TOP > 外国特許検索 > Image feature extraction method and image compression method

Image feature extraction method and image compression method

外国特許コード F110005494
整理番号 K07605WO
掲載日 2011年9月6日
出願国 アメリカ合衆国
出願番号 37605907
公報番号 20090324064
公報番号 8160368
出願日 平成19年2月2日(2007.2.2)
公報発行日 平成21年12月31日(2009.12.31)
公報発行日 平成24年4月17日(2012.4.17)
国際出願番号 JP2007051831
国際公開番号 WO2008015799
国際出願日 平成19年2月2日(2007.2.2)
国際公開日 平成20年2月7日(2008.2.7)
優先権データ
  • 特願2006-211219 (2006.8.2) JP
  • 2007WO-JP51831 (2007.2.2) WO
発明の名称 (英語) Image feature extraction method and image compression method
発明の概要(英語) (US8160368)
The image feature extraction method of the present invention includes: the step of performing k2 dividing process at least once on a given image so as to convert the given image into a multi-divided image, where the k2 dividing process comprises the steps of: a) creating matrix T based on image matrix X; b) computing singular values of the matrix T; c) determining whether or not minj|σj-σj-1|>ε; d) if the result of the determination in the step c) is “No”, returning to the step c) subsequent to computing the singular values of the enlarged matrix Tα; e) if the result of the determination in the step c) is “Yes”, obtaining U which satisfies T=USVT; f) obtaining matrix T1=UTT; and g) creating image matrix X1 based on matrix T1.
特許請求の範囲(英語) [claim1]
1. An image feature extraction method for extracting a feature of an image, comprising the step of performing k2 (k is an arbitrary integer greater than or equal to 2) dividing process at least once on a given image so as to convert the given image into a multi-divided image, wherein the k2 dividing process comprises the steps of:
a) creating matrix T based on image matrix X;
b) computing singular values sigma 1, sigma 2, . . . , sigma k^2 of the matrix T, where sigma 1 >= sigma 2 >= . . . >= sigma k^2;
c) determining whether or not minj|sigma j-sigma j-1|>epsilon , where epsilon shows a constant greater than or equal to machine epsilon;
d) if the result of the determination in the step c) is "No" returning to the step c) subsequent to computing the singular values of enlarged matrix Talpha ;
e) if the result of the determination in the step c) is "Yes", obtaining U which satisfies T=USVT, where S=diag (sigma 1, sigma 2, . . . , sigma k^2), U is an orthogonal matrix and V is an orthogonal matrix;
f) obtaining matrix T1=UTT; and
g) creating image matrix X1 based on matrix T1,
wherein the computing the singular values of the enlarged matrix Talpha in the step d) comprises the steps of:
creating enlarged matrix Talpha based on matrix T and a frame added to at least a portion of at least one side of image matrix X, the frame having a size of at least k pixels and k pixels; and
computing singular values sigma 1, sigma 2, . . . , sigma k^2 of the enlarged matrix Talpha , where sigma 1 >= sigma 2 >= . . . >= sigma k^2.
[claim2]
2. An image feature extraction method for extracting a feature of an image, comprising the step of performing k2 (k is an arbitrary integer greater than or equal to 2) dividing process at least once on a given image so as to convert the given image into a multi-divided image, wherein the k2 dividing process comprises the steps of:
a) creating matrix T based on image matrix X;
b) obtaining a singular value decomposition of the matrix T, T=USVT, where S=diag (sigma 1, sigma 2, . . . , sigma k^2), sigma 1, sigma 2, . . . , sigma k^2 are singular values of T satisfying sigma 1 >= sigma 2 >= . . . >= sigma k^2, U is an orthogonal matrix and V is an orthogonal matrix;
c) determining whether or not minj|sigma j-sigma j-1|>epsilon , where epsilon shows a constant greater than or equal to machine epsilon;
d) if the result of the determination in the step c) is "No", returning to the step c) subsequent to performing singular value decomposition of enlarged matrix Talpha ;
e) if the result of the determination in the step c) is "Yes", obtaining matrix T1=UTT; and
f) obtaining matrix T1=UTT based on matrix T1,
wherein the performing singular value decomposition of enlarged matrix Talpha comprises the steps of:
creating enlarged matrix Talpha based on matrix T and a frame added to at least a portion of at least one side of image matrix X, the frame having a size of at least k pixels and k pixels; and
obtaining the singular value decomposition of the enlarged matrix Talpha , Talpha =USVT, where S=diag (sigma 1, sigma 2, . . . , sigma k^2), sigma 1, sigma 2, . . . , sigma k^2 is a singular value of Talpha which satisfies sigma 1 >= sigma 2 >= . . . >= sigma k^2, U is an orthogonal matrix, and V is an orthogonal matrix.
[claim3]
3. An image feature extraction method according to claim 1, wherein the image is a gray scale image or a color image.
[claim4]
4. An image feature extraction method according to claim 2, wherein the image is a gray scale image or a color image.
[claim5]
5. An image feature extraction method according to claim 1, wherein the singular value decompositions of the T and the Talpha are performed by floating point arithmetic.
[claim6]
6. An image feature extraction method according to claim 2, wherein the singular value decompositions of the T and the Talpha are performed by floating point arithmetic.
[claim7]
7. An image feature extraction method according to claim 1, wherein the singular value decompositions of the T and the Talpha are performed by integer arithmetic.
[claim8]
8. An image feature extraction method according to claim 2, wherein the singular value decompositions of the T and the Talpha are performed by integer arithmetic.
[claim9]
