Score based Face Quality Assessment (FQA)
Shubhobrata Bhattacharya, Aurobinda Routray · 2017
Face image quality has a key role in the performance accuracy of automatic face recognition algorithms. In video sequence multiple faces of a subject are available of which selecting the face image(s) with high quality improves the recognition performance. Face detection algorithms often encounter the problem of detecting outliers as a face. This enhances the computational load and increases the risk of face mismatch. In this work, we propose a feature based learning framework for assessing the face image quality. The proposed method is simple and easy to implement for different recognition methods. Experimental result demonstrates its effectiveness in improving the robustness of face detection and recognition.