Papers by Author: Zhong Shi He

Paper TitlePage

Authors: Zong Ling Yan, Yuan Yuan Jia, Zhong Shi He
Abstract: Color image processing is seldom used in the recognition of roads and slopes collapse. And the application can bring great advantages to the traffic safety. Color image segmentation is the first and key step of the recognition system. By analyzing existing methods of color image segmentation, several drawbacks have been discovered. This paper proposed a novel and efficient segmentation approach which is suitable for the recognition of collapse. The Region of Interests (ROIs), i.e. the roads and slopes, was obtained with the ingenious use of the images characters. According to combine K-means clustering with region merging, connected-component algorithm and close operation, the roads and slopes are segmented with the statistical color features, geometrical features and the location of the objects. Experimental result shows feasibility and efficiency of the proposed approach.
Authors: Shao Bo Zhong, Zhong Shi He
Abstract: Grid task scheduling (GTS) is a NP-hard problem. This paper proposes an optimized GTS algorithm which combines with the advantages of cloud model based on the particle swarm optimization algorithm. This algorithm iterates tasks utilizing the advantages of particle swarm optimization algorithm and then gets a set of candidate solutions quickly. In addition, this algorithm modifies the value of entropy and excess entropy using the characteristics of cloud model and implements the transformation between qualitative variables and quantity of uncertain events. And this algorithm makes particles fly to the global optimal solutions by exact searching in local areas. Theoretical analysis and simulation results show that this algorithm makes load balance of resource efficiently. It also avoids the problems of genetic algorithm and basic particle swarm optimization algorithm, which would easily fall into local optimal solutions and premature convergence caused by too much selected pressure. This algorithm has the advantages of high precision and faster convergence and can be applied in task scheduling on computing grid.
Authors: Qi Rong Zhang, Zhong Shi He
Abstract: In this paper, we propose a new face recognition approach for image feature extraction named two-dimensional locality discriminant preserving projections (2DLDPP). Two-dimensional locality preserving projections (2DLPP) can direct on 2D image matrixes. So, it can make better recognition rate than locality preserving projection. We investigate its more. The 2DLDPP is to use modified maximizing margin criterion (MMMC) in 2DLPP and set the parameter optimized to maximize the between-class distance while minimize the within-class distance. Extensive experiments are performed on ORL face database and FERET face database. The 2DLDPP method achieves better face recognition performance than PCA, 2DPCA, LPP and 2DLPP.
Showing 1 to 3 of 3 Paper Titles