Dorsal Hand Vein Pattern Recognition: A Comparison between Manual and Automatic Segmentation Methods
Objectives Various techniques for dorsal hand vein (DHV) pattern extraction have been introduced using small datasets with poor and inconsistent segmentation. This work compared manual segmentation with our proposed hybrid automatic segmentation method (HHM) for this classification problem. Methods...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
The Korean Society of Medical Informatics
2023-04-01
|
| Series: | Healthcare Informatics Research |
| Subjects: | |
| Online Access: | http://e-hir.org/upload/pdf/hir-2023-29-2-152.pdf |
| _version_ | 1797826316379095040 |
|---|---|
| author | Waheed Ali Laghari Audrey Huong Kim Gaik Tay Chang Choon Chew |
| author_facet | Waheed Ali Laghari Audrey Huong Kim Gaik Tay Chang Choon Chew |
| author_sort | Waheed Ali Laghari |
| collection | DOAJ |
| description | Objectives Various techniques for dorsal hand vein (DHV) pattern extraction have been introduced using small datasets with poor and inconsistent segmentation. This work compared manual segmentation with our proposed hybrid automatic segmentation method (HHM) for this classification problem. Methods Manual segmentation involved selecting a region-of-interest (ROI) in images from the Bosphorus dataset to generate ground truth data. The HHM combined histogram equalization and morphological and thresholding-based algorithms to localize veins from hand images. The data were divided into training, validation, and testing sets with an 8:1:1 ratio before training AlexNet. We considered three image augmentation strategies 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 HHM method showed slightly inferior performance (76.5%). Considerable improvement was observed in the test accuracy of the model trained with the inclusion of automatically segmented and augmented images (84%), with low false acceptance and false rejection rates (0.00035% and 0.095%, respectively). A comparison with past studies further demonstrated the competitiveness of our technique. Conclusions Our technique can be feasible for extracting the ROI in DHV images. This strategy provides higher consistency and greater efficiency than the manual approach. |
| first_indexed | 2024-03-13T11:06:58Z |
| format | Article |
| id | doaj.art-ea852378b5604bbf962ccd3744b835bf |
| institution | Directory Open Access Journal |
| issn | 2093-3681 2093-369X |
| language | English |
| last_indexed | 2024-03-13T11:06:58Z |
| publishDate | 2023-04-01 |
| publisher | The Korean Society of Medical Informatics |
| record_format | Article |
| series | Healthcare Informatics Research |
| spelling | doaj.art-ea852378b5604bbf962ccd3744b835bf2023-05-16T06:23:33ZengThe Korean Society of Medical InformaticsHealthcare Informatics Research2093-36812093-369X2023-04-0129215216010.4258/hir.2023.29.2.1521159Dorsal Hand Vein Pattern Recognition: A Comparison between Manual and Automatic Segmentation MethodsWaheed Ali LaghariAudrey HuongKim Gaik TayChang Choon ChewObjectives Various techniques for dorsal hand vein (DHV) pattern extraction have been introduced using small datasets with poor and inconsistent segmentation. This work compared manual segmentation with our proposed hybrid automatic segmentation method (HHM) for this classification problem. Methods Manual segmentation involved selecting a region-of-interest (ROI) in images from the Bosphorus dataset to generate ground truth data. The HHM combined histogram equalization and morphological and thresholding-based algorithms to localize veins from hand images. The data were divided into training, validation, and testing sets with an 8:1:1 ratio before training AlexNet. We considered three image augmentation strategies 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 HHM method showed slightly inferior performance (76.5%). Considerable improvement was observed in the test accuracy of the model trained with the inclusion of automatically segmented and augmented images (84%), with low false acceptance and false rejection rates (0.00035% and 0.095%, respectively). A comparison with past studies further demonstrated the competitiveness of our technique. Conclusions Our technique can be feasible for extracting the ROI in DHV images. This strategy provides higher consistency and greater efficiency than the manual approach.http://e-hir.org/upload/pdf/hir-2023-29-2-152.pdfbiometricsveinsclassificationdeep learningtransfer learning |
| spellingShingle | Waheed Ali Laghari Audrey Huong Kim Gaik Tay Chang Choon Chew Dorsal Hand Vein Pattern Recognition: A Comparison between Manual and Automatic Segmentation Methods Healthcare Informatics Research biometrics veins classification deep learning transfer learning |
| title | Dorsal Hand Vein Pattern Recognition: A Comparison between Manual and Automatic Segmentation Methods |
| title_full | Dorsal Hand Vein Pattern Recognition: A Comparison between Manual and Automatic Segmentation Methods |
| title_fullStr | Dorsal Hand Vein Pattern Recognition: A Comparison between Manual and Automatic Segmentation Methods |
| title_full_unstemmed | Dorsal Hand Vein Pattern Recognition: A Comparison between Manual and Automatic Segmentation Methods |
| title_short | Dorsal Hand Vein Pattern Recognition: A Comparison between Manual and Automatic Segmentation Methods |
| title_sort | dorsal hand vein pattern recognition a comparison between manual and automatic segmentation methods |
| topic | biometrics veins classification deep learning transfer learning |
| url | http://e-hir.org/upload/pdf/hir-2023-29-2-152.pdf |
| work_keys_str_mv | AT waheedalilaghari dorsalhandveinpatternrecognitionacomparisonbetweenmanualandautomaticsegmentationmethods AT audreyhuong dorsalhandveinpatternrecognitionacomparisonbetweenmanualandautomaticsegmentationmethods AT kimgaiktay dorsalhandveinpatternrecognitionacomparisonbetweenmanualandautomaticsegmentationmethods AT changchoonchew dorsalhandveinpatternrecognitionacomparisonbetweenmanualandautomaticsegmentationmethods |