Enhanced Local Binary Patterns for Automatic Face Recognition
This work addresses face recognition robustness for real-world applications, though it appears incremental as it builds on existing local binary patterns.
The paper tackles the problem of face recognition under challenging conditions like noise, illumination variations, and limited training data by proposing an enhanced local binary patterns descriptor that considers more pixels and different neighborhoods. The method outperforms state-of-the-art approaches on UFI and FERET datasets and handles issues like single training samples and varying image resolutions effectively.
This paper presents a novel automatic face recognition approach based on local binary patterns. This descriptor considers a local neighbourhood of a pixel to compute the feature vector values. This method is not very robust to handle image noise, variances and different illumination conditions. We address these issues by proposing a novel descriptor which considers more pixels and different neighbourhoods to compute the feature vector values. The proposed method is evaluated on two benchmark corpora, namely UFI and FERET face datasets. We experimentally show that our approach outperforms state-of-the-art methods and is efficient particularly in the real conditions where the above mentioned issues are obvious. We further show that the proposed method handles well one training sample issue and is also robust to the image resolution.