Explainable Fingerprint ROI Segmentation Using Monte Carlo Dropout

Joshi, Indu; Kothari, Riya; Utkarsh, Ayush; Kurmi, Vinod K; Dantcheva, Antitza; Roy, Sumantra Dutta; Kalra, Prem Kumar

doi:10.1109/wacvw52041.2021.00011

Cited by 12 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RUnet (synthetic) represents the scenario when roi masks from only synthetic images (source domain) are used. RUnet (full) on the other hand, represents the case when training is conducted in a fully supervised fashion, using the fingerprint images and the corresponding annotated roi masks from the training set (subset B) of both source and target domain [18]. For comparison purposes, we have reported performance on only target sensor datasbases.…”

Section: A Benchmarking Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Sensor-invariant Fingerprint ROI Segmentation Using Recurrent Adversarial Learning

Joshi¹,

Utkarsh²,

Kothari³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

A fingerprint region of interest (roi) segmentation algorithm is designed to separate the foreground fingerprint from the background noise. All the learning based state-ofthe-art fingerprint roi segmentation algorithms proposed in the literature are benchmarked on scenarios when both training and testing databases consist of fingerprint images acquired from the same sensors. However, when testing is conducted on a different sensor, the segmentation performance obtained is often unsatisfactory. As a result, every time a new fingerprint sensor is used for testing, the fingerprint roi segmentation model needs to be re-trained with the fingerprint image acquired from the new sensor and its corresponding manually marked ROI. Manually marking fingerprint ROI is expensive because firstly, it is time consuming and more importantly, requires domain expertise. In order to save the human effort in generating annotations required by state-of-the-art, we propose a fingerprint roi segmentation model which aligns the features of fingerprint images derived from the unseen sensor such that they are similar to the ones obtained from the fingerprints whose ground truth roi masks are available for training. Specifically, we propose a recurrent adversarial learning based feature alignment network that helps the fingerprint roi segmentation model to learn sensor-invariant features. Consequently, sensor-invariant features learnt by the proposed roi segmentation model help it to achieve improved segmentation performance on fingerprints acquired from the new sensor. Experiments on publicly available FVC databases demonstrate the efficacy of the proposed work.

show abstract

Section: A Benchmarking Resultsmentioning

confidence: 99%

“…Handcrafted texture and intensity features have also been explored [27]. Recent fingerprint roi segmentation techniques exploit convolutional neural networks [18], [19], [41], [42].…”

Section: Related Workmentioning

confidence: 99%

Sensor-invariant Fingerprint ROI Segmentation Using Recurrent Adversarial Learning

Joshi¹,

Utkarsh²,

Kothari³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this study, we utilize the commonly used Dice score and intersection over union (IoU) as our performance measures [52,53]. Given an observed segmentation mask O and the expected segmentation mask E, the Dice score is defined as:…”

Section: Modelmentioning

confidence: 99%

Semi-Self-Supervised Learning for Semantic Segmentation in Images with Dense Patterns

Najafian

Ghanbari

Kish

et al. 2022

Preprint

View full text Add to dashboard Cite

Deep learning has shown potential in domains where large-scale annotated datasets are available. However, manual annotation is expensive, time-consuming, and tedious. Pixel-level annotations are particularly costly for semantic segmentation in images with dense irregular patterns of object instances, such as in plant images. In this work, we propose a method for developing high-performing deep learning models for semantic segmentation of wheat heads utilizing little manual annotation. We simulate a computationally-annotated dataset using a few annotated images, a short unannotated video clip of a wheat field, and several video clips from fields with no wheat. This dataset is then used to train a customized U-Net model for wheat head segmentation. Considering the distribution shift between the simulated and real data, we apply three domain adaptation steps to gradually bridge the domain gap. Only using two annotated images, we achieved a Dice score of 0.89 on the internal test set, i.e., images extracted from the wheat field video. The model trained using only two annotated images was evaluated on a diverse external dataset collected from 18 different domains across five countries and achieved a Dice score of 0.73. To further expose the model to images from different growth stages and environmental conditions, we incorporated two annotated images from each of the 18 domains and further fine-tuned the model. This resulted in improving the Dice score to 0.91. These promising results highlight the utility of the proposed approach in the absence of large-annotated datasets. Although the utility of the proposed method is shown on a wheat head dataset, it can be extended to other segmentation tasks with similar characteristics of irregularly repeating patterns of object instances.

show abstract

“…[44] proposed a new interpretability method for DNN‐based morphing attack detectors that determines which regions of an image contain artefacts. Interpretability has also been the focus of study on other topics related to biometrics, including biometric template security [45] and fingerprint segmentation [46].…”

Section: Related Workmentioning

confidence: 99%

An exploratory study of interpretability for face presentation attack detection

et al. 2021

View full text Add to dashboard Cite

Biometric recognition and presentation attack detection (PAD) methods strongly rely on deep learning algorithms. Though often more accurate, these models operate as complex black boxes. Interpretability tools are now being used to delve deeper into the operation of these methods, which is why this work advocates their integration in the PAD scenario. Building upon previous work, a face PAD model based on convolutional neural networks was implemented and evaluated both through traditional PAD metrics and with interpretability tools. An evaluation on the stability of the explanations obtained from testing models with attacks known and unknown in the learning step is made. To overcome the limitations of direct comparison, a suitable representation of the explanations is constructed to quantify how much two explanations differ from each other. From the point of view of interpretability, the results obtained in intra and inter class comparisons led to the conclusion that the presence of more attacks during training has a positive effect in the generalisation and robustness of the models. This is an exploratory study that confirms the urge to establish new approaches in biometrics that incorporate interpretability tools. Moreover, there is a need for methodologies to assess and compare the quality of explanations.This is an open access article under the terms of the Creative Commons Attribution-NonCommercial License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes.

show abstract

Explainable Fingerprint ROI Segmentation Using Monte Carlo Dropout

Cited by 12 publications

References 16 publications

Sensor-invariant Fingerprint ROI Segmentation Using Recurrent Adversarial Learning

Sensor-invariant Fingerprint ROI Segmentation Using Recurrent Adversarial Learning

Semi-Self-Supervised Learning for Semantic Segmentation in Images with Dense Patterns

An exploratory study of interpretability for face presentation attack detection

Contact Info

Product

Resources

About