Print Email Facebook Twitter Object detection using SIFT Title Object detection using SIFT Author Tjiam, Yuan (TU Delft Mechanical, Maritime and Materials Engineering) Contributor van den Dobbelsteen, J.J. (mentor) Butler, R.M. (graduation committee) Degree granting institution Delft University of Technology Programme Mechanical Engineering | BioMechanical Design Date 2022-08-15 Abstract Surgical teams use instrument counts to prevent leaving unintended objects in patients. This is done manually, but could potentially be done through computer vision software. This paper presents a proof of concept for detecting instruments in the operating room with the Scale Invariant Feature Transform (SIFT). The SIFT algorithm is explored and tested on a variety of household appliances to substitute medical instruments. The algorithm responds differently to metal objects compared to matte objects and has room for many improvements. Further research on run time and multi object images is necessary. The proof of concept is considered successful when not taking run time into account. Subject Scale Invariant Feature TransformComputer visionInstrument detectionOperating room To reference this document use: http://resolver.tudelft.nl/uuid:d43d8df5-6cc5-429f-9438-cd0d3c5b480f Part of collection Student theses Document type master thesis Rights © 2022 Yuan Tjiam Files PDF Yuan_Tjiam_4085027_thesis.pdf 2.35 MB Close viewer /islandora/object/uuid:d43d8df5-6cc5-429f-9438-cd0d3c5b480f/datastream/OBJ/view