Image processing system
An image processing system capable of reducing an operation time required to generate a high image quality image, includes an image obtaining section that obtains an input image having been captured; a characteristic region information obtaining section that obtains information indicating a characteristic region in the input image; a model storage section that stores a model representing an object by a character parameter; an image generating section that converts an image of an object included in the characteristic region in the input image into a high image quality image having an image quality higher than an image quality of the input image, by adapting the image of the object included in the characteristic region in the input image to the model; and an output section that outputs an image including the high image quality image and an image other than the characteristic region.
1. An image processing system comprising:
an image obtaining section that obtains an input image having been captured;
a characteristic region information obtaining section that obtains information indicating a characteristic region in the input image;
a model storage section that stores a model representing an object by a character parameter;
an image generating section that converts an image of an object included in the characteristic region in the input image into a high image quality image having an image quality higher than an image quality of the input image, by adapting the image of the object included in the characteristic region in the input image to the model; and
an output section that outputs an image including the high image quality image and an image of a region other than the characteristic region wherein
the model storage section stores the model representing an object by a statistical character parameter,
the characteristic region information obtaining section obtains information indicating a type of an object included in the characteristic region in the input image,
the model storage section stores models of different types of objects, in association with the respective types, and
the image generating section converts an image of the object included in the characteristic region in the input image into the high image quality image, by adapting the image of the object included in the characteristic region in the input image to a model stored in the model storage section in association with the type of the object included in the characteristic region indicated by the information obtained by the characteristic region information obtaining section.
2. An image processing system comprising:
an image obtaining section that obtains an input image having been captured;
a characteristic region information obtaining section that obtains information indicating a characteristic region in the input image;
a model storage section that stores a model representing an object by a character parameter;
an image generating section that converts an image of an object included in the characteristic region in the input image into a high image quality image having an image quality higher than an image quality of the input image, by adapting the image of the object included in the characteristic region in the input image to the model; and
an output section that outputs an image including the high image quality image and an image of a region other than the characteristic region, wherein
the model storage section stores the model representing an object by a principal component based on a principal component analysis,
the characteristic region information obtaining section obtains information indicating a type of an object included in the characteristic region in the input image,
the model storage section stores models of different types of objects, in association with the respective types, and
the image generating section converts an image of the object included in the characteristic region in the input image into the high image quality image, by adapting the image of the object included in the characteristic region in the input image to a model stored in the model storage section in association with the type of the object included in the characteristic region indicated by the information obtained by the characteristic region information obtaining section.
3. The image processing system according to claim 2 , wherein
the model storage section stores the model representing a form of an object by a principal component based on a principal component analysis.
4. The image processing system according to claim 2 , wherein
the model storage section stores the model representing a color of an object by a principal component based on a principal component analysis.
5. The image processing system according to claim 2 , further comprising:
a direction identifying section that identifies a direction in which an object included in the characteristic region in the input image has been captured, wherein
the model storage section stores models of an object viewed in respectively different directions, in association with the respective directions, and
the image generating section converts an image of the object included in the characteristic region in the input image into the high image quality image, by adapting the image of the object included in the characteristic region in the input image to a model stored in the model storage section in association with the direction identified by the direction identifying section.
6. The image processing system according to claim 2 , further comprising:
an illumination condition identifying section that identifies an illumination condition under which the object included in the characteristic region in the input image has been illuminated, wherein
the model storage section stores models of an object illuminated under respectively different illumination conditions, in association with the respective illumination conditions, and
the image generating section converts an image of the object included in the characteristic region in the input image into the high image quality image, by adapting the image of the object included in the characteristic region in the input image to a model stored in the model storage section in association with the illumination condition identified by the illumination condition identifying section.
7. The image processing system according to claim 2 , wherein
the image generating section generates the high image quality image having a higher resolution than the input image, by adapting the image of the object included in the characteristic region in the input image to the model.
8. The image processing system according to claim 2 , wherein
the image generating section enlarges an image of a region other than the characteristic region in the input image to an image of a same resolution as the high image quality image, and generates a single image by combining the enlarged image and the high image quality image.
9. The image processing system according to claim 2 , wherein
the image obtaining section obtains the input image generated by lowering an image quality of a captured image, and
the characteristic region information obtaining section obtains information indicating a position of a characteristic region detected from the captured image.
10. The image processing system according to claim 9 , further comprising:
a characteristic region detecting section that detects a characteristic region from the captured image;
a compression section that generates the input image by lowering the image quality of the captured image; and
an input image output section that outputs the input image in association with information indicating the position of the characteristic region detected form the captured image, wherein
the image obtaining section obtains the input image outputted from the input image output section, and
the characteristic region information obtaining section obtains the information indicating the position of the characteristic region outputted in association with the input image from the input image output section.
11. The image processing system according to claim 10 , wherein
the compression section generates the input image by changing an image quality of an image of a region other than the characteristic region in the captured image from an image quality of the image of the characteristic region.
