Lingnan University showcases five new projects at InnoCarnival 2026, including its AI facial verification system that screens for fake academic qualifications
Lingnan University shows five interdisciplinary innovations at booth D02 of InnoCarnival 2026: digital identity verification, aerospace technology, carbon neutrality, wildfire risk prediction, and creative education. Through interactive displays, the exhibits demonstrate how AI and other advanced technologies can be applied across different professional fields to address practical needs in everyday life and urban development. (Pictured centre: Prof Sun Dong, Secretary for Innovation, Technology and Industry of the Hong Kong SAR Government.)
Prof Sun Dong (right), Secretary for Innovation, Technology and Industry of the Hong Kong SAR Government, visits Lingnan University’s exhibition booth and sees how Face Fortress, an AI-powered facial verification system developed by Prof Sam Kwong Tak-wu (left) , Associate Vice-President (Strategic Research), Dean of the School of Graduate Studies, and J.K. Lee Chair Professor of Computational Intelligence at Lingnan University, uses AI to screen facial images and detect deepfakes.
Lingnan University is showing five innovative interdisciplinary projects powered by artificial intelligence (AI) at InnoCarnival 2026, the annual flagship innovation and technology event organised by the Innovation and Technology Commission (ITC). Among the exhibits is Face Fortress: Adaptive All-In-One AI for Digital ID Safety, the AI-powered facial verification system developed by Prof Sam Kwong Tak-wu, Associate Vice-President (Strategic Research), Dean of the School of Graduate Studies, and J.K. Lee Chair Professor of Computational Intelligence. The system is now being used by Lingnan as a way to screen for fake academic qualifications. Prof Sun Dong, Secretary for Innovation, Technology and Industry of the Hong Kong SAR Government, visited Lingnan’s exhibition booth today, 24 October, to learn firsthand how the system uses AI to screen facial images and detect deepfakes.
This year’s InnoCarnival theme is “Lead with I&T, Dream to Fly High”. At booth D02, Lingnan University is presenting five interdisciplinary innovations in digital identity verification, aerospace technology, carbon neutrality, wildfire risk prediction, and creative education. Through interactive displays, the exhibits demonstrate how AI and other advanced technologies can be applied in different professional fields to address practical needs in everyday life and urban development.
Developed by Prof Sam Kwong Tak-wu, Face Fortress addresses the growing threat of digital identity fraud involving deepfake technology that creates synthetic faces to impersonate real people. Reliable facial verification is essential in education, finance, and public services, where identity checks play an important role in maintaining security. The system first automatically assesses the quality of facial images based on factors such as clarity, lighting, and angle, filtering out blurred or substandard images. It then uses algorithms to detect whether an image contains a synthetic face before proceeding to facial recognition. This two-stage verification process strengthens the reliability of identity checks.
Unlike conventional approaches that require multiple systems to be integrated, Face Fortress combines image quality screening and deepfake detection into a single workflow, helping to improve operational efficiency. Currently used by Lingnan as one of the methods for screening fake academic qualifications, it demonstrates the practical application of AI in the University’s daily administrative operations.
In line with this year’s aerospace thematic zone, “Lead with I&T Dream to Fly High”, Lingnan is also showcasing the Carbon Emissions Source Database developed by Prof Li Jia, Director of the Lingnan University Shenzhen Research Institute (LUSZRI) and Associate Professor (Presidential Early Career Scholar) of the Wu Jieh Yee School of Interdisciplinary Studies. This provides high-precision ground data for national space missions, and has been used to cross-reference remote-sensing images captured by the Multi-Spectral Imaging Carbon Observatory (MUSICO), the aerospace research instrument developed under the leadership of The Hong Kong University of Science and Technology (HKUST) and used on the Tiangong Space Station. The comparison identifies the intensity and distribution of emissions from various power and industrial facilities, providing important research support for the nation’s goals of carbon peaking and carbon neutrality.
Lingnan is also presenting three other interdisciplinary innovations, demonstrating the applications of AI in environmental management, creative education, and filmmaking: TS-SatFire, an AI-powered wildfire risk prediction system developed by Prof Sam Kwong Tak-wu, combines satellite imagery with real-time weather data to predict wildfire risks. It uses low-cost algorithms to continuously scan large geographical areas, activating more advanced AI only when a high wildfire risk is detected, thereby substantially reducing computational costs.
