MblobSelectFeature

Determines a measure of the true breadth of an object, with the same advantages and disadvantages as M_LENGTH.

Determines the indices which differentiate each chain's pixels within a specified blob. The index of the blob's outermost chain is 1. Chains that delimit holes in blobs are identified by subsequent indices for each chain.

Determines the X-coordinate of each chained pixel in the specified blob, for all chains contained within the blob (both the pixels bordering a blob and those delimiting its holes). Chained pixels always form a closed chain. This implies that the starting pixel in the chain is also the closing one. If your blob has regions which are 1 pixel wide, these pixels are chained twice, once in the forward direction and then in the opposite direction.

Blobs with holes have multiple chains. To determine the chain to which this pixel's X-coordinate belongs, use M_CHAIN_INDEX.

Determines the Y-coordinate of each chained pixel in the specified blob, for all chains contained within the blob (both the pixels bordering a blob and those delimiting its holes). Chained pixels always form a closed chain. This implies that the starting pixel in the chain is also the closing one. If your blob has regions which are 1 pixel wide, these pixels are chained twice, once in the forward direction and then in the opposite direction.

Blobs with holes have multiple chains. To determine the chain to which this pixel's Y-coordinate belongs, use M_CHAIN_INDEX.

Determines the ratio between the area of a circle with the same perimeter as the blob in question, and the area of the blob itself. The minimum theoretical value of 1.0 is obtained if the blob is a perfect circle. In practice, the minimum obtainable value is slightly above 1. This is due to the effect of square pixel discretization. The more convoluted the shape, the greater the value.

The formula used is equal to where A is the area of the blob and p is the perimeter of the blob.

In the illusration above, the blobs have similar sizes but can be distinguised by their shapes. The compactness of the left blob is slightly above 1.0, while the compactness of the right blob is 1.24.

Determines the ratio between the area of a blob and the area of the blob's convex hull.

In the example above, the left blob has a convex hull fill ratio of 1.0 whereas the middle and rightmost blobs have a convex hull fill ratio of 0.9.

Determines the perimeter of the convex hull of a blob. The perimeter is calculated by summing up the distance between every 2 consecutive points on the convex hull of a blob.

For a quicker result, you can select to calculate the approximation of this perimeter using M_CONVEX_PERIMETER.

Determines the X-coordinate of each point on the convex perimeter of a blob. Convex perimeter pixels always form a closed figure. This implies that the starting pixel on the convex perimeter is also the closing one.

Determines the X- and Y-coordinate of each point on the convex perimeter of a blob. Convex perimeter pixels always form a closed figure. This implies that the starting pixel on the convex perimeter is also the closing one.

Determines the Y-coordinate of each point on the convex perimeter of a blob. Convex perimeter pixels always form a closed figure. This implies that the starting pixel on the convex perimeter is also the closing one.

Determines the approximation of the perimeter of the convex hull of a blob. It is derived from several Feret diameters; so, a larger number of Ferets gives a more accurate result.

For a more accurate result, you can select to calculate M_CONVEX_HULL_PERIMETER.

Determines a value that is equal to M_LENGTH / M_BREADTH. It is similar to M_FERET_ELONGATION, except that it should be used for long thin objects.

Determines the number of blobs - number of holes. This value is more useful for M_WHOLE_IMAGE than for M_INDIVIDUAL processing mode.

Determines the Feret diameter at the principal axis of a blob.

The principal axis is the axis at which the blob has the least moment of inertia. Also, if the blob is symmetrical, the principal axis is aligned with the blob's axis of symmetry.

Determines the Feret diameter at the secondary axis of a blob.

The secondary axis is perpendicular to the principal axis.

Determines the measure of the shape of a blob. It is equal to M_FERET_MAX_DIAMETER / M_FERET_MIN_DIAMETER.

It is accurate for reasonably compact objects, but becomes less accurate for very elongated objects (because M_FERET_MIN_DIAMETER becomes less accurate). For very elongated objects, M_ELONGATION should be used.

Determines the angle at which the maximum Feret diameter is found. The value is in degrees, with positive values indicating a counter-clockwise displacement from the positive X-axis.

Determines the largest Feret diameter found after checking a certain number of angles. More angles will give a more accurate result, but will take longer to calculate. However, the maximum Feret diameter is not very sensitive to the number of angles, and 8 usually gives an accurate result.

Determines the ratio of the maximum Feret diameter by its perpendicular Feret diameter.

Determines the angle at which the minimum Feret diameter is found. The value is in degrees, with positive values indicating a counter-clockwise displacement from the positive X-axis.

