WO2000065839A1

WO2000065839A1 - Color image segmentation method

Info

Publication number: WO2000065839A1
Application number: PCT/KR2000/000248
Authority: WO
Inventors: Hyun Doo Shin; Yang Lim Choi; B. S. Manjunath; Yining Deng
Original assignee: Samsung Electronics Co., Ltd.; The Regents Of The University Of California
Priority date: 1999-04-23
Filing date: 2000-03-22
Publication date: 2000-11-02
Also published as: JP2002543691A; AU3680700A; EP1192809A4; EP1192809A1; MY130272A; TW469412B; KR100436499B1; CN1340273A; JP3853156B2; KR20010105382A; CN1292593C

Abstract

A color image segmentation method is provided. The color image segmentation method includes the steps of: (a) calculating a predetermined value representing the degree of difference form the color of peripheral pixels by using pixel values of an input image; (b) obtaining a converted image by converting a calculated value into a value of a predetermined scale; and (c) segmenting the converted image. According to the color image segmentation method, a robust and an automatic segmentation is possible, and a segmentation speed is high even when segmenting an image containing much noise.

Description

COLOR IMAGE SEGMENTATION METHOD

Technical Field

The present invention relates to a color image segmentation method, and more particularly, to a color image segmentation method for segmenting a color image.

Background Art

The segmentation of a color image is a very important part of digital image processing and its applications. Conventional color image segmentation methods have a problem in that it is not easy to segment a color image containing texture. Also, another conventional color image segmentation method for performing an automatic segmentation is not robust with respect to an input image containing noise, and still another conventional color image segmentation method for again segmenting the image which a user segments preparatorily is robust with respect to an input image containing noise, but an automatic segmentation is not performed, therefore, it takes much time.

Disclosure of the Invention

To solve ihe above problems, it is an object of the present invention to provide a color image segmentation method capable of automatically segmenting a color image containing texture and being robust with respect to an input image containing noise. It is another object of the present invention is to provide a color image processing method containing the color image segmentation method.

It is still another object of the present invention is to provide a medium in which a computer program performing the color image segmentation method is stored. Accordingly, to achieve the above object, according to one aspect of the present invention, there is provided a color image segmentation method. The color image segmentation method comprises the steps of (a) calculating a predetermined value representing the degree of difference from the color of peripheral pixels by using pixel values of an input image, (b) obtaining a converted image by converting a calculated value into a value of a predetermined scale, and (c) segmenting the converted image

Preferably, the step (c) segments the converted image based on a region growing method

It is preferable that the color image segmentation method, prior to the step (a), further comprises the step of (p-a) quantizing pixel values of an image into a predetermined number of representative pixel values, wherein the pixel values are quantized pixel values

The representative pixel values preferably consist of 10-20 values

It is preferable that the color image segmentation method, prior to the step (a), further comprises the steps of (p-a-1 ) defining a predetermined window containing a center pixel, and (p-a-2) calculating a predetermined value representing the degree of difference from the color of peripheral pixels with respect to pixels in a defined window

It is also preferable that the step (a) comprises the steps of (a-1 ) defining a window B which is centered at a pixel p and has a size of d x d when d is a positive integer, and (a-2) classifying a pixel position Z, into a C number of classes when i is a number between 1 and C, and Z, is a set of all pixels in the window B, and (a-3) obtaining a J-value with respect to each pixel in a class-map as

S_B s_τ - _w

J =

^}ιv s„

where m, is the average of positions of N, data points in class Z„

S_τ = ∑ ||r - m\\² and S_u = ∑ S, = ∑ ||- - m

- 6/ 1 = 1

d is preferably an integer inclusive of and between 3 and 10 The predetermined scale is preferably a gray scale having values between 0 and 255

In order to achieve the above object, according to another aspect of the present invention, there is provided a color image segmentation method The color image segmentation method comprises the steps of (a) quantizing pixel values of an image into a predetermined number of representative pixel values, (b) calculating a predetermined value representing the degree of difference from the color of pixels in a predetermined size window using quantized representative pixel values, (c) obtaining a converted image by converting a calculated value into a value of a predetermined scale, and (d) segmenting the converted image using a segmentation method based on a region growing method

In order to achieve another object, there is provided an object-based color image processing method for processing a color image according to a color image segmentation method The color image segmentation method comprises the steps of (a) calculating a predetermined value representing the degree of difference from the color of peripheral pixels using pixel values of an input image, (b) obtaining a converted image by converting a calculated value into a value of a predetermined scale, and (c) segmenting the converted image

