Assoc. Prof. Dr. Md. Jakir Hossen | Deep Learning for Computer Vision | Excellence in Research Award

Published on by Computer Vision Awards
After Completing the Registration Process, your Biography will be displayed here.

Register by using your Entry ID: 8442

Register Here

Kun Chen | Machine Learning for Computer Vision | Research Excellence Award

Published on by Computer Vision Awards

Mr. Kun Chen | Machine Learning for Computer Vision | Research Excellence Award

East China Jiaotong University | China

Mr. Kun Chen is a postgraduate researcher at East China Jiaotong University, specializing in machine learning and data mining. His research focuses on clustering analysis and semi-supervised learning, contributing to advancing intelligent data-driven systems. He co-authored the article A Novel Semi-Supervised Clustering Algorithm Based on Ridge Regression with Optimal Scaling, published in Neurocomputing, demonstrating strong analytical and methodological innovation. Despite being in the early stage of his academic career, he shows promising potential through international collaboration and impactful research contributions aimed at improving data interpretation and decision-making across scientific and engineering domains.

Citation Metrics (ORCID)

View ORCID Profile

Featured Publications

Sheilla Ann Pacheco | Deep Learning for Computer Vision | Top Researcher in Computer Vision Award

Published on by Computer Vision Awards

Assist. Prof. Dr. Sheilla Ann Pacheco | Deep Learning for Computer Vision | Top Researcher in Computer Vision Award

North Eastern Mindanao State University | Philippines

Dr. Sheilla Ann Bangoy Pacheco is an Assistant Professor at North Eastern Mindanao State University, specializing in machine learning, image processing, and adversarial AI. Her research focuses on robust facial recognition, privacy-preserving federated learning, and healthcare analytics. Her work on SARGAN-based face recognition and adversarial defense contributes to the development of secure and resilient biometric systems. Actively collaborating with international researchers, she adopts interdisciplinary approaches to address real-world challenges, particularly in healthcare and data privacy. Her contributions reflect growing societal relevance and a commitment to advancing trustworthy and secure artificial intelligence systems.

Citation Metrics (Scopus)

15

10

5

0

Citations
10

Documents
5

h-index
2

🟦 Citations 🟥 Documents 🟩 h-index

View Scopus Profile
           View ORCID Profile
         View Google Scholar Profile
         View ResearchGate Profile
       View Web of Science Profile

Featured Publications


Enhanced content-based image retrieval using multivisual features fusion.

– International Journal of Computers and Applications, 47(10), 835–856. (2025). Citefd By: 4

Hidden adversarial attack on facial biometrics: A comprehensive survey.

– Procedia Computer Science, 258, 1383–1390. (2025). Cited By: 2

A comprehensive survey on federated learning and its applications in health care.

– In 2024 6th IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET) (pp. 407–412). IEEE. (2024).  Cited By: 1

Performance of students in computer programming: An analysis.

– International Journal of Engineering Research in Computer Science and Engineering (IJERCSE), 10(1). (2023).  

Madhuri Rao | Machine Learning | Best Researcher Award

Published on by Computer Vision Awards

Dr. Madhuri Rao | Machine Learning | Best Researcher Award

Senior Assistant Professor | MIT World Peace University | India

Dr. Madhuri Rao is a dedicated researcher and academic in computer science with expertise in wireless sensor networks, Internet of Things, artificial intelligence, blockchain, and cybersecurity, with her current work focusing on deep learning, cloud security, and healthcare applications. She earned her Ph.D. in Computer Science and Engineering from Biju Patnaik University of Technology, where her research emphasized energy-efficient object tracking in wireless sensor networks. Over her career, she has gained extensive professional experience as a faculty member, academic coordinator, research supervisor, and editorial board member, contributing significantly to both teaching and research. She has authored and co-authored numerous publications in reputed journals and conferences, including IEEE, Springer, Elsevier, and Scopus-indexed platforms, along with patents and book chapters that highlight her innovative approach. Her research interests span interdisciplinary applications of advanced technologies to address challenges in security, healthcare, and sustainability, with ongoing involvement in collaborative projects and international initiatives. She has received recognition through awards such as best paper honors and a best research scholar award, underscoring her contributions to the academic community. Her research skills include problem-solving, experimental design, data analysis, and guiding students at undergraduate, postgraduate, and doctoral levels, coupled with active roles as session chair, track chair, and guest lecturer in international conferences. She is also a life member of professional societies and holds certifications that strengthen her academic profile. Her impactful contributions are reflected in 116 citations and an h-index of 7.