9. An image feature extraction method according to claim 1, wherein a known k2 dividing process is used together with the k2 dividing process, so that the given image matrix X is converted into a multi-divided image.
[claim10]
10. An image feature extraction method according to claim 2, wherein a known k2 dividing process is used together with the k2 dividing process, so that the given image matrix X is converted into a multi-divided image.
[claim11]
11. An image compression method for compressing an image, comprising the steps of: performing k2 (k is an arbitrary integer greater than or equal to 2) dividing process at least once on a given image so as to convert the given image into a multi-divided image; and
performing a data compression process on the multi-divided image so as to create a compressed image,
wherein the k2 dividing process comprises the steps of:
a) creating matrix T based on image matrix X;
b) computing singular values sigma 1, sigma 2, . . . , sigma k^2 of the matrix T, where sigma 1 >= sigma 2 >= . . . >= sigma k^2;
c) determining whether or not minj|sigma j-sigma j-1|>epsilon , where epsilon shows a constant greater than or equal to machine epsilon;
d) if the result of the determination in the step c) is "No", returning to the step c) subsequent to computing the singular values of the enlarged matrix Talpha ;
e) if the result of the determination in the step c) is "Yes", obtaining U which satisfies T=USVT, where S=diag (sigma 1, sigma 2, . . . , sigma k^2), U is an orthogonal matrix and V is an orthogonal matrix;
f) obtaining matrix T1=UTT; and
g) creating image matrix X1 based on matrix T1,
wherein the computing the singular values of the enlarged matrix Talpha in the step d) comprises the steps of:
creating enlarged matrix Talpha based on matrix T and a frame added to at least a portion of at least one side of image matrix X, the frame having a size of at least k pixels and k pixels; and
computing singular values sigma 1, sigma 2, . . . , sigma k^2 of the enlarged matrix Talpha , where sigma 1 >= sigma 2 >= . . . >= sigma k^2.
[claim12]
12. An image compression method for compressing an image, comprising the steps of: performing k2 (k is an arbitrary integer greater than or equal to 2) dividing process at least once on a given image so as to convert the given image into a multi-divided image; and
performing a data compression process on the multi-divided image so as to create a compressed image,
wherein the k2 dividing process comprises the steps of:
a) creating matrix T based on image matrix X;
b) obtaining a singular value decomposition of the matrix T, T=USVT, where S=diag (sigma 1, sigma 2, . . . , sigma k^2), sigma 1, sigma 2, . . . , sigma k^2 are singular values of T satisfying sigma 1 >= sigma 2 >= . . . >= sigma k^2, U is an orthogonal matrix and V is an orthogonal matrix;
c) determining whether or not minj|sigma j-sigma j-1|>epsilon , where epsilon shows a constant greater than or equal to machine epsilon;
d) if the result of the determination in the step c) is "No", returning to the step c) subsequent to performing singular value decomposition of enlarged matrix Talpha ;
e) if the result of the determination in the step c) is "Yes", obtaining matrix T1=UTT; and
f) obtaining matrix T1=UTT based on matrix T1,
wherein the performing singular value decomposition of enlarged matrix Talpha comprises the steps of:
creating enlarged matrix Talpha based on matrix T and a frame added to at least a portion of at least one side of image matrix X, the frame having a size of at least k pixels and k pixels; and
obtaining the singular value decomposition of the enlarged matrix Talpha , Talpha =USVT, where S=diag (sigma 1, sigma 2, . . . , sigma k^2), sigma 1, sigma 2, . . . , sigma k^2 is a singular value of Talpha which satisfies sigma 1 >= sigma 2 >= . . . >= sigma k^2, U is an orthogonal matrix, and V is an orthogonal matrix.
[claim13]
13. An image compression method according to claim 11, wherein the image is a gray scale image or a color image.
[claim14]
14. An image compression method according to claim 12, wherein the image is a gray scale image or a color image.
[claim15]
15. An image compression method according to claim 11, wherein the singular value decompositions of the T and the Talpha are performed by floating point arithmetic.
[claim16]
16. An image compression method according to claim 12, wherein the singular value decompositions of the T and the Talpha are performed by floating point arithmetic.
[claim17]
17. An image compression method according to claim 11, wherein the singular value decomposition of the T and the Talpha are performed by integer arithmetic.
[claim18]
18. An image compression method according to claim 12, wherein the singular value decomposition of the T and the Talpha are performed by integer arithmetic.
[claim19]
19. An image compression method according to claim 11, wherein a known k2 dividing process is used together with the k2 dividing process, so that the given image matrix X is converted into a multi-divided image.
[claim20]
20. An image compression method according to claim 12, wherein a known k2 dividing process is used together with the k2 dividing process, so that the given image matrix X is converted into a multi-divided image.
  • 発明者/出願人(英語)
  • NAKAMURA YOSHIMASA
  • IWASAKI MASASHI
  • OBATA MASAHIKO
  • KONDO KOICHI
  • SASADA SHOHEI
  • DOSHISHA
  • JAPAN SCIENCE AND TECHNOLOGY AGENCY
国際特許分類(IPC)
参考情報 (研究プロジェクト等) PRESTO The Innovation of Simulation Technology and the Construction of Foundations for its Practical Use AREA
ライセンスをご希望の方、特許の内容に興味を持たれた方は、問合せボタンを押してください。

PAGE TOP

close
close
close
close
close
close