Image Processing and Machine Learning with Applications

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

Deadline for manuscript submissions: 25 October 2025 | Viewed by 3557

Special Issue Editors


E-Mail Website
Guest Editor
School of Computer Science, Northwestern Polytechnical University, Xi’an 710072, China
Interests: image processing; image fusion; machine learning; computer vision
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
College of Communication Engineering, Jilin University, Changchun 130012, China
Interests: image processing; sparse signal processing; machine learning

E-Mail Website
Guest Editor
School of Artificial Intelligence, Dalian University of Technology, Dalian 116024, China
Interests: computer vision; digital image processing; machine learning

Special Issue Information

Dear Colleagues,

Image processing and machine learning have grown in importance within artificial intelligence due to the swift advancement of science and technology. This field has developed rapidly in recent years due to the growing use of machine learning and deep learning in image processing and pattern recognition. This Special Issue aims to examine the most recent developments and potential directions for image processing, computer vision, and machine learning. Topics include but are not limited to

  1. Image generation, acquisition, compression, and processing;
  2. Applications of image processing;
  3. Novel visual computing and processing techniques;
  4. Multi- and cross-modal large vision/language models;
  5. Machine learning algorithm services and processes for manufacturing, industrial, and safety applications.

Prof. Dr. Qingsen Yan
Prof. Dr. Zhiyuan Zha
Dr. Xu Jia
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. 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

  • machine learning algorithm
  • computer vision
  • image processing
  • artificial intelligence

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 policies can be found here.

Published Papers (4 papers)

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

Research

30 pages, 52809 KiB  
Article
Enhancing Border Learning for Better Image Denoising
by Xin Ge, Yu Zhu, Liping Qi, Yaoqi Hu, Jinqiu Sun and Yanning Zhang
Mathematics 2025, 13(7), 1119; https://doi.org/10.3390/math13071119 - 28 Mar 2025
Viewed by 309
Abstract
Deep neural networks for image denoising typically follow an encoder–decoder model, with convolutional (Conv) layers as essential components. Conv layers apply zero padding at the borders of input data to maintain consistent output dimensions. However, zero padding introduces ring-like artifacts at the borders [...] Read more.
Deep neural networks for image denoising typically follow an encoder–decoder model, with convolutional (Conv) layers as essential components. Conv layers apply zero padding at the borders of input data to maintain consistent output dimensions. However, zero padding introduces ring-like artifacts at the borders of output images, referred to as border effects, which negatively impact the network’s ability to learn effective features. In traditional methods, these border effects, associated with convolutional/deconvolutional operations, have been mitigated using patch-based techniques. Inspired by this observation, patch-wise denoising algorithms were explored to derive a CNN architecture that avoids border effects. Specifically, we extend the patch-wise autoencoder to learn image mappings through patch extraction and patch-averaging operations, demonstrating that the patch-wise autoencoder is equivalent to a specific convolutional neural network (CNN) architecture, resulting in a novel residual block. This new residual block includes a mask that enhances the CNN’s ability to learn border features and eliminates border artifacts, referred to as the Border-Enhanced Residual Block (BERBlock). By stacking BERBlocks, we constructed a U-Net denoiser (BERUNet). Experiments on public datasets demonstrate that the proposed BERUNet achieves outstanding performance. The proposed network architecture is built on rigorous mathematical derivations, making its working mechanism highly interpretable. The code and all pretrained models are publicly available. Full article
(This article belongs to the Special Issue Image Processing and Machine Learning with Applications)
Show Figures

Figure 1

25 pages, 6330 KiB  
Article
FSDN-DETR: Enhancing Fuzzy Systems Adapter with DeNoising Anchor Boxes for Transfer Learning in Small Object Detection
by Zhijie Li, Jiahui Zhang, Yingjie Zhang, Dawei Yan, Xing Zhang, Marcin Woźniak and Wei Dong
Mathematics 2025, 13(2), 287; https://doi.org/10.3390/math13020287 - 17 Jan 2025
Viewed by 846
Abstract
The advancement of Transformer models in computer vision has rapidly spurred numerous Transformer-based object detection approaches, such as DEtection TRansformer. Although DETR’s self-attention mechanism effectively captures the global context, it struggles with fine-grained detail detection, limiting its efficacy in small object detection where [...] Read more.
The advancement of Transformer models in computer vision has rapidly spurred numerous Transformer-based object detection approaches, such as DEtection TRansformer. Although DETR’s self-attention mechanism effectively captures the global context, it struggles with fine-grained detail detection, limiting its efficacy in small object detection where noise can easily obscure or confuse small targets. To address these issues, we propose Fuzzy System DNN-DETR involving two key modules: Fuzzy Adapter Transformer Encoder and Fuzzy Denoising Transformer Decoder. The fuzzy Adapter Transformer Encoder utilizes adaptive fuzzy membership functions and rule-based smoothing to preserve critical details, such as edges and textures, while mitigating the loss of fine details in global feature processing. Meanwhile, the Fuzzy Denoising Transformer Decoder effectively reduces noise interference and enhances fine-grained feature capture, eliminating redundant computations in irrelevant regions. This approach achieves a balance between computational efficiency for medium-resolution images and the accuracy required for small object detection. Our architecture also employs adapter modules to reduce re-training costs, and a two-stage fine-tuning strategy adapts fuzzy modules to specific domains before harmonizing the model with task-specific adjustments. Experiments on the COCO and AI-TOD-V2 datasets show that FSDN-DETR achieves an approximately 20% improvement in average precision for very small objects, surpassing state-of-the-art models and demonstrating robustness and reliability for small object detection in complex environments. Full article
(This article belongs to the Special Issue Image Processing and Machine Learning with Applications)
Show Figures

