### Clean-up > Reject Features

Removes objects or fills holes based on their selected parameters being above or below a specified threshold. Parameter options include area, eccentricity, convex area/area ratio, and many more. Neighborhood conditionals are also optional, where features will only be removed if they meet both the parameter and neighborhood criteria.

### 1. Feature Parameter

Determines the measurement that will be considered for each features potential rejection. Features will be rejected based on whether they are above or below the measurement threshold you specify.

**Area:**Area of each feature.**Area Fraction:**Area fraction occupied by each feature relative to entire image.**Aspect Ratio**: Ratio of the major and minor axis lengths of each feature.**Average Neighbor**: Each feature’s average distance to its neighbors, as defined by the features’ Delaunay triangulation. Triangulation and distance are both calculated from the features’ centroids.**Caliper Diameter**: Largest line length that fits across each feature. Equivalently, the distance between the two points in the feature farthest from each other, including those points.**Convex Area:**Area of each feature’s tightest-fitting convex hull.**Eccentricity:**Describes how elongated or circular each feature is. 0 is a perfect circle. 1 is a straight line.**Equivalent Diameter:**Diameter of each feature if each was a circle of the same area.**Feature Number:**Numbers that are assigned to features when measurements are generated.**Filled Area:**Area of each feature with holes filled in.**Filled Area/Area:****First Moment of Inertia:**First moment of each feature. Describes how much feature area is extended away from its centroid.**First Moment of Inertia/Area:**Ratio between the first moment of each feature and its area.**Intensity Mean:***(requires grayscale Companion Image)*Grayscale intensity average of the entire Current Image.**Intensity StdDev:***(requires grayscale Companion Image)*Grayscale intensity standard deviation of the entire Current Image.**Intensity Sum:***(requires grayscale Companion Image)*Grayscale intensity sum over the entire Current Image.**Length – X:**Length of each feature’s bounding box in the X-direction.**Length – Y**: Length of each feature’s bounding box in the Y-direction.**Major Axis Length:**Major axis length of ellipse fit to each feature.**Minor Axis Length:**Minor axis length of ellipse fit to each feature.**Moment Invariant (Omega-1):**High-order moment which describes shape properties of each feature [1,2].**Moment Invariant (Omega-2):**High-order moment which describes shape properties of each feature [1,2].**Moment Invariant (Phi-1):**High-order moment which describes shape properties of each feature [1,2].**Moment Invariant (Phi-2):**High-order moment which describes shape properties of each feature [1,2].**Nearest Neighbor**: Each feature’s distance to the closest other feature, calculated from the features’ centroids.**Orientation:**Angle of the ellipse fit to each feature with respect to the positive X-axis. Positive angles are clockwise rotations and negative counterclockwise.**Perimeter:**Length of perimeter of each feature.**Perimeter/Area:**Perimeter of each feature relative to its area.**Roughness:**Ratio between the area of tightest-fitting convex hull and the area of each feature.**Roundness:**Ratio of equivalent diameter to caliper diameter (see above).

### 2. Features, Edge Features, Units

**Features**: You can choose which features you want to be rejected between white and black.**Edge Features**: You can choose to include or ignore edge features when choosing features to reject. You can also choose to only reject edge features.**Units**: The units you would like use to reject features.

### 3. Threshold Value

Select the threshold value (of the set measurement) for rejecting features and specify whether you would like to reject or keep features below the threshold value.

### 4. Proximity Awareness

Lets you consider the features above or below the threshold as *candidates* for removal, but only actually removed them if their neighbors pass the specified threshold.

**Less Than / =, Greater Than / =:**Choose whether neighboring features must be less than or equal to, or greater than or equal to, in order to pass the threshold.**None:**Do not use neighborhood conditionals**Within Distance**: Consider features whose centroids are within certain distance. Enter distance in which to search (in pixels);

-**Number:**Consider number of features. Enter critical number of features.

-**Total Area:**Consider total area of features. Enter critical total area (in pixels).

-**Average Area:**Consider average area of features. Enter critical average area (pixels).**Local Window**: Consider local window about each feature, including partial neighboring features.

-**Number:**Consider number of features. Enter critical number of features.

-**Total Area:**Consider total area of features. Enter critical total area (in pixels).

-**Average Area:**Consider average area of features. Enter critical average area (pixels).

## References

[1] Rosin, Paul L. 2003. “Measuring Shape: Ellipticity, Rectangularity, and Triangularity.” Machine Vision and Applications 14 (3): 172–184.

[2] MacSleyne, J P, J P Simmons, and M De Graef. 2008. “On the Use of Moment Invariants for the Automated Analysis of 3D Particle Shapes.” Modelling and Simulation in Materials Science and Engineering 16 (4) (June 1): 045008.

Need more help with this?

Chat with an expert now ››