A mixture distribution for the wire bonding image

As a measure of quality for wire bonding, the degree of formation of intermetallics between gold ball and aluminium bond pad was estimated. A digital colour circle image of the surface of the gold ball that was attached to the bond pad was obtained. The resultant image had to be modelled by a three component mixture model proposed by Noor, Rijal, Badar and Thon, (see IEEE TENCON 2000, Kuala Lumpur, p.1299-1304, September 2000), but was shown to be a bad fit. We show that digitizing the polygon image in grey level resulted in a simpler image histogram, which could be model by a two-component mixture model. As an additional method of determining cut-off points between the 'humps' in the mixture model, line profiles of the image were studied.

[1]  B. Everitt,et al.  Finite Mixture Distributions , 1981 .

[2]  Ramin Samadani,et al.  A finite mixtures algorithm for finding proportions in SAR images , 1995, IEEE Trans. Image Process..

[3]  A vision problem in wire bonding , 2000, 2000 TENCON Proceedings. Intelligent Systems and Technologies for the New Millennium (Cat. No.00CH37119).