Integration of short term learning methods for image retrieval by reciprocal rank fusion

In the image retrieval, “Fusion” refers to the problem where two or more ranked image lists are merged into a single ranked list and the unified list is presented to the user. In this paper, we focus on the combination of two ranked results from the independent Short term learning methods with Reciprocal Rank Fusion to improve the accuracy of the system. To evaluate the proposed method, we implement a Content based image retrieval systems in which each session consists of four rounds of relevance feedback and Corel data set with 10000 color images from 82 different semantic groups are used. The experimental results on 100 test images revealed the superior of suggested method to existing Short term learning methods in terms of precision.