Computes the connected components labeled image of boolean image

[labels,N] = cv.connectedComponents(image)
[labels,N,stats,centroids] = cv.connectedComponents(image)
[...] = cv.connectedComponents(..., 'OptionName', optionValue, ...)

Input

• image boolean image to be labeled, 1-channel 8-bit or logical matrix.

Output

• labels output labeled image of same size as input image and specified type in LType. Labels are in the range [0, N-1] where 0 represents the background label.
• N the total number of labels.
• stats (optional) statistics output for each label, including the background label, see below for available statistics. A Nx5 int32 matrix. Statistics are accessed via stats(label, col) where:
  • col=1: The leftmost (x) coordinate which is the inclusive start of the bounding box in the horizontal direction.
  • col=2: The topmost (y) coordinate which is the inclusive start of the bounding box in the vertical direction.
  • col=3: The horizontal size of the bounding box (width).
  • col=4: The vertical size of the bounding box (height).
  • col=5: The total area (in pixels) of the connected component.
• centroids (optional) 64-bit floating point centroid (x,y) output for each label, including the background label. A Nx2 numeric matrix. Centroids are accessed via centroids(label,:) for x and y.

Options

• Connectivity 8 or 4 for 8-way or 4-way connectivity respectively. default 8
• LType specifies the output image label type, an important consideration based on the total number of labels or alternatively the total number of pixels in the source image. Currently int32 and uint16 are supported. default int32

The last two optional output arguments are only computed if requested.