Electronic device and method for matching images

1. A method of extracting feature data of an image, the method being performed by a processor of an electronic device, the method comprising:

(a) reading the image, wherein the image is a grayscale image;

(b) computing a grayscale center of the image, wherein the grayscale center is a mean location of all the gray values in the image, where the grayscale center is computed by:

r

0

==

∑

i

×

g

ij

∑

g

ij

c

0

==

∑

j

×

g

ij

∑

g

ij

,

wherein, (r 0 , c 0 ) is the grayscale center, i represents each row of the image, j represents each column of the image, and g ij represents a gray value of the point (i, j) in the image;

(c) dividing the image into n equal parts D k(k=1˜n) according to the grayscale center, and computing a grayscale density V k of each part D k to acquire n grayscale densities V k(k=1˜n) , wherein n is a positive integer, wherein the grayscale density V k of the part D k is computed by:

V

k

=

∑

r

i

′

⁢

j

′

×

g

i

′

⁢

j

′

∑

r

ij

×

g

ij

,

wherein, (i′ j′) is a point in the part D k , (i, j) is a point in the image, r i′j′ represents a distance between the point (i′, j′) and the grayscale center(r 0 , c 0 ), r ij represents a distance between the point (i, j) and the grayscale center (r 0 , c 0 ), g i′j′ represents a gray value of the point (i′, j′), and g ij represents a gray value of the point (i, j); and

(d) regarding the n grayscale densities V k(k=1˜n) as feature data of the image, and storing the feature data of the image into a storage unit of the electronic device.

2. The method as described in claim 1 , wherein the image read in step (a) is acquired by a hardware component that captures images, or by a software application that downloads images from the Internet or a storage medium.

3. The method as described in claim 1 , before (a) further comprising:

converting the image into the grayscale image upon the condition that the image is a color image.

4. The method as described in claim 1 , after (a) further comprising:

determining outlines of the image to generate an outline image.

5. A method of matching images, the images comprising an image A and an image B, the method being performed by a processor of an electronic device and comprising:

(a) computing a grayscale center of the image A, wherein the grayscale center is a mean location of all the gray values in the image A;

(b) dividing the image A into n equal parts D k(k=1˜n) according to the grayscale center of the image A, and computing a grayscale density V k of each part D k to acquire n grayscale densities V k(k=1˜n) , wherein n is a positive integer, and regarding the n grayscale densities V k(k=1˜n) as feature data u of the image A;

(c) repeating steps (a) to (b) to extract feature data v of the image B;

(d) selecting a grayscale density V ak from the feature data u, and selecting a grayscale density V bk from the feature data v;

(e) computing a similarity γ (V ak , V bk ) of the grayscale density V ak and the grayscale density V bk using a first formula, wherein the first formula is:

γ( V ak ,V bk )=100 −|V ak −V bk |÷(( V ak +V bk )÷2)*100;

(f) repeating step (d) and (e) until there is no subsequent V ak in the feature data u, to compute n similarities γ (V ak(k=1˜n) , V bk(k=1˜n) );

(g) computing a similarity β (n, u, v) of the image A and the image B according to the n similarities γ (V ak(k=1˜n) , V bk(k=1˜n) ) using a second formula; and

(h) outputting the similarity β (n, u, v) of the image A and the image B on a display unit of the electronic device.

6. The method as described in claim 5 , wherein the second formula is:

β( n, u, v )=[Σγ( V ak , V bk )]÷ n.

7. An electronic device, comprising:

an image acquisition unit that acquires one or more images;

at least one processor;

a storage unit;

one or more programs stored in the storage unit and executed by the at least one processor, the one or more programs comprising:

an image read module to read an image from the image acquisition unit, wherein the image is a grayscale image;

a grayscale center computation module to compute a grayscale center of the image, wherein the grayscale center is a mean location of all the gray values in the image, wherein the grayscale density V k of the part D k is computed by:

V

k

=

∑

r

i

′

⁢

j

′

×

g

i

′

⁢

j

′

∑

r

ij

×

g

ij

,

wherein, (i′ j′) is a point in the part D k , (i, j) is a point in the image, r i′j′ represents a distance between the point (i′, j′) and the grayscale center(r 0 , c 0 ), r ij represents a distance between the point (i, j) and the grayscale center (r 0 , c 0 ), g i′j′ represents a gray value of the point (i′, j′), and g ij represents a gray value of the point (i, j);

a feature data extraction module to divide the image into n equal parts D k(k=1˜n) according to the grayscale center, and computing a grayscale density V k of each part D k to acquire n grayscale densities V k(k=1˜n) , wherein n is a positive integer, wherein the grayscale density V k of the part D k is computed by:

V

k

=

∑

r

i

′

⁢

j

′

×

g

i

′

⁢

j

′

∑

r

ij

×

g

ij

,

wherein, (i′ j′) is a point in the part D k , (i, j) is a point in the image, r i′j′ represents a distance between the point (i′, j′) and the grayscale center (r 0 , c 0 ), r ij represents a distance between the point (i, j) and the grayscale center (r 0 , c 0 ), g i′j′ represents a gray value of the point (i′, j′), and g ij represents a gray value of the point (i, j); and

a feature data storage module to regard the n grayscale densities V k(k=1˜n) as feature data of the image, and store the feature data of the image into the storage unit.

8. The electronic device as described in claim 7 , wherein the image acquisition unit is a hardware component that captures images, or a software application that downloads images from the Internet or a storage medium.

9. The electronic device as described in claim 7 , wherein the one or more programs further comprise:

an image conversion module to convert the image read by the image read module into the grayscale image upon the condition that the image is a color image.

10. The electronic device as described in claim 7 , wherein the one or more programs further comprise:

an outline determination module to determine outlines of the image to generate an outline image.

11. The electronic device as described in claim 7 , wherein the one or more programs further comprise:

a feature data read module to read feature data u of an image A and read feature data v of an image B from the storage unit;

a similarity computation module to select a grayscale density V ak from the feature data u, select a grayscale density V bk from the feature data v, compute a similarity γ (V ak , V bk ) of the grayscale density V ak and the grayscale density V bk using a first formula, repeat selection and computation until there is no subsequent V ak in the feature data u, to compute n similarities γ (V ak(k=1˜n) , V bk(k=1˜n) ), and compute a similarity β (n, u, v) of the image A and the image B according to the n similarities γ (V ak(k=1˜n) , V bk(k=1˜n) ) using a second formula; and

an output module to output the similarity β (n, u, v) of the image A and the image B on a display unit.

12. The electronic device as described in claim 11 , wherein the first formula is:

γ( V ak , V bk )=100 −|V ak −V bk |÷(( V ak +V bk )÷2)*100.

13. The electronic device as described in claim 11 , wherein the second formula is:

β( n, u, v )=[Σγ( V ak , V bk )]÷ n.