Portrait Quality Assessment using Multi-Scale CNN

Abstract

In this paper, we propose a novel and standardized approach to the problem of camera-quality assessment on portrait scenes. Our goal is to evaluate the capacity of smartphone front cameras to preserve texture details on faces. We introduce a new portrait setup and an automated texture measurement. The setup includes two custom-built lifelike mannequin heads, shot in a controlled lab environment. The automated texture measurement includes a Region-of-interest (ROI) detection and a deep neural network. To this aim, we create a realistic mannequins database, which contains images from different cameras, shot in several lighting conditions. The ground-truth is based on a novel pairwise comparison technology where the scores are generated in terms of Just-Noticeable-differences (JND). In terms of methodology, we propose a Multi-Scale CNN architecture with random crop augmentation, to overcome overfitting and to get a low-level feature extraction. We validate our approach by comparing its performance with several baselines inspired by the Image Quality Assessment (IQA) literature.

Image quality evaluation of video conferencing solutions with realistic laboratory scenes

“…At the current revision of this document, the scoring on the DMC is done by a trained AI algorithm [12] and has a score scale from 0, the worst, to 100, the best observed. The scoring on the fair mannequin head is done perceptually, and the results are being used to train an AI algorithm for this scene [13], and has a score scale from 0, the worst, to 100, the best observed. The edge acutance metric on the Deadleaves chart is identical to the one used on the focus range measurement.…”