CNN Algorithms for Detection of Human Face Attributes – A Survey

Abstract

In recent years, CNN algorithms are being increasingly applied for various computer vision based applications such as disaster management systems using crowd-sourced images. Flood is one such frequent natural disaster that threatens human life and property. Research is in progress to find the extent of damage in flood hit areas by calculating the depth of the water using flood images containing humans captured by smartphone cameras. Algorithms, which can detect a human face and its attributes such as age, gender and ethnicity with these crowd-sourced images, can provide valuable information during such situations. A multitude of CNN algorithms is available for these tasks. Each one of them is different in their architecture which in turn influences the accuracy of the results. In this survey, we compare the state of the art CNN algorithms which perform each of these tasks, namely, face detection, age and gender classification, and ethnicity classification. We compare these algorithms with respect to their performance and accuracy so that an appropriate algorithm can be selected for the above application.