Symmetry and Asymmetry in Computer Vision and Machine Learning
A special issue of Symmetry (ISSN 2073-8994). This special issue belongs to the section "Computer".
Deadline for manuscript submissions: 30 September 2026 | Viewed by 218
Special Issue Editors
Interests: intelligent mineral processing; signal processing method; machine learning algorithm; automatic control technology; machine vision; process parameter detection; optimization control; health status perception of mining equipment
Interests: mechanical and electronic engineering; collaborative control of electromechanical and hydraulic equipment; pattern recognition; artificial intelligence; robotics; embedded development; Internet of Things technology; signal processing; solid and contact mechanics; intelligent mining equipment
Special Issue Information
Dear Colleagues,
Symmetry—understood as invariance to transformations—is fundamental in science and increasingly central to computer vision and machine learning, guiding architectures from convolutional networks to attention mechanisms and group-equivariant models. Equally, asymmetry in real-world data—irregular shapes, anisotropic textures, and viewpoint-dependent features—provides essential cues for recognition, segmentation, and reasoning. Understanding and leveraging the interplay between symmetry and asymmetry has become key for building more robust, interpretable, and generalizable AI systems.
Symmetry and asymmetry appears naturally in many engineering scenarios: repeated patterns on conveyor belts, periodic textures on mineral surfaces, rotational or mirror structures in mechanical components, and translation-invariant features in large-scale monitoring scenes. Other examples include asymmetric cracks in steel plates, irregular gangue and foreign objects in raw coal, uneven wear on mining machinery, and non-uniform textures in concrete structures. Leveraging these symmetries and asymmetries can significantly improve detection stability, model robustness, and computational efficiency.
This Special Issue focuses on how symmetry and asymmetry can be used to build better computer vision and machine learning systems, both in theory and in real-world industrial environments. Our goal is to help researchers realize that many existing CV/ML tasks already involve symmetry-related ideas—sometimes implicitly—and to encourage contributions from varied industrial and engineering fields.
We welcome original research articles and review papers in areas including, but not limited to, the following:
- Symmetry-aware detection, segmentation, and recognition in mining, metallurgy, manufacturing, or construction;
- Using texture, shape, or geometric symmetry to enhance model robustness;
- Asymmetry-based defect detection for materials, infrastructure, or industrial products;
- Applying invariance or equivariance (e.g., rotation, translation, permutation) in practical CV/ML models;
- Data augmentation strategies based on symmetric transformations;
- Symmetry in 3D vision, point cloud analysis, and structural monitoring;
- Symmetry- or asymmetry-guided deep learning architectures for industrial inspection and automation.
This Special Issue will not only to highlight the scientific value of symmetry in machine learning but also show that many industrial computer vision tasks naturally involve symmetry concepts, even if not explicitly stated. We invite researchers from both academia and industry to share their methods, systems, and insights.
We look forward to receiving your contributions.
Dr. Ziqi Lv
Dr. Yang Yang
Guest Editors
Manuscript Submission Information
Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.
Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Symmetry is an international peer-reviewed open access monthly journal published by MDPI.
Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.
Keywords
- computer version
- machine learning
- deep learning
- defect detection
- anomaly detection
- symmetry-based data augmentation
- industrial application
Benefits of Publishing in a Special Issue
- Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
- Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
- Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
- External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
- Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.
Further information on MDPI's Special Issue policies can be found here.
