Advances of Artificial Intelligence and Vision Applications, 2nd Edition

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Artificial Intelligence".

Deadline for manuscript submissions: 15 February 2026 | Viewed by 3707

Special Issue Editors

Special Issue Information

Dear Colleagues,

Artificial intelligence technologies represented by deep learning and convolutional neural networks have greatly promoted the research and development of computer vision in the last decade. Simultaneously, advances in software and hardware also enable engineers to implement their elaborated computer vision algorithms onto powerful platforms. These advancements have enabled computer vision to attain enormous success across every aspect of modern society, including agriculture, retail, insurance, manufacturing, logistics, smart city, healthcare, pharmaceutical, construction, etc. The performance of an AI-based computer vision system is still constrained by the quality and quantity of training data and the hardware platforms' computing power and processing speed. This Special Issue aims to collect the advances and contributions of related research to the design, optimization, and implementation of artificial intelligence and computer vision applications.

General topics covered in this Special Issue include, but are not limited to, the following:

  • Image interpretation;
  • Object recognition and tracking;
  • Shape analysis, monitoring, and surveillance;
  • Biologically inspired computer vision;
  • Motion analysis;
  • Document image understanding;
  • Face and gesture recognition;
  • Vision-based human–computer interaction;
  • Human activity and behavior understanding;
  • Emotion recognition.

Dr. Dong Zhang
Prof. Dr. Dah-Jye Lee
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. Electronics is an international peer-reviewed open access semimonthly 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

  • artificial intelligence
  • computer vision
  • deep learning
  • convolutional neural networks
  • affective computing

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 (3 papers)

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

Research

24 pages, 1859 KB  
Article
Interaction-Based Vehicle Automation Model for Intelligent Vision Systems
by Julian Balcerek and Paweł Pawłowski
Electronics 2025, 14(17), 3406; https://doi.org/10.3390/electronics14173406 - 27 Aug 2025
Viewed by 195
Abstract
In this paper, we introduce a new vehicle automation model describing the latest intelligent vision systems, but not limited to them, based on interactions between the vehicle, its user, and the environment, occurring simultaneously or at different times. The proposed model addresses the [...] Read more.
In this paper, we introduce a new vehicle automation model describing the latest intelligent vision systems, but not limited to them, based on interactions between the vehicle, its user, and the environment, occurring simultaneously or at different times. The proposed model addresses the lack of vehicle automation models that would simultaneously incorporate the latest vision systems and human actions, organize them according to interaction types, and enable quantitative performance analysis. The model, based on interactions, organizes in terms of types and enables parametric analysis of the operation of the latest automatic vision systems and modern knowledge about human behavior using the perception of visual information. The concept of interaction cycles was introduced, thanks to which it is possible to analyze subsequently occurring interactions, i.e., when actions trigger reactions. Interactions were decomposed into fragments containing single direct unidirectional interactions. The interactions have been assigned consistent numerical effectiveness parameters related to image recognition by individual systems, thanks to which numerical analysis at different levels of detail is possible, depending on the needs. For each of the six interaction types, ten applications of the newest and available vision systems, including those prepared by the authors, were reviewed and selected for effectiveness analysis using the presented model. The analysis was performed by appropriately weighting and averaging or multiplying interaction effectiveness. The overall effectiveness of the interaction model for selected solutions was over 80%. The model also allows the selection of weights for individual components, depending on the criterion being analyzed, e.g., safety or environmental protection. Humans turned out to be the weakest link in interactions, e.g., reducing the human driver role increased overall effectiveness of interactions to almost 90%, and its increase resulted in an effectiveness reduction to over 70%. Examples of selecting solutions for implementation based on the interaction cycle and its fragment, taking into account the effectiveness of subsequent interactions, were also presented. The presented model is characterized by its comprehensiveness, simplicity and scalability according to needs. It can be used both for scientific analysis of existing solutions and be helpful in selecting solutions for modification and implementation by the vehicle manufacturers. Full article
Show Figures

