Image aesthetics depends on context

Simond, Florian; Arvanitopoulos, Nikolaos; Süsstrunk, Sabine

doi:10.1109/icip.2015.7351513

Cited by 15 publications

(10 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Nishiyama et al [69] proposed a method that relied on color harmony and bags of color patterns to catch color variations in local regions. In Simond et al [70], it was shown that the aesthetics in images depends on context, since the authors obtained more accurate predictions by selecting features for specific image categories.…”

Section: Classical Machine Learning Approachesmentioning

confidence: 99%

Will the Machine Like Your Image? Automatic Assessment of Beauty in Images with Machine Learning Techniques

Bodini

2019

Inventions

View full text Add to dashboard Cite

Although the concept of image quality has been a subject of study for the image processing community for more than forty years (where, with the term “quality”, we are referring to the accuracy with which an image processing system captures, processes, stores, compresses, transmits, and displays the signals that compose an image), notions related to aesthetics of photographs and images have only appeared for about ten years within the community. Studies devoted to aesthetics of images are multiplying today, taking advantage of the latest machine learning techniques and mostly due to the proliferation of huge communities and websites, specialized in digital photography sharing and archiving, such as Flickr, Imgur, DeviantArt, and Instagram. In this review, we examine the latest advances of computer methods that aim at computationally distinguishing high-quality from low-quality photos and images, relying on machine learning techniques. The paper is organized as follows: First, we introduce many approaches to aesthetics, studied in philosophy, neurobiology, experimental psychology, and sociology, to see what lighting they propose to researchers. Such points of view let us explain the weakness of the current consensus on the difficult aesthetics problem and the importance of the ongoing debates on it. Then, we analyze the work done in the community of pattern recognition and artificial intelligence on the task of automatic aesthetic assessment, and we both compare and critically examine the presented results. Finally, we describe many issues that have not been addressed, and starting from these, we outline some possible future directions.

show abstract

Section: Classical Machine Learning Approachesmentioning

confidence: 99%

Will the Machine Like Your Image? Automatic Assessment of Beauty in Images with Machine Learning Techniques

Bodini

2019

Inventions

View full text Add to dashboard Cite

show abstract

“…The first category [1][2][3][4]9] links aesthetics with handcrafted low-level image features, e.g., color distribution, edge distribution, hue channel, etc. Another category [5][6][7] uses generic image features such as SIFT [13] or Fisher Vector [14,15], which have been shown to outperform the handcrafted low-level features.…”

Section: State-of-the-artmentioning

confidence: 99%

“…Moreover, users can manage their images collections based on aesthetics. Hence, various algorithms [1][2][3][4][5][6][7][8][9][10] have been proposed in the recent years to perform image aesthetics assessment.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Image aesthetic predictors based on weighted CNNs

Jin

Segovia²,

Süsstrunk

2016

2016 IEEE International Conference on Image Processing (ICIP)

Self Cite

View full text Add to dashboard Cite

Convolutional Neural Networks (CNNs) have been widely adopted for many imaging applications. For image aesthetics prediction, state-of-the-art algorithms train CNNs on a recently-published large-scale dataset, AVA. However, the distribution of the aesthetic scores on this dataset is extremely unbalanced, which limits the prediction capability of existing methods. We overcome such limitation by using weighted CNNs. We train a regression model that improves the prediction accuracy of the aesthetic scores over state-of-the-art algorithms. In addition, we propose a novel histogram prediction model that not only predicts the aesthetic score, but also estimates the difficulty of performing aesthetics assessment for an input image. We further show an image enhancement application where we obtain an aesthetically pleasing crop of an input image using our regression model.

show abstract

“…The assessment of the aesthetic quality of videos is a challenging field of research in today's digital world. In recent years, the amount of digital media has been growing significantly, and thus the development of effective aesthetic assessment methods is in great need in order to enhance multimedia content management in various applications, such as personal image collection management [1], food photo aesthetics assessment [2], and online fashion shopping photo assessment [3]. In the video domain, the automatic assessment of each video's aesthetic value could further improve the users' experience in multimedia content distribution channels, since videos could be retrieved or recommended by also taking their aesthetic quality into account.…”

Section: Introductionmentioning

confidence: 99%

Video aesthetic quality assessment using kernel Support Vector Machine with isotropic Gaussian sample uncertainty (KSVM-IGSU)

Tzelepis¹,

Mavridaki²,

Mezaris³

et al. 2016

2016 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

In this paper we propose a video aesthetic quality assessment method that combines the representation of each video according to a set of photographic and cinematographic rules, with the use of a learning method that takes the video representation's uncertainty into consideration. Specifically, our method exploits the information derived from both low-and high-level analysis of video layout, leading to a photo-and motion-based video representation scheme. Subsequently, a kernel Support Vector Machine (SVM) extension, the KSVM-iGSU, is trained to classify the videos and retrieve those of high aesthetic value. Experimental results on our large dataset verify the effectiveness of the proposed method. We also make publicly available our dataset, in order to facilitate research in the area of video aesthetic quality assessment.

show abstract

Image aesthetics depends on context

Cited by 15 publications

References 20 publications

Will the Machine Like Your Image? Automatic Assessment of Beauty in Images with Machine Learning Techniques

Will the Machine Like Your Image? Automatic Assessment of Beauty in Images with Machine Learning Techniques

Image aesthetic predictors based on weighted CNNs

Video aesthetic quality assessment using kernel Support Vector Machine with isotropic Gaussian sample uncertainty (KSVM-IGSU)

Contact Info

Product

Resources

About