BSpline-FC
收藏资源简介:
BSpline-FC数据集由印度理工学院曼迪分校和挪威科技大学的研究团队创建,旨在通过几何建模生成逼真的额头皱纹图像。该数据集包含247个合成身份,每个身份生成10张额头皱纹图像,总计2470张图像。数据集的生成过程基于B样条和贝塞尔曲线,通过动态网格掩码和曲线控制点的扰动来增强样本的多样性。该数据集主要用于训练和评估基于额头皱纹的生物特征验证系统,旨在解决传统生物特征识别在开放集匹配中的局限性问题。
The BSpline-FC dataset was developed by research teams from the Indian Institute of Technology Mandi and the Norwegian University of Science and Technology, with the goal of generating realistic forehead wrinkle images through geometric modeling. This dataset comprises 247 synthetic identities, with 10 forehead wrinkle images generated per identity, resulting in a total of 2470 images. The dataset’s generation process relies on B-splines and Bézier curves, enhancing sample diversity via dynamic grid masks and perturbations to curve control points. This dataset is primarily used for training and evaluating forehead wrinkle-based biometric verification systems, aiming to address the limitations of traditional biometric recognition in open-set matching.




