Face image quality for actor profile image curation
Selecting an ideal profile image to represent a person is a common problem with many applications. The ideal characteristics of a representative or profile image differ based on the application. In this work, we focus on selecting a representative face which is easy to recognise and aesthetically pleasing. Manually curating these images is time consuming, repetitive, and subjective. This makes the quality of curated images inconsistent. We have built a solution to automate this process and make it efficient, scalable, and consistent. In this work, we describe the various factors which affect the suitability of a face image for recognition by humans. We propose efficient solutions which can solve the problem without the use of ground truth data. We train a regression model using weak supervision provided by heuristics based on features which affect face quality. Finally, we use professional photography techniques to create standardized and aesthetically pleasing profile images.
For the full paper, see Face image quality for actor profile image curation on the Amazon Science website.