Next Article in Journal
Design of a Sustainable and Efficient Transportation Station (SETS) Based on Renewable Sources and Efficient Electric Drives
Next Article in Special Issue
On the Legibility of Mirror-Reflected and Rotated Text
Previous Article in Journal
A New Bayesian Edge-Linking Algorithm Using Single-Target Tracking Techniques
Previous Article in Special Issue
Affine Geometry, Visual Sensation, and Preference for Symmetry of Things in a Thing
Open AccessArticle

Using Convolutional Neural Network Filters to Measure Left-Right Mirror Symmetry in Images

Experimental Aesthetics Group, Institute of Anatomy, University of Jena School of Medicine, Jena University Hospital, 07743 Jena, Germany
*
Author to whom correspondence should be addressed.
Academic Editor: Marco Bertamini
Symmetry 2016, 8(12), 144; https://doi.org/10.3390/sym8120144
Received: 3 August 2016 / Revised: 1 November 2016 / Accepted: 28 November 2016 / Published: 1 December 2016
(This article belongs to the Special Issue Symmetry in Vision)
We propose a method for measuring symmetry in images by using filter responses from Convolutional Neural Networks (CNNs). The aim of the method is to model human perception of left/right symmetry as closely as possible. Using the Convolutional Neural Network (CNN) approach has two main advantages: First, CNN filter responses closely match the responses of neurons in the human visual system; they take information on color, edges and texture into account simultaneously. Second, we can measure higher-order symmetry, which relies not only on color, edges and texture, but also on the shapes and objects that are depicted in images. We validated our algorithm on a dataset of 300 music album covers, which were rated according to their symmetry by 20 human observers, and compared results with those from a previously proposed method. With our method, human perception of symmetry can be predicted with high accuracy. Moreover, we demonstrate that the inclusion of features from higher CNN layers, which encode more abstract image content, increases the performance further. In conclusion, we introduce a model of left/right symmetry that closely models human perception of symmetry in CD album covers. View Full-Text
Keywords: symmetry perception; continuous symmetry; convolutional neural networks; aesthetics symmetry perception; continuous symmetry; convolutional neural networks; aesthetics
Show Figures

Figure 1

MDPI and ACS Style

Brachmann, A.; Redies, C. Using Convolutional Neural Network Filters to Measure Left-Right Mirror Symmetry in Images. Symmetry 2016, 8, 144.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop