2016
DOI: 10.1007/s00521-016-2285-9
|View full text |Cite
|
Sign up to set email alerts
|

A fast and accurate method for detecting fingerprint reference point

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
6
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
6
2
1

Relationship

0
9

Authors

Journals

citations
Cited by 14 publications
(6 citation statements)
references
References 33 publications
0
6
0
Order By: Relevance
“…As power consumption(inversely proportional to the energy efficiency) of the hardware accelerator is directly determined by the fabrication technology processes, technology scaling is considered to ensure the fair comparisons of the energy efficiency. For technology scaling, the definition of S and the normalization of power consumption are (7,8) from [39]. As a result, energy efficiency of the vector-SIMD DSP Matrix2000 is normalized to 16nm to be compared with the GPUs on the same fabrication technology in Figure 13.…”
Section: Resultsmentioning
confidence: 99%
See 1 more Smart Citation
“…As power consumption(inversely proportional to the energy efficiency) of the hardware accelerator is directly determined by the fabrication technology processes, technology scaling is considered to ensure the fair comparisons of the energy efficiency. For technology scaling, the definition of S and the normalization of power consumption are (7,8) from [39]. As a result, energy efficiency of the vector-SIMD DSP Matrix2000 is normalized to 16nm to be compared with the GPUs on the same fabrication technology in Figure 13.…”
Section: Resultsmentioning
confidence: 99%
“…In recent years, deep convolutional neural network (DCNN) algorithms have been widely adopted for computer vision tasks including image classification, object detection, semantic segmentation and so on [1]- [8]. In large scale visual recognition challenge (ILSVRC) 2012, AlexNet [9] achieved the best results, making DCNN the core algorithm model for image classification.…”
Section: Introductionmentioning
confidence: 99%
“…We referred to the methods used in fingerprint pattern classification field which is mainly based on smoothing processing. The refining method achieved a good result in 2D case [24], [30], [31]. We generalize the method to 3D manifold.…”
Section: Noise Deductionmentioning
confidence: 89%
“…The proposed approach achieved 59% accuracy on the subset of the mentioned databases. An extension of the previous approach has been proposed in [3]. While walking on the singularity, the location of the detected singular point is further refined using an enhancement method based on the mean-shift concept.…”
Section: Related Workmentioning
confidence: 99%