Logo des Repositoriums

Auflistung nach Autor:in "Drahanský, Martin"

1 - 5 von 5
  • Konferenzbeitrag
    3D face recognition on low-cost depth sensors
    (BIOSIG 2014, 2014) Mráček, Štěpán; Drahanský, Martin; Dvořák, Radim; Provazník, Ivo; Váňa, Jan
    This paper deals with the biometric recognition of 3D faces with the emphasis on the low-cost depth sensors; such are Microsoft Kinect and SoftKinetic DS325. The presented approach is based on the score-level fusion of individual recognition units. Each unit processes the input face mesh and produces a curvature, depth, or texture representation. This image representation is further processed by specific Gabor or Gauss-Laguerre complex filter. The absolute response is then projected to lowerdimension representations and the feature vector is thus extracted. Comparison scores of individual recognition units are combined using transformation-based, classifierbased, or density-based score-level fusion. The results suggest that even poor quality low-resolution scans containing holes and noise might be successfully used for recognition in relatively small databases.
  • Konferenzbeitrag
    Applying fusion in thermal face recognition
    (BIOSIG 2012, 2012) Váňa, Jan; Mráček, Stepán; Poursaberi, Ahmad; Yanushkevich, Svetlana; Drahanský, Martin
    Face recognition based on thermal images has minor importance in comparison to visible light spectrum recognition. Nevertheless, in applications such as livelyness detection or fever scan, thermal face recognition is used as a stand-alone module, or as part of a multi-modal biometric system. This paper investigates combinations of many methods, used for thermal face recognition, and introduces some new and modified algorithms, which have not been used in the area as of yet. Moreover, we show that the best method is always limited to a certain database (input data). In order to address this problem, the multi-algorithmic biometric fusion, based on the logistic regression, is deployed.
  • Konferenzbeitrag
    Classification of skin diseases and their impact on fingerprint recognition
    (BIOSIG 2009: biometrics and electronic signatures, 2009) Drahanský, Martin; Březinová, Eva; Orság, Filip; Lodrová, Dana
    This article describes different skin diseases which could have the influence to the process of fingerprint acquirement. There are many people, who suffer under such diseases and are therefore excluded from the set of users of a biometric system and could not e.g. get a visa to the USA or use an access biometric system installed in a company, where they work.
  • Konferenzbeitrag
    Is There Any Similarity Between a Person’s Left and Right Retina?
    (BIOSIG 2019 - Proceedings of the 18th International Conference of the Biometrics Special Interest Group, 2019) Biswas, Sangeeta; Rohdin, Johan; Mňuk, Tomáš; Drahanský, Martin
    It is often argued among biometric researchers that the left and right retinas of the same person are as different as the retinas of two different persons. In this paper we investigate to what extent this is true. We perform experiments where human volunteers are asked to judge whether a pair of the left and right retinal images displayed side-by-side belongs to the same person or two different persons. We also use two similarity measurements, structural similarity (SSIM) and cosine similarity, to do the investigation process automatically. Our experiments show that there is recognizable similarity in the left and right retina of a person. For a verification task done by human volunteers, the average accuracy was 82%. For identification tasks, automatic systems using cosine similarity were correct in up to 57%.
  • Konferenzbeitrag
    Psoriasis Damage Simulation into Synthetic Fingerprint
    (BIOSIG 2019 - Proceedings of the 18th International Conference of the Biometrics Special Interest Group, 2019) Kanich, Ondřej; Košťák, Davis; Drahanský, Martin
    The goal of this article is to describe method for simulation of damage done by psoriasis. Designed method is based on extracting subjects from real images and then including them into synthetic images. Images are damaged by six different settings. Each setting represents different level of disease severity. Results were verified by visual comparison with real images, consultation with medical doctor, quality measurement methods (NFIQ, FiQiVi), and comparison score (VeriFinger). The most severe damage achieved median score of 38 % (from the reference).