Profile: Google Scholar | ORCID | ResearchGate | LinkedIn

Featured Publications

  1. Rao, M., & Kamila, N. K. (2021). Cat swarm optimization based autonomous recovery from network partitioning in heterogeneous underwater wireless sensor network. International Journal of System Assurance Engineering and Management, 1–15.

  2. Rao, M., Kamila, N. K., & Kumar, K. V. (2016). Underwater wireless sensor network for tracking ships approaching harbor. 2016 International Conference on Signal Processing, Communication, Power and Embedded System (SCOPES), 1098–1102. IEEE.

  3. Rao, M., & Kamila, N. K. (2018). Spider monkey optimisation based energy efficient clustering in heterogeneous underwater wireless sensor networks. International Journal of Ad Hoc and Ubiquitous Computing, 29(1–2), 50–63.

  4. Chaudhury, P., Rao, M., & Kumar, K. V. (2009). Symbol based concatenation approach for text to speech system for Hindi using vowel classification technique. 2009 World Congress on Nature & Biologically Inspired Computing (NaBIC), 1393–1396. IEEE.

  5. Kumar, K. V., Kumari, P., Rao, M., & Mohapatra, D. P. (2022). Metaheuristic feature selection for software fault prediction. Journal of Information and Optimization Sciences, 43(5), 1013–1020.

Shijie Li | Embodied AI | Best Researcher Award

Published on by Computer Vision Awards

Dr. Shijie Li | Embodied AI | Best Researcher Award

Scientist | A*STAR Institute for Infocomm Research | Singapore

Dr. Shijie Li is a computer vision researcher with expertise in 3D perception, embodied AI, and vision-language models, contributing to the development of intelligent systems for real-world applications. He earned his Ph.D. in Computer Science from Bonn University under the supervision of Prof. Juergen Gall, following a master’s degree from Nankai University and a bachelor’s degree in Automation Engineering from the University of Electronic Science and Technology of China. His professional experience includes research positions and internships at A*STAR Singapore, Qualcomm AI Research in Amsterdam, Intel Labs in Munich, Alibaba DAMO Academy in China, and Technische Universität München in Germany, showcasing strong international collaborations and applied research expertise. His research interests lie in 3D scene understanding, motion forecasting, vision-language integration, semantic segmentation, and novel view synthesis. He has published in leading journals and conferences such as ICCV, CVPR, IEEE TPAMI, IEEE TNNLS, WACV, BMVC, ICRA, and IROS, reflecting impactful and consistent contributions. His academic excellence has been recognized through scholarships and awards including the Fortis Enterprise Scholarship, National Inspirational Scholarship, First Class Scholarship, and Outstanding Graduate Award. He has also served as a reviewer for top journals and conferences such as IEEE TPAMI, IJCV, CVPR, ICCV, ECCV, NeurIPS, and AAAI, reflecting his active role in the research community. His skills include deep learning, diffusion models, semantic and motion forecasting, vision-language modeling, and embodied AI, with a focus on interdisciplinary innovation. His research impact is reflected in 183 citations, 10 documents, and an h-index of 7.

Profiles: Google Scholar | Scopus | ORCID | LinkedIn

Featured Publications

Li, S., Abu Farha, Y., Liu, Y., Cheng, M., & Gall, J. (2023). MS-TCN++: Multi-stage temporal convolutional network for action segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(6), 6647–6658.

Chen, X., Li, S., Mersch, B., Wiesmann, L., Gall, J., Behley, J., & Stachniss, C. (2021). Moving object segmentation in 3D LiDAR data: A learning-based approach exploiting sequential data. IEEE Robotics and Automation Letters, 6(4), 6529–6536.

Qiu, Y., Liu, Y., Li, S., & Xu, J. (2020). MiniSeg: An extremely minimum network for efficient COVID-19 segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 34(11), 13180–13187.

Li, S., Chen, X., Liu, Y., Dai, D., Stachniss, C., & Gall, J. (2021). Multi-scale interaction for real-time LiDAR data segmentation on an embedded platform. IEEE Robotics and Automation Letters, 7(2), 738–745.

