Prof. Din-Yuen Chan | Deep Learning | Best Scholar Award

Prof. Din-Yuen Chan | Deep Learning | Best Scholar Award 

Prof. Din-Yuen Chan, National Chiayi University, Taiwan

Din-Yuen Chan is a prominent scholar in electrical engineering with extensive experience in visual signal processing and computer vision. He earned his Ph.D. in Electrical Engineering from National Cheng Kung University, Taiwan, in 1996. A member of the Visual Signal Processing and Communication Technical Committee (VSPC TC) since 2010, he served as the founding director of the Department of Electrical Engineering (2007–2011) and as Dean of the College of Science and Engineering at National Chiayi University (2017–2020). His research spans semantic object detection, video/audio coding, stereoscopic 3D, AI-based pattern recognition, and deep learning neural networks. In the past five years, he has published multiple SCI-indexed journal papers on topics such as stereo matching, instance segmentation, speaker diarization, depth estimation, and autonomous robotics. As a frequent corresponding author, he continues to lead innovations in applied AI and multimedia processing.

Professional Profile:

SCOPUS

Summary of Suitability for the Best Scholar Award

Dr. Din-Yuen Chan has maintained an outstanding academic career for over two decades, contributing significantly to the fields of electrical engineering and computer vision. His long-standing commitment to advancing knowledge is reflected in his leadership roles and consistent research output in areas such as semantic object detection, AI-based pattern recognition, video/audio coding, and stereoscopic 3D.

🎓 Education

  • Ph.D. in Electrical Engineering
    National Cheng Kung University, Taiwan 🇹🇼
    Completed in 1996

💼 Work Experience

  • 🧠 Member, Visual Signal Processing and Communication Technical Committee (VSPC TC)
    Since 2010

  • 🏛️ Founding Director, Department of Electrical Engineering, National Chiayi University
    2007 – 2011

  • 🎓 Dean, College of Science and Engineering, National Chiayi University
    2017 – 2020

🧪 Research Interests

  • 🔍 Computer Vision

  • 🎯 Semantic Object Detection

  • 🎞️ Video/Audio Coding

  • 🤖 AI-based Pattern Recognition

  • 🥽 Stereoscopic 3D

  • 🧠 Deep Learning Neural Networks

🏅 Achievements & Honors

  • ✍️ Published multiple SCI-indexed journal papers in high-impact venues, including:

    • EURASIP Journal on Image and Video Processing

    • IET Computer Vision

    • Multimedia Tools and Applications

    • Applied Sciences

  • ⭐ First or corresponding author in many significant papers on stereo matching, depth estimation, 3D object placement, and speaker diarization.

  • 🤖 Developed a low-cost autonomous outdoor robot with end-to-end deep learning navigation.

  • 🧏 Invented a new speaker-diarization technology using spectral-LSTM.

  • 🎓 Recognized leader in academia for establishing and leading research and administrative departments.

Publication Top Notes:

A new speaker-diarization technology with denoising spectral-LSTM for online automatic multi-dialogue recording

Natural-Prosodic Cross-Lingual Personalized TTS

New Efficient Depth Estimation and Real-Time Object 3D Recognition Models for Humanoid Robotic Environment Understanding

Rational 3D object placement based on deep learning based plane detection

INTEGRATED LIGHT-RESNET AND POOLFORMER NETWORKS FOR SHAPE-PRESERVING LANE DETECTION

Ms. Saleha Kamal | Pattern Recognition Awards | Best Researcher Award

Ms. Saleha Kamal | Pattern Recognition Awards | Best Researcher Award 

Ms. Saleha Kamal, Air University, Pakistan

Saleha Kamal is an accomplished AI and Computer Vision professional based in Rawalpindi, Pakistan, with expertise in image processing, silhouette detection, segmentation, and feature classification. She is currently pursuing an MS in Computer Science at Air University, Islamabad, Pakistan (2023-2025). Saleha’s research focuses on human interaction analysis and the development of advanced algorithms for computer vision tasks. Her work has been published in esteemed international conferences, including IEEE ICECT 2024 and IEEE ICET 2024, showcasing her innovative contributions to multi-feature descriptors and composite feature-based classifiers for human interaction recognition.

Professional Profile:

GOOGLE SCHOLAR

Suitability of Saleha Kamal for the Best Researcher Award

Saleha Kamal demonstrates exceptional potential and achievements in AI, machine learning, and computer vision research, making her a compelling candidate for the Best Researcher Award. Her dedication to advancing knowledge in human interaction recognition, along with her technical and academic accomplishments, positions her as a rising star in the research community.

Education 🎓

  • MS in Computer Science (2023 – 2025)
    Air University, Islamabad, Pakistan

Work and Research Experience 💼

  • Research Experience
    • Co-authored research papers published in international conferences:
      • “Multi-Feature Descriptors for Human Interaction Recognition in Outdoor Environments” – IEEE ICECT, 2024.
      • “A Novel Human Interaction Recognition via Composite Features and Max Entropy Classifier” – IEEE ICET, 2024.

Achievements and Certifications 🏆

  • Published research in prestigious IEEE conferences.
  • Certifications:
    • Advanced Computer Vision with TensorFlow – Coursera, 2023.
    • Machine Learning Specialization – Coursera, 2023.

Publication Top Notes:

A Novel Human Interaction Recognition via Composite Features and Max Entropy Classifier

CITED:8