Robust and adaptive algorithm for hyperspectral palmprint region of interest extraction

Robust and adaptive algorithm for hyperspectral palmprint region of interest extraction
复制标题

高光谱掌纹感兴趣区域提取的鲁棒自适应算法

DOI:
10.1049/iet-bmt.2018.5051
复制
发表时间:
2019-05
期刊:
影响因子:
2
通讯作者:
B. Zhang
B. Zhang
中科院分区:
计算机科学3区
文献类型:
--
作者:
S. Zhao;B. Zhang

文献摘要

参考文献

相似文献

近年来,高光谱成像因其具有判别性信息而受到越来越多的研究关注。本研究提出了一种稳健的方法,用于自适应提取由高光谱掌纹采集设备捕获的高光谱掌纹感兴趣区域(ROI),这被认为是掌纹识别中最重要的阶段之一。对于不同的光谱波长,图像具有不同的光照和不均衡的阴影。特别是,不同波段的手掌图像的平均灰度值有很大差异,因此手掌图像的二值化可被视为一项具有挑战性的任务,即从原始图像中准确地分离出手掌轮廓。为了解决这些问题,本研究提出了一种自适应ROI分割算法,即使用一种基于支持向量机的方法从图像中检测手掌,并建立坐标以确保ROI的准确性。所提出的方法在一个高光谱手掌数据集上进行了测试,该数据集涵盖了从530 - 1030nm且间隔为20nm的光谱。实验结果表明,所提出的算法在定位高光谱掌纹图像中的ROI方面是有效且高效的,从ROI中提取的局部二值模式特征在识别中实现了1.49%的等错误率(EER)和99.51%的准确率。
Recently, hyperspectral imaging has attracted more and more considerable research attention because of its discriminative information. This study proposes a robust approach to adaptively extract the hyperspectral palmprint region of interest (ROI) captured by a hyperspectral palmprint acquisition device, which is considered one of the most important stages in palmprint recognition. For different spectral wavelengths, the image has different illuminations and unbalanced shadows. In particular, mean grey values of palm images in different bands have large variations, such that binarisation of the palm image can be considered a challenging task to accurately separate the contour of the palm from the original image. To solve these problems, this study proposes an adaptive ROI segmentation algorithm, whereby a support vector machine-based method is used to detect the palm from the image and a coordinate established to ensure the accuracy of the ROI. The proposed method has been tested on a hyperspectral palm data set which covers spectrums from 530-1030 nm with 20 nm intervals. The experimental results showed that the proposed algorithm is effective and efficient at locating the ROI in hyperspectral palmprint images, where local binary pattern features were extracted from the ROIs achieving an equal error rate (EER) of 1.49% and an accuracy of 99.51% in recognition.
DOI: 10.5120/ijca2015905784
发表时间: 2015-08
期刊: International Journal of Computer Applications
影响因子: --
作者:
M. Anitha;K. A. R. Rao;K. Delac;Mislav Grgic;C. Poon;D.C.M. Wong;H. C. Shen;Chin-Chuan Han-
通讯作者: M. Anitha;K. A. R. Rao;K. Delac;Mislav Grgic;C. Poon;D.C.M. Wong;H. C. Shen;Chin-Chuan Han-
DOI: 10.1007/978-3-319-69923-3_39
发表时间: 2017-10
期刊: 2023 6th International Conference on Energy Conservation and Efficiency (ICECE)
影响因子: --
作者:
Mian Li;Weicheng Xie;L. Shen
通讯作者: Mian Li;Weicheng Xie;L. Shen
耳腮面角度:3D 耳朵识别的独特功能
DOI: 10.1016/j.patrec.2014.10.014
发表时间: 2015-02-01
影响因子: 5.1
作者:
Liu, Yahui;Zhang, Bob;Zhang, David
通讯作者: Zhang, David
一种新颖的多光谱掌纹识别分层方法
DOI: 10.1016/j.neucom.2014.09.013
发表时间: 2015-03-03
期刊: NEUROCOMPUTING
影响因子: 6
作者:
Hong, Danfeng;Liu, Wanquan;Wang, Guodong
通讯作者: Wang, Guodong
DOI: 10.1016/j.patrec.2010.05.010
发表时间: 2010-09
期刊: Pattern Recognit. Lett.
影响因子: --
作者:
Leqing Zhu;S. Zhang
通讯作者: Leqing Zhu;S. Zhang