Li, S., Zhou, Y., Yi, J., & Gall, J. (2021). Spatial-temporal consistency network for low-latency trajectory forecasting. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 10737–10746.

Wenfeng Du | Structural Generation Design | Best Researcher Award

Published on by Computer Vision Awards

Prof. Dr. Wenfeng Du | Structural Generation Design | Best Researcher Award

Director at Henan University, China

Dr. Wenfeng Du is a distinguished professor and a leading researcher in structural engineering, with expertise in intelligent design, large-span spatial structures, and 3D printing manufacturing. He is currently a faculty member at Henan University, where he also leads several research institutes and technology innovation platforms. With over 180 publications, 80 patents, and multiple academic books, his work bridges the gap between theoretical innovation and practical application. Dr. Du integrates artificial intelligence, topology optimization, and prefabricated construction methods to create smarter, more sustainable engineering solutions. His commitment to interdisciplinary collaboration and academic leadership has positioned him at the forefront of structural design research in China and beyond. In addition to his scientific achievements, he is also recognized for his excellence in teaching and mentorship, having received multiple awards for his educational contributions. His work continues to influence both academic research and the construction industry at large.

Professional Profile 

Education🎓

Dr. Wenfeng Du holds a Ph.D. in Structural Engineering from Zhejiang University, which he earned in 2007. Prior to that, he completed both his Master’s and Bachelor’s degrees in Civil Engineering, also at Zhejiang University, one of China’s most prestigious institutions. His doctoral research focused on the mechanical performance and design optimization of large-span steel structures, laying a solid foundation for his future academic pursuits. To further broaden his academic exposure and international perspective, he served as a visiting scholar at the University of Alabama in the United States in 2014. This experience enriched his research methodologies and fostered interdisciplinary collaboration. Throughout his academic journey, Dr. Du has demonstrated a strong commitment to combining rigorous theoretical knowledge with practical engineering solutions, which continues to define his work. His educational background has equipped him with the technical acumen and innovative mindset required to tackle complex challenges in modern structural engineering.

Professional Experience📝

Dr. Wenfeng Du has cultivated a distinguished career as a professor, researcher, and institutional leader at Henan University. He currently serves as the Director of multiple research institutes, including the Steel and Spatial Structures Research Institute, the Intelligent Structure Team, and the Prefabricated Construction Engineering Technology Research Center. His professional roles involve managing large-scale research projects, supervising doctoral and postgraduate students, and promoting interdisciplinary innovation in structural design and construction. He has also played a pivotal role in the development and implementation of intelligent joint systems and 3D-printed shell structures. As a registered National First-Class Structural Engineer, Dr. Du contributes extensively to engineering standards and policy-making through active participation in national committees. His professional journey is marked by a balance of research excellence, academic leadership, and practical engineering application, making him a key figure in bridging the gap between academia and industry within the field of civil and structural engineering.

Research Interest🔎

Dr. Wenfeng Du’s research interests span a broad and interdisciplinary spectrum within structural engineering. His primary focus areas include large-span spatial structures, intelligent joint design, steel structures, and 3D printing-based construction. He is particularly interested in the integration of artificial intelligence with engineering design, especially through generative design and deep learning techniques. Dr. Du explores topology optimization to develop structurally efficient and lightweight components, which are essential for sustainable and cost-effective construction. His work also delves into prefabricated building systems and modular construction technologies, aiming to revolutionize how infrastructure is designed and assembled. Additionally, he is involved in smart materials, structural vibration energy harvesting, and computational modeling of shell and lattice structures. His research consistently aims to enhance structural performance, reduce resource consumption, and incorporate automation into construction processes. Through these efforts, Dr. Du seeks to redefine modern construction practices by combining advanced computation with real-world engineering applications.

Award and Honor🏆

Dr. Wenfeng Du has received numerous awards and honors recognizing his contributions to structural engineering, education, and scientific innovation. Among his most prestigious accolades is the Henan Youth Science and Technology Award, which acknowledges his pioneering work in intelligent structural systems. He has also been honored as a Smart Teaching Star and recognized as one of the Most Beautiful Teachers, reflecting his commitment to excellence in education and student mentorship. Dr. Du’s leadership and innovation have earned him significant roles in national research initiatives, and he has been selected for several provincial and municipal talent programs in Henan. His research outputs, including patents and high-impact publications, have been widely recognized by both academic and professional communities. Furthermore, he has served as a judge and reviewer for various scientific committees and journals, underlining the respect he commands among peers. These honors reflect his holistic impact on research, education, and engineering practice.

