|
KMID : 1100520230290020152
|
|
Healthcare Informatics Research
2023 Volume.29 No. 2 p.152 ~ p.160
|
|
|
Dorsal Hand Vein Pattern Recognition: A Comparison between Manual and Automatic Segmentation Methods
|
|
Waheed Ali Laghari
Audrey Huong
Kim Gaik Tay
Chang Choon Chew
|
|
|
Abstract
|
|
|
Objectives: Various techniques for dorsal hand vein (DHV) pattern extraction have been introduced using small datasetswith poor and inconsistent segmentation. This work compared manual segmentation with our proposed hybrid automaticsegmentation method (HHM) for this classification problem.
Methods: Manual segmentation involved selecting a region-ofinterest(ROI) in images from the Bosphorus dataset to generate ground truth data. The HHM combined histogram equalizationand morphological and thresholding-based algorithms to localize veins from hand images. The data were divided intotraining, validation, and testing sets with an 8:1:1 ratio before training AlexNet. We considered three image augmentationstrategies to enlarge our training sets. The best training hyperparameters were found using the manually segmented dataset.
Results: We obtained a good test accuracy (91.5%) using the model trained with manually segmented images. The HHMmethod showed slightly inferior performance (76.5%). Considerable improvement was observed in the test accuracy of themodel trained with the inclusion of automatically segmented and augmented images (84%), with low false acceptance andfalse rejection rates (0.00035% and 0.095%, respectively). A comparison with past studies further demonstrated the competitivenessof our technique.
Conclusions: Our technique can be feasible for extracting the ROI in DHV images. This strategyprovides higher consistency and greater efficiency than the manual approach.
|
|
|
KEYWORD
|
|
|
Biometrics, Veins, Classification, Deep Learning, Transfer Learning
|
|
|
FullTexts / Linksout information
|
|
|
|
|
|
Listed journal information
|
|
|