Image Retrieval based on the Fusion of Graph Method with Color Moments, GLCM, and Hu Moments

Abstract

Retrieving images that are similar to the query image in the image database means determining the similarity between the images. This study aims to use a graph method with region adjacency graph representation in conjunction with a non-graph method in image retrieval. We represented an image as a graph and used the Graph Edit Distance (GED) method to calculate the similarity between two graphs. The feature extraction of the image graph, which exposes the content and the relationships between existing content, is a key step in image retrieval based on the graph method. The extraction of graph features is accomplished by the image segmentation method, which divides the image into regions and represents them as a region-adjacency graph (RAG), in which vertices represent regions and edges indicate two neighboring regions. Image retrieval based on the graph method is combined with low-level approaches like Color Moments, Gray Level Co-occurrence Matrix (GLCM), and Hu Moments to boost accuracy. All obtained features are normalized, weighted, and then compared between images to get the similarity value using Euclidean Distance. An image retrieval prototype based on the combined graph method and non-graph method was successfully created in this work, using four datasets: synthetic, batik, COIL-100, and Wang. The MAP of the four datasets is 67.84 percent, but when combined with the low-level feature approach, it rises to between 79.73 and 89.71 percent. The combination of graph and non-graph algorithms improves image retrieval outcomes.