Contacts Detection in PCB Image by Thinning, Clustering and Flood-filling

Abstract

The known K-means clustering, flood-fill and thinning algorithms are used to find coordinates of contacts in PCB images. Images of different types and colors are considered. The clustering algorithm is used to reduce a number of colors, to get uniform colors and to separate objects of the PCB image: background, traces, inscription and contacts. The thinning algorithm is used to build skeletons and to find specific points indicating pixels of contacts. The flood-fill algorithm is used to mark contacts, traces, background and inscriptions. Contacts with and without holes are considered.