Research Skill🔬

Dr. Wenfeng Du possesses a comprehensive set of research skills that support his advanced work in structural engineering and intelligent design. He is highly proficient in topology optimization, finite element analysis (FEA), and computational modeling, which form the foundation of his work on structural performance and smart joint systems. Dr. Du is skilled in AI-based generative design, using neural networks and deep learning algorithms to automate and enhance structural form-finding and simulation. He is also adept at applying 3D printing technologies for experimental fabrication of steel joints and prefabricated components. His hands-on expertise extends to vibration analysis, energy harvesting mechanisms, and the integration of sensor-based monitoring in structural systems. Additionally, Dr. Du excels in academic writing, patent development, and collaborative research management. His ability to bridge theoretical research with practical engineering innovations underscores his role as a leading figure in the application of advanced technologies to modern civil engineering challenges.

Conclusion💡

Dr. Wenfeng Du is a highly deserving candidate for this award due to his outstanding contributions to structural engineering, particularly in the areas of intelligent design, prefabricated structures, and 3D printing manufacturing. His prolific research output, including over 180 publications, numerous patents, and leadership of cutting-edge projects, reflects his deep commitment to innovation and scientific advancement. Beyond academia, his work has significantly impacted engineering practices and sustainable construction technologies, contributing to societal progress. With a proven record of interdisciplinary research, strong mentorship, and institutional leadership, Dr. Du is well-positioned to drive future advancements at the intersection of AI and structural engineering, and to continue shaping the next generation of global engineering excellence.

Publications Top Noted✍

  • Title: Generation of innovative structural connection components using generative adversarial networks
    Year: 2025

  • Title: Robust form finding of tree-like structure by improved slime mould algorithm
    Year: 2025

  • Title: Bio-inspired clover-shaped piezoelectric energy harvester with enhanced performance for low-speed wind energy harvesting
    Year: 2025

  • Title: The Structural Configuration and Mechanical Performance of a New Cable-Supported Reciprocal Structure
    Year: 2025

  • Title: The influence of screen mesh interception device on hydrogen-oxygen explosion in closed detonation tube
    Year: 2025

  • Title: Collaborative form-finding of multiple treelike column structures based on improved numerical inverse hanging method
    Year: 2025
    Citations: 1

  • Title: Research on topology optimization of steel joints based on improved bi-directional progressive structural optimization method
    Year: 2024

  • Title: New shape optimization method for tree structures based on BP neural network
    Year: 2024
    Citations: 3

Minh-Son Dao | Deep Learning | Best Researcher Award

Published on by Computer Vision Awards

Dr. Minh-Son Dao | Deep Learning | Best Researcher Award

Researcher at The National Institute of Information and Communications Technology (NICT), Japan.

Dr. Minh-Son DAO is a distinguished Senior Researcher and Research Manager at the Big Data Integration Research Center, National Institute of Information and Communications Technology (NICT), Japan. With over two decades of research and leadership experience across academia and government, he leads cutting-edge initiatives in artificial intelligence, big data analytics, and smart IoT systems. He has played a pivotal role in Japan’s Society 5.0 vision through projects like MMCRAI and collaborative smart-city platforms. Dr. DAO is also a committed educator, serving as a thesis supervisor and adjunct lecturer across multiple international universities. His work has earned him numerous accolades, including multiple Best Challenge Awards, national recognitions, and research excellence honors. With over 100 peer-reviewed publications and international partnerships spanning Europe and Asia, he continues to bridge academic rigor with real-world impact. His current focus lies in multimodal AI frameworks and data-driven societal innovation.

Professional Profile

Suitability For Best Researcher Award – Dr. Minh-Son Dao

Dr. Minh-Son DAO exemplifies the qualities of an outstanding researcher through his sustained, interdisciplinary contributions to artificial intelligence, big data analytics, and smart IoT systems. With over 20 years of research leadership, a strong publication record (100+ peer-reviewed papers), and international collaboration across Europe and Asia, he has significantly influenced both theoretical advancements and real-world applications. His active role in Japan’s Society 5.0 vision and the development of the MMCRAI framework further underscore his commitment to data-driven societal innovation. Dr. DAO also demonstrates excellence in mentoring, editorial roles, and academic service, enriching the broader research ecosystem.

