Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.0
2.3
Journals
Mathematics
Special Issues
New Trends in Computer Vision, Pattern Recognition and Machine Learning
share announcement

New Trends in Computer Vision, Pattern Recognition and Machine Learning

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 2025 | Viewed by 5119

Special Issue Editors

Prof. Dr. Jonathan Wu

E-Mail Website
Guest Editor
Faulty of Engineering, University of Windsor, Windsor, ON N9B3P4, Canada
Interests: computer vision systems for active vehicle safety and driver assistance; machine learning and sensor fusion for autonomous driving; sensor technology; big data analytics for medicine; cross-border security; distributed sensing for industrial monitoring and automation
Special Issues, Collections and Topics in MDPI journals
Prof. Dr. Gaurav Bhatnagar

E-Mail Website
Guest Editor
Department of Mathematics, Indian Institute of Technology Jodhpur, Jodhur 342037, Rajasthan, India
Interests: wavelet analysis; fractional transform theory; multimedia security; multi-sensor fusion

Special Issue Information

Dear Colleagues,

The study of artificial intelligence (AI) is expanding at a lightning pace. Many fields related to artificial intelligence have advanced from simple machine learning applications to some of the sophisticated applications including Industry 4.0, robotics, healthcare and social media. AI is a broad and ever-evolving discipline where innovative advances are made on a regular basis. This Special Issue on "Advances in Computer Vision, Pattern Recognition, and Machine Learning" has been proposed to present a comprehensive exploration of the latest breakthroughs in the interconnected fields of computer vision, pattern recognition and machine learning. The collection brings together cutting-edge research and innovative methodologies that have reshaped the understanding of visual data processing and AI-enabled intelligent systems.

Researchers, practitioners, and enthusiasts will find this Special Issue to be a valuable resource for staying abreast of the rapidly evolving landscape in computer vision, pattern recognition, and machine learning. As technology continues to advance, the work presented here highlights the potential for these fields to revolutionize industries ranging from healthcare to autonomous systems. This collection not only celebrates the achievements made so far but also serves as an inspiration for future innovation at the crossroads of visual data analysis and AI-enabled intelligent algorithms.

This Special Issue will accept high-quality papers containing original research results and survey articles of exceptional merit spanning computer vision, pattern recognition, and machine learning. The topics of interest include, but are not limited to:

  • Machine learning and deep learning models for computer vision and pattern recognition;
  • Deep generative models for the generation of visual virtual data;
  • Automated deep and machine learning models for visual data pre-processing and mining;
  • Novel and innovative processes for object detection, object classification and object tracking;
  • Unsupervised, semi-supervised, and supervised learning frameworks in pattern recognition;
  • Real-time computer vision and pattern recognition applications;
  • Multi-modal solutions for pattern recognition problems (such as multimodal detection, retrieval, fusion and analysis);
  • Communication pattern recognition in autonomous systems;
  • Ethical and privacy issues in computer vision and pattern recognition;
  • Zero-shot learning in computer vision and pattern recognition;
  • Application of computer vision, pattern recognition and machine learning in (but not limited to) healthcare, astronomy, gaming, finance, robotics, agriculture, industry 4.0 and education.

Prof. Dr. Jonathan Wu
Prof. Dr. Gaurav Bhatnagar
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.

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 (3 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

17 pages, 3986 KiB  
Article
Efficient Image Inpainting for Handwritten Text Removal Using CycleGAN Framework
by Somanka Maiti, Shabari Nath Panuganti, Gaurav Bhatnagar and Jonathan Wu
Mathematics 2025, 13(1), 176; https://doi.org/10.3390/math13010176 - 6 Jan 2025
Viewed by 1185
Abstract
With the recent rise in the development of deep learning techniques, image inpainting—the process of restoring missing or corrupted regions in images—has witnessed significant advancements. Although state-of-the-art models are effective, they often fail to inpaint complex missing areas, especially when handwritten occlusions are [...] Read more.
With the recent rise in the development of deep learning techniques, image inpainting—the process of restoring missing or corrupted regions in images—has witnessed significant advancements. Although state-of-the-art models are effective, they often fail to inpaint complex missing areas, especially when handwritten occlusions are present in the image. To address this issue, an image inpainting model based on a residual CycleGAN is proposed. The generator takes as input the image occluded by handwritten missing patches and generates a restored image, which the discriminator then compares with the original ground truth image to determine whether it is real or fake. An adversarial trade-off between the generator and discriminator motivates the model to improve its training and produce a superior reconstructed image. Extensive experiments and analyses confirm that the proposed method generates inpainted images with superior visual quality and outperforms state-of-the-art deep learning approaches. Full article
(This article belongs to the Special Issue New Trends in Computer Vision, Pattern Recognition and Machine Learning)
►▼ Show Figures

