Instance Segmentation for Printed Circuit Board (PCB) Component Analysis : Exploring CNNs and Transformers for Component Detection on Printed Circuit Boards

Abstract: In the intricate domain of Printed Circuit Boards (PCBs), object detection poses unique challenges, particularly given the broad size spectrum of components, ranging from a mere 2 pixels to several thousand pixels within a single high-resolution image, often averaging 4000x3000 pixels. Such resolutions are atypical in the realm of deep learning for computer vision, making the task even more demanding. Further complexities arise from the significant intra-class variability and minimal inter-class differences for certain component classes. In this master thesis, we rigorously evaluated the performance of a CNN-based object detection framework (FCOS) and a transformer model (DETR) for the task. Additionally, by integrating the novel foundational model from Meta, named ”Segment Anything,” we advanced the pipeline to include instance segmentation. The resultant model is proficient in detecting and segmenting component instances on PCB images, achieving an F1 score of 81% and 82% for the primary component classes of resistors and capacitors, respectively. Overall, when aggregated over 18 component classes, the model attains a commendable F1 score of 74%. This study not only underscores the potential of advanced deep learning techniques in PCB analysis but also paves the way for future endeavors in this interdisciplinary convergence of electronics and computer vision