Predicting Image Aesthetics with Deep Learning

Bianco, Simone; Celona, Luigi; Napoletano, Paolo; Schettini, Raimondo

doi:10.1007/978-3-319-48680-2_11

Cited by 34 publications

(25 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nowadays Deep Learning has been used for assessment of image aesthetics [32] [33].This field is under search to explore the gains that Deep learning has in comparison to machine learning techniques.…”

Section: VIImentioning

confidence: 99%

Aesthetics in Digital Photography: A Survey

Phatak¹

2020

IJRASET

View full text Add to dashboard Cite

Due to the rise in the popularity of digital cameras and digital photography, there are huge volumes of visual data available on the web. Some of these visual pictures are very beautiful and aesthetically pleasing while the others are not so appealing. Photo aesthetics is an emerging field of research which can categorize large image collections into aesthetically good and bad photographs. In our paper we discuss the existing aesthetic image evaluation on the basis of: 1) low level attributes e.g. color, texture, edges 2) Middle level attributes e.g., contours, shapes and regions. 3) High level attributes e.g. image composition, image content and sky attributes. We discuss image retrieval with respect to the relationships between the high, middle and low level attributes to reduce the semantic gap between the high level semantic features and low level attributes .Image aesthetics is a high level image retrieval attribute, we discuss and analyze the various aesthetics classification and prediction methods prevalent for determining the aesthetic inclination of an image.

show abstract

Section: VIImentioning

confidence: 99%

Aesthetics in Digital Photography: A Survey

Phatak¹

2020

IJRASET

View full text Add to dashboard Cite

show abstract

“…They allow the creation of models that can analyze any picture and predict their aesthetic value, without the need for any annotated data about its contents; and without making use of hand-crafted features. Some examples of the use of CNNs for image aesthetics prediction and related topics can be found in [2,20,33,6,11,4,9,35,10,17]. Some of those papers make use of information about the contents of the pictures to improve the predictions of the models.…”

Section: Related Work 21 Computational Aesthetic Assessment In Photomentioning

confidence: 99%

Personalised Aesthetics with Residual Adapters

Rodríguez-Pardo

Bilen

2019

Pattern Recognition and Image Analysis

View full text Add to dashboard Cite

The use of computational methods to evaluate aesthetics in photography has gained interest in recent years due to the popularization of convolutional neural networks and the availability of new annotated datasets. Most studies in this area have focused on designing models that do not take into account individual preferences for the prediction of the aesthetic value of pictures. We propose a model based on residual learning that is capable of learning subjective, userspecific preferences over aesthetics in photography, while surpassing the stateof-the-art methods and keeping a limited number of user-specific parameters in the model. Our model can also be used for picture enhancement, and it is suitable for content-based or hybrid recommender systems in which the amount of computational resources is limited.The problem of taking into account subjective preferences on image aesthetics prediction is referred to as personalized image aesthetics [27]. Most recent approaches to image aesthetics evaluation have used different deep-learning models, which require a significant amount of annotated data for their training and evaluation. In real-world situations, it is unrealistic to assume that we will have thousands of annotated examples of rated images for any given user. This puts limits on the use of deep learning models for personalized image aesthetics prediction.In order to train a machine learning model capable of taking into account individual preferences over aesthetics in photography, an annotated dataset with the identities of the raters of each picture is needed. One example of this kind of dataset is the FLICKER-AES dataset, presented by Ren et al. [27], which contains over 40000 images rated by more than 200 different human raters. Their study provides, along with this dataset (and another, smaller, dataset), a residual-based learning model capable of taking into account user-specific preferences over aesthetics in photography.We build on their work, and propose an end-to-end convolutional neural network model capable of modelling user-specific preferences with different levels of abstraction, while keeping a reduced number of user-specific parameters within the model. Our method models user-specific preferences by using residual adapters, which were presented in [26,25] and have shown success in multi-domain learning. The main difference between our model and Ren et al.'s is that they model user-specific preferences by first training a generic aesthetics network, which predicts a mean aesthetic score, and computes a user-specific offset by training a Support Vector Regressor using the predicted content and some manually-defined attributes of the picture as its input; whereas our model embeds the user-specific parameters in different layers of the neural network, therefore allowing the model to find user-specific features with different levels of abstraction, and which do not necessarily depend on the contents and a fixed set of attributes of the pictures.Our main contributions are as follows: First, we propo...

show abstract

“…Specifically, the DeepBIQ model [19] (shortly IQ), that is a CNN model trained for blind image quality assessment, is considered for encoding perceptual quality metrics such as noise, exposure, quality, JPEG quality, and sharpness. While, the DeepIA model [7] (shortly IA), which is a CNN trained for generic content aesthetic assessment, is used to extract features related to global image aesthetics concepts, such as brightness, contrast, color, etc.…”

Section: Features Extractionmentioning

confidence: 99%

“…It represents an important criterion for visual content curation and it is useful in many applications such as image retrieval [1,2], photo enhancement [3], and image cropping [4,5,6]. Aesthetic assessment of images with generic content has been addressed in [6,7,8]. However, psychology research [9] showed that certain kinds of content are more attractive than others.…”

Section: Introductionmentioning

confidence: 99%

Aesthetics Assessment of Images Containing Faces

Bianco

Celona

Schettini

2018

2018 25th IEEE International Conference on Image Processing (ICIP)

Self Cite

View full text Add to dashboard Cite

Recent research has widely explored the problem of aesthetics assessment of images with generic content. However, few approaches have been specifically designed to predict the aesthetic quality of images containing human faces, which make up a massive portion of photos in the web. This paper introduces a method for aesthetic quality assessment of images with faces. We exploit three different Convolutional Neural Networks to encode information regarding perceptual quality, global image aesthetics, and facial attributes; then, a model is trained to combine these features to explicitly predict the aesthetics of images containing faces. Experimental results show that our approach outperforms existing methods for both binary, i.e. low/high, and continuous aesthetic score prediction on four different databases in the state-of-the-art.

show abstract

Predicting Image Aesthetics with Deep Learning

Cited by 34 publications

References 25 publications

Aesthetics in Digital Photography: A Survey

Aesthetics in Digital Photography: A Survey

Personalised Aesthetics with Residual Adapters

Aesthetics Assessment of Images Containing Faces

Contact Info

Product

Resources

About