Image analysis – Color image processing – Image segmentation using color
Reexamination Certificate
1999-08-17
2003-06-10
Chang, Jon (Department: 2623)
Image analysis
Color image processing
Image segmentation using color
Reexamination Certificate
active
06577759
ABSTRACT:
TECHNICAL FIELD OF THE INVENTION
The present invention is directed, in general, to image retrieval systems and, more specifically, to an image retrieval system using color-based segmentation to retrieve region-based images.
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.
The term “visual animated data” herein refers to natural video, as well as to synthetic 2D or 3D worlds, or to a mixture of both video and graphics. Different criteria are used to search and index the content of visual animated data, such as a video clip. Video processing devices operating as image retrieval systems have been developed for searching frames of visual animated data to detect, identify and label objects of a particular shape or color, or to detect text in the frames, such as subtitles, advertisement text, or background image text, such as a street sign or a “HOTEL” sign.
Many of the existing image retrieval systems require a template image in order to search for all the images that resemble the template. For many applications, sub-image matching or object shape-based matching might be more desirable than full-image matching. For instance, a user may wish to retrieve images of red cars from an archive of images, but may not want to retrieve the remaining portion of the original image. Alternatively, a user may have a particular interest in retrieving all images that include a particular shape or a combination of shapes. This type of image retrieval is known as “region-based image retrieval.”
The extraction of image regions in an automatic and robust fashion is an extremely difficult task. Although image segmentation techniques have been studied for more than thirty years, segmentation of color images in real-world scenes is still particularly challenging for computer vision applications. This is primarily due to illumination changes in images, such as shade, highlights, and sharp contrast. For example, nonuniform illumination produces nonuniformity in the values of image pixels in RGB and YUV color spaces in conventional image segmentation techniques.
There is, therefore, a need in the art for improved video processing devices capable of performing region-based image retrieval. In particular, there is a need for improved region-based image retrieval systems capable of performing color-based segmentation that are less sensitive to illumination conditions.
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 capable of analyzing an image comprising a plurality of pixels in a first color model format, an image processing device capable of detecting and retrieving from the image a selected image portion. The image processing device comprises an image processor capable of converting the plurality of pixels in the image from the first color model format to a (Y,r,&thgr;) color model format, wherein for each pixel in the plurality of pixels, Y is an intensity component indicating a total amount of light, r is a saturation component indicating an amount of white light mixed with a color of the pixel, and &thgr; is a hue component indicating the color of the pixel. The image processor is capable of grouping spatially adjacent ones of the plurality of pixels into a plurality of image regions according to hue components of the adjacent pixels and performing a merging process wherein a first image region and a second image region proximate the first image region are merged into a composite region if a hue difference between the first and second image regions is less than a predetermined hue difference threshold.
According to an exemplary embodiment of the present invention, the image processor is capable of determining a histogram of hue components of the pixels in the image, the histogram indicating a number of pixels of similar hue in the image.
According to one embodiment of the present invention, the image processor is capable of determining a dominant hue in the image using a peak detection algorithm on the histogram.
According to another embodiment of the present invention, the image processor is capable of determining and marking ones of the plurality of image regions having less than a predetermined minimum number of pixels and disregarding the marked image regions during the merging process.
According to still another embodiment of the present invention, the image processor is capable of determining and marking achromatic ones of the plurality of image regions having less than a predetermined minimum number of pixels and disregarding the marked achromatic image regions during the merging process.
According to yet another embodiment of the present invention, the first and second image regions are merged if a number of pixels in the first image region and a number of pixels in the second image region are greater than a predetermined image region size threshold.
According to a further embodiment of the present invention, the image processor is capable of determining a plurality of adjacent regions to the first image region and calculating merit values for the plurality of adjacent regions, wherein a merit value of a first selected adjacent region is equal to a ratio of a common perimeter of the first image region and the first selected adjacent region to a total perimeter of the first selected adjacent region.
According to a still further embodiment of the present invention, the image processor selects the second image region to be merged with the first image region according to a merit value of the second image region.
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 term “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
Caron Cedric Y.
Challapali Kiran
Yan Yong
Chang Jon
Le Brian
Thorne Gregory L.
LandOfFree
System and method for performing region-based image... 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 performing region-based image..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System and method for performing region-based image... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3119410