Deep transfer learning for human identification based on footprint: A comparative study

Abstract

Identifying people based on their footprint has not yet gained enough attention from the researchers. Therefore, in this paper, an investigation of human identification conducted based on the footprint. Transfer Learning used as the main concept of this investigation. The aim of using Transfer Learning is to overcome the need for a large-scale dataset and achieve high accuracy with a low-scale dataset. Five well-known models used, namely, Alexnet, Vgg16, Vgg19, Googlenet, and Inception v3. Each of these models fine-tuned to fit-in the paper's topic. A dataset of 30 individuals constructed in order to train the models. The right and left footprint of each individual captured with iPhone camera. The models trained and evaluated based on the same settings. The evaluation shows that Inception v3 model achieved the highest accuracy compared to all other four models.

A Deep-Learning Approach for Foot-Type Classification Using Heterogeneous Pressure Data

“…ILSVRC is an image recognition competition that accurately classifies datasets having 1000 categories and millions of image data. The deep-learning architecture that scored well in this competition is usually shared in public and is used in many studies [28,31,40,41]. The VGG16 and InceptionV3 models are used in this study; they are cited in many studies because of their good performance in the ILSVRC.…”

“…In particular, because there are limitations with respect to the collection of sufficient data from experimental and clinical data, the preprocessing process takes a long time before using algorithms to achieve high accuracy [28][29][30]. Because the location and shape of the collected data varied owing to differences in the size, shape, and posture of each subject's feet, the location and foot angle must be corrected to improve learning accuracy [29][30][31].…”