Image Retrieval with Multiple Regions-of-Interest
With the proliferation of multimedia, the web and digital imaging, there now exists a high demand for intelligent tools for image management, most importantly indexing, search and retrieval, commonly referred to as QBIC or "query-by-image content." The goal of this project has been to develop a new image retrieval system based on the principle that it is the user who is most qualified to specify the "content" in an image and not the computer. The user is asked to provide salient ROIs or "regions-of-interest" and specify their spatial arrangements in the query image. This technique leads to a much more powerful image retrieval tool.
Background & Objective: Most current "query-by-image-content" database indexing and retrieval systems rely on global image characteristics such as color and texture histograms. While these simple descriptors are fast and often do succeed in capturing a vague essence of the user's query, they more often fail due to the lack of higher level knowledge about what exactly was of interest to the user in the query image. The goal of this project was to develop and test a new technique using local image representations, grouping them into multiple user-specified "regions-of-interest" while preserving their relative spatial relationships in order to build a more powerful search engine for various applications of image database retrieval.
Technical Discussion: In our system we subdivide the image into an array of 16-by-16 pixel blocks each of which contains the following feature representations: a joint color histogram in LUV color space and joint 3D histogram consisting of the edge magnitude, Laplacian and dominant edge orientation, computed at two octave scales. These non-parametric densities represent local color and texture and due to the additive property of histograms can be easily combined to form bigger image blocks. When the user specifies a region of interest, its underlying blocks are "pooled" to represent a "meta-block" to be searched for in the database. Multiple regions are likewise searched and the intersection of the best matches determines the final similarity ranking of images in the database. In addition, the user can specify whether multiple selected regions should maintain their respective spatial arrangement.
| Technical Reports: | |
| Regions-of-Interest and Spatial Layout for Content-Based Image Retrieval | |
Technology Area: Computer Vision
Modification Date: September 12, 2007