As a Computer Vision and Deep Learning tech lead, direct LinkedIn multimedia and multimodal R&D projects and drive foundational outcomes into products.

I am leading a team in BST for research and development of a series of Artificial Intelligence and Computer Vision applications in embedded system. My role includes: i) hardware and system design, ii) algorithm design and training, iii) data collection and annotation, iv) system demo and deployment.

I invented an image processing software, “CorCalDx”, which dramatically improves diagnose of coronary artery disease using low-cost, low-radiation chest X-ray. The huge market value of this technique (over 20M exams per year) has attracted numerous funds from GE Healthcare and Case-Coulter Translational Research Partnership (CCTRP). I have published 4 papers and filed an international patent on this project.

In MSU, I work in the Biometric Research Group directed by Dr. Anil. K Jain.

 I worked on unconstrained face recognition and face liveness detection in MSU.

 After 6 months, I proposed a real-time spoof detection algorithm which:

(i) outperforms most state-of-the-art methods on public databases;

(ii) has been implemented in a real-time face spoof detection demo:

Face recognition; Face gender, age and race recognition; Character recognition; Computer vision; Object(pedestrian/vehicle) detection and tracking; Content based multimedia retrieval; Lecturing two courses on C/C++ programming language