Method and apparatus for judging direction of blur and computer-readable recording medium storing a program therefor
First Claim
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 Assignments
0 Petitions
Accused Products
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.
-
Citations
11 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. - View Dependent Claims (3, 4, 5, 6, 7, 8, 9, 10)
-
-
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.
-
Specification