Image Aesthetic Assessment: An experimental survey
251
TL;DR: In this article, a review of computer vision techniques used in the assessment of image aesthetic quality is presented, which aims at computationally distinguishing high quality from low quality photos based on photographic rules, typically in the form of binary classification or quality scoring.
read more
Abstract: This article reviews recent computer vision techniques used in the assessment of image aesthetic quality. Image aesthetic assessment aims at computationally distinguishing high-quality from low-quality photos based on photographic rules, typically in the form of binary classification or quality scoring. A variety of approaches has been proposed in the literature to try to solve this challenging problem. In this article, we summarize these approaches based on visual feature types (hand-crafted features and deep features) and evaluation criteria (data set characteristics and evaluation metrics). The main contributions and novelties of the reviewed approaches are highlighted and discussed. In addition, following the emergence of deep-learning techniques, we systematically evaluate recent deep-learning settings that are useful for developing a robust deep model for aesthetic scoring.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Computational Approaches to Aesthetic Quality Assessment of Digital Photographs: State of the Art and Future Research Directives
Soma Debnath,Suvamoy Changder +1 more
TL;DR: In this article, the authors present current state of the art in aesthetic evaluation of photographs and provide few future research directions in this area and some interesting and unexplored rules of composition like Spiral structure, Framing, Symmetry, Pattern and others.
8
•Posted Content
Meta-Learning Multi-task Communication
Pengfei Liu,Xuanjing Huang +1 more
TL;DR: A general framework: Parameters Read-Write Networks (PRaWNs) is described to systematically analyze current neural models for multi-task learning, in which existing models expect to disentangle features into different spaces while features learned in practice are still entangled in shared space, leaving potential hazards for other training or unseen tasks.
Modeling the Aesthetics of Audio-Scene Reproduction
John Mourjopoulos
- 01 Jan 2020
TL;DR: This chapter examines the adaptation of existing models of aesthetic response to include listeners’ aesthetic assessments of spatial-audio reproduction in conjunction with present and evolving methods for evaluating the quality of such audio presentations and proposes a computational model structure that can incorporate aesthetic functionality beyond or in conjunctionwith quality assessment.
7
Exploring Metrics to Establish an Optimal Model for Image Aesthetic Assessment and Analysis
TL;DR: An algorithm of determining the optimal model from many photo score prediction models generated by CNN-based repetitively self-revised learning (RSRL) is proposed, and the aesthetics features of the model regarding the first fixation perspective and the assessment interest region are defined by means of the feature maps so as to analyze the consistency with human aesthetics.
7
Understanding aesthetics in photography using deep convolutional neural networks
Maciej Suchecki,Tomasz Trzciski +1 more
- 01 Sep 2017
TL;DR: This work train and evaluate a deep learning model whose goal is to classify input images by analysing their aesthetic value, and produces 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.
7
References
Deep Residual Learning for Image Recognition
Kaiming He,Xiangyu Zhang,Shaoqing Ren,Jian Sun +3 more
- 27 Jun 2016
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
ImageNet classification with deep convolutional neural networks
TL;DR: A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.
Deep learning
TL;DR: Deep learning is making major advances in solving problems that have resisted the best attempts of the artificial intelligence community for many years, and will have many more successes in the near future because it requires very little engineering by hand and can easily take advantage of increases in the amount of available computation and data.
67K
Image quality assessment: from error visibility to structural similarity
TL;DR: In this article, a structural similarity index is proposed for image quality assessment based on the degradation of structural information, which can be applied to both subjective ratings and objective methods on a database of images compressed with JPEG and JPEG2000.
•Journal Article
Visualizing Data using t-SNE
TL;DR: A new technique called t-SNE that visualizes high-dimensional data by giving each datapoint a location in a two or three-dimensional map, a variation of Stochastic Neighbor Embedding that is much easier to optimize, and produces significantly better visualizations by reducing the tendency to crowd points together in the center of the map.
Related Papers (5)
Naila Murray,Luca Marchesotti,Florent Perronnin +2 more
- 16 Jun 2012
Kaiming He,Xiangyu Zhang,Shaoqing Ren,Jian Sun +3 more
- 27 Jun 2016
Hossein Talebi,Peyman Milanfar +1 more
Yan Ke,Xiaoou Tang,Feng Jing +2 more
- 17 Jun 2006