New Trends in Symmetry/Asymmetry of Image Processing and Computer Vision

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

Deadline for manuscript submissions: 31 October 2024 | Viewed by 6964

Special Issue Editors


E-Mail Website
Guest Editor
School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, China
Interests: computer vision; image processing; few-shot learning

E-Mail Website
Guest Editor
Key Laboratory of Ministry of Education for Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China
Interests: computer vision; image processing; video analysis

Special Issue Information

Dear Colleagues,

We are delighted to announce the launch of a Special Issue on "New Trends in Symmetry/Asymmetry of Image Processing and Computer Vision". The field of image processing and computer vision has witnessed remarkable advancements in recent years, reshaping the visual relationship between humans and machines. As artificial vision continues to evolve, it permeates various aspects of our lives, revolutionizing industries and enhancing our understanding and interaction with the world. Visual signal processing plays a pivotal role in diverse domains, ranging from manufacturing, medicine, defense, and security to autonomous navigation, robotics, social interaction, and the automotive industry. The synergy of hardware advancements in computers, cameras, portable devices, robots, and graphic cards, combined with increasingly powerful machine learning algorithms, enables us to push the boundaries of what is attainable and sets the stage for future breakthroughs. This Special Issue aims to explore the profound impact of symmetry and asymmetry in image processing and computer vision, shedding light on emerging trends and cutting-edge research. We invite researchers from the fields of machine learning and computer vision to contribute their innovative works in the following areas:

  • Pattern classification and clustering analysis;
  • Object detection, tracking, and recognition;
  • Machine learning;
  • Action recognition;
  • Neural networks and deep learning;
  • Multimedia analysis and reasoning;
  • Feature extraction and feature selection;
  • Medical image processing and analysis;
  • Fundamentals of computer vision;
  • Biometric recognition;
  • Low-level visual understanding, image processing;
  • Remote sensing image interpretation;
  • 3D vision and reconstruction;
  • Optimization and learning methods;
  • Computational photography, sensing, and display technology;
  • Multimodal information processing;
  • Document analysis and recognition;
  • Video analysis and understanding;
  • Character recognition;
  • Visual applications and systems;
  • Face recognition and pose estimation;
  • Vision problems in robotics and autonomous driving.

We encourage researchers to submit their original research articles, reviews, or perspectives that explore the role of symmetry and asymmetry in image processing and computer vision. This Special Issue provides an opportunity to share novel insights, methodologies, and applications, shaping the future of the field.

Dr. Yuanjie Shao
Prof. Dr. Changxin Gao
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 100 words) can be sent to the Editorial Office for announcement on this website.

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

  • pattern classification and clustering analysis
  • object detection, tracking, and recognition
  • machine learning
  • action recognition
  • neural networks and deep learning
  • multimedia analysis and reasoning
  • feature extraction and feature selection
  • medical image processing and analysis
  • fundamentals of computer vision
  • biometric recognition
  • low-level visual understanding, image processing
  • remote sensing image interpretation
  • 3D vision and reconstruction
  • optimization and learning methods
  • computational photography, sensing, and display technology
  • multimodal information processing
  • document analysis and recognition
  • video analysis and understanding
  • character recognition
  • visual applications and systems
  • face recognition and pose estimation
  • vision problems in robotics and autonomous driving
  • symmetry

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.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (6 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

16 pages, 6651 KiB  
Article
Enhancing Oracle Bone Character Category Discovery via Character Component Distillation and Self-Merged Pseudo-Label
by Xiuan Wan, Zhengchen Li, Shouyong Pan and Yuchun Fang
Symmetry 2024, 16(9), 1098; https://doi.org/10.3390/sym16091098 - 23 Aug 2024
Viewed by 599
Abstract
Oraclebone characters (OBCs) are crucial for understanding ancient Chinese history, but existing recognition methods only recognize known categories in labeled data, neglecting novel categories in unlabeled data. This work introduces a novel approach to discovering new OBC categories in unlabeled data through generalized [...] Read more.
Oraclebone characters (OBCs) are crucial for understanding ancient Chinese history, but existing recognition methods only recognize known categories in labeled data, neglecting novel categories in unlabeled data. This work introduces a novel approach to discovering new OBC categories in unlabeled data through generalized category discovery. We address the challenges posed by OBCs’ instinctive characteristics, such as misleading contrastive views from random cropping, sub-optimal learned representation, and insufficient supervision for unlabeled data. Our method features a symmetrical structure enhanced by character component distillation and self-merged pseudo-label. We utilize random geometric transforms to create symmetrical contrastive views to avoid misleading views. Then, the proposed character component distillation procedure optimizes symmetrical shared character components for better transferable representation. Finally, we construct a self-merged pseudo-label from the model and a symmetrical teacher model to provide stable and robust supervision for unlabeled data. Extensive experiments validate the superiority of our method in recognizing ’All’ and ’Novel’ OBC categories, providing an effective tool to aid OBC researchers. Full article
Show Figures