Figure 1

16 pages, 1341 KiB  
Article
DSCEH: Dual-Stream Correlation-Enhanced Deep Hashing for Image Retrieval
by Yulin Yang, Huizhen Chen, Rongkai Liu, Shuning Liu, Yu Zhan, Chao Hu and Ronghua Shi
Mathematics 2024, 12(14), 2221; https://doi.org/10.3390/math12142221 - 16 Jul 2024
Viewed by 1029
Abstract
Deep Hashing is widely used for large-scale image-retrieval tasks to speed up the retrieval process. Current deep hashing methods are mainly based on the Convolutional Neural Network (CNN) or Vision Transformer (VIT). They only use the local or global features for low-dimensional mapping [...] Read more.
Deep Hashing is widely used for large-scale image-retrieval tasks to speed up the retrieval process. Current deep hashing methods are mainly based on the Convolutional Neural Network (CNN) or Vision Transformer (VIT). They only use the local or global features for low-dimensional mapping and only use the similarity loss function to optimize the correlation between pairwise or triplet images. Therefore, the effectiveness of deep hashing methods is limited. In this paper, we propose a dual-stream correlation-enhanced deep hashing framework (DSCEH), which uses the local and global features of the image for low-dimensional mapping and optimizes the correlation of images from the model architecture. DSCEH consists of two main steps: model training and deep-hash-based retrieval. During the training phase, a dual-network structure comprising CNN and VIT is employed for feature extraction. Subsequently, feature fusion is achieved through a concatenation operation, followed by similarity evaluation based on the class token acquired from VIT to establish edge relationships. The Graph Convolutional Network is then utilized to enhance correlation optimization between images, resulting in the generation of high-quality hash codes. This stage facilitates the development of an optimized hash model for image retrieval. In the retrieval stage, all images within the database and the to-be-retrieved images are initially mapped to hash codes using the aforementioned hash model. The retrieval results are subsequently determined based on the Hamming distance between the hash codes. We conduct experiments on three datasets: CIFAR-10, MSCOCO, and NUSWIDE. Experimental results show the superior performance of DSCEH, which helps with fast and accurate image retrieval. Full article
(This article belongs to the Special Issue New Trends in Computer Vision, Pattern Recognition and Machine Learning)
►▼ Show Figures

Figure 1

20 pages, 9501 KiB  
Article
Inverse Geometric Reconstruction Based on MW-NURBS Curves
by Musrrat Ali, Deepika Saini and Sanoj Kumar
Mathematics 2024, 12(13), 2071; https://doi.org/10.3390/math12132071 - 2 Jul 2024
Viewed by 1139
Abstract
Currently, rational curves such as the Non-Uniform Rational B-Spline (NURBS) play a significant role in both shape representation and shape reconstruction. NURBS weights are often real in nature and are referred to as challenging to assign, with the exception of conics. ‘Matrix Weighted [...] Read more.
Currently, rational curves such as the Non-Uniform Rational B-Spline (NURBS) play a significant role in both shape representation and shape reconstruction. NURBS weights are often real in nature and are referred to as challenging to assign, with the exception of conics. ‘Matrix Weighted Rational Curves’ are the expanded form of rational curves that result from replacing these real weights with matrices, or matrix weights. The only difference between these curves and conventional curves is the geometric definition of the matrix weights. In this paper, MW-NURBS curves are used to reconstruct space curves from their stereo perspectives. In particular, MW-NURBS fitting is carried out in stereo views, and the weight matrices for the MW-NURBS curves are produced using the normal vectors provided at the control points. Instead of needing to solve a complicated system, the MW-NURBS model can reconstruct curves by choosing control points and control normals from the input data. The efficacy of the proposed strategy is verified by using many examples based on both synthetic and real images. The various error types are compared to those of conventional methods like point-based and NURBS-based approaches. The results demonstrate that the errors acquired from the proposed approach are much fewer than those obtained from the point-based method and the NURBS-based method. Full article
(This article belongs to the Special Issue New Trends in Computer Vision, Pattern Recognition and Machine Learning)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-3
Back to TopTop