Enhanced image annotations based on spatial information extraction and ontologies

Abstract

Abstract-Current research on image annotation often represents images in terms of labelled regions or objects, but pays little attention to the spatial positions or relationships between those regions or objects. To be effective, general purpose image retrieval systems require images with comprehensive annotations describing fully the content of the image. Much research is being done on automatic image annotation schemes but few authors address the issue of spatial annotations directly. This paper begins with a brief analysis of real picture queries to librarians showing how spatial terms are used to formulate queries. The paper is then concerned with the development of an enhanced automatic image annotation system, which extracts spatial information about objects in the image. The approach uses region boundaries and region labels to generate annotations describing absolute object positions and also relative positions between pairs of objects. A domain ontology and spatial information ontology are also used to extract more complex information about the relative closeness of objects to the viewer.

Slice-Guided Components Detection and Spatial Semantics Acquisition of Indoor Point Clouds

“…There are many efforts that have been expended on the extraction of spatial relationships from scene images. Muda [33] used region boundaries and region labels to generate annotations describing absolute object positions and also relative positions between pairs of objects on the base of a domain ontology and spatial information ontology. Aditya et al [34] presented a general architecture where the generic visual recognition techniques for the image scenes were implemented.…”

“…The extraction of the spatial relationships between indoor scene components lays a foundation for understanding the indoor scene in a way similar to the way that humans perceive the environment. Many methods [33][34][35] have been proposed to extract spatial relationships from scene images. In contrast with the spatial relationships in images, the spatial relationships in 3D point clouds are more complex [36,37], and the extraction of them is more challenging.…”

A New Approach for CBIR Feedback based Image Classifier

“…On the other hand, due to its inherent nature of inaccuracy in description of the same semantic content by different color quantization and /or by the uncertainty of human perception, it is important to capture this inaccuracy when defining the features. We apply fuzzy logic to the traditional color histogram to help capture this uncertainty in color indexing [2], [5].In image retrieval systems color histogram is the most commonly used feature. The main reason is that it is independent of image size and orientation.…”

“…Much of this information is multimedia in nature, including digital images, video, audio, graphics, and text data. In order to make use of this vast amount of data, efficient and effective techniques to retrieve multimedia information based on its content need to be developed [2]. Among the various media types, images are of prime importance.…”