作者: Piotr Płoński , Dorota Stefan , Robert Sulej , Krzysztof Zaremba
DOI: 10.1007/978-3-319-19324-3_54
关键词:
摘要: The Liquid Argon Time Projection Chamber (LAr-TPC) detectors provide excellent imaging and particle identification ability for studying neutrinos. An efficient automatic reconstruction procedures are required to exploit potential of this technology. Herein, a novel method segmentation images from LAr-TPC is presented. proposed approach computes feature descriptor each pixel in the image, which characterizes amplitude distribution its neighbourhood. supervised classifier employed distinguish between pixels representing particle’s track noise. trained evaluated on hand-labeled dataset. can be preprocessing step reconstructing algorithms working directly detector images.