US6728406B1
Expired / Lapsed
US
⏱️ 0.0 years remaining
Image analyzing apparatus and method as well as program record medium
Assignee: Fujitsu Ltd
•
Filing: 2000-08-09
•
Granted: 2004-04-27
•
Expires: 2020-08-09
Abstract
Abstract A gray scale image or a color image is entered for wavelet transformation. A layout feature is determined from a coefficient of the lowest frequency band after the wavelet transformation. A shape feature is determined from a coefficient of the second lowest frequency band after wavelet transformation. Furthermore, a texture feature is determined from the average and deviation of frequency bands excepting the lowest frequency band after wavelet transformation.
Inventors
- 👤 Kohei Murao
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 21:56
CPC Classifications
G; G06; G06V; G06V20/00; G06V10/00; G06V10/40; G06V10/44; G06V10/443
Claims Analysis
Total Claims: 14
Claim 1
Independent Claim
216 words
An image analyzing apparatus comprising: a wavelet transformation unit for receiving images to effect a wavelet transformation thereon, wherein said wavelet transformation unit upon reception of a color image in RGB color space transforms said color image received into a color image in YUV space to thereafter effect a wavelet transformation thereon; a layout feature extraction unit determining a layout feature from a coefficient of the lowest frequency band after wavelet transformation, wherein said layout feature extraction unit transforms a coefficient of the lowest frequency band after wavelet transformation into a color representation in another color space matching human senses to thereby determine said layout feature; a shape feature extraction unit Determining a shape feature from a coefficient of the second lowest frequency band after wavelet transformation, wherein said shape feature extraction unit uses only luminance values Y of YUV components constituting said coefficient of said second lowest frequency band after wavelet transformation to thereby determine said shape feature; and a texture feature extraction unit determining a texture feature from the average and deviation of frequency bands excepting the lowest frequency band after wavelet transformation, wherein said texture feature extraction unit determines said texture feature from the average and deviation of only luminance values Y of YUV components constituting coefficients of frequency bands after wavelet transformation.
Claim 2
Dependent Claim
216 words
An image analyzing apparatus comprising: a wavelet transformation unit for receiving images to effect a wavelet transformation thereon, wherein said wavelet transformation unit upon reception of a color image in RGB color space transforms said color image received into a color image in YUV space to thereafter effect a wavelet transformation thereon; a layout feature extraction unit determining a layout feature from a coefficient of the lowest frequency band after wavelet transformation, wherein said layout feature extraction unit transforms a coefficient of the lowest frequency band after wavelet transformation into a color representation in another color space matching human senses to thereby determine said layout feature; a shape feature extraction unit Determining a shape feature from a coefficient of the second lowest frequency band after wavelet transformation, wherein said shape feature extraction unit uses only luminance values Y of YUV components constituting said coefficient of said second lowest frequency band after wavelet transformation to thereby determine said shape feature; and a texture feature extraction unit determining a texture feature from the average and deviation of frequency bands excepting the lowest frequency band after wavelet transformation, wherein said texture feature extraction unit determines said texture feature from the average and deviation of only luminance values Y of YUV components constituting coefficients of frequency bands after wavelet transformation.
Claim 3
Dependent Claim
45 words
An apparatus according to claim 1 , wherein said layout feature extraction unit transforms said coefficient of said lowest frequency band after wavelet transformation into a color representation in HSV color space, Lab color space or Munsell color space to thereby determine said layout feature.
Claim 4
Dependent Claim
25 words
An apparatus according to claim 1 , wherein said layout feature extraction unit normalizes said lowest frequency band after wavelet transformation into a predetermined size.
Claim 5
Dependent Claim
30 words
An apparatus according to claim 3 , wherein said layout feature extraction unit interpolates shorter sides of said lowest frequency band after wavelet transformation to thereby achieve a size normalization.
Claim 6
Dependent Claim
56 words
An apparatus according to claim 1 , wherein with respect to three bands in each of which is arranged said coefficient of said second lowest frequency band after wavelet transformation, said shape feature extraction unit finds an absolute value of each coefficient and averages coefficients at relatively same locations within said bands into one band coefficient.
Claim 7
Dependent Claim
86 words
An apparatus according to claim 1 , wherein said texture feature extraction unit generates as texture features a vector whose vector components are an average and a deviation of coefficients of frequency bands of contour vertical components excepting said lowest frequency band after wavelet transformation, a vector whose vector components are an average and a deviation of coefficients of frequency bands of contour horizontal components, and a vector whose vector components are an average and a deviation of coefficients of frequency bands of contour diagonal components.
Claim 8
Dependent Claim
59 words
An apparatus according to claim 1 , further comprising: a similarity calculation unit to determine similarities between two images with respect to said layout feature, said shape feature and said texture feature that have been extracted by said feature extraction unit, said similarity calculation unit imparting weights to said similarities to determine a total similarity between the two images.
Claim 9
Dependent Claim
65 words
An image analyzing method comprising: entering an image for a wavelet transformation; determining a layout feature from a coefficient of the lowest frequency band after wavelet transformation; determining a shape feature from a coefficient of the second lowest frequency band after wavelet transformation; and determining a texture feature from an average and a deviation of frequency bands excepting said lowest frequency band after wavelet transformation.
Claim 10
Dependent Claim
65 words
An image analyzing method comprising: entering an image for a wavelet transformation; determining a layout feature from a coefficient of the lowest frequency band after wavelet transformation; determining a shape feature from a coefficient of the second lowest frequency band after wavelet transformation; and determining a texture feature from an average and a deviation of frequency bands excepting said lowest frequency band after wavelet transformation.
Claim 11
Dependent Claim
75 words
A computer readable recording medium comprising an image feature extraction program controlling a computer to: enter an image for a wavelet transformation; determine a layout feature from a coefficient of the lowest frequency band after wavelet transformation; determine a shape feature from a coefficient of the second lowest frequency band after wavelet transformation; and determine a texture feature from an average and a deviation of frequency bands excepting said lowest frequency band after wavelet transformation.
Claim 12
Dependent Claim
75 words
A computer readable recording medium comprising an image feature extraction program controlling a computer to: enter an image for a wavelet transformation; determine a layout feature from a coefficient of the lowest frequency band after wavelet transformation; determine a shape feature from a coefficient of the second lowest frequency band after wavelet transformation; and determine a texture feature from an average and a deviation of frequency bands excepting said lowest frequency band after wavelet transformation.
Claim 13
Independent Claim
80 words
An apparatus to analyze received wavelet transformations of images, comprising: a layout feature extraction unit determining a layout feature from a coefficient of a lowest frequency band of the wavelet transformations; a shape feature extraction unit determining a shape feature from a coefficient of a second lowest frequency band of the wavelet transformations; and a texture feature extraction unit determining a texture feature from the average and deviation of frequency bands excepting the lowest frequency band of the wavelet transformations.
Claim 14
Independent Claim
80 words
An apparatus to analyze received wavelet transformations of images, comprising: a layout feature extraction unit determining a layout feature from a coefficient of a lowest frequency band of the wavelet transformations; a shape feature extraction unit determining a shape feature from a coefficient of a second lowest frequency band of the wavelet transformations; and a texture feature extraction unit determining a texture feature from the average and deviation of frequency bands excepting the lowest frequency band of the wavelet transformations.
References Cited (Backward Citations)
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2007-04-27 | 2007-10-27 | 2008-04-27 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2011-04-27 | 2011-10-27 | 2012-04-27 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2015-04-27 | 2015-10-27 | 2016-04-27 | $7700.00 | Window Closed / Lapsed |