The BlobDetector return a list of TIEVisionKeyPoint
The IEVision documentation says:
TIEVisionKeyPoint = packed record
pt: TIEVisionPoint2f; // coordinates of the keypoints
size: single; // diameter of the meaningful keypoint neighborhood
angle: single; // computed orientation of the keypoint (-1 if not applicable); it's in [0,360) degrees and measured relative to image coordinate system, ie in clockwise.
response: single; // the response by which the most strong keypoints have been selected. Can be used for the further sorting or subsampling
octave: int32_t; // octave (pyramid layer) from which the keypoint has been extracted
class_id: int32_t; // object class (if the keypoints need to be clustered by an object they belong to)
These parameters are abstruses, for example what is "diameter of the meaningful keypoint neighborhood"?
Is it possible to acquire the contour of the Blob, or the true area of the Blob?
Are the coordinates
pt: TIEVisionPoint2f the coordonates of the gravity Center????