Determines the smallest Feret diameter found after checking a certain number of angles. More angles will give a more accurate result, but will take longer to calculate. Note that this feature will not be very accurate for long thin blobs. However, you can get an accurate measure of the breadth of long thin blobs more quickly using M_BREADTH.

Determines the ratio of the minimum Feret diameter by its perpendicular Feret diameter.

Determines the ratio of the Feret diameter at the principal axis to the Feret diameter at the secondary axis. It is equal to M_FERET_AT_PRINCIPAL_AXIS_ANGLE / M_FERET_AT_SECONDARY_AXIS_ANGLE.

Determines the dimension of the minimum bounding box of a blob in the horizontal direction; that is, M_BOX_X_MAX - M_BOX_X_MIN + 1.

Determines the dimension of the minimum bounding box of a blob in the vertical direction; that is, M_BOX_Y_MAX - M_BOX_Y_MIN + 1.

Determines (along with M_FIRST_POINT_Y) a unique point for each object, that is always on the perimeter of the object. The X-coordinate is that of the left-most pixel on the top-most line of the object.

Determines (along with M_FIRST_POINT_X) a unique point for each object, that is always on the perimeter of the object. The Y-coordinate is that of the topmost line of the object.

Determines the general Feret diameter at an angle specified using MblobSelectFeret(). If you don't call MblobSelectFeret() before performing a calculation, a MIL error will be generated.

Determines the number of times a transition from background to foreground (not vice versa) occurs in the horizontal direction for the entire blob. In other words, it is equal to the number of times the neighborhood configuration [ B, F ] occurs in a blob, where B is a background pixel and F is a foreground pixel.

Determines the label value for each blob in an image. This is a positive integer (>= 1) that is unique for each blob. This feature is always calculated; you do not need to select it.

Determines the measure of the true length of an object, although it can only be applied to certain object types because it is derived from the perimeter (P) and area (A) assuming that P = 2(length + breadth) and A = length x breadth. It complements M_FERET_MAX_DIAMETER because it is accurate for different blob types (for example, long thin ones). Note, it is calculated much faster than the maximum Feret diameter.

Determines the angle of the minimum-area bounding box of a blob. The angle is always measured from the X-axis to the side from which the width is measured.

Determines the height of the minimum-area bounding box of a blob. The height is always taken as the shortest side of the box.

Determines the width of the minimum-area bounding box of a blob. The width is always taken as the longest side of the box.

Determines the X-coordinate of the n ^th vertex of the minimum-area bounding box of a blob, where n stands for an integer between 1 and 4.

Note that due to potential rotations of the bounding box, the labelling of the vertices might be inconsistent.

Determines the Y-coordinate of the n ^th vertex of the minimum-area bounding box of a blob, where n stands for an integer between 1 and 4.

Note that due to potential rotations of the bounding box, the labelling of the vertices might be inconsistent.

Determines the angle of the minimum-perimeter bounding box of a blob. The angle is always measured from the X-axis to the side from which the width is measured.

Determines the height of the minimum-perimeter bounding box of a blob. The height is always taken as the shortest side of the box.

Determines the width of the minimum-perimeter bounding box of a blob. The width is always taken as the longest side of the box.

Determines the X-coordinate of the n ^th vertex of the minimum-perimeter bounding box of a blob, where n stands for an integer between 1 and 4.

Note that due to potential rotations of the bounding box, the labelling of the vertices might be inconsistent.

Determines the Y-coordinate of the n ^th vertex of the minimum-perimeter bounding box of a blob, where n stands for an integer between 1 and 4.

Note that due to potential rotations of the bounding box, the labelling of the vertices might be inconsistent.

Determines a value that is equal to the number of holes in a blob. Holes that intersect the edge of the image are not counted (they might not be holes). This value is equal to 1 - M_EULER_NUMBER and is therefore a true hole count only in M_INDIVIDUAL processing mode.

Determines a value that is equal to the total number of runs in a blob. A run is defined as a horizontal string of consecutive foreground pixels.

Determines the total length of edges in a blob (including the edges of any holes), with an allowance made for the staircase effect that is produced when diagonal edges are digitized (inside corners are counted as 1.414, rather than 2.0). A single pixel blob (area = 1) has a perimeter of 4.0.

Determines the degree to which a blob resembles a rectangle. To do this, MblobSelectFeature() calculates the ratio of the blob's area to the product of its minimum Feret diameter and the Feret diameter perpendicular to the minimum Feret diameter.

