Abstract
Ocelots are big felines in danger to be extinct but still found in some areas in Mexico, the spots in the body of ocelots make a pattern that is unique to each specimen and can be used for identification purposes. Ecologists are interested in non-intrusive census of these wild felines. In this paper, a method for automatic identification of specific individuals among ocelots is proposed. The proposed method maps each spot to the ellipse that best fits the spot, then keeps only the center of the ellipse and a vector that shows the orientation of the ellipse. Each animal is then characterized by a set of dots and associated vectors, just as human fingerprints are characterized after minutiae has been extracted. The proposed technique identifies individual ocelots by searching for local structures in the corresponding set of dots and associated vectors. According to the experiments, the proposed method outperforms Scale Invariant Feature Transform (SIFT), Speed Up Robust Feature (SURF), and Oriented fast and Rotated Brief (ORB) based identification systems in the ocelot identification problem.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
