Save detected images differently about pigo

[esimov]

Yes, it is possible, since the API will return the rectangle coordinates of the detected faces. You only need to subtract the subregions of the detected faces from the original image.

A use case scenario should look like the following:

type SubImager interface {
	SubImage(r image.Rectangle) image.Image
}

//.....

// Run the classifier over the obtained leaf nodes and return the detection results.
// The result contains quadruplets representing the row, column, scale and detection score.
dets := classifier.RunCascade(cParams, 0.0)

// Calculate the intersection over union (IoU) of two clusters.
dets = classifier.ClusterDetections(dets, 0)


for i := 0; i < len(dets); i++ {
	if dets[i].Q >= 5.0 {
		rect := image.Rect(
			dets[i].Col-dets[i].Scale/2,
			dets[i].Row-dets[i].Scale/2,
			dets[i].Scale,
			dets[i].Scale,
		)

		subImg := img.(SubImager).SubImage(rect)
		bounds := subImg.Bounds()

		// Do whatever you want with the subImg
	}
}

[adigunhammedolalekan]

I will try this. Thank You