Colour Image Retrieval Based on Structural Equation Model and Orthogonality

This paper proposes a novel technique for colour image retrieval, based on Statistical analysis, such as Correlation analysis, Structural Equation model. The correlation analysis, which computes the association among the colours, such as Red, Green, and Blue, on region-wise. The obtained correlation coefficient on colour features is tested whether it is significant or not. If it is significant, then it is inferred that the query and target images are same or similar; otherwise it is assumed that the two images are different. The Structural Equation model plays a significant role in fusing the features at low-level features. Thus, in this paper, we have made an attempt to combine the features of various parts of the query image, and then it compares with the features of the target image in the feature database using Structural Equation model. In order to measure the performance of the proposed technique, mean average precision is employed in terms of precision and recall. The obtained results are comparable with the existing methods.