Analysis of performance of Mobile Agents in distributed content based Image Retrieval

Mobile agents often have the task to collect data from several predefined servers. The factors that affect the performance of mobile agents in retrieving information from the network are the number of agents and the routing time taken by the participated agents to complete the assigned tasks. This paper presents an approach for distributed content based image retrieval using mobile agents. The proposed approach aims at reducing the network traffic of query passing in the network by clustering similar images inside each sever together. During query processing, the characteristic of the clusters used as the basis for selecting the source of the images; consequently, mobile agent is routed intelligently to all servers maintaining images belonging to the respective clusters. Experimental results show that the proposed approach reduces the network traffic and also improve the total time taken to retrieve the query results compared with other approaches.