The three blobs above have the same minimum Feret diameter and the same Feret diameter perpendicular to the minimum Feret diameter. Only their shape and area differs. The rectangularity of the left blob is 1.0, indicating a perfect rectangle. The rectangularity of the middle blob is 0.8 and the rectangularity of the rightmost blob is 0.5.

Determines a measure of how rough a blob is and is equal to M_PERIMETER / M_CONVEX_PERIMETER. A smooth convex object will have the minimum roughness of 1.0.

In the example above, the left blob has a roughness of 1.0, the middle blob has a roughness of 1.1, and the right blob has a roughess of 1.5.

Determines an X-coordinate that touches the maximum Y-coordinate of a blob, calculated in the relative coordinate system. In the case where more than one X-coordinate touches the maximum Y-coordinate of a blob, it cannot be specified which X-coordinate will be calculated and returned.

Determines an X-coordinate that touches the minimum Y-coordinate of a blob, calculated in the relative coordinate system. In the case where more than one X-coordinate touches the minimum Y-coordinate of a blob, it cannot be specified which X-coordinate will be calculated and returned.

Determines an Y-coordinate that touches the maximum X-coordinate of a blob, calculated in the relative coordinate system. In the case where more than one T-coordinate touches the maximum X-coordinate of a blob, it cannot be specified which Y-coordinate will be calculated and returned.

Determines an Y-coordinate that touches the minimum X-coordinate of a blob, calculated in the relative coordinate system. In the case where more than one Y-coordinate touches the minimum X-coordinate of a blob, it cannot be specified which Y-coordinate will be calculated and returned.

Determines the maximum X-coordinate at the maximum Y-coordinate of a blob, calculated in the pixel coordinate system. Together with M_BOX_Y_MAX, this determines one of the contact points on the convex perimeter of the blob.

Determines the maximum X-coordinate at the minimum Y-coordinate of a blob, calculated in the pixel coordinate system. Together with M_BOX_Y_MIN, this determines one of the contact points on the convex perimeter of the blob.

Determines the minimum X-coordinate at the maximum Y-coordinate of a blob, calculated in the pixel coordinate system. Together with M_BOX_Y_MAX, this determines one of the contact points on the convex perimeter of the blob.

Determines the minimum X-coordinate at the minimum Y-coordinate of a blob, calculated in the pixel coordinate system. Together with M_BOX_Y_MIN, this determines one of the contact points on the convex perimeter of the blob.

Determines the maximum Y-coordinate at the maximum X-coordinate of a blob, calculated in the pixel coordinate system. Together with M_BOX_X_MAX, this determines one of the contact points on the convex perimeter of the blob.

Determines the maximum Y-coordinate at the minimum X-coordinate of a blob, calculated in the pixel coordinate system. Together with M_BOX_X_MIN, this determines one of the contact points on the convex perimeter of the blob.

Determines the minimum Y-coordinate at the maximum X-coordinate of a blob, calculated in the pixel coordinate system. Together with M_BOX_X_MAX, this determines one of the contact points on the convex perimeter of the blob.

Determines the minimum Y-coordinate at the minimum X-coordinate of a blob, calculated in the pixel coordinate system. Together with M_BOX_X_MIN, this determines one of the contact points on the convex perimeter of the blob.

Determines the difference between the maximum and minimum pixel values of a blob. It is equal to M_MAX_PIXEL - M_MIN_PIXEL.

Determines the mean pixel value in a blob. It is equal to M_SUM_PIXEL / M_AREA.

Determines the standard deviation of pixel values in a blob. It is equal to , where N = number of pixels and p = pixel value.

Determines the angle at which a blob has the least moment of inertia. For elongated blobs, it is aligned with the longest axis. The result is always between -90° and +90°, measured in a counter-clockwise direction from the positive X-axis. It is calculated as:

Determines the angle perpendicular to M_AXIS_PRINCIPAL_ANGLE. It is always between -90° and +90°.

Determines the X-position of the center of gravity of a blob. The grayscale version is M_MOMENT_X1_Y0 / M_SUM_PIXEL. The binary version uses M_AREA instead of M_SUM_PIXEL.

Determines the Y-position of the center of gravity of a blob. The grayscale version is M_MOMENT_X0_Y1 / M_SUM_PIXEL. The binary version uses M_AREA instead of M_SUM_PIXEL.

Determines the necessary calculation of the central moment where the order of X equals 0 and the order of Y equals 2.

