CASIA掌纹数据集和CASIA多光谱掌纹数据集下载

Jxbs

于 2024-03-28 15:56:21 发布

阅读量1k

点赞数 15

文章标签：深度学习人工智能

本文链接：https://blog.csdn.net/qq_41537900/article/details/137114667

版权

本文介绍了CASIA掌纹数据集，包含5,502张图像，来自312名个体，以及CASIA多光谱掌纹数据集，有7,200张图像，来自100人，使用自定义多光谱设备采集，具有不同电磁波谱和手姿变化。提供详细设备描述和样本多样性。数据集链接可在百度云获取。

摘要由CSDN通过智能技术生成

CASIA掌纹数据集和CASIA多光谱掌纹数据集

官网

1、CASIA掌纹数据集

CASIA Palmprint Image Database (or CASIA-Palmprint for short) contains 5,502 palmprint
images captured from 312 subjects.

2、CASIA多光谱掌纹数据集

CASIA Multi-Spectral Palmprint Image Database contains 7,200 palm images captured from
100 different people using a self-designed multiple spectral imaging device,as shown in Fig.1. All
palm images are 8 bit gray-level JPEG files. For each hand, we capture two sessions of palm
images. The time interval between the two sessions is more than one month. In each session, there
are three samples. Each sample contain six palm images which are captured at the same time with
six different electromagnetic spectrums. Wavelengthes of the illuminator corresponding to the six
spectrum are 460nm,630nm,700nm,850nm,940nm and white light respectively. Between two
samples, we allow a certain degree of variations of hand postures. Through that, we aim to
increase diversity of intra-class samples and simulate practical use.
In our device, there are no pegs to restrict postures and positions of palms. Subjects are
required to put his palm into the device and lay it before a uniform-colored background. The
device supplies an evenly distributed illumination and captures palmt images using a CCD camera
fixed on the bottom of the device. We design a control circuit to adjust spectrums automatically.
Six typical palmprint images in the database are shown in Fig.2

在这里插入图片描述