Patch image merge system using deep neural network for chip defect analysis

In the integrated circuit/chip manufacturing process, failure analysis performed to find defects utilizes high-resolution chip images obtained through auto-shot scope equipment, which combines microscopy and automatic photography. However, due to the incorrect focus and the unexpected overlap size depending on the distance between the microscope and the chip, these systems are noisy. Thus, failure analysis cannot be performed effectively because the individual conducting the examination is exposed to noisy images, thereby taking a long time. We propose a system called DeepMerge that utilizes deep learning-based features such as point extraction and feature matching to overcome the aforementioned challenges. We will be indicating the effectiveness and efficiency of our system by obtaining practical image data from the industry. © ICROS 2021.