Comparison of Optimized Image Retrieval Methods Based on Color and Texture Features

Abstract

Nowadays our lives intensively depend upon multimedia based information acquired from different sources such as internet, television, radio, cellular phones etc. These multimedia documents were retrieved using their associated text contents. However, a significant amount of non-textual data is also available on these documents that may be omitted due to inappropriate keywords. There are various examples where text based query is highly inefficient. To resolve this issue there is a lot of research being done on Contents Based Image Retrieval (CBIR). However, it is identified that optimization for CBIR methods was an unattended issue. Moreover, a comprehensive comparison of such optimization methods is not available for researchers who want to attack this issue. In this paper a comparative study of various optimization methods for CBIR is presented. Particularly, Similarity Index Measure (SIM), Genetic Algorithm (GA) and Interactive GA (IGA) are under consideration