Figure 1

25 pages, 2129 KB  
Article
Zero-Shot 3D Reconstruction of Industrial Assets: A Completion-to-Reconstruction Framework Trained on Synthetic Data
by Yongjie Xu, Haihua Zhu and Barmak Honarvar Shakibaei Asli
Electronics 2025, 14(15), 2949; https://doi.org/10.3390/electronics14152949 - 24 Jul 2025
Viewed by 424
Abstract
Creating high-fidelity digital twins (DTs) for Industry 4.0 applications, it is fundamentally reliant on the accurate 3D modeling of physical assets, a task complicated by the inherent imperfections of real-world point cloud data. This paper addresses the challenge of reconstructing accurate, watertight, and [...] Read more.
Creating high-fidelity digital twins (DTs) for Industry 4.0 applications, it is fundamentally reliant on the accurate 3D modeling of physical assets, a task complicated by the inherent imperfections of real-world point cloud data. This paper addresses the challenge of reconstructing accurate, watertight, and topologically sound 3D meshes from sparse, noisy, and incomplete point clouds acquired in complex industrial environments. We introduce a robust two-stage completion-to-reconstruction framework, C2R3D-Net, that systematically tackles this problem. The methodology first employs a pretrained, self-supervised point cloud completion network to infer a dense and structurally coherent geometric representation from degraded inputs. Subsequently, a novel adaptive surface reconstruction network generates the final high-fidelity mesh. This network features a hybrid encoder (FKAConv-LSA-DC), which integrates fixed-kernel and deformable convolutions with local self-attention to robustly capture both coarse geometry and fine details, and a boundary-aware multi-head interpolation decoder, which explicitly models sharp edges and thin structures to preserve geometric fidelity. Comprehensive experiments on the large-scale synthetic ShapeNet benchmark demonstrate state-of-the-art performance across all standard metrics. Crucially, we validate the framework’s strong zero-shot generalization capability by deploying the model—trained exclusively on synthetic data—to reconstruct complex assets from a custom-collected industrial dataset without any additional fine-tuning. The results confirm the method’s suitability as a robust and scalable approach for 3D asset modeling, a critical enabling step for creating high-fidelity DTs in demanding, unseen industrial settings. Full article
Show Figures

Figure 1

23 pages, 2687 KB  
Article
A New Joint Training Method for Facial Expression Recognition with Inconsistently Annotated and Imbalanced Data
by Tao Chen, Dong Zhang and Dah-Jye Lee
Electronics 2024, 13(19), 3891; https://doi.org/10.3390/electronics13193891 - 1 Oct 2024
Viewed by 2190
Abstract
Facial expression recognition (FER) plays a crucial role in various applications, including human–computer interaction and affective computing. However, the joint training of an FER network with multiple datasets is a promising strategy to enhance its performance. Nevertheless, widespread annotation inconsistencies and class imbalances [...] Read more.
Facial expression recognition (FER) plays a crucial role in various applications, including human–computer interaction and affective computing. However, the joint training of an FER network with multiple datasets is a promising strategy to enhance its performance. Nevertheless, widespread annotation inconsistencies and class imbalances among FER datasets pose significant challenges to this approach. This paper proposes a new multi-dataset joint training method, Sample Selection and Paired Augmentation Joint Training (SSPA-JT), to address these challenges. SSPA-JT models annotation inconsistency as a label noise problem and selects clean samples from auxiliary datasets to expand the overall dataset size while maintaining consistent annotation standards. Additionally, a dynamic matching algorithm is developed to pair clean samples of the tail class with noisy samples, which enriches the tail classes with diverse background information. Experimental results demonstrate that SSPA-JT achieved superior or comparable performance compared with the existing methods by addressing both annotation inconsistencies and class imbalance during multi-dataset joint training. It achieved state-of-the-art performance on RAF-DB and CAER-S datasets with accuracies of 92.44% and 98.22%, respectively, reflecting improvements of 0.2% and 3.65% over existing methods. Full article
Show Figures

Figure 1

Back to TopTop