OpenCV  3.4.20-dev
Open Source Computer Vision
Contour Properties

Prev Tutorial: Contour Features

Next Tutorial: Contours : More Functions

Goal

1. Aspect Ratio

It is the ratio of width to height of bounding rect of the object.

\[Aspect \; Ratio = \frac{Width}{Height}\]

let rect = cv.boundingRect(cnt);
let aspectRatio = rect.width / rect.height;

2. Extent

Extent is the ratio of contour area to bounding rectangle area.

\[Extent = \frac{Object \; Area}{Bounding \; Rectangle \; Area}\]

let area = cv.contourArea(cnt, false);
let rect = cv.boundingRect(cnt));
let rectArea = rect.width * rect.height;
let extent = area / rectArea;

3. Solidity

Solidity is the ratio of contour area to its convex hull area.

\[Solidity = \frac{Contour \; Area}{Convex \; Hull \; Area}\]

let area = cv.contourArea(cnt, false);
cv.convexHull(cnt, hull, false, true);
let hullArea = cv.contourArea(hull, false);
let solidity = area / hullArea;

4. Equivalent Diameter

Equivalent Diameter is the diameter of the circle whose area is same as the contour area.

\[Equivalent \; Diameter = \sqrt{\frac{4 \times Contour \; Area}{\pi}}\]

let area = cv.contourArea(cnt, false);
let equiDiameter = Math.sqrt(4 * area / Math.PI);

5. Orientation

Orientation is the angle at which object is directed. Following method also gives the Major Axis and Minor Axis lengths.

let rotatedRect = cv.fitEllipse(cnt);
let angle = rotatedRect.angle;

6. Mask and Pixel Points

In some cases, we may need all the points which comprises that object.

We use the function: cv.transpose (src, dst)

Parameters
srcinput array.
dstoutput array of the same type as src.

7. Maximum Value, Minimum Value and their locations

We use the function: cv.minMaxLoc(src, mask)

Parameters
srcinput single-channel array.
maskoptional mask used to select a sub-array.
let result = cv.minMaxLoc(src, mask);
let minVal = result.minVal;
let maxVal = result.maxVal;
let minLoc = result.minLoc;
let maxLoc = result.maxLoc;

8. Mean Color or Mean Intensity

Here, we can find the average color of an object. Or it can be average intensity of the object in grayscale mode. We again use the same mask to do it.

We use the function: cv.mean (src, mask)

Parameters
srcinput array that should have from 1 to 4 channels so that the result can be stored in Scalar.
maskoptional operation mask.
let average = cv.mean(src, mask);