Finding Missing Children: Aging Deep Face Features
This addresses the challenge of identifying missing children who have aged, which is crucial for combating child trafficking or abduction, though it appears incremental as it builds on existing face matchers.
The paper tackles the problem of identifying missing children from face images after long time lapses, where standard face recognition systems perform poorly, and proposes an age-progression module that improves identification accuracy, e.g., boosting FaceNet from 40% to 49.56% and CosFace from 56.88% to 61.25% for time lapses over 10 years.
Given a gallery of face images of missing children, state-of-the-art face recognition systems fall short in identifying a child (probe) recovered at a later age. We propose an age-progression module that can age-progress deep face features output by any commodity face matcher. For time lapses larger than 10 years (the missing child is found after 10 or more years), the proposed age-progression module improves the closed-set identification accuracy of FaceNet from 40% to 49.56% and CosFace from 56.88% to 61.25% on a child celebrity dataset, namely ITWCC. The proposed method also outperforms state-of-the-art approaches with a rank-1 identification rate from 94.91% to 95.91% on a public aging dataset, FG-NET, and from 99.50% to 99.58% on CACD-VS. These results suggest that aging face features enhances the ability to identify young children who are possible victims of child trafficking or abduction.