Super-Resolution for Selfie Biometrics: Introduction and Application to Face and Iris

• URL: http://arxiv.org/abs/2204.05688v1
• Date: Tue, 12 Apr 2022 10:28:31 GMT
• Title: Super-Resolution for Selfie Biometrics: Introduction and Application to Face and Iris
• Authors: Fernando Alonso-Fernandez, Reuben A. Farrugia, Julian Fierrez, Josef Bigun
• Abstract summary: Lack of resolution has a negative impact on the performance of image-based biometrics. Super-resolution techniques have to be adapted for the particularities of images from a specific biometric modality. This chapter presents an overview of recent advances in super-resolution reconstruction of face and iris images.
• Score: 67.74999528342273
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The lack of resolution has a negative impact on the performance of image-based biometrics. Many applications which are becoming ubiquitous in mobile devices do not operate in a controlled environment, and their performance significantly drops due to the lack of pixel resolution. While many generic super-resolution techniques have been studied to restore low-resolution images for biometrics, the results obtained are not always as desired. Those generic methods are usually aimed to enhance the visual appearance of the scene. However, producing an overall visual enhancement of biometric images does not necessarily correlate with a better recognition performance. Such techniques are designed to restore generic images and therefore do not exploit the specific structure found in biometric images (e.g. iris or faces), which causes the solution to be sub-optimal. For this reason, super-resolution techniques have to be adapted for the particularities of images from a specific biometric modality. In recent years, there has been an increased interest in the application of super-resolution to different biometric modalities, such as face iris, gait or fingerprint. This chapter presents an overview of recent advances in super-resolution reconstruction of face and iris images, which are the two prevalent modalities in selfie biometrics. We also provide experimental results using several state-of-the-art reconstruction algorithms, demonstrating the benefits of using super-resolution to improve the quality of face and iris images prior to classification. In the reported experiments, we study the application of super-resolution to face and iris images captured in the visible range, using experimental setups that represent well the selfie biometrics scenario.

Related papers

• Periocular biometrics: databases, algorithms and directions [69.35569554213679]
  Periocular biometrics has been established as an independent modality due to concerns on the performance of iris or face systems in uncontrolled conditions. This paper presents a review of the state of the art in periocular biometric research.
  arXiv  Detail & Related papers  (2023-07-26T11:14:36Z)
• Multimodal Adaptive Fusion of Face and Gait Features using Keyless attention based Deep Neural Networks for Human Identification [67.64124512185087]
  Soft biometrics such as gait are widely used with face in surveillance tasks like person recognition and re-identification. We propose a novel adaptive multi-biometric fusion strategy for the dynamic incorporation of gait and face biometric cues by leveraging keyless attention deep neural networks.
  arXiv  Detail & Related papers  (2023-03-24T05:28:35Z)
• Iris super-resolution using CNNs: is photo-realism important to iris recognition? [67.42500312968455]
  Single image super-resolution techniques are emerging, especially with the use of convolutional neural networks (CNNs) In this work, the authors explore single image super-resolution using CNNs for iris recognition. They validate their approach on a database of 1.872 near infrared iris images and on a mobile phone image database.
  arXiv  Detail & Related papers  (2022-10-24T11:19:18Z)
• Super-Resolution and Image Re-projection for Iris Recognition [67.42500312968455]
  Convolutional Neural Networks (CNNs) using different deep learning approaches attempt to recover realistic texture and fine grained details from low resolution images. In this work we explore the viability of these approaches for iris Super-Resolution (SR) in an iris recognition environment. Results show that CNNs and image re-projection can improve the results specially for the accuracy of recognition systems.
  arXiv  Detail & Related papers  (2022-10-20T09:46:23Z)
• Verification system based on long-range iris and Graph Siamese Neural Networks [0.5480546613836199]
  We present a novel methodology for converting LR iris images into graphs and then use Graph Siamese Neural Networks (GSNN) to predict whether two graphs belong to the same person. Results demonstrate the suitability of this approach, encouraging the community to explore graph application in biometric systems.
  arXiv  Detail & Related papers  (2022-07-28T09:22:11Z)
• A Survey of Super-Resolution in Iris Biometrics with Evaluation of Dictionary-Learning [0.0]
  The lack of resolution has a negative impact on the performance of image-based biometrics. This paper presents a survey of iris super-resolution approaches proposed in the literature. We have also adapted an Eigen-patches reconstruction method based on PCA Eigen-transformation of local image patches.
  arXiv  Detail & Related papers  (2022-03-27T03:58:10Z)
• Orthonormal Product Quantization Network for Scalable Face Image Retrieval [14.583846619121427]
  This paper integrates product quantization with orthonormal constraints into an end-to-end deep learning framework to retrieve face images. A novel scheme that uses predefined orthonormal vectors as codewords is proposed to enhance the quantization informativeness and reduce codewords' redundancy. Experiments are conducted on four commonly-used face datasets under both seen and unseen identities retrieval settings.
  arXiv  Detail & Related papers  (2021-07-01T09:30:39Z)
• Selfie Periocular Verification using an Efficient Super-Resolution Approach [11.352465961204775]
  Super-resolution has to be used to increase the quality of the captured images. Most of the state of the art super-resolution methods use deep networks with large filters. We propose an Efficient Single Image Super-Resolution (ESISR) algorithm, which takes into account a trade-off between the efficiency of the deep neural network and the size of its filters.
  arXiv  Detail & Related papers  (2021-02-16T21:01:12Z)
• Analysis and evaluation of Deep Learning based Super-Resolution algorithms to improve performance in Low-Resolution Face Recognition [0.0]
  Super-resolution algorithms may be able to recover the discriminant properties of the subjects involved. This project aimed at evaluating and adapting different deep neural network architectures for the task of face super-resolution. Experiments showed that general super-resolution architectures might enhance face verification performance of deep neural networks trained on high-resolution faces.
  arXiv  Detail & Related papers  (2021-01-19T02:41:57Z)
• Deep Learning-based Face Super-resolution: A Survey [78.11274281686246]
  Face super-resolution, also known as face hallucination, is a domain-specific image super-resolution problem. To date, few summaries of the studies on the deep learning-based face super-resolution are available. In this survey, we present a comprehensive review of deep learning techniques in face super-resolution in a systematic manner.
  arXiv  Detail & Related papers  (2021-01-11T08:17:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.