Submit to Special Issue Submit Abstract to Special Issue Review for Symmetry Propose a Special Issue

Journal Menu

Journal Browser

► Journal Browser

Symmetry and Its Applications in Computer Vision

Special Issue Editors
Special Issue Information
Keywords
Benefits of Publishing in a Special Issue
Published Papers

A special issue of Symmetry (ISSN 2073-8994). This special issue belongs to the section "Computer".

Deadline for manuscript submissions: 30 April 2026 | Viewed by 11704

Share This Special Issue

Special Issue Editors

Prof. Dr. Yunyi Yan

E-Mail Website
Guest Editor

School of Aerospace Science and Technology, Xidian University, Xi’an 710126, China
Interests: modeling and optimization design of complex system; intelligent algorithms in computer vision; situation awareness based on image understanding

Prof. Dr. Junxuan Wang

E-Mail Website
Guest Editor

School of Communications and Information Engineering, Xi'an University of Posts and Telecommunications, Xi'an, China
Interests: Signal processing; Broadband wireless communication; Internet of Things

Dr. Lu Zhao

E-Mail Website
Guest Editor

Institute for Neuroimaging and Informatics, University of Southern California, Los Angeles, CA, USA
Interests: computational neuroimaging analysis and the application to studies of neuroanatomy and brain connectivity networks and their relationship to development, aging and pathological conditions

Special Issue Information

Dear Colleagues,

Symmetry and its relative extension has driven great innovations in sciences including physics, chemical, and mathematics. In fact, the importance of symmetry is undeniable in computer vision as it plays a crucial role in various theories and applications from signal processing and object recognition to scene understanding.

This Special Issue aims to bring together a collection of at least 10 articles that explore the scientific background, theoretical foundations, and practical applications of symmetry or asymmetry in computer vision. The Special Issue may be printed in book form if the minimum number of articles is reached. And articles submitted to this Special Issue will be published by the journal within 5 or less days on average if it is accepted after reviewing is finished.

We invite original research articles and reviews that address, but are not limited to, the followings:

Theoretical foundations of symmetry or asymmetry in computer vision;
Symmetry-based algorithms for object recognition and scene analysis;
Applications of symmetry in medical image processing;
Symmetry and/or asymmetry study of neuroscience cases;
Symmetry computational intelligence in signal and multimedia analysis;
Signal analysis theory applications in symmetry detection;
Optimization techniques involving symmetry architecture;
Large models design and application inspired by symmetry concept;
Novel methods in computer vision originating from other fields.

Please submit your manuscript via the journal's online submission system, ensuring that you select the appropriate article type for the Special Issue. All submissions will undergo rigorous peer review, and authors will be notified of the outcome as soon as possible.

We look forward to receiving your contributions and to showcasing the latest research in symmetry and its applications in computer vision. For any inquiries regarding the Special Issue, please do not hesitate to contact Dr. Yunyi Yan directly.

Prof. Dr. Yunyi Yan
Prof. Dr. Junxuan Wang
Dr. Lu Zhao
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

symmetry and asymmetry
computer vision
artificial intelligence and neuroscience
signal and image processing or analysis
large model optimization and 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.

Published Papers (9 papers)

Download All Papers

Order results

Result details

Show export options Show export options

Select all

Export citation of selected articles as:

Research

24 pages, 837 KB

Open AccessArticle

HDIM-JER: Modeling Higher-Order Semantic Dependencies for Joint Entity–Relation Extraction in Threat Intelligence Texts

by Siyu Zhu, Weicheng Mao, Lin Miao, Jing Yin, Chao Du, Xin Li, Xiangyun Guo, Liang Wang and Ning Li

Symmetry 2026, 18(2), 340; https://doi.org/10.3390/sym18020340 - 12 Feb 2026

Viewed by 486

Abstract

Extracting structured threat intelligence from unstructured cybersecurity texts requires accurate identification of entities together with their underlying semantic relations. However, threat reports often exhibit intricate sentence structures, long-range contextual dependencies, and tightly coupled entity–relation patterns, which pose substantial challenges for existing extraction approaches. To address these challenges, this study investigates joint entity–relation extraction from the perspective of semantic dependency modeling and develops HDIM-JER, a unified framework that captures structured interactions among heterogeneous linguistic features. HDIM-JER integrates character-level cues, contextual representations, and higher-order semantic dependency evidence to enhance structural awareness during joint inference, where different second-order dependency configurations provide an interpretable perspective on structurally symmetric and hierarchically asymmetric interaction patterns among entity–relation instances. By incorporating multi-level dependency interactions, HDIM-JER effectively alleviates error propagation associated with pipeline-based architectures and improves the modeling of complex relational dependencies. Extensive experiments on a threat intelligence corpus and a public benchmark dataset demonstrate consistent performance improvements over representative state-of-the-art methods in both entity recognition and relation extraction, confirming the effectiveness of higher-order semantic dependency interaction modeling for threat intelligence analysis. Full article

