The Application of Deep Neural Networks in Image Processing

A special issue of Mathematics (ISSN 2227-7390). This special issue belongs to the section "E1: Mathematics and Computer Science".

Deadline for manuscript submissions: 20 June 2026 | Viewed by 3241

Special Issue Editor

Department of Computer Engineering, Korea National University of Transportation, Chungju 27469, Republic of Korea
Interests: digital image processing; machine learning; deep learning; biodata and bioimage analysis; brain-computer interface; FPGA prototyping; embedded system design
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Deep neural networks (DNNs) have become prevalent in the field of image processing, offering high-accuracy solutions to various problems such as image classification, object detection, semantic segmentation, image enhancement, and image restoration. DNNs have even surpassed human performance in many applications, notably object detection, demonstrating great potential in fields like medical diagnostics, autonomous vehicles, aerial surveillance, and smart CCTVs.

To maximize the impact of these applications, preprocessing methods are applied to enhance input data quality, enabling DNNs to learn more effectively. Postprocessing techniques also play an important role, refining the output quality to ensure actionable and precise results. Altogether, DNNs provide transformative capabilities in image processing, with preprocessing and postprocessing steps further enhancing their impact across real-world applications.

This Special Issue is open to papers on the application of DNNs in image processing, covering areas such as image classification, object detection, semantic segmentation, image enhancement, and image restoration. We also welcome contributions that explore innovative preprocessing and postprocessing methods for DNNs. Whether your work focuses on improving DNN accuracy, developing new preprocessing techniques, or enhancing postprocessing methods, your research will make a valuable contribution to advancing the field.

We look forward to receiving your contributions.

Dr. Dat Ngo
Guest Editor

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. Mathematics 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 2600 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

  • image classification
  • object detection
  • semantic segmentation
  • image enhancement (e.g., denoising, deblurring, contrast enhancement, sharpness enhancement)
  • image restoration (e.g., dehazing, deraining, desnowing, deweathering)
  • edge inference of DNNs

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 (5 papers)

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

Research

17 pages, 86811 KB  
Article
The Role of Feature Vector Scale in the Adversarial Vulnerability of Convolutional Neural Networks
by Hyun-Cheol Park and Sang-Woong Lee
Mathematics 2025, 13(18), 3026; https://doi.org/10.3390/math13183026 - 19 Sep 2025
Abstract
In image classification, convolutional neural networks (CNNs) remain vulnerable to visually imperceptible perturbations, often called adversarial examples. Although various hypotheses have been proposed to explain this vulnerability, a clear cause has not been established. We hypothesize an unfair learning effect: samples are learned [...] Read more.
In image classification, convolutional neural networks (CNNs) remain vulnerable to visually imperceptible perturbations, often called adversarial examples. Although various hypotheses have been proposed to explain this vulnerability, a clear cause has not been established. We hypothesize an unfair learning effect: samples are learned unevenly depending on the scale (norm) of their feature vectors in feature space. As a result, feature vectors with different scales exhibit different levels of robustness against noise. To test this hypothesis, we conduct vulnerability tests on CIFAR-10 using a standard convolutional classifier, analyzing cosine similarity between original and perturbed feature vectors, as well as error rates across scale intervals. Our experiments show that small-scale feature vectors are highly vulnerable. This is reflected in low cosine similarity and high error rates, whereas large-scale feature vectors consistently exhibit greater robustness with high cosine similarity and low error rates. These findings highlight the critical role of feature vector scale in adversarial vulnerability. Full article
(This article belongs to the Special Issue The Application of Deep Neural Networks in Image Processing)
Show Figures

Figure 1

21 pages, 4013 KB  
Article
Image Visibility Enhancement Under Inclement Weather with an Intensified Generative Training Set
by Se-Wan Lee, Seung-Hwan Lee, Dong-Min Son and Sung-Hak Lee
Mathematics 2025, 13(17), 2833; https://doi.org/10.3390/math13172833 - 3 Sep 2025
Viewed by 465
Abstract
Image-to-image translation inputs an image and transforms it into a new image. Deep learning-based image translation requires numerous training data to prevent overfitting; therefore, this study proposes a method to secure training data efficiently by generating and selecting fake water-droplet images using a [...] Read more.
Image-to-image translation inputs an image and transforms it into a new image. Deep learning-based image translation requires numerous training data to prevent overfitting; therefore, this study proposes a method to secure training data efficiently by generating and selecting fake water-droplet images using a cycle-consistent generative adversarial network (CycleGAN) and a convolutional neural network (CNN) for image enhancement under inclement weather conditions. A CNN-based classification model was employed to select 1200 well-formed virtual paired sets, which were then added to the existing dataset to construct an augmented training set. Using this augmented dataset, a CycleGAN-based removal module was trained with a modified L1 loss incorporating a difference map, enabling the model to focus on water-droplet regions while preserving the background color configuration. Additionally, we introduce a second training step with tone-mapped target images based on Retinex theory and CLAHE to enhance image contrast and detail preservation under low-light rainy conditions. Experimental results demonstrate that the proposed framework improves water-droplet removal performance compared to the baseline, achieving higher scores in image quality metrics such as BRISQUE and SSEQ and yielding clearer images with reduced color distortion. These findings indicate that the proposed approach contributes to improving image clarity and the safety of autonomous driving under inclement weather conditions. Full article
(This article belongs to the Special Issue The Application of Deep Neural Networks in Image Processing)
Show Figures

