A METHOD OF SEMANTIC-BASED IMAGE RETRIEVAL USING GRAPH CUT

Semantic extraction for images is a topical problem and is applied in many different semantic search systems. In this paper, a method of semantic image retrieval is proposed based on the set of similar images to the input image; then, the semantics of the images are queried on the ontology through the visual words vector. The objects of each image are extracted and classified by the Mask R-CNN and stored on the cluster graph to extract semantics for the image. The similar images of query image are extracted on the cluster graph; then, the k-NN algorithm is applied to find the visual words vector as the basis for querying the semantic of the query image on the ontology by the SPARQL query. On the basis of the proposed method, an experiment was built and evaluated on two large-volume image datasets MIRFLICKR-25K and MS COCO. Experimental results are compared with recently published works on the same datasets to demonstrate the effectiveness of the proposed method. According to the experimental results, the method of semantic image retrieval in this paper has improved the accuracy to 0.897 for MIRFLICKR-25K, 0.833 for MS COCO.