Download PDFOpen PDF in browser

Quality of Pre-trained Deep-Learning Models for Palmprint Recognition

EasyChair Preprint no. 4150

8 pagesDate: September 7, 2020


This paper presents a comprehensive study of deep learning methods and datasets used for solving the palmprint recognition problem. The quality of image embeddings provided by deep neural networks, pre-trained on the ImageNet dataset, are evaluated on palmprint recognition in the visible spectrum task. In our tests, we used twelve publicly available datasets obtained with different types of acquisition procedures: constrained, partially constrained and unconstrained. Sixteen convolutional neural networks (two from the VGG family, six from ResNet, three from Inception, two from MobileNet and three from DenseNet) were evaluated. We analyzed the results from the point of view of specialization potential, dataset difficulty and general parameter tuning. For evaluation, EER (Equal Error Rate) was employed. We ranked the datasets and appraised the feature vectors computed by the pre-trained networks using this metric. The best results, on average, were provided by the deep neural networks from the MobileNet family. The distances used for comparing the feature vectors were Euclidean, Cityblock, cosine and correlation. The best results were obtained with the cosine family distances.

Keyphrases: Convolutional Neural Networks, deep learning, palmprint datasets, Palmprint recognition, Transfer Learning

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
  author = {Valentin Rosca and Anca Ignat},
  title = {Quality of Pre-trained Deep-Learning Models for Palmprint Recognition},
  howpublished = {EasyChair Preprint no. 4150},

  year = {EasyChair, 2020}}
Download PDFOpen PDF in browser