Thermal heat distribution features for hand identification

作者：

Highlights：

• Hand heat distribution features allow to perform biometric identification.

• A novel image processing algorithm segments thermal hand images.

• Statistical features computed from 15 locations characterize each image .

• A compact train model is former by t-SNE, classification results are above 90%.

• The low-dimensional space helps to explore the robustness of the proposed method.

摘要

•Hand heat distribution features allow to perform biometric identification.•A novel image processing algorithm segments thermal hand images.•Statistical features computed from 15 locations characterize each image .•A compact train model is former by t-SNE, classification results are above 90%.•The low-dimensional space helps to explore the robustness of the proposed method.

论文关键词：Thermal imaging,Biometric identification,Dimension reduction,Medical imaging

论文评审过程：Received 31 March 2021, Revised 27 April 2022, Accepted 28 April 2022, Available online 6 May 2022, Version of Record 12 May 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117462