OpenCV C# - Detecting simple object in static image

Question

I have no experience with images. I have to detect simple object in static image. For example I have image like:

I want to detect edges and remove background. Just to compare them. Something like this.

Do u have any solutions of this problem? Images have often white backgrounds.

I've just thought about detect edges, and take everything what they contains.

Simple object is white circle or square on black background. But not this. You can try extract edges, but you'll also get shadows, and horizontal line on background. And these edges are stronger than your object edges. — Andrey Smorodov
– Andrey Smorodov, Commented Sep 19, 2017 at 12:13
I've thought about convert image to HSV and change H, S and V values to get contour of object. This comparer mustn't have be so much accurate. I will get scores and set ranges. — Krzysztof Lichwiarz
– Krzysztof Lichwiarz, Commented Sep 19, 2017 at 12:59
Simply do adaptive threshold, sobelx and dilation in the order on the image. You'll segment out the shoe. Then fixing a box around shouldn't be an issue. — I.Newton
– I.Newton, Commented Sep 20, 2017 at 5:51

I.Newton · Accepted Answer · 2017-09-20 06:37:01Z

1

To segment out the shoe-

Anadptive Threshold to remove the smooth changing background.
Sobelx, which removes the apparent background line, which i assume is common for images of this setup.
dilate, closing operation to separate out the shoe.
Find contours, bounding box etc as per your choice.

Do an additional threshold if you want to remove the shadow at the bottom.

answered Sep 20, 2017 at 6:37

I.Newton

1,7931 gold badge12 silver badges14 bronze badges

Sign up to request clarification or add additional context in comments.

1 Comment

This is what I wanted. When I'll have contour, I will subtract from original image, my product to create histogram to compare ;) Big thanks! :)