US5301241A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Image compression method and apparatus employing principal component analysis
Assignee: FFEI Ltd
•
Filing: 1991-03-06
•
Granted: 1994-04-05
•
Expires: 2011-03-06
Abstract
Abstract A method and apparatus for compressing digital data defining the colour component content of pixels of a coloured image, the apparatus comprises a processor (1) for performing a principal component analysis on each of a number of non-overlapping blocks of pixels making up the image to determine the principal component vectors corresponding to the block; for rounding the principal component vectors to a fixed set of intervals; for transforming the original pixel data into the colour space defined by the rounded principal component vectors; for performing a compression algorithm on the transformed pixel data; and for performing a separate compression algorithm on the rounded principal component vector values.
Inventors
- 👤 Richard A. Kirk
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-24 23:39
CPC Classifications
H; H04; H04N; H04N1/00; H04N1/46; H04N1/64; G; G06; G06T; G06T9/00; G06T9/008
Claims Analysis
Total Claims: 6
Claim 1
Independent Claim
149 words
Apparatus for compressing digital data defining the colour component content of pixels of a coloured image, the apparatus comprising a computer including means for performing a principal component analysis on each of a number of non-overlapping blocks of pixels making up the image to determine the principal component vectors corresponding to the block; a first memory for storing said principal component vectors; said computer further comprising means for rounding the principal component vectors to a fixed set of intervals; a second memory for, together with said computer, transforming the original pixel data into the colour space defined by the rounded principal component vectors and storing transformed pixel data; said computer further comprising means for performing a compression algorithm on the transformed pixel data; and a third memory for, together with said computer, performing a separate compression algorithm on the rounded principal component vector values and storing compressed image data.
Claim 2
Dependent Claim
149 words
Apparatus for compressing digital data defining the colour component content of pixels of a coloured image, the apparatus comprising a computer including means for performing a principal component analysis on each of a number of non-overlapping blocks of pixels making up the image to determine the principal component vectors corresponding to the block; a first memory for storing said principal component vectors; said computer further comprising means for rounding the principal component vectors to a fixed set of intervals; a second memory for, together with said computer, transforming the original pixel data into the colour space defined by the rounded principal component vectors and storing transformed pixel data; said computer further comprising means for performing a compression algorithm on the transformed pixel data; and a third memory for, together with said computer, performing a separate compression algorithm on the rounded principal component vector values and storing compressed image data.
Claim 3
Dependent Claim
44 words
An apparatus according to claim 1, wherein said means for performing principal component analysis comprises means for determining a covariance matrix for said pixel block; and means for determining the eigenvectors and eigenvalues for said covariance matrix, the eigenvectors constituting said principal component vectors.
Claim 4
Dependent Claim
40 words
An apparatus according to claim 2, wherein each block is classified into one of a number of different classes depending upon its "energy", each class defining a degree of truncation or compression for the eigenvectors and the transformed colour values.
Claim 5
Dependent Claim
70 words
An apparatus according to claim 2, further comprising means for selecting the eigenvector corresponding to the largest eigenvalue, means for truncating the vector values to a level determined in accordance with the largest eigenvalue, the truncation being repeated for each of the other eigenvectors selected in order of their eigenvalue magnitudes until a truncated eigenvector has no non-zero AC values, and means for rounding all remaining eigenvector values to zero.
Claim 6
Dependent Claim
41 words
An apparatus according to claim 2, wherein the compression of the eigenvectors is carried out prior to transforming the pixel data into the colour space defined by the eigenvectors so that upon decompression an accurate regeneration of pixel values is achieved.
References Cited (Backward Citations)
US4962540A
Cited
US4920426A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1997-04-04 | 1997-10-04 | 1998-04-05 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2001-04-04 | 2001-10-04 | 2002-04-05 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2005-04-04 | 2005-10-04 | 2006-04-05 | $7700.00 | Window Closed / Lapsed |