KMITL

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

Browse

Settings

Author: search.filters.author.Pintavirooj, ChuchartSubject: search.filters.subject.Biometric

Search Results

Now showing 1 - 3 of 3
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Vein pattern verification and identification based on local geometric invariants constructed from minutia points and augmented with barcoded local feature
    (2020-05-01)
    Pititheeraphab, Yutthana
    ;
    Thongpance, Nuntachai
    ;
    Aoyama, Hisayuki
    ;
    Pintavirooj, Chuchart
    This paper presents the development of a hybrid feature-dorsal hand vein and dorsal geometry-modality for human recognition. Our proposed hybrid feature extraction method exploits two types of features: dorsal hand geometric-related and local vein pattern. Using geometric affine invariants, the peg-free system extracts minutia points and vein termination and bifurcation and constructs a set of geometric invariants, which are then used to establish the correspondence between two sets of minutiae-one for the query vein image and the other for the reference vein image. When the correspondence is established, geometric transformation parameters are computed to align the query with the reference image. Once aligned, hybrid features are extracted for identification. In this study, the algorithm was tested on a database of 140 subjects, in which ten different dorsal hand geometric-related images were taken for each individual, and yielded the promising results. In this regard, we have achieved an equal error rate (EER) of 0.243%, indicating that our method is feasible and effective for dorsal vein recognition with high accuracy. This hierarchical scheme significantly improves the performance of personal verification and/or identification.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Footprint Identification using Deep Learning
    (2019-01-10)
    Keatsamarn, Tanapon
    ;
    Pintavirooj, Chuchart
    Human footprint is the biometric system of the individual person. Everyone has specific footprints. It can be used instead of password-based authentication in the security system such as a user authentication for the financial transaction. The password-based system cannot verify that the person who entered the password is valid or not. Therefore the biometric system is more secure than the password-based system. For that reason, it's interesting to use footprint image in the creating of the footprint-based identification system. In this paper, the convolutional neural network training is used for deep learning classification. Convolutional neural networks are essential for deep learning and suited for image recognition.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Contactless palmprint alignment based on intrinsic local affine-invariant feature points
    (2014-02-12)
    Phromsuthirak, Choopol
    ;
    Tangsuksant, Watcharin
    ;
    Sanpanich, Arthorn
    ;
    Pintavirooj, Chuchart
    A Palmprint, biométrie characteristics, was mostly found in civil and commercial applications for security system because it has more reliable and easy to capture by low resolution devices. This paper was to develop a new contactless palmprint alignment with general USB camera on tripod. The palmprint image is acquired by this camera and using intrinsic local affine-invariant key points residing on the area patches spanning between two successive fingers to align palmprint image. The key points are relative affine invariant to affine transformations so this algorithm does not need the guidance pegs in acquisition process to fix hand position to avoid the scaling, translation and rotation problems for correctly palmprint image alignment. Finally, the developed algorithm was tested by 10 left-handed palmprint images collected from different subjects. The simulation results indicate by distance map error of 1.4899 pixels.