(This article belongs to the Special Issue Symmetry and Its Applications in Computer Vision)

► Show Figures

Figure 1

19 pages, 4029 KB

Open AccessArticle

Hyperspectral Image Compression Method Based on Spatio-Spectral Joint Feature Extraction and Attention Mechanism

by Yan Zhang and Huachao Xiao

Symmetry 2025, 17(12), 2065; https://doi.org/10.3390/sym17122065 - 3 Dec 2025

Viewed by 693

Abstract

Traditional hyperspectral image compression methods often struggle to achieve high compression ratios while maintaining satisfactory reconstructed image quality under low-bitrate conditions. With the progressive development of deep learning, it has demonstrated significant advantages in lossy image compression research. Compared to visible light images, hyperspectral images possess rich spectral information. When directly applying visible light image compression models to hyperspectral image compression, the spectral information of hyperspectral images is overlooked, making it difficult to achieve optimal compression performance. In this paper, we combine the characteristics of hyperspectral images by extracting spatial and spectral features and performing fusion-based encoding and decoding to achieve end-to-end lossy compression of hyperspectral images. The structures of the encoding end and the decoding end are in symmetry. Additionally, attention mechanism is incorporated to enhance reconstruction quality. The proposed model is compared with the latest hyperspectral image compression standard algorithms to validate its effectiveness. Experimental results show that, under the same image quality, the proposed method reduces the bpp (bits per pixel) by 4.67% compared to CCSDS123.0-B-2 on the Harvard hyperspectral dataset while also decreasing the spectral angle loss by 13.68%, achieving better performance. Full article

(This article belongs to the Special Issue Symmetry and Its Applications in Computer Vision)

► Show Figures

Figure 1

21 pages, 3452 KB

Open AccessArticle

The WOA-VMD Combined with Improved Wavelet Thresholding Method for Noise Reduction in Sky Screen Target Projectile Signals

by Haorui Han and Hanshan Li

Symmetry 2025, 17(11), 1908; https://doi.org/10.3390/sym17111908 - 7 Nov 2025

Viewed by 614

Abstract

Aiming at the problem of low signal-to-noise ratio of the projectile signal output by the sky screen sensor, the symmetrical characteristics of the projectile signal and the noise sources were analyzed, and a joint denoising method of variational mode decomposition (VMD) and wavelet threshold based on the whale optimization algorithm (WOA) was proposed. This method employs the whale optimization algorithm (WOA) to globally optimize the key parameters of variational mode decomposition (VMD), namely the number of modes

K

and the penalty factor

α

, to obtain the optimal parameter combination that minimizes the envelope entropy. The original projectile signal is adaptively decomposed through the optimal VMD parameters. The variance contribution rate is used to screen the decomposed intrinsic mode function to retain the IMF component containing the projectile signal information and improve the signal-to-noise ratio of the projectile signal. Then, a wavelet threshold function is introduced to conduct secondary denoising processing on the selected modal components, further improving the signal-to-noise ratio of the projectile signal. Through noise reduction experiments on the measured projectile signals, it is proved that the signal-to-noise ratio of the signals has been significantly improved, indicating that this method can suppress noise while retaining the effective signal of the projectile to the greatest extent, laying a foundation for the recognition of projectile signals of the sky screen target. Full article

(This article belongs to the Special Issue Symmetry and Its Applications in Computer Vision)

► Show Figures

Figure 1

25 pages, 689 KB

Open AccessArticle

UMEAD: Unsupervised Multimodal Entity Alignment for Equipment Knowledge Graphs via Dual-Space Embedding

by Siyu Zhu, Qitao Tai, Jingbo Wang, Mingfei Tang, Liang Wang, Ning Li, Shoulu Hou and Xiulei Liu

