• VeriEye SDK

 

VERIEYE SDK
IRIS IDENTIFICATION FOR STAND-ALONE AND WEB SOLUTIONS
VeriEye iris identification technology is designed for biometric systems developers and integrators. The technology includes many proprietary solutions that enable robust iris enrollment under various conditions and fast iris matching in 1-to-1 and 1-to-many modes.
Available as a software development kit that allows development of stand-alone and Web-based solutions on Microsoft Windows, Linux, Mac OS X, iOS and Android platforms.

VERIEYSDK
单机系统和WEB解决方案的虹膜识别
VeriEye虹膜识别技术是为生物识别系统开发人员和集成商设计的。该技术包括许多专有解决方案,可以在各种条件下进行虹膜注册,并在1:1和1:N模式下快速匹配虹膜。
作为一种软件开发工具包,允许在Microsoft Windows、Linux、Mac OS X、iOS和Android平台上开发单机和基于Web的解决方案。

 

FEATURES AND CAPABILITIES

  • Rapid and accurate iris identification, proven by NIST IREX.
  • Robust recognition, even with gazing-away eyes or narrowed eyelids.
  • Original proprietary algorithm solves the limitations and drawbacks of existing state-of-the-art algorithms.
  • Contact lens detection can prevent spoof with fake iris images.
  • Available as multiplatform SDK that supports multiple programming languages.
  • Reasonable prices, flexible licensing and free customer support.

产品特点和功能

  • 快速准确的虹膜识别,NIST IREX证明.
  • 识别能力很强,即使眼睛注视远处,或者眯缝眼也没问题。
  • 原创专有算法解决了现有最先进算法的局限性和缺点。
  • 具有隐形眼镜检测功能,可以防止假虹膜图像的欺骗。
  • 支持多种编程语言的多平台SDK
  • 合理的价格,灵活的许可和免费的客户支持。

Neurotechnology began research and development in the field of eye iris biometrics in 1994 and has released VeriEye iris recognition algorithm in 2008. The original proprietary algorithm solves the limitations and drawbacks of existing state-of-the-art algorithms. VeriEye implements advanced iris segmentation, enrollment and matching using robust digital image processing algorithms:

  • Robust iris detection. Irises are detected even when there are obstructions to the image, visual noise and/or different levels of illumination. Lighting reflections, eyelids and eyelashes obstructions are eliminated. Images with narrowed eyelids or eyes that are gazing away are also accepted.
  • Automatic interlacing detection and correction results in maximum quality of iris features templates from moving iris images.
  • Gazing-away eyes are correctly detected on images, segmented and transformed as if it were looking directly into the camera (see Figure 1).
  • Correct iris segmentation is obtained even under these conditions:
    • Perfect circles fail. VeriEye uses active shape models that more precisely model the contours of the eye, as iris boundaries are not modeled by perfect circles.
    • The centers of the iris inner and outer boundaries are different (see Figure 2). The iris inner boundary and its center are marked in red, the iris outer boundary and its center are marked in green.
    • Iris boundaries are definitely not circles and even not ellipses (see Figure 3) and especially in gazing-away iris images.
    • Iris boundaries seem to be perfect circles. The recognition quality can still be improved if boundaries are found more precisely (see Figure 4). Note these slight imperfections when compared to perfect circular white contours.
    • Iris is partially occluded by eyelids. The upper and lower lids are marked in red and green correspondingly (see Figure 5).
  • Iris image quality determination and spoof prevention. The image quality estimation can be used during iris enrollment to ensure that only the best quality iris template will be stored into database. Also, cosmetic (decorative) contact lens, which obscure an iris with some artistic or fake iris texture and/or change iris color, can be detected.
  • Reliability. VeriEye algorithm has shown excellent recognition accuracy during the NIST IREX evaluations, as well as during testing on publicly available datasets.

神网科技有限公司于1994年开始在眼虹膜生物特征识别领域进行研究和开发,并于2008年发布了VeriEye虹膜识别算法。这一原创专有算法解决了现有的最先进算法的局限性和缺陷。Veriye的数字图像处理算法实现了先进的虹膜分割、登录和匹配,鲁棒性极强:

  • 鲁棒的虹膜检测 即使在图像有障碍物、视觉噪声和/或不同的光照水平时,也会检测到虹膜。照明反射,眼睑和睫毛等障碍均可被消除。小眼睑或小眼睛的图像也会被接受。
  • 自动隔行检测与校正 可从运动虹膜图像中获得最大质量的虹膜特征模板。
  • 注视远处的眼睛 也可以在图像上正确地检测到,分割和转换,就好像它是直接看着摄像机。
  • 正确的虹膜分割 即使在这些条件下均能实现:
    • 未采集到完整的圆型边界 Veriye使用主动形状模型,更精确地模拟眼睛的轮廓,因为虹膜边界不是由完美的圆圈建模的。
    • 虹膜内外边界的中心不同 虹膜的内边界及其中心用红色标记,虹膜的外边界及其中心用绿色标记。
    • 虹膜边界绝对不是圆,甚至不是椭圆  尤其是在远眺的虹膜图像中。
    • 虹膜边界似乎是完美的圆圈。如果更精确地找到边界,识别质量仍然可以提高,注意这些轻微的缺陷,当与完美的圆形白色轮廓相比。
    • 虹膜被眼睑部分遮住  上下盖子相应地用红色和绿色标记。
  • 虹膜图像质量的测定和预防欺骗。图像质量评估可以在虹膜登录过程中使用,以确保只有最佳质量的虹膜模板才能存储到数据库中。此外,化妆品(装饰)接触镜,用某种艺术或假虹膜纹理和/或变化的虹膜颜色,可以检测到。
  • 可靠性。NIST IREX评估测试中,Veriye算法表现优异,显示出了很好的识别精度。在其他公开的数据集上的测试,也同样有优秀表现。