Face Recognition Based on the Coefficient Tree for Three Scale Wavelet Transformation

Lyanpen, Wang; Petrosyan, O. G.; Du, Jian Hua

doi:10.3103/s0146411619080315

Cited by 3 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It employs wavelet functions to break down and reconstruct the image, thereby extracting information about different frequencies present in the image. The wavelet transform of image enables image into low-frequency and highfrequency components [43]. The low-frequency component contains general structure and low-frequency details, while the high-frequency component comprises fine details such as edges and textures within the image.…”

Section: Wavelet Transformmentioning

confidence: 99%

Research on Fingerprint Image Differential Privacy Protection Publishing Method Based on Wavelet Transform and Singular Value Decomposition Technology

Liu,

Zhi,

Zhao

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Due to the inherent privacy concerns associated with fingerprint image, technology of fingerprint recognition has been extensively utilized for identity authentication. However, direct publication of fingerprint image on the Internet can result in the leakage of sensitive information. In order to protect the sensitive information in fingerprint image, this paper proposes a novel method called LSDP that combines wavelet transform and singular value decomposition while ensuring the differential privacy protection. The primary focus of protecting fingerprint image involves safeguarding matrix of two-dimensional image. To mitigate excessive noise generated by the differential privacy when adding noise to the matrix of fingerprint image, this study employs wavelet transform as a solution. Additionally, the exponential mechanism is utilized in conjunction with the wavelet transform to select an appropriate threshold in order to reduce noise added by the differential privacy. This approach is referred to as DWP. Furthermore, the singular value decomposition applied to the wavelet transforms coefficients. In order to reduce the effect of noise errors, perturbation noise is only added to the singular values instead of all coefficients. This proposed method is termed SDP. To enhance the privacy protection of publication of fingerprint image, the proposed LSDP add perturbation noise to only some of the singular values. The experimental results demonstrate that our proposed algorithm outperforms the direct application of the wavelet transform or the singular value decomposition in terms of safeguarding fingerprint image.INDEX TERMS wavelet transforms, singular value decomposition, differential privacy, publication of fingerprint image

show abstract

Section: Wavelet Transformmentioning

confidence: 99%

Research on Fingerprint Image Differential Privacy Protection Publishing Method Based on Wavelet Transform and Singular Value Decomposition Technology

Liu,

Zhi,

Zhao

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…With the application of face recognition in various fields, how to apply it to the medical field has become a hotspot of current research. For example, Lyanpen and others applied face recognition to patient admission management, which greatly saved the time of admission [ 16 ]; Mamata and Ninad combined face recognition with voice assistance to help patients call nursing services [ 17 ]; Jenifa et al applied face recognition to patients' expression evaluation, which can assist in the evaluation of patients' emotions [ 18 ]. However, it has been found in practice that the application of face recognition technology in medical institutions is increasing, but there are not many studies on the application of bar codes in laboratory departments.…”

Section: Introductionmentioning

confidence: 99%

Design of Association Application System of Face Recognition and Test-Tube Barcode Based on CNN

Zhou

Niu

2022

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

In order to improve the standardization and accuracy of business process management of laboratory department in hospitals, combined with convolutional neural networks (CNN) and face recognition technology, an association application system of laboratory face recognition and test-tube barcode is designed by inputting patient’s face and blood test-tube barcode into the system for storage. When the patient logs into the system again, the system uses the patient’s face to automatically search for a matching test-tube barcode to obtain the test results. The simulation results show that the system can accurately recognize the face and match the corresponding test-tube barcode, and the accuracy and ROC of face recognition are 0.85 and 0.94, respectively. In addition, when the patient’s face is within 5 m from the system camera, the accuracy of face recognition can reach 100%. It can be seen that the system designed in this paper shows good performance.

show abstract

QoS Based Route Selection in Cellulr IP Networks Using PSO

Anbar¹,

Ahmad²,

Mohammad³

et al. 2022

2022 4th International Youth Conference on Radio Electronics, Electrical and Power Engineering (REEPE)

View full text Add to dashboard Cite

Face Recognition Based on the Coefficient Tree for Three Scale Wavelet Transformation

Cited by 3 publications

References 8 publications

Research on Fingerprint Image Differential Privacy Protection Publishing Method Based on Wavelet Transform and Singular Value Decomposition Technology

Research on Fingerprint Image Differential Privacy Protection Publishing Method Based on Wavelet Transform and Singular Value Decomposition Technology

Design of Association Application System of Face Recognition and Test-Tube Barcode Based on CNN

QoS Based Route Selection in Cellulr IP Networks Using PSO

Contact Info

Product

Resources

About