The goal of this work was to automate the crack detection of pads on a wafer piece. This process allows the engineer to check a huge number of pads for cracks to obtain a meaningful statistical result of the Pad-Over-Active-Areas (POAA) stability, which is a typical task in the failure analysis laboratories. It is possible that cracks in POAA appear during the electrical test or the bonding process. The current analysis process is very time consuming as thousands of pads have to be inspected for cracks by an engineer. The process starts with the chemical preparation of a wafer piece to make the crack below the pad visible. After that, the engineer examines each pad individually through the optical microscope for cracks. For the automation of this process a new workflow had to be developed and is described in this work. Moreover, it comprises the automation of a light microscope as well as an automated image evaluation based on a neural network.