Image Recognition Using LBP Feature Extraction and Joint Bayesian Algorithm
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing facial recognition technologies based on Mahalanobis distance calculations suffer from low accuracy due to limitations in their algorithms.
Innovation Solution
The integration of Local Binary Pattern (LBP) feature extraction with a joint Bayesian algorithm for image recognition, which involves extracting LBP feature vectors, calculating high-dimensional feature vectors, and using a training matrix to perform image recognition, enhancing accuracy and robustness against variations in facial expressions and lighting conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If Mahalanobis distance-based calculation algorithm is used for similarity calculation, then the calculation process is simple, but the accuracy of similarity calculation is low
Solution Approach 1:
The patent segments the feature extraction process into multiple components: LBP feature extraction, high-dimensional feature vector calculation, and joint Bayesian algorithm processing. This segmentation allows each component to be optimized independently, achieving high accuracy without excessive overall complexity
Solution Approach 2:
The patent combines multiple algorithmic components (LBP feature extraction + high-dimensional feature vector + joint Bayesian algorithm) to create a composite recognition system. This composite approach achieves superior accuracy by integrating the strengths of different methods while managing complexity through modular design
2Reliability
If traditional facial recognition methods are used, then the implementation is straightforward, but the accuracy under variations in facial expressions and lighting conditions is low
Solution Approach 1:
The patent applies LBP (Local Binary Pattern) feature extraction which focuses on local texture characteristics of facial regions. By analyzing local patterns rather than global features, the system maintains high reliability under variations in lighting and expressions while keeping the computational approach manageable
Solution Approach 2:
The patent performs preliminary feature extraction using LBP and calculates high-dimensional feature vectors before applying the joint Bayesian algorithm. This preliminary processing prepares the data in advance, enabling the recognition system to handle variations in expressions and lighting more effectively without increasing real-time complexity
Data Source
AI summary
The present disclosure discloses an image recognition method and apparatus, and belongs to the field of computer technologies. The method includes: extracting a local binary pattern (LBP) feature vector of a target image; calculating a high-dimensional feature vector of the target image according to the LBP feature vector; obtaining a training matrix, the training matrix being a matrix obtained by training images in an image library by using a joint Bayesian algorithm; and recognizing the target image according to the high-dimensional feature vector of the target image and the training matrix. The image recognition method and apparatus according to the present disclosure may combine LBP algorithm with a joint Bayesian algorithm to perform recognition, thereby improving the accuracy of image recognition.