This dissertation aims at building and using knowledge-driven models in order to improve the accuracy of automatic image annotation. Currently, many image annotation approaches are based on the automatic association between low-level or mid-level visual features and semantic concepts using machine learning techniques. Nevertheless, the only use of machine learning seems to be insufficient to br...

In this demo, a system for the semantic annotation of images is presented. The proposed knowledge-assisted analysis architecture comprises algorithms that perform semantic image segmentation, region-level classification and fuzzy reasoning; hence, it constitutes a complete solution to the problem of image annotation based on semantic criteria.

Image segmentation has an essential role in the image annotation process which assigns meaningful words to an image taking into account its content. For this reason it is important to identify which segmentation algorithm is producing better results. This evaluation can be made using segmentation error measures for consistency quantification and by analyzing the results of the annotation proces...

Automatic image annotation is a process by which metadata is assigned in form of captioning or keywords to a digital image. Large annotation databases are difficult to build because some of the images have partial annotations and noise tags problem. In order to solve the problems with the annotation of large databases, in our approach we remove noise and invalid images from the dataset and extr...

Automatic image annotation is a newly developed and promising technique to provide semantic image retrieval via text descriptions. It concerns a process of automatically labeling the image contents with a pre-defined set of keywords which are exploited to represent the image semantics. A Maximum Entropy Model-based approach to the task of automatic image annotation is proposed in this paper. In...

Structured knowledge models, such as semantic hierarchies and ontologies, appear to be a way to improve the accuracy of automatic image annotation. It allows modeling many valuable semantic relations between concepts based on image annotation using contextual and spatial relationships. Indeed, these relationships have been proved to be of prime importance for the understanding of image semantic...