This central moment is defined as , where i and n are the lower and upper bounds of the summation respectively, p_i = value of a pixel (always 1 for binary moments), y_i = its Y-coordinate, = the first order ordinary moment about Y divided by the sum of the pixel values (M_SUM_PIXEL for grayscale values) p_i .

For central moments, coordinates are relative to each blob's center of gravity, as opposed to ordinary moments, which use coordinates that are relative to the image origin (top-left corner). Calculate higher moments by calling MblobSelectMoment().

Determines the necessary calculation of the central moment where the order of X equals 1 and the order of Y equals 1.

This central moment is defined as , where i and n are the lower and upper bounds of the summation respectively, p_i = value of a pixel (always 1 for binary moments), x_i = its X-coordinate and, y_i = its Y-coordinate, = the first ordinary order moment about X_i divided by the sum of the pixel values (M_SUM_PIXEL for grayscale values) p_i , and = the first order ordinary moment about Y_i divided by the sum of the pixel values (M_SUM_PIXEL for grayscale values) p_i .

For central moments, coordinates are relative to each blob's center of gravity, as opposed to ordinary moments, which use coordinates that are relative to the image origin (top-left corner). Calculate higher moments by calling MblobSelectMoment().

Determines the necessary calculation of the central moment where the order of X equals 2 and the order of Y equals 0.

This central moment is defined as , where i and n are the lower and upper bounds of the summation respectively, p_i = value of a pixel (always 1 for binary moments), x_i = its X-coordinate, = the first order ordinary moment about x_i divided by the sum of the pixel values (M_SUM_PIXEL for grayscale values) p_i .

For central moments, coordinates are relative to each blob's center of gravity, as opposed to ordinary moments, which use coordinates that are relative to the image origin (top-left corner). Calculate higher moments by calling MblobSelectMoment().

Determines the necessary calculation of the ordinary moment where the order of X equals 0 and the order of Y equals 1.

This ordinary moment is defined as , where i and n are the lower and upper bounds of the summation respectively, p_i = value of a pixel (always 1 for binary moments) and y_i = its Y-coordinate.

In order to calculate the weighted arithmetic mean about Y, take the result returned by the calculation of this feature and divide it by the M_SUM_PIXEL feature (for grayscale values).

For ordinary moments, coordinates are relative to the image origin (top-left corner), as opposed to central moments, which use coordinates that are relative to each blob's center of gravity. Calculate higher moments by calling MblobSelectMoment().

Determines the necessary calculation of the ordinary moment where the order of X equals 0 and the order of Y equals 2.

This ordinary moment is defined as , where i and n are the lower and upper bounds of the summation respectively, p_i = value of a pixel (always 1 for binary moments) and y_i = its Y-coordinate.

For ordinary moments, coordinates are relative to the image origin (top-left corner), as opposed to central moments, which use coordinates that are relative to each blob's center of gravity. Calculate higher moments by calling MblobSelectMoment().

Determines the necessary calculation of the ordinary moment where the order of X equals 1 and the order of Y equals 0.

This ordinary moment is defined as , where i and n are the lower and upper bounds of the summation respectively, p_i = value of a pixel (always 1 for binary moments) and x_i = its X-coordinate.

In order to calculate the weighted arithmetic mean about X, take the result returned by the calculation of this feature and divide it by the M_SUM_PIXEL feature (for grayscale values).

For ordinary moments, coordinates are relative to the image origin (top-left corner), as opposed to central moments, which use coordinates that are relative to each blob's center of gravity. Calculate higher moments by calling MblobSelectMoment().

Determines the necessary calculation of the ordinary moment where the order of X equals 1 and the order of Y equals 1.

This ordinary moment is defined as , where i and n are the lower and upper bounds of the summation respectively, p_i = value of a pixel (always 1 for binary moments), x_i = its X-coordinate and y_i = its Y-coordinate.

For ordinary moments, coordinates are relative to the image origin (top-left corner), as opposed to central moments, which use coordinates that are relative to each blob's center of gravity. Calculate higher moments by calling MblobSelectMoment().

Determines the necessary calculation of the ordinary moment where the order of X equals 2 and the order of Y equals 0.

This ordinary moment is defined as , where i and n are the lower and upper bounds of the summation respectively, p_i = value of a pixel (always 1 for binary moments) and x_i = its X-coordinate.

For ordinary moments, coordinates are relative to the image origin (top-left corner), as opposed to central moments, which use coordinates that are relative to each blob's center of gravity. Calculate higher moments by calling MblobSelectMoment().

Adds all 4 chain features. Note that the chain code is computed depending on the lattice and foreground values set with MblobControl().