Development of new edge-detection filter based on genetic algorithm: an application to a soldering joint inspection

This paper proposes a new technique of edge detection for inspecting edge and perfection of soldering joint in the flip-chip, which is an important part of a hard disk drive. Summation of error between the actual values and the measured values from the designed system of several data sets is formulated as the objective function. Genetic algorithm is adopted to find the optimal filter mask to enhance the accuracy of the inspection system. As the results indicated, the accuracy of a system with the proposed edge-detection technique is superior to that of a system with conventional filters.