Fast retrieval and efficient identification of monument images using features based adaptive clustering and optimized deep belief network

Abstract

ABSTRACT Content-Based Image Retrieval (CBIR) is an extensively used image processing technique for retrieving similar images (general, images, monument images, etc) from large datasets. Some existing approaches' accuracy and retrieval time are ineffective for monument image retrieval. To overcome these challenges, the monument images are identified and retrieved efficiently using the visual feature extraction and adaptive density-based clustering approach (ADCA). Features required for efficient retrieval is obtained and the obtained multiple features are fused into a single feature using the hybrid weighted and average weighted methods. An optimized Deep belief network (ODBN) is designed to label the clusters based on the grouped images and then retrieve the images relevant to query images. From the experimental results, the overall accuracy achieved by the proposed framework are 99.63% (Architectural heritage dataset), 98.88% (synthetic dataset) and 99.1% (Kaggle dataset), respectively. The experimental results proved the efficiency of proposed in retrieving monument images.