Education

Dr. Minh-Son DAO holds a Ph.D. in Information and Communications Technology from Trento University, Italy, where his research focused on similarity measures and shape matching using genetic algorithms. His doctoral dissertation introduced the Edge Potential Function (EPF), a novel contribution to shape-based image retrieval. Prior to that, he earned a Master’s degree in Computer Science from Vietnam National University, specializing in handwritten character recognition using Convolutional Neural Networks—an early demonstration of his interest in deep learning. His Bachelor’s degree, also in Computer Science from the University of HCM City, Vietnam, emphasized image processing and hypertext applications. These academic milestones laid a strong foundation in AI, machine learning, and multimedia processing, enabling him to merge theoretical knowledge with practical innovation throughout his career. His educational journey reflects a continuous pursuit of excellence across diverse computational and applied domains.

Experience

Dr. Minh-Son DAO brings over 20 years of extensive research and leadership experience across Asia and Europe. Currently, he serves as Research Manager and Senior Researcher at NICT Japan, spearheading national AI and Smart IoT initiatives. His prior roles include Deputy Director and Senior Assistant Professor at Universiti Teknologi Brunei, where he also founded the ELEDIA@UTB lab focused on smart farming and wireless technologies. He has held prestigious research roles at Trento University, Osaka University (as a JSPS Fellow), and GraphiTech Italy. He has supervised more than 40 postgraduate students, co-authored over 100 publications, and led multi-institutional projects in smart cities, multimedia analytics, and health informatics. His teaching portfolio spans creative multimedia, data science, and database systems. Known for building strong global research networks, Dr. DAO has established successful collaborations with institutions in Norway, Ireland, Vietnam, and Switzerland, playing a vital role in cross-disciplinary and cross-cultural scientific advancements.

Professional Development

Dr. Minh-Son DAO has consistently invested in professional development to enhance his academic and leadership capabilities. He completed the UTB Faculty Development Program and the Foundations of University Learning and Teaching at Universiti Teknologi Brunei, gaining proficiency in teaching pedagogy, assessment strategies, and flipped classroom techniques. He also holds Oracle certifications in SQL, PL/SQL, and web application development. His involvement as a guest editor for high-impact journals such as IEEE ACCESS, ACM TOMM, and Frontiers in Big Data, along with his participation as program committee member for numerous international conferences, highlights his role as a thought leader in multimedia, AI, and big data. Dr. DAO frequently chairs and organizes conferences and workshops, including ICMLSC, ICCRD, and MediaEval. His holistic development in research, teaching, industry consulting, and international collaboration exemplifies a well-rounded professional commitment to lifelong learning and knowledge dissemination in cutting-edge computing technologies.

Research Focus

Dr. Minh-Son DAO’s research primarily focuses on multidisciplinary applications of Artificial Intelligence, Big Data Analytics, and Smart IoT systems, aligning closely with the vision of a data-driven, intelligent society (Society 5.0). His most notable initiative, the Multimodal and Cross-modal AI Framework (MMCRAI), demonstrates his commitment to converting raw multimodal data into actionable insights across domains like environmental monitoring, health informatics, multimedia forensics, and smart cities. He has applied his research to real-world challenges such as air pollution prediction, disaster management, and cheapfake detection. His work spans from foundational AI techniques to practical societal applications, including the integration of sensor networks, robotics, and citizen-driven data platforms. Through collaborative international projects, he explores the intersections between cyber-physical-social systems, smart urban planning, and sustainable development. This focus enables him to address complex problems with scalable, intelligent solutions that impact public health, education, urban resilience, and digital media integrity.

Research Skills

Dr. Minh-Son DAO possesses a comprehensive suite of research skills that bridge theoretical and applied domains. He is proficient in machine learning, deep learning, multimedia retrieval, and big data analytics, often applying these in cross-modal and multimodal AI frameworks. His technical abilities include programming in C++, R, SQL, HTML/JavaScript, and Python, and working with AI tools such as TensorFlow and Keras. Dr. DAO’s expertise spans data fusion, smart sensor integration, pattern recognition, event detection, and AI-based forecasting models, enabling him to tackle large-scale and heterogeneous data sources. Additionally, he has extensive experience in research project management, proposal writing, international collaboration, and supervising graduate students. His editorial and peer-review roles in IEEE, Springer, and Elsevier journals further reflect his analytical and evaluative skill set. These capabilities have allowed him to lead multi-disciplinary teams and create impactful AI-driven solutions for urban management, environmental monitoring, and personalized health analytics.

