Technol Health Care. 2020;28(S1):25-35. doi: 10.3233/THC-209004.
Video-based face recognition (VFR) is one of the frontier topics in the domain of computer vision, which aims to automatically track and recognize facial regions of interests (ROIs) in video sequences.
In videos with multiple faces, the trajectories of individuals are incredibly complex. This is less studied than videos with a single face per frame.
In this paper, we present a multi-trajectory incremental learning (MTIL) algorithm, which categorizes trajectories using a Euclidean distance-based greedy algorithm and estimates the most likely labels for each trajectory by incremental learning to correct their classification and improve the accuracy of recognition. Furthermore, this study proposes an enhanced detection method that combines face detection with a robust tracking-learning-detection (TLD) algorithm to improve the performance of face detection in video. The method can also be extended for medical video recognition applications such as gesture recognition control based medical system.
Experiments on Honda/UCSD and BMP (seq_mb) database demonstrate that our method can improve the face detection and face recognition (single or multiple) performance. The method also performs well on the gesture recognition system.
The proposed MTIL algorithm can significantly improve the performance of the VFR system and the gesture recognition system.
基于视频的人脸识别（VFR）是计算机视觉领域的前沿课题之一，旨在自动跟踪和识别视频序列中的感兴趣的面部区域（ROI）。
在多个人脸的视频中，个体的轨迹非常复杂。这比每一帧一个人脸的视频研究得少。
在本文中，我们提出了一种多轨迹增量学习（MTIL）算法，该算法使用基于欧几里得距离的贪婪算法对轨迹进行分类，并通过增量学习估计每个轨迹的最可能标签，以纠正其分类并提高识别的准确性。此外，本研究提出了一种增强的检测方法，该方法将人脸检测与鲁棒的跟踪-学习-检测（TLD）算法相结合，以提高视频中人脸检测的性能。该方法还可以扩展到基于手势识别控制的医疗视频识别应用程序中。
在 Honda/UCSD 和 BMP（seq_mb）数据库上的实验表明，我们的方法可以提高人脸检测和人脸识别（单人或多人）的性能。该方法在手势识别系统中也表现良好。
所提出的 MTIL 算法可以显著提高 VFR 系统和手势识别系统的性能。