Symmetry 2025, 17(11), 1869; https://doi.org/10.3390/sym17111869 - 5 Nov 2025

Cited by 1 | Viewed by 1238

Abstract

The symmetry between different representation spaces plays a crucial role in effectively modeling complex multimodal data. To address the challenge of equipment knowledge graphs containing hierarchical relationships that cannot be fully represented in a single space, this study proposes UMEAD, an unsupervised multimodal entity alignment method based on dual-space embeddings. The method simultaneously learns graph embeddings in both Euclidean and hyperbolic spaces, forming a structural symmetry where the Euclidean space captures local regularities and the hyperbolic space models global hierarchies. Their complementarity achieves a balanced and symmetric representation of multimodal knowledge. An adaptive feature fusion strategy is further employed to dynamically weight semantic and visual modalities, enhancing the symmetry and complementarity between different modalities. To reduce reliance on scarce pre-aligned data, pseudo seed instances are generated from multimodal features, and an iterative constraint mechanism progressively enlarges the training set, enabling unsupervised alignment. Experiments on public datasets, including EMMEAD, FB15K-DB15K, and FB15K-YAGO15K, demonstrate that the combination of dual-space embeddings, adaptive fusion, and iterative constraints significantly improves alignment accuracy. In summary, the proposed method reduces dependence on pre-aligned data, strengthens multimodal and structural alignment, and its symmetric embedding and fusion design offers a promising approach for the construction and application of multimodal knowledge graphs in the equipment domain. Full article

(This article belongs to the Special Issue Symmetry and Its Applications in Computer Vision)

► Show Figures

Figure 1

23 pages, 548 KB

Open AccessArticle

Symmetry- and Asymmetry-Aware Dual-Path Retrieval and In-Context Learning-Based LLM for Equipment Relation Extraction

by Mingfei Tang, Liang Zhang, Zhipeng Yu, Xiaolong Shi and Xiulei Liu

Symmetry 2025, 17(10), 1647; https://doi.org/10.3390/sym17101647 - 4 Oct 2025

Cited by 2 | Viewed by 1049

Abstract

Relation extraction in the equipment domain often exhibits asymmetric patterns, where entities participate in multiple overlapping relations that break the expected structural symmetry of semantic associations. Such asymmetry increases task complexity and reduces extraction accuracy in conventional approaches. To address this issue, we propose a symmetry- and asymmetry-aware dual-path retrieval and in-context learning-based large language model. Specifically, the BGE-M3 embedding model is fine-tuned for domain-specific adaptation, and a multi-level retrieval database is constructed to capture both global semantic symmetry at the sentence level and local asymmetric interactions at the relation level. A dual-path retrieval strategy, combined with Reciprocal Rank Fusion, integrates these complementary perspectives, while task-specific prompt templates further enhance extraction accuracy. Experimental results demonstrate that our method not only mitigates the challenges posed by overlapping and asymmetric relations but also leverages the latent symmetry of semantic structures to improve performance. Experimental results show that our approach effectively mitigates challenges from overlapping and asymmetric relations while exploiting latent semantic symmetry, achieving an F1-score of 88.53%, a 1.86% improvement over the strongest baseline (GPT-RE). Full article

(This article belongs to the Special Issue Symmetry and Its Applications in Computer Vision)

► Show Figures

Figure 1

20 pages, 2152 KB

Open AccessArticle

EBiDNet: A Character Detection Algorithm for LCD Interfaces Based on an Improved DBNet Framework

by Kun Wang, Yinchuan Wu and Zhengguo Yan

Symmetry 2025, 17(9), 1443; https://doi.org/10.3390/sym17091443 - 3 Sep 2025

Cited by 1 | Viewed by 985

Abstract

Characters on liquid crystal display (LCD) interfaces often appear densely arranged, with complex image backgrounds and significant variations in target appearance, posing considerable challenges for visual detection. To improve the accuracy and robustness of character detection, this paper proposes an enhanced character detection algorithm based on the DBNet framework, named EBiDNet (EfficientNetV2 and BiFPN Enhanced DBNet). This algorithm integrates machine vision with deep learning techniques and introduces the following architectural optimizations. It employs EfficientNetV2-S, a lightweight, high-performance backbone network, to enhance feature extraction capability. Meanwhile, a bidirectional feature pyramid network (BiFPN) is introduced. Its distinctive symmetric design ensures balanced feature propagation in both top-down and bottom-up directions, thereby enabling more efficient multiscale contextual information fusion. Experimental results demonstrate that, compared with the original DBNet, the proposed EBiDNet achieves a 9.13% increase in precision and a 14.17% improvement in F1-score, while reducing the number of parameters by 17.96%. In summary, the proposed framework maintains lightweight design while achieving high accuracy and strong robustness under complex conditions. Full article

(This article belongs to the Special Issue Symmetry and Its Applications in Computer Vision)