Figure 1

22 pages, 3045 KiB  
Article
Enhancing User Perception of Reliability in Computer Vision: Uncertainty Visualization for Probability Distributions
by Xinyue Wang, Ruoyu Hu and Chengqi Xue
Symmetry 2024, 16(8), 986; https://doi.org/10.3390/sym16080986 - 3 Aug 2024
Viewed by 713
Abstract
Non-expert users often find it challenging to perceive the reliability of computer vision systems accurately. In human–computer decision-making applications, users’ perceptions of system reliability may deviate from the probabilistic characteristics. Intuitive visualization of system recognition results within probability distributions can serve to enhance [...] Read more.
Non-expert users often find it challenging to perceive the reliability of computer vision systems accurately. In human–computer decision-making applications, users’ perceptions of system reliability may deviate from the probabilistic characteristics. Intuitive visualization of system recognition results within probability distributions can serve to enhance interpretability and support cognitive processes. Different visualization formats may impact users’ reliability perceptions and cognitive abilities. This study first compared the mapping relationship between users’ perceived values of system recognition results and the actual probabilistic characteristics of the distribution when using density strips, violin plots, and error bars to visualize normal distributions. The findings indicate that when density strips are used for visualization, users’ perceptions align most closely with the probabilistic integrals, exhibiting the shortest response times and highest cognitive arousal. However, users’ perceptions often exceed the actual probability density, with an average coefficient of 2.53 times, unaffected by the form of uncertainty visualization. Conversely, this perceptual bias did not appear in triangular distributions and remained consistent across symmetric and asymmetric distributions. The results of this study contribute to a better understanding of user reliability perception for interaction designers, helping to improve uncertainty visualization and thereby mitigate perceptual biases and potential trust risks. Full article
Show Figures

Figure 1

18 pages, 5225 KiB  
Article
An Improved Pedestrian Detection Model Based on YOLOv8 for Dense Scenes
by Yuchao Fang and Huanli Pang
Symmetry 2024, 16(6), 716; https://doi.org/10.3390/sym16060716 - 9 Jun 2024
Cited by 3 | Viewed by 1410
Abstract
In dense scenes, pedestrians often exhibit a variety of symmetrical features, such as symmetry in body contour, posture, clothing, and appearance. However, pedestrian detection poses challenges due to the mutual occlusion of pedestrians and the small scale of distant pedestrians in the image. [...] Read more.
In dense scenes, pedestrians often exhibit a variety of symmetrical features, such as symmetry in body contour, posture, clothing, and appearance. However, pedestrian detection poses challenges due to the mutual occlusion of pedestrians and the small scale of distant pedestrians in the image. To address these challenges, we propose a pedestrian detection algorithm tailored for dense scenarios called YOLO-RAD. In this algorithm, we integrate the concept of receiving field attention (RFA) into the Conv and C2f modules to enhance the feature extraction capability of the network. A self-designed four-layer adaptive spatial feature fusion (ASFF) module is introduced, and shallow pedestrian feature information is added to enhance the multi-scale feature fusion capability. Finally, we introduce a small-target dynamic head structure (DyHead-S) to enhance the capability of detecting small-scale pedestrians. Experimental results on WiderPerson and CrowdHuman, two challenging dense pedestrian datasets, show that compared with YOLOv8n, our YOLO-RAD algorithm has achieved significant improvement in detection performance, and the detection performance of [email protected] has increased by 2.5% and 6%, respectively. The detection performance of [email protected]:0.95 was improved by 2.7% and 6.8%, respectively. Therefore, the algorithm can effectively improve the performance of pedestrian detection in dense scenes. Full article
Show Figures

Figure 1

23 pages, 3028 KiB  
Article
Effective Video Summarization Using Channel Attention-Assisted Encoder–Decoder Framework
by Faisal Alharbi, Shabana Habib, Waleed Albattah, Zahoor Jan, Meshari D. Alanazi and Muhammad Islam
Symmetry 2024, 16(6), 680; https://doi.org/10.3390/sym16060680 - 1 Jun 2024
Viewed by 991
Abstract
A significant number of cameras regularly generate massive amounts of data, demanding hardware, time, and labor resources to acquire, process, and monitor. Asymmetric frames within videos pose a challenge to automatic summarization of videos, making it challenging to capture key content. Developments in [...] Read more.
A significant number of cameras regularly generate massive amounts of data, demanding hardware, time, and labor resources to acquire, process, and monitor. Asymmetric frames within videos pose a challenge to automatic summarization of videos, making it challenging to capture key content. Developments in computer vision have accelerated the seamless capture and analysis of high-resolution video content. Video summarization (VS) has garnered considerable interest due to its ability to provide concise summaries of lengthy videos. The current literature mainly relies on a reduced set of representative features implemented using shallow sequential networks. Therefore, this work utilizes an optimal feature-assisted visual intelligence framework for representative feature selection and summarization. Initially, the empirical analysis of several features is performed, and ultimately, we adopt a fine-tuning InceptionV3 backbone for feature extraction, deviating from conventional approaches. Secondly, our strategic encoder–decoder module captures complex relationships with five convolutional blocks and two convolution transpose blocks. Thirdly, we introduced a channel attention mechanism, illuminating interrelations between channels and prioritizing essential patterns to grasp complex refinement features for final summary generation. Additionally, comprehensive experiments and ablation studies validate our framework’s exceptional performance, consistently surpassing state-of-the-art networks on two benchmarks (TVSum and SumMe) datasets. Full article
Show Figures

