Yingyong Qi
Papers
1
Total Citations
5
H-Index
1
About
Yingyong Qi is a researcher whose work bridges computer vision, parallel computing, and image processing. His most notable contribution is the development of a parallelized color-entropy preprocessed Chan–Vese model for face contour detection, which he implemented on multi-core CPUs and GPUs. This work, published in 2015, addresses the computational challenges of real-time face detection by optimizing the active contour model—a classic segmentation technique—through entropy-based preprocessing and parallelization. The approach significantly accelerates contour detection, making it viable for high-performance applications. While his most-cited paper has garnered 5 citations, its impact lies in demonstrating how algorithm-hardware co-design can enhance computer vision tasks. Qi’s research is particularly relevant for students and engineers working on efficient image segmentation, GPU acceleration, and real-time facial analysis systems. His work exemplifies the synergy between mathematical modeling and parallel computing, offering practical insights for deploying complex vision algorithms on modern hardware.
Research Focus
Key Achievements
Top Papers
- 1