PGCon2007 - Confirmed
PGCon 2007
The PostgreSQL Conference
| Speakers | |
|---|---|
|
Denise Guliato |
| Schedule | |
|---|---|
| Day | 3 |
| Room | SITE G0103 |
| Start time | 10:00 |
| Duration | 01:00 |
| Info | |
| ID | 55 |
| Event type | Lecture |
| Track | Advanced Features |
| Language | English |
| Feedback | |
|---|---|
|
Did you attend this event? Give Feedback |
PostgreSQL-IE
An Image-Handling Extension to support Content-based Image Retrieval
PostgreSQL-IE is an extension to PostgreSQL to support content-based image retrieval. The extension makes available a new image data type, and extends the Structured Query Language – SQL with new functions that are able to create new feature descriptors, new feature vectors as combinations of previously defined features, new access methods, and to pose similarity queries.
The last decade witnessed a growing interest in research on content-based image retrieval (CBIR) and related areas. Several systems for managing and retrieving images have being proposed, each one tailored to a specific application. Functionalities commonly available in these CBIR systems include: storage and management of complex data; development of feature extractors to support similarity queries; development of index structures to speed up image retrieval; and design and implementation of an intuitive graphical user interface tailored to each application. In order to facilitate the development of new CBIR systems, we propose an image-handling extension to the relational database management system (RDBMS) PostgreSQL. This extension, called PostgreSQL-IE, is independent of application, and provides the advantage of being open-source and portable.
The proposed system extends the functionalities of Structure Query Language (SQL) with new functions that are able to create new feature extraction procedures, new feature vectors as combinations of previously defined features, new access methods, and similarity queries.
PostgreSQL-IE makes available a new image data type, which permits the association of various images with a given unique image attribute. This resource makes it possible to combine visual features of different images in the same feature vector. To illustrate and validate the concepts and resources available in the proposed extended RDBMS, we present a CBIR system applied to the analysis of mammograms developed using PostgreSQL-IE.