StorySketcher, an AI-powered, child-led storytelling platform developed by Prof Xu Xian, Assistant Professor of the Department of Digital Arts and Creative Industries, transforms children’s drawings into complete and original written stories and turns them into videos. The platform makes storytelling fun while stimulating children’s narrative creativity, logical thinking, and language expression.
CineSim, a film production simulation and educational software system led by Prof Tobby Kan Shiu-tao, Assistant Professor of Teaching of the Department of Digital Arts and Creative Industries, enables students and creators to learn filmmaking, lighting, and cinematography in a computer-simulated environment without physical equipment, overcoming the limitations imposed by traditional film sets and equipment. CineSim recently won the Technological or Digital Innovation of the Year award at the Times Higher Education Awards Asia 2026, widely regarded as the “Oscars of higher education”. It emerged as sole winner from more than 500 competing entries.
Lingnan has actively promoted interdisciplinary research centred on its “AI +” strategy in recent years, and aims, through the five projects showcased at InnoCarnival 2026, to give the public direct insights into how intelligent technologies can be applied to fraud prevention, everyday learning, urban development, and environmental governance. The interactive exhibits also seek to deepen public understanding of innovation and technology, and to encourage young people to explore opportunities in the innovation and technology sector.
For more details, please visit https://innocarnival.hk/en.
Lingnan innovative projects’ introduction:
Project Title | Face Fortress: Adaptive All-In-One AI for Digital ID Safety |
Lingnan Faculty and Staff | Prof Sam Kwong Tak-wu, Associate Vice-President (Strategic Research), Dean of the School of Graduate Studies, and J.K. Lee Chair Professor of Computational Intelligence Prof Guo Haifeng, Research Assistant Professor of the Division of Artificial Intelligence of the School of Data Science |
Description | The system’s innovation lies in the seamless integration of deepfake detection, quality screening, and facial recognition into a unified verification workflow. It first automatically evaluates key quality metrics such as image clarity and lighting, then uses advanced algorithms to detect the presence of synthetic faces, and finally performs facial recognition. It is particularly well-suited for identity verification and public safety applications.
Key Features: Dual-Gate Protection: By combining deepfake detection, quality screening, and facial recognition into a single workflow, the system eliminates the cumbersome integration steps of running multiple systems and improves operational efficiency and reliability. Image Filtering: It automatically assesses quality indicators of uploaded facial images, such as clarity, lighting, and angle, and actively filters blurred or substandard images to ensure the accuracy of subsequent verification processes. Critical Scenario Suitability: Tailored for applications with stringent accuracy requirements such as remote bank account opening involving identity verification, or immigration security checks, the system delivers reliable, robust results. |
Project Title | TS-SatFire: AI-Powered Wildfire Risk Prediction |
Lingnan Faculty and Staff | Prof Sam Kwong Tak-wu, Associate Vice-President (Strategic Research), Dean of the School of Graduate Studies, and J.K. Lee Chair Professor of Computational Intelligence Prof Guo Haifeng, Research Assistant Professor of the Division of Artificial Intelligence of the School of Data Science Mr Yue Yuanchao, PhD Student of the Division of Artificial Intelligence of the School of Data Science Mr Cheng Liang, PhD Student of the Division of Artificial Intelligence of the School of Data Science Ms Hong Yuxin, PhD Student of the Division of Artificial Intelligence of the School of Data Science |
Description | The innovation of this system lies in its cost-aware, hierarchical approach to large-scale wildfire detection. By combining real-time, broad-area screening with selective AI-powered deep analysis, it enables continuous, automated early warnings across vast, hard-to-reach terrain, while drastically reducing computational costs. It is particularly well-suited for monitoring hilly countrysides, dense forests, and mountainous regions such as the Hong Kong SAR where manual ground patrols are inefficient.
