Deep Learning and Machine Learning in Image Processing and Pattern Recognition—Second Edition

Dear Colleagues,

Over the last decade, deep learning and machine learning have steadily reshaped how researchers tackle image processing and pattern recognition. Rather than relying on fixed feature descriptors or manually engineered pipelines, modern approaches learn visual structure directly from data, enabling significant improvements in tasks such as classification, detection, segmentation, restoration, and broader scene understanding. These developments have also stimulated progress in many applied areas, including medical diagnostics, industrial inspection, environmental and remote-sensing analysis, autonomous systems, and security applications.

Even with this rapid growth, many challenges remain. Real-world imaging data are often noisy, imbalanced, or limited in quantity, and models must deal with domain shifts, varying illumination and viewpoints, and constraints on computation or memory. Researchers continue to investigate how classical image processing techniques can be combined with advanced neural architectures, how to improve model interpretability and stability, and how to adapt learned representations across tasks, modalities, and application scenarios. Meanwhile, emerging imaging technologies—such as hyperspectral and multi-modal sensors—raise new scientific questions that cannot be fully addressed by current methods.

This Special Issue seeks contributions that address these challenges from methodological, theoretical, and application-oriented perspectives. We welcome studies that propose new learning strategies, algorithmic ideas, or practical solutions supported by experimental evidence. Our goal is to provide a platform that reflects the current landscape of the field while highlighting directions that are likely to shape its future development.

Topics of interest include (but are not limited to) the following:

• Image enhancement, restoration, denoising, and super-resolution;
• Feature extraction, feature selection, and representation learning for visual data;
• Image classification, object detection, object tracking, and image segmentation;
• Pattern recognition techniques for images, including clustering, retrieval, and similarity learning;
• Multi-modal, hyperspectral, and 3D image processing;
• Scene understanding, image captioning, and high-level visual reasoning;
• Transfer learning, domain adaptation, few-shot and semi-supervised learning;
• Lightweight or efficient deep models for edge devices or real-time systems;
• Interpretability, robustness, uncertainty modeling, and generalization in ML/DL;
• Applications in biomedical imaging, remote sensing, industrial monitoring, autonomous driving, security and surveillance, agriculture, and cultural heritage analysis.

Dr. Meng Wang
Prof. Dr. Haitao Zhao
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 250 words) can be sent to the Editorial Office for assessment.

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. Applied Sciences 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.

• deep learning
• machine learning
• image processing
• pattern recognition
• feature representation
• image classification
• object detection
• image segmentation
• multi-modal imaging
• computer vision