Image processing apparatus, image processing method, and image processing program

• US 20060257047A1
• Filed: 05/11/2006
• Published: 11/16/2006
• Est. Priority Date: 05/11/2005
• Status: Active Grant

• Current Assignee: Fujifilm Corporation (Fujifilm Holdings Corporation)
• Original Assignee: Fuji Photo Film Co Limited (Fujifilm Holdings Corporation)
• Inventors: Ito, Wataru, Kameyama, Hirokazu
• Granted Patent: US 8,107,764 B2
• Time in Patent Office: Days
• US Class Current: 382/275
• CPC Class Codes: G06V 10/30 Noise filtering
• CPC Class Codes: G06V 10/7557 based on appearance, e.g. active appearance models [AAM]
• CPC Class Codes: G06V 40/165 using facial parts and geometric relationships

Abstract

In order to accurately remove an unnecessary periodic noise component from an image, a reconstruction unit generates a reconstructed image without a periodic noise component by fitting to a face region detected in an image by a face detection unit a mathematical model generated according a method of AAM using a plurality of sample images representing human faces without a periodic noise component. The periodic noise component is extracted by a difference between the face region and the reconstructed image, and a frequency of the noise component is determined. The noise component of the determined frequency is then removed from the image.

Claims

1. An image processing apparatus comprising:

reconstruction means for obtaining a reconstructed image of a predetermined structure by reconstructing an image representing the structure after fitting a model representing the structure to the structure in an input image having a periodic noise component, the model obtained by carrying out predetermined statistical processing on a plurality of images representing the predetermined structure without a periodic noise component, and the model representing the structure by one or more statistical characteristic quantities and weighting parameter or parameters for weighting the statistical characteristic quantity or quantities according to an individual characteristic of the structure;

noise component extraction means for extracting the periodic noise component in the structure in the input image by calculating a difference value between values of pixels corresponding to each other in the structure in the reconstructed image and in the input image;

noise frequency determination means for determining a frequency of the periodic noise component having been extracted; and

noise removal means for generating a noise-free image by removing the periodic noise component of the determined frequency from the input image.

2. The image processing apparatus according to claim 1, wherein the predetermined structure is a human face.

3. The image processing apparatus according to claim 1 further comprising detection means for detecting the structure in the input image, wherein

the reconstruction means obtains the reconstructed image by fitting the model to the detected structure.

4. The image processing apparatus according to claim 1 further comprising selection means for obtaining a 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 reconstruction means obtains the reconstructed image by fitting the selected model to the structure in the input image.

5. An image processing method comprising the steps of:

obtaining a reconstructed image of a predetermined structure by reconstructing an image representing the structure after fitting models representing the structure to the structure in an input image having a periodic noise component, the models obtained by carrying out predetermined statistical processing on a plurality of images representing the predetermined structure without a periodic noise component, and the model representing the structure by one or more statistical characteristic quantities and weighting parameter or parameters for weighting the statistical characteristic quantity or quantities according to an individual characteristic of the structure;

extracting the periodic noise component in the structure in the input image by calculating a difference value between values of pixels corresponding to each other in the structure in the reconstructed image and in the input image;

determining a frequency of the periodic noise component having been extracted; and

generating a noise-free image by removing the periodic noise component of the determined frequency from the input image.

6. An image processing program for causing a computer to function as:

reconstruction means for obtaining a reconstructed image of a predetermined structure by reconstructing an image representing the structure after fitting a model representing the structure to the structure in an input image having a periodic noise component, the model obtained by carrying out predetermined statistical processing on a plurality of images representing the predetermined structure without a periodic noise component, and the model representing the structure by one or more statistical characteristic quantities and weighting parameter or parameters for weighting the statistical characteristic quantity or quantities according to an individual characteristic of the structure;

noise component extraction means for extracting the periodic noise component in the structure in the input image by calculating a difference value between values of pixels corresponding to each other in the structure in the reconstructed image and in the input image;

noise frequency determination means for determining a frequency of the periodic noise component having been extracted; and

noise removal means for generating a noise-free image by removing the periodic noise component of the determined frequency from the input image.