3D Face Recognition For Cows

Deepak Yeleshetty, Luuk Spreeuwers, Yan Li

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

24 Downloads (Pure)


This paper presents a method to recognize cows using their 3D face point clouds. Face is chosen because of the rigid structure of the skull compared to other parts. The 3D face point clouds are acquired using a newly designed dual 3D camera setup. After registering the 3D faces to a specific pose, the cow’s ID is determined by running Iterative Closest Point (ICP) method on the probe against all the point clouds in the gallery. The root mean square error (RMSE) between the ICP correspondences is used to identify the cows. The smaller the RMSE, the more likely that the cow is from the same class. In a closed set of 32 cows with 5 point clouds per cow in the gallery, the ICP recognition demonstrates an almost perfect identification rate of 99.53%.

Original languageEnglish
Title of host publicationBIOSIG 2020
Subtitle of host publicationProceedings of the 19th International Conference of the Biometrics Special Interest Group
EditorsArslan Bromme, Christoph Busch, Antitza Dantcheva, Kiran Raja, Christian Rathgeb, Andreas Uhl
Place of PublicationBonn
PublisherGesellschaft für Informatik
Number of pages9
ISBN (Electronic)978-3-88579-700-5
Publication statusPublished - 2020
Event19th Annual International Conference of the Biometrics Special Interest Group, BIOSIG 2020 - Darmstadt, Germany
Duration: 16 Sep 202018 Sep 2020
Conference number: 19

Publication series

NameLecture Notes in Informatics (LNI)
PublisherGesellschaft fur Informatik (GI)
ISSN (Print)1617-5468


Conference19th Annual International Conference of the Biometrics Special Interest Group, BIOSIG 2020
Abbreviated titleBIOSIG 2020


  • 3D face recognition
  • Biometrics
  • Cows
  • Iterative Closest Point
  • Pointcloud registration
  • Realsense cameras
  • Visual identification


Dive into the research topics of '3D Face Recognition For Cows'. Together they form a unique fingerprint.

Cite this