Abstract Face stands out as a preferable biometric trait for automatic human authentication as it is intuitive and non-intrusive. This paper investigates various feature-based automatic face recognition approaches in detail. High degree of freedom in head movement and human emotion leads a face recognition system to face critical challenges in terms of pose, illumination and expression. Human face also undergoes irreversible changes due to aging. These factors makes the process of face recognition non trivial and hard. This paper also provides a review of the facial recognition approaches individually dealing with these issues. Applications of face recognition in the forensic domain sometimes needs identification using a scanned facial image. The scenario is quite useful to get investigative leads. Important approaches for the same are also been discussed in the manuscript. Recent developments in the low-cost image capturing devices has flooded the facial image databases with a lot of images, at the same time availability of GPU based compute power has helped develop deep learning approaches to handle the face recognition at a very accurate and massive level. The same has also been surveyed and analyzed in the manuscript.

中文翻译：

---

人脸识别的最新进展

摘要 人脸因其直观且非侵入性而成为自动人体身份验证的首选生物特征。本文详细研究了各种基于特征的自动人脸识别方法。头部运动和人类情感的高度自由导致人脸识别系统面临姿势、光照和表情方面的严峻挑战。人脸也会因衰老而发生不可逆转的变化。这些因素使人脸识别的过程变得不平凡和艰难。本文还回顾了单独处理这些问题的面部识别方法。人脸识别在法医领域的应用有时需要使用扫描的面部图像进行识别。该场景对于获得调查线索非常有用。手稿中也讨论了相同的重要方法。低成本图像捕捉设备的最新发展使大量图像充斥着面部图像数据库，同时基于 GPU 的计算能力的可用性帮助开发了深度学习方法来处理非常准确和大规模的面部识别. 手稿中也进行了相同的调查和分析。