FPGA-based object detection and classification inside scanning electron microscopes

Object-detection and classification is a key task in micro- and nanohandling. The microscopy image is often the only available sensor to detect information about the positions and orientations of objects. Recently, Field Programmable Gate Arrays (FPGAs) have been used for scanning electron microscope (SEM) image acquisition. Such an FPGA image acquisition system is extended to perform basic image processing and on-line object detection. The connected component labeling algorithm for binary large object detection is presented and analyzed for its feasibility in terms of on-line object detection and classification. The features of binary large objects are discussed and analyzed for their feasibility with a single-pass connected component labeling approach, with focus on principal component analysis based features. It is shown that an FPGA implementation of the algorithm can be used to detect and classify carbon-nanotubes (CNTs) during image acquisition, allowing for fast object detection before the whole image is captured.