SIFT Based Vein Recognition Models: Analysis and Improvement

Wang, Guoqing; Wang, Jun

doi:10.1155/2017/2373818

Cited by 17 publications

(10 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(iv) The set of all extremal regions can be enumerated in worst-case ( ), where is the number of pixels in the image (16). Use of other detectors such as SIFT (Scale-Invariant Feature Transform) has been described (18)(19)(20). However, in the present study, use of the MSER detector was appropriate.…”

Section: Mser Detectormentioning

confidence: 98%

Automatic 2D Segmentation of an Intracardiac Catheter Based on MSER Blob Detector and Eccentricity

Danilov

Skirnevskiy

Gerget

et al. 2018

Proceedings of the VTH International Workshop "Critical Infrastructures: Contingency Management, Intelligent, Agent-Based, Clou

View full text Add to dashboard Cite

The present study describes an algorithm for automatic catheter detection and segmentation based on echocardiography data. The catheter area was recognized and then delineated by combination of detection and segmentation techniques such as the maximally stable extremal regions (MSER) algorithm, feature analysis and Kittler-Illingworth thresholding algorithm. Regions processed by MSER detector were restricted by eccentricity. Eccentricity, assessing the shape of the particular region, was chosen as the main feature. Morphological closing was applied at the pre-processing step. After applying MSER blob detector, detection accuracy of the catheter made up 86.7±11.5%. After performing an additional restriction based on the shape analysis, the accuracy increased to 92.8±6.6%. The proposed algorithm allows performing automatic detection and segmentation of the catheter inside the heart based on 2D echocardiography data.

show abstract

Section: Mser Detectormentioning

confidence: 98%

Automatic 2D Segmentation of an Intracardiac Catheter Based on MSER Blob Detector and Eccentricity

Danilov

Skirnevskiy

Gerget

et al. 2018

Proceedings of the VTH International Workshop "Critical Infrastructures: Contingency Management, Intelligent, Agent-Based, Clou

View full text Add to dashboard Cite

show abstract

“…The first convolution layer has a 2 × 2 stride. [39] 2011 100 1.10 Improved SIFT [40] 2017 100 1.08 Gradient-based 2D Gabor [41] 2019 100 1.60 Wave Atom Transform [42] 2020 100 0 MWCDE [43] 2020 100 0.62 MSFRA [44] 2021 100 0.791 Proposed-880 nm 2020 100 0…”

Section: Comparison With Related Workmentioning

confidence: 99%

Contactless Multispectral Palm-Vein Recognition With Lightweight Convolutional Neural Network

Chen

Hsia²,

Chen

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The average curvature values of different directions for each point are used. Wang et al [7] applied the scale-invariant feature transformation (SIFT) algorithm to extract detailed finger-vein features. The intersection point of finger-vein textures is chosen.…”

Section: Introductionmentioning

confidence: 99%

FFV-MBC: A Novel Fused Finger-Vein Recognition Method Based on Monogenic Binary Coding

Tao¹,

Tao²,

Wang³

et al. 2023

Journal of Compurters

View full text Add to dashboard Cite

<p>To improve pattern representation capabilities and robustness in traditional finger-vein recognition algorithms. In this paper, we propose FFV-MBC, a novel fused finger-vein recognition method based on monogenic binary coding (MBC). First of all, the amplitude, orientation, and phase information of the finger-vein images are filtered by a multi-scale monogenic log-Gabor filter and encoded by the binary coding theory. Three local features, MBC-A, MBC-P, and MBC-O, are achieved from different combinations of local image intensity and variation coding. After obtaining the features, we utilize the block-based Fisher Linear Discriminant method to reduce the dimension. Finally, the similarity components are calculated by the cosine distance and fused for the final finger-vein recognition results. We evaluate our proposed method on two publicly available datasets and one self-built dataset, i.e., Malaysian Polytechnic University (FV-USM), the Group of Machine Learning and Applications of Shandong University (SDUMLA-HMT), and our team, Signal and Information Processing Laboratory (FV-SIPL). On average, the proposed method achieved high recognition accuracy, i.e., 99.30%, and 1.10% equal error rates (EER). Overall, the proposed method performs better than most classical and state-of-the-art finger-vein recognition methods.</p> <p> </p>

show abstract

SIFT Based Vein Recognition Models: Analysis and Improvement

Cited by 17 publications

References 34 publications

Automatic 2D Segmentation of an Intracardiac Catheter Based on MSER Blob Detector and Eccentricity

Automatic 2D Segmentation of an Intracardiac Catheter Based on MSER Blob Detector and Eccentricity

Contactless Multispectral Palm-Vein Recognition With Lightweight Convolutional Neural Network

FFV-MBC: A Novel Fused Finger-Vein Recognition Method Based on Monogenic Binary Coding

Contact Info

Product

Resources

About