Structure Oriented Local Image Feature Description

Radial Edge Configuration for Semi-local Image Structure Description

We present a novel semi-local image descriptor which encodes multiple edges corresponding to the image structure boundaries around an interest point. The proposed method addresses the problem of poor edge detection through a robust, scale and orientation invariant, descriptor distance. In addition, a clustering of descriptors capable of extracting distinctive shapes from a set of descriptors is...

Feature-Oriented Description, Formal Methods, and DFC

This paper explores the close relationship between feature-oriented and architectural styles of formal system description, and explains the formal methods needed to support descriptions in these styles. In the telecommunications domain, DFC is a successful example of a feature-oriented, architectural description technique. Although formal methods for DFC are in their infancy, there are already ...

Content-Based Image Feature Description and Retrieving

Image Reconstruction based on Local feature Descriptors

In this project, we show that an image can be reconstructed using local descriptors, with or without complete geometrical metadata. We use greedy algorithms to progressively learn the missing information before reconstruction and colorization is performed. Our experiments show that most of the vital information about a query image can be recovered even if scale metadata is missing. Compared to ...

Local Invariant Feature Histograms for Image Retrieval

Among other techniques especially methods working fully automatically are of interest for image retrieval from large data collections. Histograms proved successful in automatic image retrieval, however their drawback is, that all structural information is lost. Therefore we use histograms of features, that take into account the relations within a local neighbourhood. These features are based on...