Palm vein recognition based on end-to-end convolutional neural network / 南方医科大学学报

We propose a novel palm-vein recognition model based on the end-to-end convolutional neural network. In this model, the convolutional layer and the pooling layer were alternately connected to extract the image features, and the categorical attribute was estimated simultaneously via the neural network classifier. The classification error was minimized via the mini-batch stochastic gradient descent algorithm with momentum to optimize the feature descriptor along with the direction of the gradient descent. Four strategies including data augmentation, batch normalization, dropout, and L2 parameter regularization were applied in the model to reduce the generalization error. The experimental results showed that for classifying 500 subjects form PolyU database and a self-established database, this model achieved identification rates of 99.90% and 98.05%, respectively, with an identification time for a single sample less than 9 ms. The proposed approach, as compared with the traditional method, could improve the accuracy of palm vein recognition in clincal applications and provides a new approach to palm vein recognition.

Discussion on Privacy Protection in the Application of Biometric Identification Technology / 中国医学伦理学

First of all,this paper summarized the new features of privacy in the context of biometrics identifica-tion,namely the permanence of biometric information,the concealment of biometric information infringement,and the disclosure to medical information. Secondly,this paper analyzed the challenges faced by privacy protection from three aspects of database security,function creep and informatization of the body. Finally,from the perspective of ethics,this paper put forward some management suggestions for the privacy protection problems brought by the ap-plications of biometric identification technology.