Unsupervised Algorithm to Detect Damage Patterns in Microstructure Images of Metal Films
Electrical measurement of degradation in metal films induced by high thermo-mechanical stress is not possible. Therefore, different imaging methods are used in practice to visualize the changes in material microstructure. In this work, SEM (Scanning Electron Microscopy) cross section images of the metal layer of interest that illustrate the fatigue induced degradation and material microstructure are analyzed. We propose an unsupervised algorithm for detection and quantitative assessment of the damage in mentioned images. In the first stage of the algorithm, the metal layer of interest is extracted from the background using k-Means method. In the second stage, the non-local means (NL-means) denoising method with automatically computed standard noise deviation followed by post-processing and k-Means is used to detect the damage patterns. Visual and quantitative evaluation of results reveals that the algorithm provides robust and plausible results.