Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
7.3
3.8
Journals
J. Imaging
Special Issues
Computer Vision and Image Processing: Advances and Challenges
share announcement

Computer Vision and Image Processing: Advances and Challenges

A Special Issue of Journal of Imaging (ISSN 2313-433X) belonging to the section "Computer Vision and Pattern Recognition".

Deadline for manuscript submissions: 31 October 2026 | Viewed by 1562

Editors

Dr. Shengeng Tang

E-Mail Website
Guest Editor
School of Computer Science and Information Engineering, Hefei University of Technology, Hefei 230601, China
Interests: computer vision; multimedia content understanding and generation; cross-media reasoning
Dr. Lechao Cheng

E-Mail Website
Guest Editor
School of Computer Science and Information Engineering, Hefei University of Technology, Hefei 230601, China
Interests: machine learning; 3D scene reconstruction; visual semantic segmentation
Dr. Weidong Chen

E-Mail Website
Guest Editor
School of Information Science and Technology, University of Science and Technology of China, Hefei 230026, China
Interests: multimedia; computer vision; deep learning

Special Issue Information

Dear Colleagues,

We are now in an era in which computer vision and image processing are fundamentally transforming how machines perceive and understand the visual world. Driven by advances in artificial intelligence, enhanced sensor capabilities, and growing computational power, these technologies now enable systems to interpret complex scenes, analyze intricate patterns, and generate realistic imagery with remarkable accuracy. They form the foundation for a wide spectrum of critical applications, from autonomous driving and medical imaging to surveillance, augmented reality, and multimedia content creation. Yet, this rapid evolution also presents substantial challenges, including ensuring robustness in uncontrolled environments, developing interpretable and trustworthy models, managing large-scale visual data efficiently, and addressing the ethical and privacy concerns inherent in pervasive visual analysis.

In response, the research community continues to push the boundaries across all stages of the imaging pipeline. Innovations span novel algorithms in deep learning, self-supervised and few-shot learning, 3D vision, generative models (AIGC), and multimodal fusion. The pursuit extends beyond raw performance, emphasizing computational efficiency, model generalizability across domains, and practical usability in human-centric applications.

Given this scope, computer vision and image processing have become indispensable enabling technologies. They provide the core intelligence for systems requiring real-time decision-making, deep analytical insight from visual data, and the creation of interactive digital experiences. Their continued advancement is crucial to both technological innovation and addressing complex societal needs.

This Special Issue, titled “Computer Vision and Image Processing: Advances and Challenges”, aims to curate a diverse collection of high-quality research articles and reviews. We welcome contributions that present significant methodological advances, innovative applications, and critical discussions on persistent challenges and emerging trends, thereby offering a comprehensive overview of the current landscape and future directions in this dynamic field.

Dr. Shengeng Tang
Dr. Lechao Cheng
Dr. Weidong Chen
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-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Journal of Imaging 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 1800 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 vision
  • image processing
  • deep learning
  • self-supervised
  • few-shot learning
  • 3D vision
  • generative models (AIGC)
  • multimodal fusion

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 (2 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

32 pages, 6052 KB  
Article
A Hybrid Vision Transformer and EfficientNet-B3 Framework for Facial Expression Recognition
by Sasan Karamizadeh, Saman Shojae Chaeikar and Mazdak Zamani
J. Imaging 2026, 12(8), 360; https://doi.org/10.3390/jimaging12080360 - 7 Aug 2026
Viewed by 324
Abstract
Facial expression recognition technology is vital for security, verification, and personalization, but it faces challenges due to variations in scale, illumination, occlusion, and facial expressions. This paper presents a hybrid architecture that combines Vision Transformers (ViTs) to capture global context with EfficientNet-B3 for [...] Read more.
Facial expression recognition technology is vital for security, verification, and personalization, but it faces challenges due to variations in scale, illumination, occlusion, and facial expressions. This paper presents a hybrid architecture that combines Vision Transformers (ViTs) to capture global context with EfficientNet-B3 for multi-scale feature extraction. Unlike simple concatenation, our approach projects the ViT’s [CLS] token and the EfficientNet’s global pooling features into a shared 512-dimensional space before merging, enabling better alignment of global and local features. When tested on the FERPlus dataset, it reaches an accuracy of 94.4 ± 0.3%, surpassing several recent methods, notably existing transformer- and CNN-based methods. Ablation studies show each component’s contribution, with the full model outperforming the no-fusion version by 2.6%. With around 98 million parameters and an inference time of ~23 ms per image, it balances efficiency and high performance, suitable for real-time use on suitable hardware. Evaluation via confusion matrix, t-SNE visualization, and comparisons with recent techniques such as HLA-ViT (90.13%), AU-ViT (90.15%), and CCFER (91.24%) demonstrates its robustness and discriminative feature learning. This work highlights the promise of hybrid deep learning architectures in tackling real-world facial expression recognition challenges. Full article
(This article belongs to the Special Issue Computer Vision and Image Processing: Advances and Challenges)
►▼ Show Figures

Figure 1

19 pages, 7862 KB  
Article
Fast-CenLaneNet: A Lightweight Instance Segmentation-Based Network for Real-Time Lane Detection
by Qidong Han, Shuo Feng, Yang Gao, Mengyao Li, Teng Meng, Ke Li and Yuhao Yang
J. Imaging 2026, 12(7), 320; https://doi.org/10.3390/jimaging12070320 - 13 Jul 2026
Viewed by 522
Abstract
Lane detection is a critical component of autonomous driving systems, requiring both high accuracy and real-time performance under complex driving scenarios. Unlike current methods that rely on predefined lane counts, instance segmentation methods can handle an arbitrary number of lanes, making them more [...] Read more.
Lane detection is a critical component of autonomous driving systems, requiring both high accuracy and real-time performance under complex driving scenarios. Unlike current methods that rely on predefined lane counts, instance segmentation methods can handle an arbitrary number of lanes, making them more adaptable in real-world applications. However, this flexibility typically relies on dense pixel-level predictions, which necessitate large-scale networks and result in prohibitively high computational costs, hindering deployment on embedded platforms. To address these challenges, we present Fast-CenLaneNet, a lightweight architecture that improves inference efficiency while maintaining detection accuracy. Specifically, we design a lightweight backbone to reduce model parameters and computational cost, propose a learnable spatial similarity attention module to capture spatial dependencies within lane regions and enhance feature discriminability, and construct multi-branch output heads with Ghost convolutions to refine lane-related features with low computational overhead. Experiments on the TuSimple and CULane benchmarks demonstrate that Fast-CenLaneNet achieves a favorable accuracy–efficiency trade-off. On TuSimple, Fast-CenLaneNet obtains 96.40 ± 0.06% accuracy and 162.7 ± 6.8 FPS with 4.7 M parameters and 9.9 GFLOPs. Compared with CenLaneNet, it reduces the number of parameters by 89.1% and improves forward inference speed by 107.5%, with an accuracy decrease of only 0.08 percentage points. Full article
(This article belongs to the Special Issue Computer Vision and Image Processing: Advances and Challenges)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-2
Back to TopTop