Related Experiment Video
Updated: Dec 25, 2025
14:58
Optical Scatter Microscopy Based on Two-Dimensional Gabor Filters
Published on: June 2, 2010
9.9K
Feature extraction of face image based on LBP and 2-D Gabor wavelet transform
Qian Zhang1, Hai Gang Li1, Ming Li1
1School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, China.
Mathematical Biosciences and Engineering : MBE
|April 3, 2020
Summary
This study introduces a robust face recognition algorithm using 2-D Gabor wavelet transform and Local Binary Patterns (LBP). The combined approach enhances classification accuracy by achieving invariance to illumination, pose, and expression variations.
Area of Science:
- Computer Science
- Image Processing
- Pattern Recognition
Background:
- Face image patterns are susceptible to variations in illumination, gesture, and expression.
- Robust data representation is crucial for accurate face pattern classification.
Purpose of the Study:
- To propose a novel face image recognition algorithm.
- To enhance classification accuracy by combining 2-D Gabor wavelet transform and Local Binary Pattern (LBP).
Main Methods:
- Utilized 2-D Gabor wavelet transform for invariance to pose and expression variations.
- Employed Local Binary Pattern (LBP) as a descriptor invariant to illumination.
- Integrated image blocking, histogram statistics, PCA dimensionality reduction, and nearest-neighbor classification.
Main Results:
- The 2-D Gabor wavelet representation demonstrated good classification accuracy at large scales.
- Combining LBP with 2-D Gabor wavelet features improved face recognition performance.
- The algorithm showed enhanced classification performance across different scales and directions.
Conclusions:
- The proposed algorithm offers a robust solution for face image recognition.
- The combination of 2-D Gabor wavelet transform and LBP effectively handles variations in face images.
- This approach achieves superior classification performance in diverse conditions.
