Automated inspection of through hole solder joints utilizing X-ray imaging

Solder joint inspection has traditionally been done by manual inspection. The disadvantage of manual inspection is the large amount of time required and the decrease in efficiency as operator fatigue occurs. This has prompted the development of automated inspection systems to speed up the inspection process and increase efficiency. Automated inspection systems typically use visible light, infrared light or X-rays to illuminate the board. These systems require solder joint position information that is provided either by CAD data or by human entry of the position information. This paper describes a preliminary, automated inspection system that finds the solder joints in an X-ray image and inspects them using an artificial neural network (ANN). The identification of solder joints in the gray-scale image is done using image processing techniques; CAD data or manual registration of the solder joints is not required. The image processing techniques also yield binary maps (i.e., black and white images) showing the locations of ICs and other components, which is useful for other diagnostics.<>