Abstract The paper proposes an alternative approach to improve the performance of image retrieval. In this work, a framework for image retrieval based on machine learning and semantic retrieval is proposed. In the preprocessing phase, the image is segmented objects by using Graph‐cut, and the feature vectors of objects presented in the image and their visual relationships are extracted using R‐CNN. The feature vectors, visual relationships, and their symbolic labels are stored in KD‐Tree data structures which can be used to predict the label of objects and visual relationships later. To facilitate semantic query, the images use the RDF data model and create an ontology for the symbolic labels annotated. For each query image, after extracting their feature vectors, the KD‐Tree is used to classify the objects and predict their relationship. After that, a SPARQL query is built to extract a set of similar images. The SPARQL query consists of triple statements describing the objects and their relationship which were previously predicted. The evaluation of the framework with the MS‐COCO dataset and Flickr showed that the precision achieved scores of 0.9218 and 0.9370, respectively.

The problems of image mining and semantic image retrieval play an important role in many areas of life. In this paper, a semantic-based image retrieval system is proposed that relies on the combination of C-Tree, which was built in our previous work, and a neighbor graph (called Graph-CTree) to improve accuracy. The k-Nearest Neighbor (k-NN) algorithm is used to classify a set of similar images that are retrieved on Graph-CTree to create a set of visual words. An ontology framework for images is created semi-automatically. SPARQL query is automatically generated from visual words and retrieve on ontology for semantics image. The experiment was performed on image datasets, such as COREL, WANG, ImageCLEF, and Stanford Dogs, with precision values of 0.888473, 0.766473, 0.839814, and 0.826416, respectively. These results are compared with related works on the same image dataset, showing the effectiveness of the methods proposed here.

Abstract In this paper, we approach a method of clustering binary signature of image in order to create a clustering graph structure for building the content‐based image retrieval. First, the paper presents the segmentation method based on low‐level visual features including colour and texture of image. On the basis of segmented image, the paper creates binary signature to describe location, colour, and shape of interest objects. In order to match similar images, the paper presents a similarity measure between the images based on binary signature. From that, the paper proposes the method of clustering binary signature to quickly query similar images. At the same time, the graph data structure is built using the partition cluster technique and the rules of binary signatures' distribution of images. On the basis of data structure, we propose a graph creation algorithm, a cluster splitting/merging algorithm, and a similarity image retrieval algorithm. To illustrate the proposed theory, we build an image retrieval application and assess the experimental results on the image datasets including COREL (1,000 images), CBIR images (1,344 images), WANG (10,800 images), MSRDI (15,720 images), and ImageCLEF (20,000 images).