► Show Figures

Figure 1

19 pages, 2322 KB

Open AccessArticle

A Rolling Bearing Vibration Signal Noise Reduction Processing Algorithm Using the Fusion HPO-VMD and Improved Wavelet Threshold

by Siqi Peng, Jing Xing and Xiaohu Liu

Symmetry 2025, 17(8), 1316; https://doi.org/10.3390/sym17081316 - 13 Aug 2025

Cited by 2 | Viewed by 1348

Abstract

In order to solve the problem of random noise in rolling bearing vibration signals under complex working conditions, this paper use a symmetry VMD theory to set up a rolling bearing vibration signal noise reduction processing algorithm using the fusion HPO-VMD and improved wavelet threshold. Based on the theory of variational mode decomposition (VMD), we introduce the hunter–prey optimization (HPO) algorithm to optimize the core parameters of VMD with the minimum envelope entropy as the objective function and obtain the optimal decomposition modes that contain the rolling bearing vibration signal. And then, we propose to use an improved wavelet threshold processing method to denoise the decomposed rolling bearing vibration signal to improve the recognition effect. Through the acquisition and test of the rolling bearing vibration signal, the proposed algorithm is verified; the results show that the method can reduce random noise and avoid the information loss caused by excessive noise reduction and improve the signal-to-noise ratio. Full article

(This article belongs to the Special Issue Symmetry and Its Applications in Computer Vision)

► Show Figures

Figure 1

21 pages, 2471 KB

Open AccessArticle

Attention-Based Mask R-CNN Enhancement for Infrared Image Target Segmentation

by Liang Wang and Kan Ren

Symmetry 2025, 17(7), 1099; https://doi.org/10.3390/sym17071099 - 9 Jul 2025

Cited by 3 | Viewed by 2213

Abstract

Image segmentation is an important method in the field of image processing, while infrared (IR) image segmentation is one of the challenges in this field due to the unique characteristics of IR data. Infrared imaging utilizes the infrared radiation emitted by objects to produce images, which can supplement the performance of visible-light images under adverse lighting conditions to some extent. However, the low spatial resolution and limited texture details in IR images hinder the achievement of high-precision segmentation. To address these issues, an attention mechanism based on symmetrical cross-channel interaction—motivated by symmetry principles in computer vision—was integrated into a Mask Region-Based Convolutional Neural Network (Mask R-CNN) framework. A Bottleneck-enhanced Squeeze-and-Attention (BNSA) module was incorporated into the backbone network, and novel loss functions were designed for both the bounding box (Bbox) regression and mask prediction branches to enhance segmentation performance. Furthermore, a dedicated infrared image dataset was constructed to validate the proposed method. The experimental results demonstrate that the optimized model achieves higher segmentation accuracy and better segmentation performance compared to the original network and other mainstream segmentation models on our dataset, demonstrating how symmetrical design principles can effectively improve complex vision tasks. Full article

(This article belongs to the Special Issue Symmetry and Its Applications in Computer Vision)

► Show Figures

Figure 1

24 pages, 9307 KB

Open AccessArticle

DASS-YOLO: Improved YOLOv7-Tiny with Attention-Guided Shape Awareness and DySnakeConv for Spray Code Defect Detection

by Yixuan Shi, Shiling Zheng, Meiyue Bian, Xia Zhang and Lishan Yang

Symmetry 2025, 17(6), 906; https://doi.org/10.3390/sym17060906 - 8 Jun 2025

Cited by 2 | Viewed by 1842

Abstract

To address the challenges of detecting spray code defects caused by complex morphological variations and the discrete characterization of dot-matrix spray codes, an improved YOLOv7-tiny algorithm named DASS-YOLO is proposed. Firstly, the DySnakeConv module is employed in Backbone–Neck cross-layer connections. With a dynamic structure and adaptive learning, it can capture the complex morphological features of spray codes. Secondly, we proposed an Attention-guided Shape Enhancement Module with CAA (ASEM-CAA), which adopts a symmetrical dual-branch structure to facilitate bidirectional interaction between local and global features, enabling precise prediction of the overall spray code shape. It also reduces feature discontinuity in dot-matrix codes, ensuring a more coherent representation. Furthermore, Slim-neck, which is famous for its more lightweight structure, is adopted in the Neck to reduce model complexity while maintaining accuracy. Finally, Shape-IoU is applied to improve the accuracy of the bounding box regression. Experiments show that DASS-YOLO improves the detection accuracy by 1.9%. Additionally, for small defects such as incomplete code and code spot, the method achieves better accuracy improvements of 8.7% and 2.1%, respectively. Full article

(This article belongs to the Special Issue Symmetry and Its Applications in Computer Vision)

► Show Figures

Journal Menu

Journal Browser

Symmetry and Its Applications in Computer Vision

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (9 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI