- 1、原创力文档(book118)网站文档一经付费(服务费),不意味着购买了该文档的版权,仅供个人/单位学习、研究之用,不得用于商业用途,未经授权,严禁复制、发行、汇编、翻译或者网络传播等,侵权必究。。
- 2、本站所有内容均由合作方或网友上传,本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺!文档内容仅供研究参考,付费前请自行鉴别。如您付费,意味着您自己接受本站规则且自行承担风险,本站不退款、不进行额外附加服务;查看《如何避免下载的几个坑》。如果您已付费下载过本站文档,您可以点击 这里二次下载。
- 3、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等,请点击“版权申诉”(推荐),也可以打举报电话:400-050-0827(电话支持时间:9:00-18:30)。
- 4、该文档为VIP文档,如果想要下载,成为VIP会员后,下载免费。
- 5、成为VIP后,下载本文档将扣除1次下载权益。下载后,不支持退款、换文档。如有疑问请联系我们。
- 6、成为VIP后,您将拥有八大权益,权益包括:VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
- 7、VIP文档为合作方或网友上传,每下载1次, 网站将根据用户上传文档的质量评分、类型等,对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档
查看更多
OSIRIS v4.1虹膜识别开源代码使用文档
A biometric reference system for iris
OSIRIS version 4.1
Foreword. This version of OSIRIS_v4.1 was developed by Telecom Sud Paris (previously
GET-INT) by Guillaume Sutra, Bernadette Dorizzi and Sonia Garcia-Salicetti. This
documentation was written by Nadia Othman.
Abstract. The OSIRIS (Open Source for IRIS) reference system is an open source iris
recognition system developed in the framework of the BioSecure project [1]. The system is
inspired by Daugman works [2]. It is composed of four processing modules (segmentation,
normalisation, encoding and matching), which correspond to the four steps of the complete
iris recognition procedure. In version v4.1, the segmentation part uses a Viterbi algorithm to
find the boundaries of the iris and of the pupil [3]. The normalisation step is based on
Daugmans rubber-sheet model and it uses the coarse contours detected by the Viterbi. Note
that there is no assumption of circularity of the normalized iris and pupil contours. The
encoding and matching parts are based respectively on Gabor phase demodulation and
Hamming distance classification.
Introduction:
This document describes the version 4.1 of the OSIRIS reference system and explains
how to use it in practice to build an automatic verification experiment based on iris modality.
This document is divided into fives parts. In the first part, we present how to install the
system. Then, in the second part, the database used and the protocol assiciated are described.
In the third part, the role of each module and how to use it are explained. In the fourth part,
the algorithms of each module are detailed and finally, the experimental results obtained in
the verification are shown in the last part. This document refers to version 4.1 of th
文档评论(0)