12. The image processing system according to claim 11 , wherein
the compression section generates the input image by lowering the image quality of the image of the region other than the characteristic region in the captured image than the image quality of the image of the characteristic region.
13. The image processing system according to claim 12 , wherein
the characteristic region detecting section detects a plurality of characteristic regions from the captured image, and
the compression section generates the input image by lowering an image quality of images of the plurality of characteristic regions in the captured image down to an image quality determined in advance according to respective characteristics of the plurality of characteristic regions.
14. The image processing system according to claim 13 , wherein
the characteristic region detecting section detects, from the captured image, a plurality of characteristic regions including respectively different types of captured objects, and
the compression section generates the input image by lowering the image quality of the images of the plurality of characteristic regions in the captured image down to an image quality determined in advance according to respective types of objects included in the plurality of characteristic regions.
15. The image processing system according to claim 13 , further comprising:
an image quality obtaining section that obtains an image quality in association with a characteristic of each characteristic region, wherein
the compression section generates the input image by lowering the image quality of the images of the plurality of characteristic regions in the captured image down to the image quality obtained by the image quality obtaining section in association with the characteristic of each characteristic region.
16. The image processing system according to claim 10 , wherein
the compression section generates the input image by lowering at least one of resolution of the captured image, a number of gradations of the captured image, a number of colors of the captured image, and a spatial frequency component of a spatial frequency region higher than a predetermined spatial frequency.
17. The image processing system according to claim 1 , further comprising:
a second model storage section that stores a second model representing an object by a character parameter;
a characteristic region detecting section that detects a characteristic region from a captured image;
a parameter value calculating section that calculates a value of a character parameter of a second model representing an object included in an image of the characteristic region in the captured image, by adapting the image of the object included in the image of the characteristic region in the captured image to the second model stored in the second model storage section;
an intermediate output section that outputs the value of the character parameter calculated by the parameter value calculating section and an image of a region other than the characteristic region in the captured image;
an intermediate image obtaining section that obtains the image of the region other than the characteristic region in the captured image whose image quality has been lowered and the value of the character parameter outputted from the intermediate output section;
an intermediate image generating section that generates the image of the object included in the image of the characteristic region in the captured image, from the second model based on the value of the character parameter; and
an image output section that outputs an image obtained by combining the image of the object generated from the second model and the image of the region other than the characteristic region obtained by the intermediate image obtaining section, wherein
the image obtaining section obtains the image outputted from the image output section as the input image.
18. The image processing system according to claim 17 , further comprising:
a compression section that compresses the image of the region other than the characteristic region in the captured image by lowering the image quality of the image of the region other than the characteristic region in the captured image, wherein
the intermediate output section outputs the value of the character parameter calculated by the parameter value calculating section and the image of the region other than the characteristic region whose image quality has been lowered by the compression section.
19. The image processing system according to claim 18 , wherein
the second model storage section stores the second model representing an object by a statistical character parameter.
20. The image processing system according to claim 1 , wherein
the image obtaining section obtains an input moving image including a plurality of moving image constituting images,
the characteristic region information obtaining section obtains information indicating a position of a characteristic region in each of the plurality of moving image constituting images,
the image processing system further comprises a characteristic region selecting section that selects a first characteristic region and a second characteristic region having correlation higher than a value determined in advance, from among the characteristic regions of the plurality of moving image constituting images, and
the image generating section converts an image of an object included in the first characteristic region and an image of an object included in the second characteristic region into a first high image quality image and a second high image quality image, by respectively adapting the image of the object included in the first characteristic region and the image of the object included in the second characteristic region to the model, and generates the high image quality image having a higher resolution than the image of the object included in the first characteristic region and the image of the object included in the second characteristic region, by using the first high image quality image, the second high image quality image, and a difference in position between the first characteristic region and the second characteristic region.
21. The image processing system according to claim 20 , wherein
the image generating section generates the high image quality image by combining the first high image quality image and the second high image quality image based on the difference in position.
22. The image processing system according to claim 21 , wherein
the image generating section generates the high image quality image by overlapping the first high image quality image and the second high image quality image by displacing the first high image quality image and the second high image quality image by the difference in position.
23. An image processing system comprising:
an image obtaining section that obtains an input image;
a characteristic region information obtaining section that obtains information indicating a characteristic region in the input image;
an object image information storage section that stores a high frequency component of an image of an object in association with a type of the object; and
an image generating section that converts an image of each of a plurality of objects included in the input image, into a higher image quality image, by using a high frequency component stored in the object image information storage section in association with a type of the object, wherein
the object image information storage section stores the information indicating the characteristic region in the input image by a statistical character parameter,
the characteristic region information obtaining section obtains information indicating a type of an object included in the characteristic region in the input image,
the object image information storage section stores object image information of different types of objects, in association with the respective types, and
the image generating section converts the image of the object included in the characteristic region in the input image into the high image quality image, by adapting the image of the object included in the characteristic region in the input image to object image information stored in the object image information storage section in association with the type of the object included in the characteristic region indicated by the information obtained by the characteristic region information obtaining section.