Ask Your Question
0

Detect chip orientation

asked 2016-01-15 17:36:16 -0500

I am trying to develop an application that will give me the orientation and offset of an integrated circuit (IC, chip) compared to a reference image. I can be sure that the device is within its width and about 30 degrees of the target.

Extracting keypoints then using FlannBasedMatcher works well if it's an identical device (same markings, lighting etc) but offering up a different item.... oh dear. Because the device is so uniform in structure, each pin is identical to the next, but surface markings are different, matches are almost at random. The surf feature detector works but the features it detects are too small and numerous and, again, there's no uniformity to the matching. I can't work out how to make it look for larger features. I've tried Sobel differentiation and produced some very good outline images then used a harris corner detect but I still can't work out how to match like for like on a structured basis i.e. match pin 1 to pin 1 and so forth.

Does anyone have any ideas of what sequence of steps I should take.

edit retag flag offensive close merge delete

Comments

1

example images will sure be helpful

berak gravatar imageberak ( 2016-01-16 01:54:40 -0500 )edit

1 answer

Sort by ยป oldest newest most voted
1

answered 2016-01-16 10:56:18 -0500

Tetragramm gravatar image

updated 2016-01-16 10:58:43 -0500

Try the GeneralizedHoughTransform. In general, this does exactly what you want.

It seems you want to use cv::createGeneralizedHoughGuil which detects position, traslation and rotation. The other one just detects position.

edit flag offensive delete link more

Comments

since we don't have any sample code (or say, documentation ..) for this in opencv, - what about a little demo snippet ?

berak gravatar imageberak ( 2016-01-17 09:46:33 -0500 )edit
1

There'll be a bit of a delay on this one. It seems that several of the functions used only appear in V3.1. I'm currently using 2.4.11 so that's another download and 14 hour compilation to get the latest version.

Watch this space......

John@fnc gravatar imageJohn@fnc ( 2016-01-18 13:57:42 -0500 )edit

Question Tools

1 follower

Stats

Asked: 2016-01-15 17:36:16 -0500

Seen: 707 times

Last updated: Jan 16 '16