Home | Links | Contact Us | More About Intellectual Property | Bookmark
Search patents:
Home Image Analysis Integrated-systolic-architecture-for-decomposition-and-reconstruction-of-signals-using-wavelet-transforms

 DWT-based up-sampling algorithm suitable for image display in an LCD panel
What is disclosed is a method comprising constructing virtual (Discrete Wavelet Transform) DWT sub-...


 Block mapping based up-sampling method and apparatus for converting color images
The present invention provides a system for a block mapping based up-sampling process to up-sample ...


 Efficient memory mapping of a huffman coded list suitable for bit-serial decoding
OF THE INVENTION Referring to the figures, exemplary embodiments of the invention will now be ...


 Scaling algorithm and architecture for integer scaling in video
A method for scaling of an image that includes providing an N-tap filter to be applied upon an ...


 Median computation-based integrated color interpolation and color space conversion methodology from 8-bit bayer pattern RGB color space to 24-bit CIE XYZ color space
What is disclosed is a method including the steps of (1) providing an integrated median computation ...


 Method and apparatus for automatic focusing in an image capture system using symmetric FIR filters
OF THE INVENTION The present invention provides an automatic focusing method and apparatus ...


 Hi-speed deterministic approach in detecting defective pixels within an image sensor
OF THE INVENTION Referring to the figures, exemplary embodiments of the invention will now be ...


 Mathematical model for gray scale and contrast enhancement of a digital image
What is disclosed is a method that specifies identifying a category to which a pixel belongs and ...


 Interpolation device, process and recording medium on which interpolation processing program is recorded
Thus, one object of the invention is to provide an interpolation device and process that estimates ...


 Optical device, optical device driving unit, and camera system
It is an object of the present invention to change and set preset velocity information and change ...


 Integrated systolic architecture for decomposition and reconstruction of signals using wavelet transforms

Details
Inventors: Acharya, Tinku;
Assignee: Intel Corporation (Santa Clara, CA)
Primary Examiner: Mai; Tan V.
Assistant Examiner:
Attorney, Agent or Firm: Blakely, Sokoloff, Taylor & Zafman LLP

The invention provides an integrated systolic architecture which can perform both forward and inverse Discrete Wavelet Transforms with a minimum of complexity. A plurality of processing cells, each having an adder and a multiplier, are coupled to a set of multiplexers and delay elements to selectively receive a single input datastream in the forward DWT mode and two datastreams in the inverse DWT mode. In the forward DWT mode, the integrated architecture decomposes the input datastream into two output sequences--a high frequency sub-band output and a low frequency sub-band output. In the inverse DWT mode, the integrated architecture reconstructs the original input sequence by outputting even terms and odd terms on alternating clock cycles. As a result, the architecture can achieve 100% utilization and is suitable to be implemented in VLSI circuitry.

DETAILED DESCRIPTION OF THE INVENTION FIG.
1 shows a systolic array for computing a forward Discrete Wavelet Transform FIG.
1 shows an input xi 100 which is a single N-bit integer or floating point value from an input sequence representing discrete samples of an input signal that is to be encoded.
Though not specifically mentioned, all inputs and outputs are of the precision/type of the input.
Further, the various adders, multipliers and registers discussed can be readily designed by one skilled in the art depending upon the precision/type required.
In order for the array shown in FIG.
1 to be initialized, inputs x.
sub.
1, x.
sub.
2, x.
sub.
3, and x.
sub.
4 must first propagate through the delay elements 110, 112, 114, and 116.
Thereafter, for every x.
sub.
i 100 that is input, two outputs will be generated by the array.
These two outputs are shown in FIG.
1 as a.
sub.
i-4 150, which is the low frequency sub-band (LFS) output and, c.
sub.
i-3 160, which is the high frequency sub-band (HFS) output.
Each of the basic processing cells which compose the array are comprised of an adder and a multiplier and produce two sets of intermediate outputs.
The first set of intermediate outputs, L.
sub.
0 from cell D.
sub.
0 121, L.
sub.
1 from cell D.
sub.
1 122, L.
sub.
2 from cell D.
sub.
2 124, L.
sub.
3 from cell D.
sub.
3 126, and L.
sub.
4 from cell D.
sub.
4 128, are added by adder 130 to generate the LFS values a.
sub.
i-4 150.
Likewise, the second set of intermediate outputs, M.
sub.
1 from cell D.
sub.
1 122, M.
sub.
2 from cell D.
sub.
2 124, M.
sub.
3 from cell D.
sub.
3 126, and M.
sub.
4 from cell D.
sub.
4 128, are added together by adder 140 to generate the HFS values c.
sub.
i-3 160.
To generate the first HFS output c.
sub.
0, which occurs at i=3 (i=0,1,2 .
.
.
), the first four clock cycles and, consequently, the first three intermediate outputs, L.
sub.
1, L.
sub.
2, and L.
sub.
3 are required.
On the next clock cycle, at i=4, the LFS output a.
sub.
0 will be generated and observed.
Thus, the outputs a.
sub.
i-4 150 and c.
sub.
i-3 160 are observed alternately at the trailing edges of even and odd clock cycles



Related patents
  Integrated architecture for computing a forward and inverse discrete wavelet transforms
OF THE INVENTION FIG. 1 shows a systolic array for computing a forward Discrete Wavelet Transform FIG. 1 shows an input x.sub.i 100 which is a single N-bit integer or ...
  Companding algorithm to transform an image to a lower bit resolution
What is disclosed is a mapping circuit configured to map a range of captured intensity values to a companded intensity level based upon the density of captured intensity ...
  Efficient algorithm for color recovery from 8-bit to 24-bit color pixels
An interpolation method is disclosed for a raw image composed of pixels that utilizes color medians of surrounding blocks of Green pixels in order to select neighboring ...
  General image enhancement framework
FIG. 1 illustrates an embodiment of the invention. According to FIG. 1, approximator 11 receives an input image and generates at its output an approximation of the ...
  Method, apparatus and system for compressing data
It is an object of the present invention to provide a novel data compression method, apparatus and system which obviates or mitigates some of the disadvantages of prior ...
  Auto-focusing algorithm using discrete wavelet transform
OF THE INVENTION The exemplary embodiments described herein are provided merely to illustrate the principles of the invention and should not be construed as limiting ...
  Efficient data structure for entropy encoding used in a DWT-based high performance image compression
A method comprising determining a number of bits L utilized to store a word R, said word R accompanied by a flag, said flag and word R comprising a structure; and ...
  MMX optimized data packing methodology for zero run length and variable length entropy encoding
What is claimed is: 1. A method comprising: entropy encoding a set of data values into bits; and packing into storage the entropy encoded bits by packing two or more ...
  Efficient algorithm and architecture for image scaling using discrete wavelet transforms
OF THE INVENTION The exemplary embodiments described herein are provided merely to illustrate the principles of the invention and should not be construed as limiting ...
  Image compression using directional predictive coding of the wavelet coefficients
A method comprising determining the direction of most probable correlation of a transformed set of image data, and error encoding transformed data, the error determined ...

0.004

Archive: All patents - Links

Copyright (c)2006 Eipa-patents.org - All rights reserved