Logo des Repositoriums

Auflistung nach Autor:in "Greitans, Modris"

1 - 4 von 4
  • Konferenzbeitrag
    Bimodal palm biometric feature extraction using a single RGB image
    (BIOSIG 2014, 2014) Eglitis, Teodors; Pudzs, Mihails; Greitans, Modris
    This paper proposes a method for palm bimodal biometric feature (vein and crease pattern) acquisition from a single RGB image. Typical bimodal biometric systems require combining infrared and visible images for this task. We use a single CMOS color sensor and a specific illumination comprising of two wavelengths to acquire the image. As a result each biometric modality is more pronounced in its own color channel. The image is processed by applying adapted matched filters with nonlinear modifications. Performance of the proposed method is evaluated against feature separation with optical band-pass and band-stop approach on a database of 64 people. The results show the average true positive rate is 70.6 \% for vein detection and 64.7 \% for crease detection, whereas in 14.8 \% and 9.29 \% of the cases feature of wrong modality is detected.
  • Konferenzbeitrag
    FPGA based palmprint and palm vein biometric system
    (BIOSIG 2013, 2013) Pudzs, Mihails; Fuksis, Rihards; Ruskuls, Rinalds; Eglitis, Teodors; Kadikis, Arturs; Greitans, Modris
    This paper presents an FPGA based multimodal palm biometric system. System is prototyped on an Altera DE2-115 board from Terasic, using an additional hardware for palm image acquisition in two light spectrums, communication with smart card, and debugging. System captures person's palmprint and palm vein images, extracts biometric data, encrypts it, and prepares for comparison. The comparison of the biometric data is performed on smart card for additional security. The proposed multimodal palm biometric system achieves a matching accuracy of EER of 16.65 % and a verification processing time of 0.8 seconds.
  • Konferenzbeitrag
    Increasing the reliability of biometric verification by using 3D face information and palm vein patterns
    (BIOSIG 2010: Biometrics and Electronic Signatures. Proceedings of the Special Interest Group on Biometrics and Electronic Signatures, 2010) Nikisins, Olegs; Greitans, Modris; Fuksis, Rihards; Pudzs, Mihails; Serzane, Zanda
    The improvment of the reliability for biometric image-based identification systems is discussed in this paper. Accuracy rising of the verification process is based on two main principles: implementation of multidimensionality and advanced image acquisition. The multidimensionality principle is based on two factors: the system structure (multimodality of biometric system) and the acquired biometric data (visual and spatial information about the object). The advanced image acquisition is based on multi-view principle and photography that is sensitive in infrared spectrum.
  • Konferenzbeitrag
    Local binary patterns and neural network based technique for robust face detection and localization
    (BIOSIG 2012, 2012) Nikisins, Olegs; Greitans, Modris
    This paper proposes an adaptation of Local Binary Pattern (LBP) operator for the design of the precise face localization technique. Presented approach is divided into three main stages: face detection, detection of eye regions and localization of eye pupils. Introduced optimization principles and the discriminative power of the LBP significantly reduces the number of features used to describe the classes and simplifies the structure of the utilized classifier, namely, artificial neural network. The combination of the reduced dimensionality of the feature space and the presented histogram-based sliding window makes the proposed algorithm well applicable for the task of precise face localization in high resolution images. The parameters of the algorithms are evaluated on a color FERET database.