Figure 1

33 pages, 17354 KiB  
Article
Index for Quantifying ‘Order’ in Three-Dimensional Shapes
by Takahiro Shimizu, Masaya Okamoto, Yuto Ieda and Takeo Kato
Symmetry 2024, 16(4), 381; https://doi.org/10.3390/sym16040381 - 22 Mar 2024
Viewed by 1074
Abstract
In this study, we focused on assessing the symmetry of shapes and quantifying an index of ‘order’ in three-dimensional shapes using curvature, which is important in product design. Specifically, the target three-dimensional shape was divided into two segments, and the Jensen–Shannon distance was [...] Read more.
In this study, we focused on assessing the symmetry of shapes and quantifying an index of ‘order’ in three-dimensional shapes using curvature, which is important in product design. Specifically, the target three-dimensional shape was divided into two segments, and the Jensen–Shannon distance was calculated for the distribution of the Casorati curvatures in both segments to determine the similarity between them. This was proposed as an indicator of the ‘order’ exhibited by the shape. To validate the effectiveness of the proposed index, sensory evaluation experiments were conducted on three shapes: extruded, rotated, and vase. For the rotated shape, the coefficient of determination between the proposed index and the sensory evaluation value of ‘order’ on a 5-point Likert scale was found to be less than 0.1. The reason for the poor correlation coefficient of determination may be attributed to the bias in human perception, where individuals tend to perceive mirror symmetry with respect to the plane that includes the vertical axis when recognizing the mirror symmetry of an object. In contrast, for the extruded and vase shapes, the coefficients of determination were 0.36 and 0.66, respectively, supporting the validity of the proposed index. Nonetheless, the coefficient of determination decreased slightly for familiar extruded shapes and asymmetric vase shapes. In future research, our aim is to quantify ‘aesthetic preference’ by combining the ‘order’ and ‘complexity’ indexes. Full article
Show Figures

Figure 1

19 pages, 6665 KiB  
Article
PointNAC: Copula-Based Point Cloud Semantic Segmentation Network
by Chunyuan Deng, Ruixing Chen, Wuyang Tang, Hexuan Chu, Gang Xu, Yue Cui and Zhenyun Peng
Symmetry 2023, 15(11), 2021; https://doi.org/10.3390/sym15112021 - 6 Nov 2023
Cited by 2 | Viewed by 1177
Abstract
Three-dimensional point cloud data generally contain complex scene information and diversified category structures. Existing point cloud semantic segmentation networks tend to learn feature information between sampled center points and their neighboring points, while ignoring the scale and structural information of the spatial context [...] Read more.
Three-dimensional point cloud data generally contain complex scene information and diversified category structures. Existing point cloud semantic segmentation networks tend to learn feature information between sampled center points and their neighboring points, while ignoring the scale and structural information of the spatial context of the sampled center points. To address these issues, this paper introduces PointNAC (PointNet based on normal vector and attention copula feature enhancement), a network designed for point cloud semantic segmentation in large-scale complex scenes, which consists of the following two main modules: (1) The local stereoscopic feature-encoding module: this feature-encoding process incorporates distance, normal vectors, and angles calculated based on the cosine theorem, enabling the network to learn not only the spatial positional information of the point cloud but also the spatial scale and geometric structure; and (2) the copula-based similarity feature enhancement module. Based on the stereoscopic feature information, this module analyzes the correlation among points in the local neighborhood. It enhances the features of positively correlated points while leaving the features of negatively correlated points unchanged. By combining these enhancements, it effectively enhances the feature saliency within the same class and the feature distinctiveness between different classes. The experimental results show that PointNAC achieved an overall accuracy (OA) of 90.9% and a mean intersection over union (MIoU) of 67.4% on the S3DIS dataset. And on the Vaihingen dataset, PointNAC achieved an overall accuracy (OA) of 85.9% and an average F1 score of 70.6%. Compared to the segmentation results of other network models on public datasets, our algorithm demonstrates good generalization and segmentation capabilities. Full article
Show Figures

Figure 1

Back to TopTop