Mathematical Foundations and Deep Learning Advances in Computer Vision and Image Analysis

Dear Colleagues,

We are pleased to announce this Special Issue, titled “Mathematical Foundations and Deep Learning Advances in Computer Vision and Image Analysis”, dedicated to the exploration of applied mathematics and state-of-the-art deep learning (DL) algorithms across a wide spectrum of visual computing research. This Special Issue will offer a platform for researchers, developers, and practitioners to present innovative research that bridges theoretical insight and practical impact in domains ranging from medical image computing and remote sensing to robotic vision and multimedia understanding.

Theoretical Contributions

We invite submissions that rigorously examine mathematical structures underlying DL models for computer vision and image analysis. Topics of interest include the following:

• Mathematical modeling of neural architectures such as convergence properties, expressivity, and generalization for convolutional, recurrent, and transformer-based networks.
• Variational formulations of image processing tasks such as segmentation, restoration, and registration, as well as their integration with DL.
• Non-linear optimization theory in high-dimensional spaces, with emphasis on intuitive loss functions, regularization strategies, and training dynamics.
• Topological and geometric DL, including manifold learning, graph neural networks, and shape analysis for structured visual data.
• Probabilistic and statistical frameworks, such as Bayesian DL, uncertainty quantification, and information–theoretic approaches to model robustness and interpretability.

Applied Contributions

We also welcome high-quality papers that report the application of DL models in diverse image analysis contexts. Areas of interest include the following:

• Multi-modal and multi-scale fusion, integrating images from various sensors or modalities using deep architectures.
• Explainable AI (X-AI), emphasizing mathematical transparency in model behavior for sensitive or critical applications.
• Hybrid models, combining DL with classical mathematical techniques such as fuzzy logic and differential equations to improve model performance.
• Domain-specific applications, highlighting how mathematical foundations inform the design and deployment of DL systems in real-world image analysis.

Dr. Paramate Horkaew
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.

• convolutional neural network
• manifold learning
• geometric deep learning and explainable AI
• information theory
• optimization strategy
• pattern recognition
• object detection
• image fusion