Explore chapters and articles related to this topic
Image Retrieval
Published in Ling Guan, Yifeng He, Sun-Yuan Kung, Multimedia Image and Video Processing, 2012
Motivated by the phenomenal success of web image search engines, researchers started to study the problem of automatic image annotation, aiming at automatically generating metadata in the form of captioning or keywords to digital images, and thus facilitating keyword-based image search, browsing, and organization. The problem is also related to object recognition, scene classification, or video concept detection in different research communities. The fundamental problem is to learn the mapping between visual features and textual keywords, and then apply the learned model to analyze and annotate the semantic concepts of new images. The study of this problem is also helpful to clean the noisy surrounding text or user-generated tags of web images, which is also called image annotation refinement in the literature. The mainstream of image annotation research is based on statistical approaches to model the relationship between visual features and semantic concepts. In contrast to model-based approaches, recent work shows data-driven approaches to be another promising direction. This is due to the explosive growth of multimedia data and large-scale image datasets readily available on the web. By treating web as a huge repository of weakly labeled images, data-driven approaches complement model-based approaches from a different angle and make image annotation more practical for large-scale image retrieval systems.
Semantic Enrichment for Automatic Image Retrieval
Published in Spyrou Evaggelos, Iakovidis Dimitris, Mylonas Phivos, Semantic Multimedia Analysis and Processing, 2017
Clement H. C. Leung, Yuanxi Li
Automatic image annotation: (also known as automatic image tagging or linguistic indexing) is the process by which a computer system automatically assigns data in the form of captioning or keywords to a digital image. This technique is used in image retrieval systems to organize and locate images of interest from a database.
Markov chain latent space probabilistic for feature optimization along with Hausdorff distance similarity matching in content-based image retrieval
Published in The Imaging Science Journal, 2022
Significant research has been conducted to increase the effectiveness of automatic image annotation; however, something which are visible variations provide a poor impression of the image retrieval process [7,8]. A platform known as Content-Based Image Retrieval (CBIR) overcomes problems caused by other methods because it relies on visual analysis of data which is regarded as a component of quality assurance. The similarity in visual proximity to the picture feature and the query image may both utilize the mapping of photographs stored in an archive as data input. The foundation for identifying photos with the same content is provided by vector [9]. The query is used to calculate low-level visual elements and comparison of the attributes is used to confirm the arrangement of the results [10].