Key Features: Two-Tier Smart Verification: Continuously scans wide areas using low-cost algorithms, and activates advanced AI only for high-risk spots, drastically cutting computational costs. Multimodal Environmental Fusion: Combines satellite imagery with real-time weather data to track active fires and dangerous ignition risks simultaneously. Actionable Decision Support: Features an interactive dashboard with clear risk scores, helping emergency teams quickly verify threats and dispatch targeted patrols. |
Project Title | Carbon Emissions Source Database (supports MUSICO’s space-based greenhouse gas monitoring) |
Lingnan Faculty and Staff | Prof Li Jia, Director of the Lingnan University Shenzhen Research Institute and Associate Professor (Presidential Early Career Scholar) of the Wu Jieh Yee School of Interdisciplinary Studies |
Description | When the Hong Kong SAR payload specialist Lai Ka-ying joined a national mission aboard the Tiangong Space Station, she helped deploy MUSICO, a space-based research instrument led by the Hong Kong University of Science and Technology (HKUST) to monitor greenhouse gases from orbit. To make space-based observations actionable for environmental monitoring and emission reduction, the mission relies on Lingnan University’s comprehensive ground-level carbon emission database, which provides precise local data to cross-reference and verify orbital measurements, ensuring satellite observations translate into reliable intelligence for climate action and heavy-industry decarbonisation on Earth.
Key Features: Precision Mission: Tracks greenhouse gas point sources from space and ground to enable targeted, data-driven climate action. Extensive Database Coverage: Catalogues and maps over 50 per cent of national emission sources into a database, providing an unmatched data foundation for large-scale carbon tracking. HK Space-to-Ground Monitoring Solution: Delivers a high-precision ground database that serves as an essential reference for verifying orbital satellite readings. Strategic Decarbonisation Value: Powers targeted heavy-industry emission cuts and evaluates carbon dioxide storage potential to support national and global green goals. |
Project Title | StorySketcher: A Multi-Agent AI System for Child-Led Co-Creative Storytelling |
Lingnan Faculty and Staff | Prof Xu Xian, Assistant Professor of the Department of Digital Arts and Creative Industries |
Description | Built on a “child-led, AI-assisted” core, this platform uses AI-guided questioning to turn children's drawings into unique stories. Once a story is complete, it automatically generates an animated short film complete with lively narration within minutes, turning imagination into a visual work that can be shared and enjoyed, stimulating children's narrative creativity, logical thinking, and verbal ability, and making creation both effortless and fun.
Key Features: Enquiry-Based Inspiration: Acting as a collaborative partner, the system translates visuals into a short film with subtitles, asking questions to inspire children to extend their storylines. This helps them construct a complete narrative framework step-by-step, while ensuring the story’s direction remains entirely up to the child. Co-Creation and Multilingual Learning: Designed around a drawing board interface that is simple and straightforward, the platform can be operated independently by children, but remains intuitive enough for parental guidance and companionship, allowing families to enjoy collaborative creation together. The system also supports multilingual output in Chinese, English, French, amongst other languages, turning the creative process into a cross-lingual learning experience. |
Project Title | CineSim Virtual Filming Studio: Bridge Film Theory and Practice and Unleash Creativity |
Lingnan Faculty and Research Staff | Prof Tobby Kan Shiu-tao, Assistant Professor of Teaching of the Department of Digital Arts and Creative Industries |
Description | This is a 3D film production simulation educational software designed for beginners, students, and professionals in the film industry. By integrating immersive VR technology, it creates a virtual film set where users can experience realistic production scenarios and practise key filmmaking skills such as cinematography, lighting, camera movement, and storyboard design. The system overcomes the limitations of physical equipment and venues, fostering creativity, conceptual understanding, and technical skills while providing a cost-effective alternative to expensive physical studios and filming equipment. The full desktop version of CineSim has been released on the STEAM platform, and the VR version is scheduled for release early next year. Key Features: Developed with Unreal Engine Users can select realistic 3D scene templates from multiple presets such as a nostalgic Hong Kong-style bing sutt or a public housing estate, and adjust lighting, switch between day and night, modify camera angles, and direct character movements to learn and practise filmmaking techniques. They can also develop their own scenes quickly in CineSim to improve pre-production efficiency. Cost-Effective and Efficient Students can experiment with different setups and generate multiple versions to compare within minutes, significantly reducing the time required for pre-production planning and communication. |