Figure 1

17 pages, 3307 KiB  
Article
MCADNet: A Multi-Scale Cross-Attention Network for Remote Sensing Image Dehazing
by Tao Tao, Haoran Xu, Xin Guan and Hao Zhou
Mathematics 2024, 12(23), 3650; https://doi.org/10.3390/math12233650 - 21 Nov 2024
Viewed by 1087
Abstract
Remote sensing image dehazing (RSID) aims to remove haze from remote sensing images to enhance their quality. Although existing deep learning-based dehazing methods have made significant progress, it is still difficult to completely remove the uneven haze, which often leads to color or [...] Read more.
Remote sensing image dehazing (RSID) aims to remove haze from remote sensing images to enhance their quality. Although existing deep learning-based dehazing methods have made significant progress, it is still difficult to completely remove the uneven haze, which often leads to color or structural differences between the dehazed image and the original image. In order to overcome this difficulty, we propose the multi-scale cross-attention dehazing network (MCADNet), which offers a powerful solution for RSID. MCADNet integrates multi-kernel convolution and a multi-head attention mechanism into the U-Net architecture, enabling effective multi-scale information extraction. Additionally, we replace traditional skip connections with a cross-attention-based gating module, enhancing feature extraction and fusion across different scales. This synergy enables the network to maximize the overall similarity between the restored image and the real image while also restoring the details of the complex texture areas in the image. We evaluate MCADNet on two benchmark datasets, Haze1K and RICE, demonstrating its superior performance. Ablation experiments further verify the importance of our key design choices in enhancing dehazing effectiveness. Full article
(This article belongs to the Special Issue Image Processing and Machine Learning with Applications)
Show Figures

Figure 1

13 pages, 881 KiB  
Article
Image Processing Application for Pluripotent Stem Cell Colony Migration Quantification
by Timofey Chibyshev, Olga Krasnova, Alina Chabina, Vitaly V. Gursky, Irina Neganova and Konstantin Kozlov
Mathematics 2024, 12(22), 3584; https://doi.org/10.3390/math12223584 - 15 Nov 2024
Cited by 1 | Viewed by 812
Abstract
Human pluripotent stem cells (hPSCs) attract tremendous attention due to their unique properties. Manual extraction of trajectories of cell colonies in experimental image time series is labor intensive and subjective, thus the aim of the work was to develop a computer semi-automated protocol [...] Read more.
Human pluripotent stem cells (hPSCs) attract tremendous attention due to their unique properties. Manual extraction of trajectories of cell colonies in experimental image time series is labor intensive and subjective, thus the aim of the work was to develop a computer semi-automated protocol for colony tracking. The developed procedure consists of three major stages, namely, image registration, object detection and tracking. Registration using discrete Fourier transform and tracking based on the solution of a linear assignment problem was implemented as console programs in the Python 3 programming language using a variety of packages. Object detection was implemented as a multistep procedure in the ProStack in-house software package. The procedure consists of more than 40 elementary operations that include setting of several biologically relevant parameters, image segmentation and performing of quantitative measurements. The developed procedure was applied to the dataset containing bright-field images from time-lapse recording of the human embryonic cell line H9. The detection step took about 6 h for one image time series with a resolution of 2560 by 2160; about 1 min was required for image registration and trajectories extraction. The developed procedure was effective in detecting and analyzing the time series of images with “good” and “bad” phenotypes. The differences between phenotypes in the distance in pixels between the starting and finishing positions of trajectories, in the path length along the trajectory, and the mean instant speed and mean instant angle of the trajectories were identified as statistically significant by Mann–Whitney and Student’s tests. The measured area and perimeter of the detected colonies differed, on average, for different phenotypes throughout the entire time period under consideration. This result confirms previous findings obtained by analyzing static images. Full article
(This article belongs to the Special Issue Image Processing and Machine Learning with Applications)
Show Figures

Figure 1

Back to TopTop