Studying Aesthetics in Photographic Images Using a Computational Approach

By Ritendra Datta, Dhiraj Joshi, Jia Li, James Ze Wang. 2006

1,045 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Computer Vision and Pattern Recognition

Citations in the corpus

Recognizing Image Style (2013, methodology): “[4], designed visual features to represent concepts such as colorfulness, saturation, rule-of-thirds, and depth-of-field, and evaluated aesthetic rating predictions on photographs; The same approach was further applied to a small set of Impressionist paintings [18].”
Affective image classification using features inspired by psychology and art theory (2010, methodology): “Although some work suggests that art and impression speciﬁc features are of advantage [32, 7], some of the works in this ﬁeld use common or generic features that are designed for example for object categorisation (e.g. in [3, 33, 34]). arbitrary emotional categories —”
Predicting users' first impressions of website aesthetics with a quantification of perceived visual complexity and colorfulness (2013, background): “Prior work in this direction mostly focused on extracting aesthetic features in natural images and evaluating their usefulness with ratings of appeal [9, 10].”
The Interestingness of Images (2013, background): “These include image quality [15], memorability [14] and aesthetics [10, 11].”
RAPID: Rating Pictorial Aesthetics using Deep Learning (2014, background): “Earlier visual aesthetics assessment research focused on examining handcrafted visual features based on common cues such as color [6, 26, 27], texture [6, 13], composition [21, 20, 7], and content [20, 7], as well as generic image descriptors [23, 31, 24].”
Salient object detection: A survey (2014, methodology): “peciﬁc task to improve the performance of an algorithm. For instance, for aesthetics reasons (e.g., rule of thirds), photographers tend to frame the salient object near the center of the image [153], [255]. From an application point of view, most images we are dealing with are intentionally captured”
Large-scale visual sentiment ontology and detectors using adjective noun pairs (2013, background): “The closest that comes to sentiment analysis for visual content is the analysis of aesthetics [6, 15, 22], interestingness [12], and affect or emotions [13, 21, 37, 36].”
Assessing the aesthetic quality of photographs using generic image descriptors (2011, methodology): “For the segmentation, a simple k-means region segmentation could be used [4], while more complex methods can spot in focus objects by detecting blurry edges (corresponding to background) [17].”
Content-based photo quality assessment (2011, methodology): “However, later studies [5, 12, 20] showed that regional features lead to better performance, since human beings perceive subject areas differently from the background (see examples in Figure 1).”
Image retrieval: Ideas, influences, and trends of the new age (2008, methodology): “What, in CBIR, is analogous to such ranking, given that a large subset of the images are determined to be semantically relevant? This question has been recently addressed in [Datta et al. 2006].”
High level describable attributes for predicting aesthetics and interestingness (2011, methodology): “Content Attributes - characteristics related to the presence of specific objects or categories of objects including faces, animals, and scene types.”
Predicting Pre-click Quality for Native Advertisements (2016, methodology): “Finally, we look at the Depth of Field, which measures the ranges of distances from the observer that appear acceptably sharp in a scene, using wavelet coefficients as in [7].”
AVA: A large-scale database for aesthetic visual analysis (2012, background): “Photo.net (PN) [3] : PN contains 3,581 images gathered from the social network Photo.net.”
Creating Summaries from User Videos (2014, methodology): “To predict the aesthetic quality of a frame we compute colorfulness [3], contrast [14] and the distribution of edges [14].”
Photo Aesthetics Ranking Network with Attributes and Content Adaptation (2016, background): “Early works formulate aesthetic analysis as a classification or a regression problem of mapping images to aesthetic ratings provided by human raters [5,11,18,6,26].”
A framework for photo-quality assessment and enhancement based on visual aesthetics (2010, background): “In addition to some of these low level cues, the authors of [6, 7] investigate the impact of features such as familiarity measures, wavelet responses on textures, aspect ratio and region composition on the aesthetic appeal of natural images.”
Automatic salient object segmentation based on context and shape prior (2011, background): “The second one as a location prior, has been studied in photo quality assessment [4, 8, 20], known as Rule of Thirds.”
Towards computational models of kinship verification (2010, neutral): “Similar to [5].”
Improving Post-Click User Engagement on Native Ads via Survival Analysis (2016, background): “Works on computational aesthetics, for instance [10], may bring additional perspectives in what makes a positive versus negative post-click experience.”