Output details

Multi-feature query language for image classification

<17>The research investigates a novel approach in a domain-independent way of automatized image categorization based on the theory of Content Based Image Retrieval (CBIR). A CBIR query language is constructed to build query-like descriptors for each category to be learned. The developed learning algorithm has been deployed by analysing the quality of images for the welding industry extensible to other disciplines, such as healthcare, archaeology, museum or personal image collections. The resulting descriptors are aimed to be understandable and modifiable by expert users. This research is the culmination of long standing research collaboration with Hamburg University, Germany.