Adaptive Spatial Transformation Networks for Periocular Recognition
Open Access
Abstract
Periocular recognition has emerged as a particularly valuable biometric identification method in challenging scenarios, such as partially occluded faces due to COVID-19 protective masks masks, in which face recognition might not be applicable. This work presents a periocular recognition framework based on deep learning, which automatically localises and analyses the most important areas in the periocular region. The main idea is to derive several parallel local branches from a neural network architecture, which in a semi-supervised manner learn the most discriminative areas in the feature map and solve the identification problem solely upon the corresponding cues. Here, each local branch learns a transformation matrix that allows for basic geometrical transformations (cropping and scaling), which is used to select a region of interest in the feature map, further analysed by a set of shared convolutional layers. Finally, the information extracted by the local branches and the main global branch are fused together for recognition. The experiments carried out on the challenging UBIRIS-v2 benchmark show that by integrating the proposed framework with various ResNet architectures, we consistently obtain an improvement in mAP of more than 4% over the “vanilla” architecture. In addition, extensive ablation studies were performed to better understand the behavior of the network and how the spatial transformation and the local branches influence the overall performance of the model. The proposed method can be easily adapted to other computer vision problems, which is also regarded as one of its strengths.Keywords
Funding Information
- German Science Foundation (DFG) (TRR 169, UIDB/EEA/50008/2020)
- FCT/MCTES (TRR 169, UIDB/EEA/50008/2020)
This publication has 38 references indexed in Scilit:
- A survey on periocular biometrics researchPattern Recognition Letters, 2016
- Stable, fast computation of high-order Zernike moments using a recursive methodPattern Recognition, 2016
- Selecting discriminative regions for periocular verification2016
- Ocular biometrics: A survey of modalities and fusion approachesInformation Fusion, 2015
- FaceNet: A unified embedding for face recognition and clustering2015
- Going deeper with convolutions2015
- Probabilistic Deformation Models for Challenging Periocular Image VerificationIEEE Transactions on Information Forensics and Security, 2015
- Multi-modal authentication system for smartphones using face, iris and periocular2015
- Matching heterogeneous periocular regions: Short and long standoff distances2014
- UBIRIS: A Noisy Iris Image Database2005