The proceedings present a collection of articles from the 3rd International Conference on Machine Vision, Image Processing & Imaging Technology (MVIPIT 2025), held from September 27 to 29, 2025, in Shenyang, China. The proceedings offer a comprehensive collection of cutting-edge research, innovative methodologies, and practical applications. Readers will find detailed analyses and results on the latest advancements in machine vision and image processing, which are crucial for developing more efficient algorithms and technologies. A key benefit of these proceedings is the exposure to novel techniques and solutions that address real-world challenges, fostering both academic and industrial advancements. Researchers, professionals, and students will gain valuable knowledge that can be applied to their own work, driving forward the field of machine vision and image processing.

Showcases the latest research and innovations in machine vision and imaging technology Presents state-of-the-art applications of machine vision in various industries Addresses current challenges and future trends in image processing and imaging technology

Autorentext

Bin Wang received the PhD degree in computer science from Northeastern University, in 2008. He is a member of the Jiu San Society and currently serves as a Professor and Doctoral Supervisor at the School of Computer Science and Engineering, Northeastern University. He is a member of the Jiu San Society and was selected as a member of the "Liaoning BaiQianWan Talents Program" in 2011. His research interests include design and analysis of algorithms, queries processing over streaming data, and distributed systems. He is a member of the CCF.

Chao Ren (Member, IEEE) received the B.S. and Ph.D. degrees from Sichuan University, Chengdu, China, in 2012 and 2017, respectively., Since September 2021, he has been an Associate Researcher at the School of Electronic Information, Sichuan University, focusing on image/video processing, computer vision, artificial intelligence, multimedia communication, and information systems. He has led several research projects funded by the National Natural Science Foundation of China. In 2017, he was selected for the National Postdoctoral Innovation Talent Support Program, and in 2023, he was included in Sichuan University's "Double Hundred Talent Program." In 2024, he received the Sichuan University Outstanding Research Talent - Academic Newcomer Award. He has published over 60 papers in SCI journals and international academic conferences.

Chen Li received the B.E. degree from the University of Science and Technology Beijing, China, in 2008, the M.Sc. degree from Northeast Normal University, China, in 2011, and the Dr.-Ing. degree from the University of Siegen, Germany, in 2016. From 2016 to 2017, he worked as a Postdoctoral Researcher with the Johannes Gutenberg University of Mainz, Germany. He is currently working as an Associate Professor with Northeastern University, China. He is also the Head of the Research Group for Microscopic Image and Medical Image Analysis, College of Medicine and Biological Information Engineering, Northeastern University. His research interests are in microscopic image analysis, medical image analysis, machine learning, pattern recognition, machine vision, and multimedia retrieval. He is a Reviewer for several journals and conferences, including Pattern Recognition, Future Generation Computer Systems, Artificial Intelligence in Medicine, Chemometrics and Intelligent Laboratory Systems, IEEE Access, AAAI-20, and ITIB 2020.

Inhalt

Single Image Highlight Removal via Innovative Pseudo Image Bases Fusion with a Dual-Network.- Boosting the Generalization Ability of Person Re-Identification via Architecture-Level Contrast and Data Augmentation Strategies.-
Efficient Large-Kernel CNN with Cross-Scale-Attention Feature Fusion for AFP Defect Segmentation.- Research on Tibetan Antelope Detection and Tracking Algorithm Based on Improved YOLO11.- A Two-stage Coarse-to-fine Detection Model Integrating YOLO11 and VGG16 for Cell Subtyping in High-Content Imaging.- A Multi-Stage Transformer-Diffusion Framework for Blind Image Super-Resolution.- MET-SE: A Channel Attention Module for High-Fidelity Metallographic Image Generation.- Design of an Underwater Fish Recognition System Based on Intelligent Edge Computing.- MambaSOD-Lite: Efficient RGB-D Saliency.- Detection via State Space Modeling.- Geochemical Fields are Imagery, and How to Integrate Geochemical Data and Geological Settings using Visual Machine Learning.- etc.