Image analysis – Applications – Biomedical applications
Reexamination Certificate
1999-02-02
2002-04-30
Mancuso, Joseph (Department: 2721)
Image analysis
Applications
Biomedical applications
C128S922000
Reexamination Certificate
active
06381352
ABSTRACT:
FIELD OF THE INVENTION
The invention relates generally to image processing, and more particularly to an image processing method that can isolate relevant subject matter from a substantially homogeneous background.
BACKGROUND OF THE INVENTION
In many fields, two-dimensional images of relevant subject matter are surrounded or at least partially bordered by a dark (i.e., black) homogenous background in which bright (i.e., white) labeling or artifacts are present due to imaging anomalies or errors, or to identify the subject matter, provide scaling information, time/date information, etc. Examples of such two-dimensional images include x-ray, mammographic, sonographic and sonar images. However, the dark background and bright labeling or artifacts use the lower and upper regions, respectively, of a display=s dynamic range. As a result, image contrast of the relevant subject matter is reduced because the relevant subject matter is not able to utilize the full dynamic range of the display. Reduced contrast of the relevant subject matter means that important details (e.g., tumor presence, bone fractures, fetal anomalies, etc., in the field of medicine; structural defects in the field of static structure analysis; and missed targets or other anomalies in sonar image analysis) could be overlooked or misread.
SUMMARY OF THE INVENTION
Accordingly, it is an object of the present invention to provide an image processing method that improves the image quality of relevant subject matter.
Another object of the present invention is to provide an image processing method that isolates the relevant subject matter of a two-dimensional image from a dark homogenous background which may incorporate bright labeling and/or artifacts.
Still another object of the present invention is to provide an image processing method that defines the boundaries of the relevant subject matter to improve computation speed for any post-processing.
Other objects and advantages of the present invention will become more obvious hereinafter in the specification and drawings.
In accordance with the present invention, an image processing method uses digital data representing grey scale values of a two-dimensional image of relevant subject matter and a substantially homogeneous background that at least partially borders on the relevant subject matter. A first sub-image is defined from the two-dimensional image. The first sub-image includes the relevant subject matter and a reduced amount of the substantially homogeneous background. A second sub-image is defined from the first sub-image. The second sub-image predominantly defines just the relevant subject matter. A smoothing routine can be applied to the second sub-image if any small areas of homogeneous background remain. The second sub-image can then be re-scaled to a given dynamic range for improved contrast of the relevant subject matter as compared to the initial image.
REFERENCES:
patent: 4922543 (1990-05-01), Ahlbom et al.
patent: 5278887 (1994-01-01), Chiu et al.
patent: 5452367 (1995-09-01), Bick et al.
patent: 5457754 (1995-10-01), Han et al.
patent: 5684888 (1997-11-01), Vuylsteke
patent: 5859891 (1999-01-01), Hibbard
patent: 6058322 (2000-05-01), Nishikawa et al.
Gilbert Harvey A.
Mancuso Joseph
Peck Donald G.
Tabatabai Abolfazl
The United States of America as represented by the Secretary of
LandOfFree
Method of isolating relevant subject matter in an 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 Method of isolating relevant subject matter in an image, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method of isolating relevant subject matter in an image will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2903118