Noise Sensitivity of Local Descriptors vs ConvNets: An application to Facial Recognition
This work addresses noise robustness in facial recognition systems, but it is incremental as it applies existing methods to a new problem.
This study compared the noise sensitivity of local descriptors (LBP and LDP) versus a ConvNet (ResNet50) for facial recognition, finding that ResNet50 was more robust across five noise levels on the Extended Yale B dataset.
The Local Binary Patterns (LBP) is a local descriptor proposed by Ojala et al to discriminate texture due to its discriminative power. However, the LBP is sensitive to noise and illumination changes. Consequently, several extensions to the LBP such as Median Binary Pattern (MBP) and methods such as Local Directional Pattern (LDP) have been proposed to address its drawbacks. Though studies by Zhou et al, suggest that the LDP exhibits poor performance in presence of random noise. Recently, convolution neural networks (ConvNets) were introduced which are increasingly becoming popular for feature extraction due to their discriminative power. This study aimed at evaluating the sensitivity of ResNet50, a ConvNet pre-trained model and local descriptors (LBP and LDP) to noise using the Extended Yale B face dataset with 5 different levels of noise added to the dataset. In our findings, it was observed that despite adding different levels of noise to the dataset, ResNet50 proved to be more robust than the local descriptors (LBP and LDP).