Using fuzzy logic to detect dimple defects of polished wafer surfaces

Using the concept of fuzzy logic, the authors develop an algorithm for an automated visual inspection system to detect dimple defects of polished wafer surfaces. The algorithm consists of two major processing stages. At the first stage, preprocessing is performed to eliminate noise and to reduce the number of potential candidates of dimple defects. At the-second stage, four pattern features are defined based on the consideration of scale-, position-, and orientation-invariant. Fuzzy membership function is utilized to cope with the wide range of shape variations of the dimple defects. A decision-making mechanism is developed to detect dimple defects. The attractive features of the system include the fact that the algorithm is distortion-invariant