Awards and Honors

Dr. Minh-Son DAO has received numerous national and international awards recognizing his research excellence and innovation. Notably, he won the Best Challenge Awards at ICMR 2023 and ACM MM 2022 for his groundbreaking work in cheap fake detection. He was honored with the Excellent Performance Award by Japan’s NICT in 2022, reflecting his leadership in national projects. Earlier, he earned first-place awards at prestigious competitions such as image CLEF 2018 and Media Eval 2017 for his contributions to multimedia understanding and disaster response. He received the Research Excellence Mid-Career Academic Award from University Technology Brunei in 2017. His early career was marked by competitive international fellowships, including the JSPS International Fellowship (Japan) and ERCIM Fellowship (Europe), and he was awarded Vietnam’s highest youth scientific honor, the Creative Youth Medal. These accolades affirm his sustained contributions to AI, data science, and societal innovation across multiple countries and disciplines.

Conclusion

Dr. Minh-Son DAO’s profile aligns exceptionally well with the criteria for a Best Researcher Award. His work bridges high-impact research, global collaboration, and societal benefit. His innovations in AI and multimodal systems, combined with his leadership in international research initiatives and dedication to mentorship, make him a deserving candidate. His recognition through prestigious awards and fellowships across continents further validates his global research excellence.

Publication Top Notes

1. Deep learning for mobile multimedia: A survey

  • Authors: K Ota, MS Dao, V Mezaris, FGBD Natale

  • Journal: ACM Transactions on Multimedia Computing, Communications, and Applications

  • Cited by: 188

  • Year: 2017

Summary:
This comprehensive survey explores how deep learning techniques have been adapted and optimized for mobile multimedia applications. It covers both theoretical advancements and practical implementation challenges. The paper also discusses energy efficiency and processing limitations of mobile devices. It has become a foundational reference in mobile multimedia research.

2. Exploring convolutional neural network architectures for EEG feature extraction

  • Authors: I Rakhmatulin, MS Dao, A Nassibi, D Mandic

  • Journal: Sensors, Vol. 24(3), Article 877

  • Cited by: 62

  • Year: 2024

Summary:
This paper investigates CNN-based methods for extracting features from EEG signals, a key step in brain-computer interface development. Multiple CNN architectures are compared for performance and accuracy. The study demonstrates significant improvement in signal interpretation. It contributes to the emerging field of AI-powered neuro technology.

3. Daily human activities recognition using heterogeneous sensors from smartphones

  • Authors: MS Dao, TA Nguyen-Gia, VC Mai

  • Journal: Procedia Computer Science, Vol. 111, pp. 323–328

  • Cited by: 34

  • Year: 2017

Summary:
The paper presents a method for recognizing daily human activities using various smartphone sensors. It highlights sensor fusion techniques to improve detection accuracy. The approach is lightweight and suitable for real-time implementation. It holds potential for fitness, health, and smart environment applications.

4. A real-time complex event discovery platform for cyber-physical-social systems

  • Authors: MS Dao, S Pongpaichet, L Jalali, K Kim, R Jain, K Zettsu

  • Conference: International Conference on Multimedia Retrieval

  • Cited by: 34

  • Year: 2014

Summary:
This work proposes a real-time platform for discovering complex events from integrated cyber, physical, and social sources. It focuses on fusing multi-modal data streams for event detection. The platform is designed for smart city and situational awareness applications. It bridges the gap between social sensing and real-time analytics.

5. Edge potential functions (EPF) and genetic algorithms (GA) for edge-based matching of visual objects

  • Authors: MS Dao, FGB De Natale, A Massa

  • Journal: IEEE Transactions on Multimedia, Vol. 9(1), pp. 120–135

  • Cited by: 33

  • Year: 2006

Summary:
This paper introduces edge potential functions (EPF) combined with genetic algorithms for visual object matching. It enhances robustness in noisy or occluded conditions. The method shows improvements in object recognition performance. It contributes foundational techniques for multimedia and computer vision systems.