.png){kind=icon}
Return
Application of Optimized Local Binary Pattern Algorithm in Small Pose Face Recognition under Machine Vision
.png){kind=icon}
PRE
AI
DOI：10.1007/s11042-021-11809-9.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
With the development of information technology, face recognition technology is becoming more robust against the influence of illumination, pose, and noise. The purpose is to study the application of an optimized Local Binary Pattern (LBP) algorithm based on machine vision in small-pose face recognition, thereby promoting the application of face recognition technologies in various fields. An improved LBP algorithm is proposed, namely the Gradient Local Binary Pattern (GLBP). Multiple path lines are used for sampling, then the neighborhood of two scales in the collected face image is calculated by GLBP, and the two-scale GLBP coding values are fused to obtain Two Gradient Local Binary Pattern (TGLBP) algorithm. Finally, the face recognition performance of the TGLBP algorithm is analyzed under simulation.The recognition accuracy of the proposed system is verified under comparative analysis with different algorithms. The results suggest that the recognition accuracy of the proposed TGLBP algorithm has reached 99.31%, 96.84%, and 95.31%, respectively in background set, expression set, and ornament set, all of which are at least 2.5% higher than that of other algorithms; Under the noise robustness recognition analysis, the robustness recognition accuracy of the proposed TGLBP algorithm model is significantly better than other algorithms, which is always over 90%. Therefore, the proposed TGLBP algorithm has higher face recognition accuracy and better noise robustness. The results can provide an experimental reference for the later intellectual development of image recognition.
Keywords:
Local binary pattern algorithm
Face recognition
TGLBP
Robustness
Background set
Journal
IF:
3
Papers:
2.0W
Citations:
3.2W
Organization
Cited Papers
ShareSaveComparison of Non-Oncological Postoperative Outcomes Following Robotic and Laparoscopic Colorectal Resection for Colorectal Malignancy: A Systematic Review and Meta-Analysis.png)
Cureus
OAAI
CureusIF0
OAAIShareSaveShareSaveExtended visual cryptography-based copyright protection scheme for multiple images and owners using LBP-SURF descriptorsVISUAL COMPUTER
VISUAL COMPUTERIF2.9
PREAI
ShareSaveShareSaveCollaborative representation based face classification exploiting block weighted LBP and analysis dictionary learningPATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAIShareSaveShareSaveThree-dimensional salient point detection based on the Laplace-Beltrami eigenfunctionsVISUAL COMPUTER
VISUAL COMPUTERIF2.9
PREAI
ShareSaveShareSave
View more