Method and apparatus for judging direction of blur and computer-readable recording medium storing a program therefor

• US 7,848,588 B2
• Filed: 09/22/2006
• Issued: 12/07/2010
• Est. Priority Date: 09/27/2005
• Status: Active Grant

• Current Assignee: Fujifilm Corporation (Fujifilm Holdings Corporation)
• Original Assignee: Fujifilm Corporation (Fujifilm Holdings Corporation)
• Inventors: Ito, Wataru, Li, Yuanzhong
• Primary Examiner(s): Chen; Wenpeng
• Assistant Examiner(s): Thirugnanam; Gandhi
• Application Number:
  US11/525,073
• Publication Number:
  US 20070071346A1
• Time in Patent Office: 1,537 Days
• Field of Search: 382/107, 382/118, 382/254, 382/255, 382/264, 348/208.99, 348/208.44, 396 52- 55, 396/153
• US Class Current: 382/255
• CPC Class Codes: G06T 2207/20201 Motion blur correction
• CPC Class Codes: G06T 2207/30201 Face
• CPC Class Codes: G06T 5/73 Deblurring; Sharpening
• CPC Class Codes: G06T 7/13 Edge detection
• CPC Class Codes: G06V 10/7557 based on appearance, e.g. active appearance models [AAM]
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation

Abstract

Without use of special hardware such as an angular rate sensor, a direction of blur can be judged with high accuracy. A parameter acquisition unit obtains weighting parameters for principal components representing directions of blur in a predetermined structure in an image by fitting to the structure a mathematical model generated by a method of Active Appearance Models (AAM) using a plurality of sample images representing the structure in different conditions of blur. A blur direction judgment unit judges the direction of blur based on the weighting parameters, and a blur width acquisition unit finds a width of blur based on an edge component found by an edge detection unit in the direction perpendicular to the direction of blur. A blur correction unit corrects the blur in the image based on the direction and the width of blur.

Claims

1. A blur direction judgment method comprising the steps of:

obtaining one or more weighting parameters for one or more statistical characteristic quantities representing a direction of blur in a predetermined structure in an input image by fitting a model representing the structure to the structure in the input image, the model having been obtained by carrying out predetermined statistical processing on a plurality of images representing the predetermined structure in different conditions of blur, and the model representing the structure by one or more statistical characteristic quantities including the statistical characteristic quantity or quantities representing the direction of blur and by one or more weighting parameters for weighting the statistical characteristic quantity or quantities according to an individual characteristic of the structure; and

judging the direction of blur represented in the input image according to a value or values of the weighting parameter or parameters having been obtained.

2. A blur direction judgment apparatus comprising:

parameter acquisition means for obtaining one or more weighting parameters for one or more statistical characteristic quantities representing a direction of blur in a predetermined structure in an input image by fitting a model representing the structure to the structure in the input image, the model having been obtained by carrying out predetermined statistical processing on a plurality of images representing the predetermined structure in different conditions of blur, and the model representing the structure by one or more statistical characteristic quantities including the statistical characteristic quantity or quantities representing the direction of blur and by one or more weighting parameters for weighting the statistical characteristic quantity or quantities according to an individual characteristic of the structure; and

blur direction judgment means for judging the direction of blur represented in the input image according to a value or values of the weighting parameter or parameters having been obtained by the parameter acquisition means.

3. The blur direction judgment apparatus according to claim 2 further comprising blur width acquisition means for finding a width of blur in the direction of blur having been judged by the blur direction judgment means.

4. The blur direction judgment apparatus according to claim 3, wherein the blur width acquisition means finds the width of blur based on the value or values of the weighting parameter or parameters for the statistical characteristic quantity or quantities representing the direction of blur.

5. The blur direction judgment apparatus according to claim 4 further comprising blur correction means for correcting the blur represented in the input image based on the direction of blur having been judged by the blur direction judgment means and the width of blur obtained by the blur width acquisition means.

6. The blur direction judgment apparatus according to claim 5, wherein the blur correction means corrects the blur in the structure in the input image by changing the value or values of the weighting parameter or parameters for the statistical characteristic quantity or quantities representing the direction of blur.

7. The blur direction judgment apparatus according to claim 2 further comprising detection means for detecting the structure in the input image, wherein

the parameter acquisition means obtains the weighting parameter or parameters by fitting the model to the structure having been detected.

8. The blur direction judgment apparatus according to claim 2 further comprising selection means for obtaining at least one property of the structure in the input image and for selecting the model corresponding to the obtained property from a plurality of the models representing the structure for respective properties of the predetermined structure, wherein

the parameter acquisition means obtains the weighting parameter or parameters by fitting the selected model to the structure in the input image.

9. The blur direction judgment apparatus according to claim 2, wherein the predetermined structure is a human face.

10. The blur direction judgment apparatus according to claim 2, wherein the model and the fitting of the model are realized by a method of Active Appearance Model.

11. A non-transitory computer-readable recording medium storing a blur direction judgment program causing a computer to function as:

parameter acquisition means for obtaining one or more weighting parameters for one or more statistical characteristic quantities representing a direction of blur in a predetermined structure in an input image by fitting a model representing the structure to the structure in the input image, the model having been obtained by carrying out predetermined statistical processing on a plurality of images representing the predetermined structure in different conditions of blur, and the model representing the structure by one or more statistical characteristic quantities including the statistical characteristic quantity or quantities representing the direction of blur and by one or more weighting parameters for weighting the statistical characteristic quantity or quantities according to an individual characteristic of the structure; and

blur direction judgment means for judging the direction of blur represented in the input image according to a value or values of the weighting parameter or parameters having been obtained by the parameter acquisition means.