Shengbin Li

Papers

Total Citations

H-Index

About

Shengbin Li’s research focuses on robust computer vision and pattern recognition, particularly in challenging scenarios like face recognition under disguise. His most cited work, “An Improved Robust Sparse Coding for Face Recognition with Disguise” (2012), advances sparse representation-based classification (SRC) by developing a more resilient dictionary learning method that uses only clean training samples to accurately identify disguised test images. This contribution addresses a critical problem in robotic vision and security systems, where occlusions or alterations can degrade performance. With 5 citations, this paper has influenced subsequent studies in robust feature extraction and sparse coding. Li’s work is notable for its practical impact on real-world applications, such as surveillance and human-robot interaction, where reliable recognition under adverse conditions is essential. His research continues to explore efficient, noise-tolerant algorithms that bridge theoretical advances with deployable solutions, making him a valuable contributor to the field of computer vision.