Image analysis – Image enhancement or restoration – Edge or contour enhancement
Reexamination Certificate
2001-05-15
2004-11-23
Boudreau, Leo (Department: 2624)
Image analysis
Image enhancement or restoration
Edge or contour enhancement
C382S268000
Reexamination Certificate
active
06823087
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Field of the Invention
The present invention pertains to video compression and decompression, and, more particularly, to a technique for mitigating edge “edge effects” in decompressing video data.
2. Description of the Related Art
In watching a video, the viewer is actually seeing a series of video images, or “frames,” displayed in rapid succession. How rapid depends largely on geographic location because different locations use different standards with different numbers. In the United States, successive video images are displayed at a rate of 60 images per second. Each frame typically differs from the one before and the one after only very slightly. Thus, when the series is displayed rapidly enough, it creates the illusion of continued movement.
Each video image, however, contains a relatively large amount of information. This has caused problems with the advent of digital video systems. The digital video system breaks the image into pieces (called “pixels”, or “picture elements”), transmits them, reassembles the pieces and displays the transmitted image. However, the amount of information that must be handled in the given time quickly overwhelms most digital electronics. Most digital electronics systems will take too long so that the successive images cannot be displayed quickly enough to create the illusion of continued motion. If the work is an audiovisual work so that it includes sound as well as imagery, the problem becomes particularly acute.
One solution employs video compression/decompression (“codec”) techniques. There are “lossy” and “non-lossy” codec techniques. A lossy technique “loses” some information in the process of compressing and decompressing the information. For instance, lossy codec techniques take advantage of the fact that successive images will usually differ very little. Codec techniques quickly compare a frame with the frame image and then transmit only the differences instead of all the information. Standards setting bodies have defined standards for various codec techniques, but there are also many non-standard techniques. Each has advantages and disadvantages that impact performance differently.
One common problem with codec techniques are “edge effects.” Technically, edge effects result in decompression from the quantization of what are known as the “discrete cosine-transformation” (“DCT”) coefficients during compression. Referring now to
FIG. 1
, the video frame
100
is broken into a number of pixels
105
. Pixels are usually handled in square blocks, such as the blocks
110
. Each block
110
is defined by two horizontal edges and two vertical edges
115
,
120
that will suffer from edge effects. More precisely, the pixels
105
lining the horizontal and vertical edges
115
,
120
will suffer from “edge effects.” Note that the number of pixels
105
and blocks
110
of pixels
105
are illustrative only, and are not intended to reflect the application of any particular standard.
Edge effects are mitigated by filtering the pixels
105
lining the horizontal and vertical edges
115
,
120
. “Horizontal” filters are applied to the horizontal edges
115
and “vertical” filters are applied to the vertical edges
120
. Because of the way the data is organized when the information is stored to memory, the computation for the horizontal edges is manipulated to “parallelize.” Parallelizing the computation is desirable because it decreases the time necessary to perform the computation. However, the data organization makes the vertical computation difficult to parallelize. Depending on the length of the filters employed, what requires a single memory access in the horizontal computation might take as many as four memory accesses in the vertical computation.
The present invention is directed to resolving, or at least reducing, one or all of the problems mentioned above.
SUMMARY OF THE INVENTION
The invention, in a first aspect, is a method for mitigating edge effects in a decompressed video image. The method comprises first reads an N×N group of pixels defining a vertical edge between two blocks in a video frame row by row into N registers, wherein N is a predetermined number defining the length of a filter. The content of the N registers is then transposed and then filtered in the filter. The filtered content of the N registers is then transposed and stored back from where it was read. In other aspects, the invention is a program storage device encoded with instructions that, when executed by a computer, perform such a method; a computer programmed to perform such a method; and a computing system capable of performing such a method.
REFERENCES:
patent: 4463372 (1984-07-01), Bennett et al.
patent: 5719958 (1998-02-01), Wober et al.
patent: 5796875 (1998-08-01), Read
patent: 5832135 (1998-11-01), Merhav et al.
patent: 6002801 (1999-12-01), Strongin et al.
patent: 6052490 (2000-04-01), Haskell et al.
patent: 6175592 (2001-01-01), Kim et al.
patent: 6175892 (2001-01-01), Sazzad et al.
patent: 6285801 (2001-09-01), Mancuso et al.
patent: 6389177 (2002-05-01), Chu et al.
patent: 6625721 (2003-09-01), Chen
Gorishek Frank
Hsu Wei-Lien
Liu Yi
Advanced Micro Devices , Inc.
Boudreau Leo
Rosario-Vasquez Dennis
Williams Morgan & Amerson P.C.
LandOfFree
Parallel edge filters in video codec does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Parallel edge filters in video codec, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Parallel edge filters in video codec will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3300931