Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Gestalt Principles of Perception01:21

Gestalt Principles of Perception

Gestalt principles provide a framework for understanding how humans perceive objects as unified wholes within their context. These principles are essential in explaining the cognitive processes that make sense of complex visual stimuli by organizing them into coherent groups. One fundamental principle is proximity, which posits that objects located close to each other are perceived as a collective group. For instance, when dots are positioned near one another, the visual system interprets them...
Symmetry01:26

Symmetry

The equation of an ellipse centered at the origin defines all points whose distances from the center maintain a constant ratio between the horizontal and vertical axes. This equation results in a smooth, closed curve that extends further along the x-axis than the y-axis, giving it a horizontal orientation. Such an ellipse demonstrates three kinds of symmetry: across the x-axis, across the y-axis, and about the origin. These symmetries are essential in understanding the graph's structure and...
Perceptual Constancy01:12

Perceptual Constancy

Perceptual constancy is the ability to recognize that objects remain consistent and unchanged even when their appearance varies due to changes in sensory input. There are four main types of perceptual constancy: size constancy, shape constancy, color constancy, and brightness constancy.
Size constancy is the recognition that an object remains the same size, even when its image on the retina changes. For instance, a bus is perceived to be large enough to carry people, even if it looks tiny from...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Understanding Navon: Different designs of local-global tasks capture different bias effects.

Attention, perception & psychophysics·2026
Same author

Tracing aesthetic experience from perception and conception to appraisal using deep convolutional neural networks.

iScience·2026
Same author

Finding Closure: A Closer Look at the Gestalt Law of Closure in Convolutional Neural Networks.

Computational brain & behavior·2026
Same author

Variability and predictability as key factors in a new approach to choreographic complexity in dance.

Cognition·2026
Same author

Rethinking neuroaesthetics: Toward a multidimensional and integrative science of aesthetic experience.

Neuron·2026
Same author

The element of surprise distinguishes beauty from pleasure and interest in visuo-tactile perception of art.

Scientific reports·2026

Related Experiment Video

Updated: May 8, 2026

Generating Strictly Controlled Stimuli for Figure Recognition Experiments
05:39

Generating Strictly Controlled Stimuli for Figure Recognition Experiments

Published on: March 18, 2019

From pixels to perception: A benchmark for human-like symmetry detection.

Gonzalo Muradás Odriozola1, Lisa Koßmann2, Tinne Tuytelaars3

  • 1Department of Brain and Cognition, University of Leuven (KU Leuven), Tiensestraat 102 - Box 3711, Leuven, 3000, Belgium; Image and Speech Processing (PSI), Department of Electrical Engineering (ESAT), Castle Park Arenberg 10 - bus 2440, Leuven, 3001, Belgium; Leuven.AI, KU Leuven Institute for AI, Leuven, 3000, Belgium.

Vision Research
|May 6, 2026
PubMed
Summary

This study introduces PIX2PER, a new dataset for reflection symmetry detection, and WF1, a modified F1 score. These tools improve computer vision models to better reflect human perception of symmetry.

Keywords:
Art imagesBenchmark datasetComputer visionHuman symmetry perceptionNatural imagesSynthetic data

More Related Videos

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments
08:12

A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments

Published on: March 1, 2022

Related Experiment Videos

Last Updated: May 8, 2026

Generating Strictly Controlled Stimuli for Figure Recognition Experiments
05:39

Generating Strictly Controlled Stimuli for Figure Recognition Experiments

Published on: March 18, 2019

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments
08:12

A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments

Published on: March 1, 2022

Area of Science:

  • Computer Vision
  • Perception Science
  • Image Analysis

Background:

  • Symmetry is crucial in nature, science, and art, yet computer vision models struggle with its detection due to varied forms and subjective human perception.
  • Existing datasets for symmetry detection lack sufficient annotators and fail to capture the nuances of human perceptual judgments.
  • Human perception of symmetry often deviates from strict mathematical definitions, posing a challenge for algorithmic approaches.

Purpose of the Study:

  • To introduce PIX2PER, a novel dataset for reflection symmetry detection in natural scenes and artworks, capturing human perceptual nuances.
  • To propose WF1, a weighted F1 score that accounts for perceived symmetry strength, enhancing evaluation metrics.
  • To develop and evaluate improved computer vision models for symmetry detection that align better with human perception.

Main Methods:

  • Developed PIX2PER, a dataset featuring reflection symmetry annotations for natural scenes and artworks, incorporating human perception.
  • Introduced WF1, a modified F1 score weighting precision and recall based on perceived symmetry strength.
  • Created a synthetic dataset for pretraining symmetry detection models, followed by fine-tuning with human-centric data.

Main Results:

  • Comparative analysis of existing symmetry detection models on the PIX2PER dataset revealed performance variations based on human perception.
  • Fine-tuning pretrained models with human data from PIX2PER significantly improved detection performance.
  • The WF1 score demonstrated effectiveness in evaluating symmetry detection models according to perceived symmetry strength.

Conclusions:

  • The PIX2PER dataset and WF1 score provide valuable resources for advancing symmetry detection research.
  • Pretraining on synthetic data and fine-tuning on human-centric data offers a robust strategy for improving symmetry detection models.
  • This work contributes to developing computer vision systems that more accurately represent human perceptual capabilities in recognizing symmetry.