Skip to main content

Effects of Postmortem Decomposition on Face Recognition

by David C Cornett, David S Bolme, Dawnie Steadman, Kelly Sauerwein, Tiffany Saul
Publication Type
Conference Paper
Journal Name
Biometrics: Theory, Applications and Systems
Book Title
Proceedings of the 10th IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS)
Publication Date
Page Numbers
1 to 8
Conference Name
IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS 2019)
Conference Location
Tampa, Florida, United States of America
Conference Sponsor
Conference Date

Although viable tools are available for the identification of unknown deceased individuals, recognition rates with these methods are greatly impacted by the degree to which decomposition has occurred. Therefore, identifying highly decomposed remains poses a major challenge. This paper analyzes the effect of facial decomposition on the recognition rates of several facial recognition commercial-off-the-shelf systems, research-grade systems, as well as algorithms contained in a custom recognition library. The custom dataset of facial images used in the experiment is composed of 42 subjects at stages of decomposition ranging from intake at a research facility to complete natural decomposition. It is shown that an algorithm’s ability to correctly detect a decomposing face is a crucial first step that not all face models can accurately handle. However, some of the evaluated Convolution Neural Network (CNN)-inspired methods provide promising results even in cases of severely decomposed faces.