Understanding Aesthetics in Photography using Deep Convolutional Neural Networks
This work addresses the challenge of subjective aesthetic evaluation in photography, offering a tool to improve workflows for professionals, though it is incremental as it applies existing deep learning methods to this domain.
The paper tackled the problem of evaluating aesthetic value in digital photographs by using deep convolutional neural networks trained on over 1.7 million Flickr photos, resulting in a publicly available Web-based application for real-life use such as assisting professional photographers.
Evaluating aesthetic value of digital photographs is a challenging task, mainly due to numerous factors that need to be taken into account and subjective manner of this process. In this paper, we propose to approach this problem using deep convolutional neural networks. Using a dataset of over 1.7 million photos collected from Flickr, we train and evaluate a deep learning model whose goal is to classify input images by analysing their aesthetic value. The result of this work is a publicly available Web-based application that can be used in several real-life applications, e.g. to improve the workflow of professional photographers by pre-selecting the best photos.