Reconocimiento y localización de instrumental médico usando análisis automatizado de imágenes
Abstract
In this work, we propose a simple but effective methodology for the recognition and localization of medical instruments from images of then. In the first stage of learning, for each instrument, we get an invariant description in the presence of image transformations such as translations and rotations. The set of descriptions is used to train several classifiers to verify their performance. During the test stage, an image containing one or more medical instruments is processed to get as a result the identity of each object in the image. For localization, for each instrument we get the coordinates of its centroid, the value of the angle of its major axis as well as the coordinates of taking holes, in the case of clamps. The proposal is proven with a set of images, specially designed for such intention.
Downloads
Downloads
Published
How to Cite
Issue
Section
License
Upon acceptance of an article in the RMIB, corresponding authors will be asked to fulfill and sign the copyright and the journal publishing agreement, which will allow the RMIB authorization to publish this document in any media without limitations and without any cost. Authors may reuse parts of the paper in other documents and reproduce part or all of it for their personal use as long as a bibliographic reference is made to the RMIB. However written permission of the Publisher is required for resale or distribution outside the corresponding author institution and for all other derivative works, including compilations and translations.
