AI-Track-tive: open-source software for automated recognition and counting of surface semi-tracks using computer vision (artificial intelligence)

Abstract. A new method for automatic counting of etched fission tracks in minerals is described and presented this article. Artificial intelligence techniques such as deep neural networks computer vision were trained to detect surface semi-tracks on images. The can be used an open-source program semi-automated track dating called “AI-Track-tive”. Our custom-trained use the YOLOv3 object detection algorithm, which currently one most powerful fastest recognition algorithms. developed successfully finds microscope images; however, user still needs supervise counting. have high precision apatite (97 %) mica (98 %). Recall values are lower (86 than (91 application online at https://ai-track-tive.ugent.be (last access: 29 June 2021), or it downloaded offline Windows.