R. Donida Labati, A. Genovese, V. Piuri, F. Scotti, Touchless palmprint and fingerprint recognition, Advances in Computing, Informatics, Networking and Cybersecurity - A Book Honoring Prof. Mohammad S. Obaidat’s Significant Scientific Contributions, Lecture Notes in Networks and Systems, vol. 289, pp. 267-298, Springer, Cham, 2022, ISSN 978-3-030-87049-2.
Biometric systems
COntactlesS Multibiometric mObile System in the wild
COSMOS
COSMOS — COntactlesS Multibiometric mObile System in the wild was a PRIN research project aimed at developing a comprehensive platform for the contactless verification and recognition of individuals in realistic, weakly controlled environments. The project responded to the need for biometric systems that are both secure and convenient, reducing the cooperation required from users and avoiding dedicated contact-based sensors. Its central concept was to exploit widely available mobile devices—such as smartphones and tablets—to acquire and process multiple biometric characteristics, adapting the acquisition and recognition strategy to the user, the available sensors and the surrounding operational conditions.
COSMOS investigated the complementary use of hard biometric traits, including 2D and 3D face, iris, ear, fingerprint and palmprint, together with behavioural and soft traits such as gait, gaze and facial age information. The different modalities were intended to be combined through adaptive fusion strategies, improving reliability when individual samples were affected by illumination variations, motion, occlusions, perspective distortion, limited resolution or other typical “in-the-wild” acquisition problems. Multi-person detection and tracking were also studied to enable screening from a distance and to maintain usable biometric observations even when subjects were partially occluded.
The associated research produced advances in several enabling technologies. These included deep-learning approaches for touchless palmprint recognition using biometric-specific, unsupervised filter learning; fusion of palmprint and inner-finger texture from a single contactless hand image; smartphone-based fingerphoto recognition; robust iris segmentation under non-ideal illumination and occlusion; and CNN-based extraction of fingerprint pores from touch-based, touchless and latent images.
Further activities explored deep models for ECG recognition, facial age estimation and explainable face-aging systems, extending the project beyond conventional image-based identifiers toward continuous and interpretable biometric authentication. Throughout the project, particular attention was given to privacy, data protection, ethical implications, user acceptance, interoperability and efficient execution on resource-constrained mobile platforms.
COSMOS investigated the complementary use of hard biometric traits, including 2D and 3D face, iris, ear, fingerprint and palmprint, together with behavioural and soft traits such as gait, gaze and facial age information. The different modalities were intended to be combined through adaptive fusion strategies, improving reliability when individual samples were affected by illumination variations, motion, occlusions, perspective distortion, limited resolution or other typical “in-the-wild” acquisition problems. Multi-person detection and tracking were also studied to enable screening from a distance and to maintain usable biometric observations even when subjects were partially occluded.
The associated research produced advances in several enabling technologies. These included deep-learning approaches for touchless palmprint recognition using biometric-specific, unsupervised filter learning; fusion of palmprint and inner-finger texture from a single contactless hand image; smartphone-based fingerphoto recognition; robust iris segmentation under non-ideal illumination and occlusion; and CNN-based extraction of fingerprint pores from touch-based, touchless and latent images.
Further activities explored deep models for ECG recognition, facial age estimation and explainable face-aging systems, extending the project beyond conventional image-based identifiers toward continuous and interpretable biometric authentication. Throughout the project, particular attention was given to privacy, data protection, ethical implications, user acceptance, interoperability and efficient execution on resource-constrained mobile platforms.
Relevant publications
A. Genovese, V. Piuri, K. N. Plataniotis, F. Scotti, PalmNet: Gabor-PCA Convolutional Networks for touchless palmprint recognition, IEEE Transactions on Information Forensics and Security, vol. 14, no. 12, pp. 3160-3174, December 2019, ISSN 1556-6013.
A. Genovese, V. Piuri, F. Scotti, S. Vishwakarma, Touchless palmprint and finger texture recognition: A Deep Learning fusion approach, Proc. of the 2019 IEEE Int. Conf. on Computational Intelligence & Virtual Environments for Measurement Systems and Applications (CIVEMSA 2019), pp. 1-6, Tianjin, China, June 2019, ISSN 978-1-5386-8344-6.
R. Donida Labati, E. Muñoz, V. Piuri, A. Ross, F. Scotti, Non-ideal iris segmentation using Polar Spline RANSAC and illumination compensation, Computer Vision and Image Understanding, vol. 188, Elsevier, November 2019, ISSN 1077-3142.
A. Genovese, V. Piuri, F. Scotti, Towards explainable face aging with Generative Adversarial Networks, Proc. of the 26th IEEE Int. Conf. on Image Processing (ICIP 2019), pp. 3806-3810, Taipei, Taiwan, September 2019, ISSN 978-1-5386-6249-6.
R. Donida Labati, E. Muñoz, V. Piuri, R. Sassi, F. Scotti, Deep-ECG: Convolutional Neural Networks for ECG biometric recognition, Pattern Recognition Letters, vol. 126, pp. 78-85, Elsevier, September 2019, ISSN 0167-8655.
R. Donida Labati, A. Genovese, V. Piuri, F. Scotti, A scheme for fingerphoto recognition in smartphones, Selfie Biometrics, Advances in Computer Vision and Pattern Recognition, pp. 49-66, Springer, Cham, 2019, ISSN 978-3-030-26972-2.
A. Genovese, E. Muñoz, V. Piuri, F. Scotti, Advanced biometric technologies: emerging scenarios and research trends, From Database to Cyber Security: Essays Dedicated to Sushil Jajodia on the Occasion of His 70th Birthday, Lecture Notes in Computer Science, vol. 11170, pp. 324-352, Springer International Publishing, Cham, 2018, ISSN 978-3-030-04834-1.
R. Donida Labati, A. Genovese, E. Muñoz, V. Piuri, F. Scotti, A novel pore extraction method for heterogeneous fingerprint images using Convolutional Neural Networks, Pattern Recognition Letters, vol. 113, pp. 58-66, October 2018, ISSN 0167-8655.
A. Anand, R. Donida Labati, A. Genovese, E. Muñoz, V. Piuri, F. Scotti, Age estimation based on face images and pre-trained Convolutional Neural Networks, Proc. of the 2017 IEEE Symp. on Computational Intelligence for Security and Defense Applications (CISDA 2017), pp. 1-7, Honolulu, HI, USA, November 2017, ISSN 978-1-5386-2726-6.
A. Anand, R. Donida Labati, M. Hanmandlu, V. Piuri, F. Scotti, Text-independent speaker recognition for ambient intelligence applications by using information set features, Proc. of the 2017 IEEE Int. Conf. on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA 2017), pp. 30-35, Annecy, France, July 2017, ISSN 978-1-5090-4253-1.