Information processing apparatus, image processing method and recording medium on which image processing program is recorded
An information processing apparatus, includes: a memory; and a processor coupled to the memory, wherein the processor: generates a sharpened image of a fingerprint image by emphasizing edges of a fingerprint pattern included in the fingerprint image; calculates an edge density of the sharpened image based on a local change of luminance; and decides based on the edge density whether each of pixels of the sharpened image is in a fingerprint region or a background region.
1. An information processing apparatus, comprising:
a memory; and
a processor coupled to the memory, wherein the processor:
generates, by emphasizing edges, which correspond to changes of luminance of a fingerprint pattern included in a fingerprint image, a sharpened image of the fingerprint image;
applies a second order differential filter to the sharpened image;
divides the sharpened image into a plurality of small regions; and
calculates, for each of the plurality of small regions, a ratio of pixels in regard to which an absolute value of a response of the second order differential filter is equal to or higher than a threshold value from among pixels included in the small region as the edge density; and
decides based on the edge density whether each of pixels of the sharpened image is in a fingerprint region or a background region.
2. The information processing apparatus according to claim 1 , wherein the processor divides the sharpened image into a plurality of small regions and calculates, for each of the plurality of small regions, a ratio of pixels each of which a degree of change of a luminance value from a luminance value of a peripheral pixel is equal to or higher than a threshold value from among pixels included in the small region as the edge density.
3. The information processing apparatus according to claim 1 , wherein the second order differential filter is a Laplacian of Gaussian filter.
4. The information processing apparatus according to claim 1 , wherein the processor classifies each of pixels of the sharpened image into a fingerprint region candidate or a background region candidate in response to the edge density; and deforms the sharpened image such that sets of fingerprint region candidates and sets of background region candidates individually become figures having no hole therein to separate the sharpened image into the fingerprint region and the background region.
5. The information processing apparatus according to claim 4 , wherein the processor applies an expansion process and a contraction process of morphology operation to the sets of the fingerprint region candidates and the sets of the background region candidates to deform the sharpened image such that the fingerprint region and the background region individually form one figure in the sharpened image.
6. The information processing apparatus according to claim 1 , wherein noise in the background region is reduced by setting luminance values in the background region decided by the processor to luminance values equal to or higher than a given value.
7. The information processing apparatus according to claim 6 , wherein the processor extracts a verification biological feature in the image in which the noise is reduced; and verifies a registration biological feature registered in advance and the verification biological feature with each other to perform individual authentication.
8. An image processing method, comprising:
generating, by a computer, by emphasizing edges, which correspond to changes of luminance of a fingerprint pattern included in a fingerprint image, a sharpened image of the fingerprint image;
applying a second order differential filter to the sharpened image;
dividing the sharpened image into a plurality of small regions; and
calculating, for each of the plurality of small regions, a ratio of pixels in regard to which an absolute value of a response of the second order differential filter is equal to or higher than a threshold value from among pixels included in the small region as the edge density; and
deciding based on the edge density whether each of pixels of the sharpened image is in a fingerprint region or a background region.
9. The image processing method according to claim 8 , further comprising:
dividing the sharpened image into a plurality of small regions, and
calculating, for each of the plurality of small regions, a ratio of pixels each of which a degree of change of a luminance value from a luminance value of a peripheral pixel is equal to or higher than a threshold value from among pixels included in the small region as the edge density.
10. The image processing method according to claim 8 , wherein the second order differential filter is a Laplacian of Gaussian filter.
11. The image processing method according to claim 8 , further comprising:
classifying each of pixels of the sharpened image into a fingerprint region candidate or a background region candidate in response to the edge density; and
deforming the sharpened image such that sets of fingerprint region candidates and sets of background region candidates individually become figures having no hole therein to separate the sharpened image into the fingerprint region and the background region.
12. The image processing method according to claim 11 , further comprising:
applying an expansion process and a contraction process of morphology operation to the sets of the fingerprint region candidates and the sets of the background region candidates to deform the sharpened image such that the fingerprint region and the background region individually form one figure in the sharpened image.
13. The image processing method according to claim 8 , wherein noise in the background region is reduced by setting luminance values in the background region decided by the processor to luminance values equal to or higher than a given value.
14. The image processing method according to claim 13 , further comprising:
extracting a verification biological feature in the image in which the noise is reduced; and
verifying a registration biological feature registered in advance and the verification biological feature with each other to perform individual authentication.
15. A non-transitory computer-readable medium recording an image processing program which causes a computer to perform a process, the process comprising:
generating, by emphasizing edges, which correspond to changes of luminance of a fingerprint pattern included in a fingerprint image, a sharpened image of the fingerprint image;
applying a second order differential filter to the sharpened image;
dividing the sharpened image into a plurality of small regions; and
calculating, for each of the plurality of small regions, a ratio of pixels in regard to which an absolute value of a response of the second order differential filter is equal to or higher than a threshold value from among pixels included in the small region as the edge density; and
deciding based on the edge density whether each of pixels of the sharpened image is in a fingerprint region or a background region.
16. The non-transitory computer-readable medium according to claim 15 , further comprising:
dividing the sharpened image into a plurality of small regions, and
calculating, for each of the plurality of small regions, a ratio of pixels each of which a degree of change of a luminance value from a luminance value of a peripheral pixel is equal to or higher than a threshold value from among pixels included in the small region as the edge density.
17. The non-transitory computer-readable medium according to claim 15 , further comprising:
classifying each of pixels of the sharpened image into a fingerprint region candidate or a background region candidate in response to the edge density; and
deforming the sharpened image such that sets of fingerprint region candidates and sets of background region candidates individually become figures having no hole therein to separate the sharpened image into the fingerprint region and the background region.