically
assign names based on the measurements and the bin number.
Enter the bin names separated by commas
(Used only if Give each bin a name? is checked)
Enter names for each of the bins, separated by commas.
An example including three bins might be First,Second,Third.
Retain an image of the classified objects?
Select Yes to keep an image of the objects which is color-coded according
to their classification, for use later in the pipeline (for example,
to be saved by a SaveImages module).
Name the output image
Enter the name to be given to the classified object
image.
Select the object name
Choose the object that you want to measure from the list.
This should be an object created by a previous module such as
IdentifyPrimaryObjects, IdentifySecondaryObjects, or
IdentifyTertiaryObjects.
Select the first measurement
Choose a measurement made on the above object. This is
the first of two measurements that will be contrasted together.
The measurement should be one made on the object in a prior
module.
Method to select the cutoff
Objects are classified as being above or below a cutoff
value for a measurement. You can set this cutoff threshold in one
of three ways:
- Mean: At the mean
of the measurement's value for all objects in the image cycle.
- Median: At the median of the
measurement's value for all objects in the image set.
- Custom: You specify a custom threshold value.
Enter the cutoff value
This is the cutoff value separating objects in the two
classes.
Select the second measurement
Select a measurement made on the above object. This is
the second of two measurements that will be contrasted together.
The measurement should be one made on the object in a prior
module.
Method to select the cutoff
Objects are classified as being above or below a cutoff
value for a measurement. You can set this cutoff threshold in one
of three ways:
- Mean: At the mean
of the measurement's value for all objects in the image cycle.
- Median: At the median of the
measurement's value for all objects in the image set.
- Custom: You specify a custom threshold value.
Use custom names for the bins?
Select Yes if you want to specify the names of each bin
measurement.
Select No to create names based on the
measurements. For instance, for
"Intensity_MeanIntensity_Green" and "Intensity_TotalIntensity_Blue",
the module generates measurements such as
"Classify_Intensity_MeanIntensity_Green_High_Intensity_TotalIntensity_Low".
Enter the low-low bin name
(Used only if using a pair of measurements)
Name of the measurement for objects that
fall below the threshold for both measurements.
Enter the low-high bin name
(Used only if using a pair of measurements)
Name of the measurement for objects whose
first measurement is below threshold and whose second measurement
is above threshold.
Enter the high-low bin name
(Used only if using a pair of measurements)
Name of the measurement for objects whose
first measurement is above threshold and whose second measurement
is below threshold.
Enter the high-high bin name
(Used only if using a pair of measurements)
Name of the measurement for objects that
are above the threshold for both measurements.
Retain an image of the classified objects?
Select Yes to retain the image of the objects color-coded according
to their classification, for use later in the pipeline (for example,
to be saved by a SaveImages module).
Enter the image name
(Used only if the classified object image is to be retained for later use in the pipeline)
Enter the name to be given to the classified object image.