Sharif Digital Repository

Considering each of the visual features as one modality in image annotation task, efficient fusion of different modalities is essential in graph-based learning. Traditional graph-based methods consider one node for each image and combine its visual features into a single descriptor before constructing the graph. In this paper, we propose an approach that constructs a subgraph for each modality in such a way that edges of subgraph are determined using a search-based approach that handles class-imbalance challenge in the annotation datasets. Multiple subgraphs are then connected to each other to have a supergraph. This follows by introducing a learning framework to infer the tags of... 

Automatic image annotation is a challenging problem in the field of image retrieval. Dealing with large databases makes the annotation problem more difficult and therefore an effective approach is needed to manage such databases. In this work, an annotation system has been developed which considers images in separate categories and constructs a profiling model for each category. To describe an image, we propose a new feature extraction method based on color and texture information that describes image content using discrete distribution signatures. Image signatures of one category are partitioned using spectral clustering and a prototype is determined for each cluster by solving an... 

The number of digital images uploaded in the virtual world is rapidly growing every day. Therefore, an automatic image annotation system that can retrieve information from these images seems to be in high demand. One of the challenges in this field is the imbalanced data sets and the difficulty of successfully learning tags from them. Even if a nearly balanced data set exists for image annotation, it is unlikely to find a single learner, which could learn all tags with the same accuracy. In this paper, we suggest a novel integration system that selects an elite group of models from all existing annotation models and then combines them to take the best advantage of each model’s learning...