Figure 1

18 pages, 4927 KB  
Article
A Multi-Resolution Attention U-Net for Pavement Distress Segmentation in 3D Images: Architecture and Data-Driven Insights
by Haitao Gong, Jueqiang Tao, Xiaohua Luo and Feng Wang
Mathematics 2025, 13(17), 2752; https://doi.org/10.3390/math13172752 - 27 Aug 2025
Viewed by 481
Abstract
High-resolution 3D pavement images have become a valuable data source for automated surface distress detection and assessment. However, accurately identifying and segmenting cracks from pavement images remains challenging, due to factors such as low contrast and hair-like thinness. This study investigates key factors [...] Read more.
High-resolution 3D pavement images have become a valuable data source for automated surface distress detection and assessment. However, accurately identifying and segmenting cracks from pavement images remains challenging, due to factors such as low contrast and hair-like thinness. This study investigates key factors affecting segmentation performance and proposes a novel deep learning architecture designed to enhance segmentation robustness under these challenging conditions. The proposed model integrates a multi-resolution feature extraction stream with gated attention mechanisms to improve spatial awareness and selectively fuse information across feature levels. Our extensive experiments on a 3D pavement dataset demonstrated that the proposed method outperformed several state-of-the-art architectures, including FCN, U-Net, DeepLab, DeepCrack, and CrackFormer. Compared with U-Net, it improved F1 from 0.733 to 0.780. The gains were most pronounced on thin cracks, with F1 from 0.531 to 0.626. Our paired t-tests across folds showed the method is statistically better than U-Net and DeepCrack on Recall, IoU, Dice, and F1. These findings highlight the effectiveness of the attention-guided, multi-scale feature fusion method for robust crack segmentation using 3D pavement data. Full article
(This article belongs to the Special Issue The Application of Deep Neural Networks in Image Processing)
Show Figures

Figure 1

28 pages, 3267 KB  
Article
Alzheimer’s Disease Detection in Various Brain Anatomies Based on Optimized Vision Transformer
by Faisal Mehmood, Asif Mehmood and Taeg Keun Whangbo
Mathematics 2025, 13(12), 1927; https://doi.org/10.3390/math13121927 - 10 Jun 2025
Cited by 1 | Viewed by 753
Abstract
Alzheimer’s disease (AD) is a progressive neurodegenerative disorder and a growing public health concern. Despite significant advances in deep learning for medical image analysis, early and accurate diagnosis of AD remains challenging. In this study, we focused on optimizing the training process of [...] Read more.
Alzheimer’s disease (AD) is a progressive neurodegenerative disorder and a growing public health concern. Despite significant advances in deep learning for medical image analysis, early and accurate diagnosis of AD remains challenging. In this study, we focused on optimizing the training process of deep learning models by proposing an enhanced version of the Adam optimizer. The proposed optimizer introduces adaptive learning rate scaling, momentum correction, and decay modulation to improve convergence speed, training stability, and classification accuracy. We integrated the enhanced optimizer with Vision Transformer (ViT) and Convolutional Neural Network (CNN) architectures. The ViT-based model comprises a linear projection of image patches, positional encoding, a transformer encoder, and a Multi-Layer Perceptron (MLP) head with a Softmax classifier for multiclass AD classification. Experiments on publicly available Alzheimer’s disease datasets (ADNI-1 and ADNI-2) showed that the enhanced optimizer enabled the ViT model to achieve a 99.84% classification accuracy on Dataset-1 and 95.75% on Dataset-2, outperforming Adam, RMSProp, and SGD. Moreover, the optimizer reduced entropy loss and improved convergence stability by 0.8–2.1% across various architectures, including ResNet, RegNet, and MobileNet. This work contributes a robust optimizer-centric framework that enhances training efficiency and diagnostic accuracy for automated Alzheimer’s disease detection. Full article
(This article belongs to the Special Issue The Application of Deep Neural Networks in Image Processing)
Show Figures

Figure 1

15 pages, 3221 KB  
Article
Domain Adaptation Based on Human Feedback for Enhancing Image Denoising in Generative Models
by Hyun-Cheol Park, Dat Ngo and Sung Ho Kang
Mathematics 2025, 13(4), 598; https://doi.org/10.3390/math13040598 - 12 Feb 2025
Viewed by 922
Abstract
How can human feedback be effectively integrated into generative models? This study addresses this question by proposing a method to enhance image denoising and achieve domain adaptation using human feedback. Deep generative models, while achieving remarkable performance in image denoising within training domains, [...] Read more.
How can human feedback be effectively integrated into generative models? This study addresses this question by proposing a method to enhance image denoising and achieve domain adaptation using human feedback. Deep generative models, while achieving remarkable performance in image denoising within training domains, often fail to generalize to unseen domains. To overcome this limitation, we introduce a novel approach that fine-tunes a denoising model using human feedback without requiring labeled target data. Our experiments demonstrate a significant improvement in denoising performance. For example, on the Fashion-MNIST test set, the peak signal-to-noise ratio (PSNR) increased by 94%, with an average improvement of 1.61 ± 2.78 dB and a maximum increase of 18.21 dB. Additionally, the proposed method effectively prevents catastrophic forgetting, as evidenced by the consistent performance on the original MNIST domain. By leveraging a reward model trained on human preferences, we show that the quality of denoised images can be significantly improved, even when applied to unseen target data. This work highlights the potential of human feedback for efficient domain adaptation in generative models, presenting a scalable and data-efficient solution for enhancing performance in diverse domains. Full article
(This article belongs to the Special Issue The Application of Deep Neural Networks in Image Processing)
Show Figures

Figure 1

Back to TopTop