CVMar 29, 2022

Face segmentation: A comparison between visible and thermal images

arXiv:2203.15366v122 citationsh-index: 34
Originality Synthesis-oriented
AI Analysis

This work addresses face segmentation for biometric systems, but it is incremental as it adapts existing methods to thermal imagery.

The paper tackled face segmentation in thermal images by proposing a new algorithm and comparing it to the Viola-Jones method on visible images, finding it to be over 10 times faster and more accurate for thermal data.

Face segmentation is a first step for face biometric systems. In this paper we present a face segmentation algorithm for thermographic images. This algorithm is compared with the classic Viola and Jones algorithm used for visible images. Experimental results reveal that, when segmenting a multispectral (visible and thermal) face database, the proposed algorithm is more than 10 times faster, while the accuracy of face segmentation in thermal images is higher than in case of Viola-Jones

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes