Image analysis – Image transformation or preprocessing – Changing the image coordinates
Reexamination Certificate
1999-08-04
2003-04-08
Mehta, Bhavesh M. (Department: 2625)
Image analysis
Image transformation or preprocessing
Changing the image coordinates
C382S276000, C345S582000, C345S649000
Reexamination Certificate
active
06546155
ABSTRACT:
TECHNICAL FIELD OF THE INVENTION
The present invention is directed, in general, to image processing systems and, more specifically, to a system for representing textures in images in a rotation invariant Markov random field.
BACKGROUND OF THE INVENTION
The advent of digital television (DTV), the increasing popularity of the Internet, and the introduction of consumer multimedia electronics, such as compact disc (CD) and digital video disc (DVD) players, have made tremendous amounts of multimedia information available to consumers. As video and animated graphics content becomes readily available and products for accessing it reach the consumer market, searching, indexing and identifying large volumes of multimedia data becomes even more challenging and important.
Content-based retrieval systems have been developed that search and retrieve image files, including video images and still images, that contain a certain type of content, usually specified by a user. For example, a user may use a content-based retrieval system to retrieve images files that contain images of circular red objects. Content-based retrieval systems often use texture, along with color and shape, as a criteria for searching in image files.
Texture is one of the important visual features present in images. The ability of a content-based retrieval system to retrieve an image based on texture depends on how texture is represented in an image file. Markov random field (MRF) models are one of the many representations that have been successfully used to represent texture to an image or regions within the image. An MRF model uses a few selected MRF parameters to represent texture characteristics of each region with the image.
For example, Gauss Markov random field (MRF) models represent a selected pixel in an image as a linear combination of a small number of pixels present in a neighborhood around the selected pixel, plus a noise term. However, Gauss MRF parameters are not rotation invariant. That is, if the texture in an image is modeled by MRF parameters and the image is subjected to a rotation (e.g., 90 degrees clockwise) then the MRF texture parameters in the resulting image will be different from the original texture parameters. This is a drawback with respect to applications such as content-based image search and retrieval, which cannot use the texture parameters of a user-selected texture in the original image to search for the same texture in the rotated image. To facilitate content-based image retrieval, it is preferable to have a texture representation that does not vary with image rotation.
There is therefore a need in the art for improved systems and methods for performing content-based image retrieval. In particular, there is a need for systems and methods capable of representing textures in images in a manner that is rotation invariant.
SUMMARY OF THE INVENTION
To address the above-discussed deficiencies of the prior art, it is a primary object of the present invention to provide, for use in an image retrieval system, an image processing device capable of receiving an image comprising a selected pixel having associated therewith a first texture representation specified in a rotation variant format and converting the first texture representation to a second texture representation specified in a rotation invariant format. The image processing device comprises an image processor capable of analyzing rotation variant texture parameters associated with the first texture representation and determining therefrom one of: 1) a first plurality of rotation invariant texture parameters circularly disposed about the selected pixel in at least one ring, wherein the first plurality of rotation invariant texture parameters comprise the second texture representation; and 2) a second plurality of rotation invariant texture parameters disposed along at least one radial line extending through the selected pixel, wherein the second plurality of rotation invariant texture parameters comprise the second texture representation.
According to one embodiment of the present invention, the rotation variant texture parameters are Markov random field parameters.
According to another embodiment of the present invention, a number of the first plurality of rotation invariant texture parameters is equal to a number of the at least one ring.
According to still another embodiment of the present invention, a number of the second plurality of rotation invariant texture parameters is equal to a number of the at least one radial line.
According to a further embodiment of the present invention, the image processor is capable of determining from the second plurality of rotation invariant texture parameters an angular amount of rotation between the image and a rotated version of the image.
According to a still further embodiment of the present invention, the image processor is capable of detecting the angular amount of rotation in increments of 180/K degrees, where K is a number of the at least one radial line.
According to a yet further embodiment of the present invention, the image, processor determines the angular amount of rotation between the image and the rotated version of the image by rotating the second plurality of rotation invariant texture parameters to a plurality of rotation points in increments of 180/K degrees, where K is a number of the at least one radial line, comparing the second plurality of rotation invariant texture parameters with a third plurality of rotation invariant texture parameters associated with the rotated version of the image at each of the plurality of rotation points, and determining a selected one of the plurality of rotation points at which a minimum difference occurs between the second and third plurality of rotation invariant texture parameters.
The foregoing has outlined rather broadly the features and technical advantages of the present invention so that those skilled in the art may better understand the detailed description of the invention that follows. Additional features and advantages of the invention will be described hereinafter that form the subject of the claims of the invention. Those skilled in the art should appreciate that they may readily use the conception and the specific embodiment disclosed as a basis for modifying or designing other structures for carrying out the same purposes of the present invention. Those skilled in the art should also realize that such equivalent constructions do not depart from the spirit and scope of the invention in its broadest form.
Before undertaking the DETAILED DESCRIPTION, it may be advantageous to set forth definitions of certain words and phrases used throughout this patent document: the terms “include” and “comprise,” as well as derivatives thereof, mean inclusion without limitation; the term “or,” is inclusive, meaning and/or; the phrases “associated with” and “associated therewith,” as well as derivatives thereof, may mean to include, be included within, interconnect with, contain, be contained within, connect to or with, couple to or with, be communicable with, cooperate with, interleave, juxtapose, be proximate to, be bound to or with, have, have a property of, or the like; and the terms “processor” or “controller” means any device, system or part thereof that controls at least one operation, such a device may be implemented in hardware, firmware or software, or some combination of at least two of the same. It should be noted that the functionality associated with any particular controller may be centralized or distributed, whether locally or remotely. Definitions for certain words and phrases are provided throughout this patent document, those of ordinary skill in the art should understand that in many, if not most instances, such definitions apply to prior, as well as future uses of such defined words and phrases.
REFERENCES:
patent: 4267573 (1981-05-01), Chaikin et al.
patent: 4989257 (1991-01-01), Horowitz
patent: 5956427 (1999-09-01), Greenspan et al.
patent: 6002807 (1999-12-01), Guerci
patent: 6192150 (2001-02-01), Leow et al.
“Circular
Gross Russell
Mehta Bhavesh M.
Patel Kanji
LandOfFree
System and method for rotation invariant representation of... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with System and method for rotation invariant representation of..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System and method for rotation invariant representation of... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3100460