融合局部特征与深度学习的三维掌纹识别

3D palmprint recognition by using local features and deep learning

为了探索三维掌纹在生物特征识别领域的应用,基于局部纹理特征和深度学习,提出一种有效的三维掌纹识别方法.通过曲率特征、形状指数、表面类型分别来描述三维掌纹的局部几何特征,将其作为深度神经网络的输入,完成三维掌纹识别任务.在香港理工大学的三维掌纹数据库上对不同的几何特征、不同的深度神经网络模型进行全面分析与比较.三维掌纹识别实验结果表明,与其他三维掌纹识别方法相比较,所提方法的识别率更高,识别时间更短,在实时掌纹识别领域具有较大的应用潜力.

An efficient 3 D palmprint recognition method was proposed by using local texture feature sets and deep learning, in order to explore the usage of 3 D palmprint in biometrics recognition. Curvature feature, shape index and surface type were employed to describe the geometry characteristics of local regions in 3 D palmprint data, and then take the charasteristics as the input of the deep neural network to finish 3 D palmprint recognition task.Comprehensive experiments on Hong Kong Polytechnic University 3 D palmprint database were further conducted by using different geometrical features and deep neural network models. The final experimental results of 3 D palmprint recognition validate that the proposed method outperforms existing state-of-the-art methods in terms of recognition accuracy and runtime, showing high potential for real-time palmprint recognition applications.