Computer graphics processing and selective visual display system – Display peripheral interface input device
Reexamination Certificate
1998-08-13
2001-09-18
Luu, Matthew (Department: 2672)
Computer graphics processing and selective visual display system
Display peripheral interface input device
C345S156000, C382S244000
Reexamination Certificate
active
06292168
ABSTRACT:
BACKGROUND OF THE INVENTION
This application relates to the digital image processing arts. More particularly, the application relates to a method and apparatus for converting image data from a first bit depth (number of bits per sample) to a second bit depth as required for different image processing modules or operations in an image processing system.
Traditionally, digital image files were created with a variety of bit depths or number of bits per sample (i.e., bits per pixel for monochromatic image data or bits per separation pixel for color image data) ranging from 1-8.
More recently, it is not uncommon for digital image data to be presented in terms of 10-16 bits per sample. Generally, image processing modules are designed to utilize only image data presented in one or two different bit depths, e.g., 1 bit per sample or 8 bits per sample. Because image data is typically encoded in many different formats, each having a different number of bits per sample, it is necessary for image processing modules to use a bit conversion library to perform bit conversion operations among the different encoding formats as needed in a quick and efficient manner.
Heretofore, such bit conversion operations have been performed in image processing systems from an input bit depth to a desired or working bit depth on an individual sample-by-sample basis for each scan line of an image without regard to any periodic relationship between the input bit depth and the output bit depth. In this prior approach, the bits for each individual sample are extracted from a scanline and converted to the desired format through use of some non-optimized conversion algorithm. This individual sample-by-sample conversion method is relatively slow and inefficient due to the fact that input scanlines are often arbitrary in length and the input sample bit depth is generally not in terms of a standard computational data length, i.e., not a byte (8 bits) or some multiple thereof. This increases the number of steps required to extract the subject data bits from the input scanline, and consequently results in use of excessive amounts of valuable computational time.
In modern image processing systems, high speed data processing is essential. As such, it has been deemed desirable to develop a new and improved method and apparatus for performing optimized bit conversion operations in a high speed and efficient manner.
SUMMARY OF THE INVENTION
In accordance with a first aspect of the present invention, a period-based method of converting digital image data for a plurality of pixels from a first bit depth to a second bit depth includes receiving an input scanline of an arbitrary length comprising digital image data for a plurality of input image pixels. Each of the input image pixels is defined at the first bit depth. The input scanline is divided into a plurality of periods each comprising digital image data for a select number of input image pixels. The period is selected so that the image data for the select number of input image pixels exactly comprises m bytes when defined at the first bit depth and exactly comprises n bytes when defined at the second bit depth, wherein m and n are different integers. For each of the periods in succession, the image data for each of the select number of input image pixels is converted from the first bit depth to the second bit depth.
In accordance with another aspect of the present invention, an apparatus for converting digital image data from a first bit depth to a second bit depth includes means for supplying an input scanline of image data representing an plurality of input image pixels at the first bit depth and means for dividing the image data of the input scanline into a plurality of equal periods. Each period comprises image data for a select number of input image pixels. The select number of input image pixels per period is determined based upon the following:
p
_in
=
input_block
_size
gcd
(
input_block
_size
,
c
)
p
_out
=
output_block
_size
gcd
(
output_block
_size
,
x
)
Input
Pixels
P
/
Period
Z
=
lcm
(
p
_in
,
p
_out
)
wherein:
input—block_size=the natural word size of the input pixel data;
output_block_size=the natural word size of the output pixel data;
gcd=greatest common denominator operation;
lcm=lowest common multiple operation;
c=the input bit depth; and,
x=the output bit depth.
The apparatus further includes means for accessing the image data of each of the plurality of periods of the input scanline image data and for converting the image data for each input image pixel from the first bit depth to image data for a plurality of output image pixels at the second bit depth. Means for storing the image data in an output scanline is included and stores the image data at the second bit depth for each of the plurality of output image pixels.
In accordance with still another aspect of the present invention, a method of converting digital image data from a first bit depth of c bits per pixel to a second bit depth of x bits per pixel, wherein c and x are integers, includes receiving input image data for a plurality of input pixels at the first bit depth. A plurality of input pixels of said input image are selected and exactly comprise an n byte period so that the image data for the period of input pixels, when converted to output image data having the second bit depth, exactly comprises m bytes of output image data, wherein m and n are integers. The input image data for each of said input pixels in said period is converted from the first bit depth to the second bit depth. The foregoing operations are repeated for all n byte periods of the input image data so that the input image data included in each period is converted from the first bit depth to the second bit depth.
One advantage of the present invention resides in the provision of a new and improved method and apparatus for optimized bit conversion in an image processing system.
Another advantage of the present invention resides in the provision of an image processing system and method for implementing fast and efficient bit conversion to convert digital image data from a first number of bits per sample to a second number of bits per sample using a period-based approach.
Still another advantage of the present invention is the provision of an image processing system wherein a file is used to define which bit conversion operations are to be hard-coded, and which bit conversion operations are to be carried out using a generic conversion method.
A further advantage of the present invention is found in the provision of an image processing system including a code-generator which is invoked for purposes of creating optimized program instructions and an associated bit conversion look-up table implementing bit conversion operations in accordance with the present invention with respect to particular, specified bit conversion operations.
Still other benefits and advantages of the present invention will become apparent to those of ordinary skill in the art upon reading and understanding the present specification.
REFERENCES:
patent: 4236228 (1980-11-01), Nagashima
patent: 4663729 (1987-05-01), Matick
patent: 4689807 (1987-08-01), Maan
patent: 5319395 (1994-06-01), Larky
patent: 5390262 (1995-02-01), Pope
patent: 5604527 (1997-02-01), Ng
patent: 5854620 (1998-12-01), Mills
patent: 5943040 (1999-08-01), Rice
patent: 5995122 (1999-11-01), Hsieh
patent: 6009191 (1999-12-01), Julier
patent: 6020897 (2000-02-01), Carlsen
patent: 6038576 (2000-03-01), Ulichney
Fleckenstein, Jr. Patrick A.
Fuss William A.
Venable Dennis L.
Fay Sharpe Fagan Minnich & McKee LLP
Luu Matthew
Sajous Wesner
Xerox Corporation
LandOfFree
Period-based bit conversion method and apparatus for digital... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Period-based bit conversion method and apparatus for digital..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Period-based bit conversion method and apparatus for digital... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2478829