Projects

Touchless 2D Fingerprint Recognition

Most of the fingerprint recognition systems use touch-based acquisition devices, which suffer from important intrinsic problems, such as non-linear deformations of the captured images, non-uniform contrast of the fingerprint regions, presence of latent fingerprints on the sensor surface, sensibility to dust and dirt, and low social acceptance. Touchless fingerprint recognition systems based on CCD cameras are studied in order to overcome these problems.

With respect to techniques based on three-dimensional models, the studied methods based on a single touchless image have the advantage of requiring low-cost and small hardware setups, which can easily be integrated in mobile devices and consumer applications.

An important characteristic of the studied approaches is that they do not use finger placement guides, reducing the acquisition constraints with respect to most of the contactless fingerprint recognition systems in the literature.

The studied techniques regard different aspects of contactless biometric systems: acquisition, quality evaluation of biometric samples, computation of contact-equivalent images, matching algorithms, and computation of synthetic samples.

Fingerprint images captured by a traditional sensor and a contctless sensors

Quality measurement of fingerprint images

Core point estimation

Neural approach for perspective and rotation effects reduction

References
  • R. Donida Labati, A. Genovese, E. Muñoz, V. Piuri, F. Scotti, "A novel pore extraction method for heterogeneous fingerprint images using Convolutional Neural Networks", in Pattern Recognition Letters, pp. 58-66, October, 2018. ISSN: 0167-8655. [DOI: 10.1016/j.patrec.2017.04.001][PDF]
  • A. Genovese, E. Muñoz, V. Piuri, F. Scotti, G. Sforza, "Towards touchless pore fingerprint biometrics: a neural approach", in Proc. of the 2016 IEEE Congress on Evolutionary Computation (CEC 2016), Vancouver, BC, Canada, pp. 4265-4272, July 24-29, 2016. ISBN: 978-1-5090-0623-6. [DOI: 10.1109/CEC.2016.7744332][PDF]
  • R. Donida Labati, V. Piuri, F. Scotti, Touchless Fingerprint Biometrics, CRC Press, August, 2015. ISBN: 9781498707619. [Link]
  • R. Donida Labati, A. Genovese, V. Piuri, F. Scotti, "Touchless fingerprint biometrics: a survey on 2D and 3D technologies", in Journal of Internet Technology, pp. 325-332, May, 2014. ISSN: 1607-9264. [DOI: 10.6138/JIT.2014.15.3.01][PDF]
  • R. Donida Labati, A. Genovese, V. Piuri, F. Scotti, "Contactless fingerprint recognition: a neural approach for perspective and rotation effects reduction", in Proc. of the IEEE Workshop on Computational Intelligence in Biometrics and Identity Management (CIBIM 2013), Singapore, pp. 22-30, April 16-19, 2013. ISBN: 978-1-4673-5879-8. [DOI: 10.1109/CIBIM.2013.6607909][PDF]
  • R. Donida Labati, V. Piuri, F. Scotti, "A neural-based minutiae pair identification method for touchless fingeprint images", in Proc. of the 2011 IEEE Workshop on Computational Intelligence in Biometrics and Identity Management (CIBIM 2011), Paris, France, pp. 96-102, April 11-15, 2011. ISBN: 978-1-4244-9899-4. [DOI: 10.1109/CIBIM.2011.5949224][PDF]
  • R. Donida Labati, A. Genovese, V. Piuri, F. Scotti, "Measurement of the principal singular point in contact and contactless fingerprint images by using computational intelligence techniques", in Proc. of the 2010 IEEE Int. Conf. on Computational Intelligence for Measurement Systems and Applications (CIMSA 2010), Taranto, Italy, pp. 18-23, September 6-8, 2010. ISBN: 978-1-4244-7228-4. [DOI: 10.1109/CIMSA.2010.5611769][PDF]
  • R. Donida Labati, V. Piuri, F. Scotti, "Neural-based quality measurement of fingerprint images in contactless biometric systems", in Proc. of the 2010 IEEE-INNS Int. Joint Conf. on Neural Networks (IJCNN 2010), Barcelona, Spain, pp. 1-8, July 18-23, 2010. ISBN: 978-1-4244-6916-1. [DOI: 10.1109/IJCNN.2010.5596694][PDF]