Subject Bias in Image Aesthetic Appeal Ratings

Journal Title: Data Science: Journal of Computing and Applied Informatics - Year 2017, Vol 1, Issue 1

Abstract

Automatic prediction of image aesthetic appeal is an important part of multimedia and computer vision research, as it contributes to providing better content quality to users. Various features and learning methods have been proposed in the past to predict image aesthetic appeal more accurately. The effectiveness of these proposed methods often depend on the data used to train the predictor. Since aesthetic appeal is a subjective construct, factors that influence the subjectivity in aesthetic appeal data need to be understood and addressed. In this paper, we look into the subjectivity of aesthetic appeal data, and how it relates with image characteristics that are often used in aesthetic appeal prediction. We use subject bias and confidence interval to measure subjectivity, and check how they might be influenced by image content category and features.

Authors and Affiliations

Ernestasia Siahaan, Esther Nababan

Keywords

Related Articles

Data Analysis as a Method to gather Data to study the Relation between Fundamental Rights and Rule of Law

The research described here involves the relation between fundamental rights and the rule of law. In the end we want to find out what meaning is attributed to ‘rule of law’ by the European Court of Human Rights. In this...

The Determining Gender Using Facial Recognition Based On Neural Network With Backpropagation

One area of science that can apply facial recognition applications is artificial intelligence. The algorithms used in facial recognition are quite numerous and varied, but they all have the same three basic stages, face...

Using random search and brute force algorithm in factoring the RSA modulus

Abstract. The security of the RSA cryptosystem is directly proportional to the size of its modulus, n. The modulus n is a multiplication of two very large prime numbers, notated as p and q. Since modulus n is public, a c...

Time Series And Data Envelopment Analysis On The Performance Efficiency Of Dmmmsu-South La Union Campus

This study entitled “Time Series and Data Envelopment Analysis (DEA) on the Performance Efficiency of DMMMSU-South La Union Campus” determined the performance of the Don Mariano Marcos Memorial State University -South La...

On Factoring The RSA Modulus Using Tabu Search

It is intuitively clear that the security of RSA cryptosystem depends on the hardness of factoring a very large integer into its two prime factors. Numerous studies about integer factorization in the field of number theo...

Download PDF file
  • EP ID EP435198
  • DOI 10.32734/jocai.v1.i1-63
  • Views 54
  • Downloads 0

How To Cite

Ernestasia Siahaan, Esther Nababan (2017). Subject Bias in Image Aesthetic Appeal Ratings. Data Science: Journal of Computing and Applied Informatics, 1(1), 13-20. https://europub.co.uk/articles/-A-435198