Enhanced Crack Segmentation (ecs): A Reference Algorithm for Segmenting Cracks in Multicrystalline Silicon Solar Cells

The annually produced quantity of solar modules has steadily increased over the past decades. Rising production speeds and the associated high throughput of wafers, cells, and modules will make an automatized quality inspection mandatory. In the case of visual optical inspection, automatized quality control by using machine vision is already possible. To localize cracks in solar cells, luminescence imaging is used, where several approaches for an automatized inspection exist, but a standard solution for an automatized inspection algorithm is not yet available. This is, in particular, true for multicrystalline solar cells, where the grainy structures in the luminescence images are hard to distinguish from small cracks. Another obstacle in automatic crack analysis is that reference segmentation algorithms are generally not publicly available. Accordingly, a new algorithm can hardly be compared by ranking it to an existing standard. In this paper, we adapted the vesselness algorithm for automatic processing of electroluminescence images of multicrystalline silicon solar cells. Segmentation of cracks in multicrystalline solar cells with the proposed enhanced crack segmentation algorithm shows very promising results on the used database compared with three different commonly used approaches. Furthermore, the segmentation code is made publicly available, and we propose that this algorithm may serve as a reference algorithm, sparking further progress in automatized crack segmentation for multicrystalline silicon solar cells.