KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Settings

Author: search.filters.author.Pintavirooj, C.Subject: search.filters.subject.Biometric

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Study of ECG variation in daily activity
    (2017-12-19)
    Samona, Yanisa
    ;
    Pintavirooj, C.
    ;
    Visitsattapongse, S.
    Electrocardiogram (ECG) records electrical activity of the heart spreading through the heart muscle to make the heart contract. Recently ECG has been captured attention as biometric feature due to its uniqueness and large reliabilities for human identifications. In this study we aimed to verify the conservative ECG of human in their activities to ensure whether it is suitable to be used as biometric devices. Experiment studies involved 6 participants of which the age ranges is between 21 and 23. We test the robustness of ECG under various situation including health condition, emotional state and heart rate variation. The recorded ECG signal is forwarded for analysis using Matlab. Correlation coefficient of ECG Fourier transform is used as criterion to validate the ECG robustness. The result indicates that ECG is not stable and seems to vary with daily activity and emotional state. This will hampers ECG to be used as Biometric.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Directional filter bank: An enhancement for fingerprint feature detection
    (2006-12-01)
    Tantachun, S.
    ;
    Pintavirooj, C.
    ;
    Sangworasil, M.
    ;
    Kitjaidure, Y.
    Fingerprints is the most popular biometric modality. Fingerprint features include core, delta, ridge bifurcation, ridge ending, enclosure and short edge. In order to increase the performance of fingerprint identification system, it is essential that these directional-related features are needed to be enhanced. In this paper, we purpose the directional filter bank to enhance the fingerprint features which later used in classification step. Our 2D FIR filter is designed using a 2D frequency-transform method which is easily implemented and easily imposed a zero phase response. Our proposed technique demonstrates the promising results. © 2006 IEEE.