Abstract
Face recognition approaches, especially those based on deep learning models, are becoming increasingly attractive for missing person identification, due to their effectiveness and the relative simplicity of obtaining information available for comparison. However, these methods still suffer from large accuracy drops when they have to tackle cross-age recognition, which is the most common condition to face in this specific task. To address these challenges, in this paper we investigate the contribution of different generative and discriminative models that extend the Probabilistic Linear Discriminant Analysis (PLDA) approach. These models aim at disentangling identity from other facial variations (including those due to age effects). As such, they can improve the age invariance characteristics of state-of-the-art deep facial embeddings. In this work, we experiment with a standard PLDA, a non-linear version of PLDA, the Pairwise Support Vector Machine (PSVM), and introduce a nonlinear version of PSVM (NL–PSVM) as a novelty. We thoroughly analyze the proposed models’ performance when addressing cross-age recognition in a large and challenging experimental dataset containing around 2.5 million images of 790,000 individuals. Results on this testbed confirm the challenges in age invariant face recognition, showing significant differences in the effects of aging across embedding models, genders, age ranges, and age gaps. Our experiments show as well the effectiveness of both PLDA and its proposed extensions in reducing the age sensitivity of the facial features, especially when there are significant age differences (more than ten years) between the compared images or when age-related facial changes are more pronounced, such as during the transition from childhood to adolescence or from adolescence to adulthood. Further experiments on three standard cross-age benchmarks (MORPH2, CACD-VS, and FG-NET) confirm the proposed models’ effectiveness.
Highlights
The “Collegno amnesiac” case is a notorious judicial affair that was discussed in the Italian media for more than 40 years [1]
NON–LINEAR Pairwise Support Vector Machine (PSVM) In Section III-B we have shown that, once the transformation g has been estimated, the NL–Probabilistic Linear Discriminant Analysis (PLDA) model can be interpreted as a PLDA model in the transformed feature space
We have shown that the PSVM approach has formally the same classification rules as PLDA
Summary
The “Collegno amnesiac” case is a notorious judicial affair that was discussed in the Italian media for more than 40 years [1]. The man did not remember his name and was later identified as several missing persons before concluding a lengthy investigation. His true identity was never indisputably proven. Face recognition (FR) is a well-studied problem in Computer Vision and Machine Learning. Since [5] surpassed human accuracy on the LFW dataset benchmark [27], novel Convolutional Neural Networks (CNN) architectures, lighter and more accurate, or using innovative objective functions, are proposed continuously in the literature. As soon as the accuracy on the LFW benchmark reached 99.7% and there was no room for significant improvements on simple sets, researchers started focusing on more challenging datasets and specific tasks, like improving the robustness to challenging image variations (e.g., cross-pose or cross-age FR). For a comprehensive review of the recent literature, we refer the interested readers to these two recent surveys [28], [29]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
