MobileNet Convolutional Neural Networks and Support Vector Machines for Palmprint Recognition

Due to the ease of handling with low resolution images, low cost hardware and high recognition accuracy, palmprint recognition has been attracting in the recent years. Many different features extracted of the palmprint image have been employed to perform the recognition tasks. Most of the recognition efforts consequently has been put on the designing and obtaining a relevant set of effective hand-crafted features which is considered to be the drawback of the traditional image based biometric recognition systems. To overcome the aforementioned problem, in this paper we explore the applicability of MobileNet V2 deep convolutional neural networks on palmprint recognition by fine-tuning a pretrained MobileNet neural networks. We also explore the performance of dropout support vector machines (SVM) by training them on the deep features of the similar pretrained networks. The experiments are carried out using datasets provided by Hong Kong Polytechnic University of Science and Technology. The dataset consists of 6000 grayscale images of 128x128 pixels from 500 different palms. It is demonstrated that the proposed schemes exhibit state-of-the-art performance on the datasets. The second scheme, MobileNet V2 based features with SVM classifier, is able to achieve best average testing and validation accuracy rate of 100% outperforming the best previous reported results.