Non-intrusive fingerprints extraction from hyperspectral imagery

Longbin Yan, Jie Chen

科研成果: 书/报告/会议事项章节会议稿件同行评审

5 引用 (Scopus)

摘要

Fingerprint extraction plays an important role in criminal investigation and information security. Conventionally, latent fingerprints are not readily visible and imaging often requires to use intrusive manners. Hyperspectral imaging techniques provide a possibility to extract fingerprints in a non-intrusive manner, however it requires well-designed image analysis algorithms. In this paper, we consider the problem of fingerprint extraction from hyperspectral images and propose a processing scheme. The proposed scheme extracts image textures by local total variation (LTV) and uses Histogram of Oriented Gradient (HOG) information to fuse these channels. Experiment results with a real image show the ability of the proposed method for extracting fingerprints from complex backgrounds.

源语言英语
主期刊名2018 26th European Signal Processing Conference, EUSIPCO 2018
出版商European Signal Processing Conference, EUSIPCO
1432-1436
页数5
ISBN(电子版)9789082797015
DOI
出版状态已出版 - 29 11月 2018
活动26th European Signal Processing Conference, EUSIPCO 2018 - Rome, 意大利
期限: 3 9月 20187 9月 2018

出版系列

姓名European Signal Processing Conference
2018-September
ISSN(印刷版)2219-5491

会议

会议26th European Signal Processing Conference, EUSIPCO 2018
国家/地区意大利
Rome
时期3/09/187/09/18

指纹

探究 'Non-intrusive fingerprints extraction from hyperspectral imagery' 的科研主题。它们共同构成独一无二的指纹。

引用此