Jinzhu Liu

About

Jinzhu Liu is a researcher whose work centers on the theory and application of Cellular Neural/Nonlinear Networks (CNNs) for image and video signal processing, with a particular emphasis on robust template design. His major contributions lie in developing systematic methods for creating CNN templates that are not only functional but also robust against parameter variations—a critical requirement for real-world engineering. Liu’s most influential work, “Design for CNN Templates with Performance of Global Connectivity Detection” (2004, 20 citations), established parameter inequalities for global connectivity detection, a fundamental task in robotic and biological vision. He extended this research to gray-scale processing (2007, 12 citations), focusing on universality and robustness. Further notable achievements include robust designs for fingerprint feature extraction (2008, 4 citations) and selected objects extraction (2007, 2 citations), demonstrating the practical applicability of his methods. By bridging theoretical CNN design with robust, implementable solutions, Liu has provided engineers with tools to build reliable vision systems, making his work a valuable resource for those advancing image processing and neuromorphic computing.

Research Focus

Key Achievements

Top Papers

1. 1
   Design for CNN Templates with Performance of Global Connectivity Detection

   20 citations · 2004
2. 2
   ROBUST DESIGNS FOR GRAY-SCALE GLOBAL CONNECTIVITY DETECTION CNN TEMPLATES

   12 citations · 2007
3. 3
   Robust Designs for Fingerprint Feature Extraction CNN with Von Neumann Neighborhood

   4 citations · 2008
4. 4
   Robust Template Designs for Selected Objects Extraction and Masked Object CNNs with Applications

   2 citations · 2007

Key Collaborators

Contact & Links