Research on Deep Learning for Advanced Image Processing and Computer Vision

Dear Colleagues,

Computer vision and image processing have witnessed a paradigm shift with the advent of deep learning. While object identification remains a fundamental problem, modern algorithms' capabilities extend far beyond simple detection. Today, deep learning models are essential for a vast array of applications, ranging from autonomous driving, robotics, and augmented reality to medical diagnostics, remote sensing, and industrial inspection.

Deep learning-based methods, initially popularised by Convolutional Neural Networks (CNNs) and more recently by Vision Transformers (ViTs) and generative models (e.g., GANs, Diffusion Models), have revolutionised how we extract rich representations from visual data. These models successfully address challenges not only in accurately localising items but also in image classification, semantic and instance segmentation, image restoration, registration, and synthesis across complex and varied settings.

The Special Issue covers a broad spectrum of study areas, emphasising the creation of innovative architectures, feature extraction strategies, and training approaches, as well as the application of deep learning models to solve complex image processing challenges. We invite researchers to explore a range of designs and practical implementations, moving beyond traditional boundaries to encompass the whole pipeline of visual understanding. Furthermore, integrating attention mechanisms, transfer learning, and multimodal analysis is of significant interest for enhancing performance across diverse domains.

This Special Issue aims to present a thorough summary of current developments and new directions in deep learning for image processing, compiling original research and review articles on recent advances, technologies, solutions, practical applications, and novel challenges in this field.

Potential topics include, but are not limited to, the following:

• Novel deep learning architectures for image analysis (CNNs, Vision Transformers, Graph Neural Networks);
• Innovative applications of deep learning in medical imaging (CT, MRI, X-ray analysis, tumour detection);
• Remote sensing and aerial imagery applications (satellite data analysis, drone/UAV surveillance, precision agriculture);
• Image segmentation and classification (semantic, instance, and panoptic segmentation);
• Image restoration and enhancement (super-resolution, denoising, deblurring, and colourisation);
• Generative AI for Image Processing (GANs and diffusion models for synthesis and data augmentation);
• Real-time image processing for autonomous vehicles and robotics;
• Defect detection and quality control in industrial settings;
• Challenges in dataset annotation, bias mitigation, and domain adaptation;
• Edge computing and mobile deployment of vision models.

Dr. Sandra Pereira
Dr. António Manuel Trigueiros Da Silva Cunha
Dr. Paulo Jorge Coelho
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-anonymized 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.

• object detection
• deep learning
• computer vision
• image processing
• feature extraction