In order to achieve still another object, there is provided a medium for storing program codes performing a color image segmentation method for segmenting a color image into a plurality of regions The color image segmentation method comprises the steps of (a) quantizing pixel values of an image into a predetermined number of representative pixel values, (b) calculating a predetermined value representing the degree of difference from the color of pixels in a predetermined size window using quantized representative pixel values, (c) obtaining a converted image by converting a calculated value into a value of a predetermined scale, and (d) segmenting the converted image using a segmentation method based on a region growing method Brief Description of the Drawings

The above objects and advantages of the present invention will become more apparent by describing in detail a preferred embodiment thereof with reference to the attached drawings in which FIG 1 is a flowchart illustrating a color image segmentation method according to a preferred embodiment of the present invention,

FIGS 2A through 2C illustrate class-maps and J-values formed according to a color image segmentation method of FIG 1 ,

FIGS 3A and 3B illustrate segmented class-maps, FIG 4A illustrates one image frame of a "container" as a test image and a test image segmented by the color image segmentation method according to the present invention,

FIG 4B illustrates one image frame of a "foreman" as a test image and a test image segmented by the color image segmentation method according to the present invention,

FIG 4C illustrates one image frame of a "coast" as a test image and a test image segmented by the color image segmentation method according to the present invention,

FIG 4D illustrates one image frame of a "flower garden" as a test image and a test image segmented by the color image segmentation method according to the present invention, and

FIG 4E illustrates one image frame of a "mother and daughter" as a test image and a test image segmented by the color image segmentation method according to the present invention

Best mode for carrying out the Invention

Referring to FIG 1 , which illustrates a flowchart illustrating a color image segmentation method according to a preferred embodiment of the present invention, a color image is input (step 102), and pixel values of an input image are quantized into several representative pixel values (step 104)

In order to classify an image in natural scenes, the representative pixel values consist of 10-20 values In this embodiment, quantization is performed using three representative pixel values for convenience of explanation Next, a class-map is formed by assigning labels corresponding to a quantized representative pixel values (step 106) More preferably, a window centered at a pixel to be processed in an entire image is defined That is, when d is a positive integer, preferably between 3 and 10, a window B which is centered at a pixel p and has a size of d x d, is defined Also, an assumption is made that i is the number between 1 and C, and Z, is a set of all the pixels in the window B In other words, an assumption is made that Z, is classified into a C number of classes Preferably, the d determining the size of the window is an integer inclusive of and between 3 and 10

Also, an assumption is made that m, is the average of positions of Λ/, data points in class Z, as (equation 1 )

Also, S_r and S_w are defined by (equation 2)

S_τ = ∑ll- - w||² and zeZ

(equation 3)

respectively

Next, a J-value with respect to each pixel in a class-map is obtained (step 108) The J-value with respect to each pixel in the class-map is defined as follows (equation 4) s_f y _j

J =

< _w

The J-values obtained by equation 3 are converted into a gray scale value between 0 and 255, so that a gray scale image having values and capable of being referred to as a J-image is obtained (step 110) The J-image has the same form as a three-dimensional topographic map containing valleys and mountains that actually represent region centers and region boundaries, respectively

Lastly, the J-image is segmented based on a region growing method (step 112) The region growing method is known to one of ordinary skill in the art as a method used for the segmentation of a digital image, therefore, an explanation thereof is not given

FIGS 2A through 2C illustrate class-maps and J-values formed according to a color image segmentation method of FIG 1 The J-value at the center pixel is 1 720 in the class-map of FIG 2A, and in the class-map of FIG 2B, the J-value at the center pixel is 0, and in the ciass-map of FIG 2C, the J-value at the center pixel is obtained as 0 855 Here, like in the class-map of FIG 2A, in the case where pixels represented as + located at the left of the center pixel, pixels represented as 0 located at the right of the center pixel, and pixels represented as * located at the right of the center pixel form regions most clearly, the J-value is 1 720, a relative large value Also, like in the class-map of FIG 2B, in the case where the pixels represented as +, the pixels represented as 0, and the pixels represented as ^* are uniformly distributed and hardly form regions, the J-value is 0 Furthermore, like in the class-map of FIG 2C, in the case where the pixels represented as ^* located at the right of the center pixel form regions, but the pixels represented as 0 and ^* hardly form regions, the J-value is 0 855 That is, the larger the J-value is, the more likely that the pixel is near to a region boundary, therefore a segmentation based on the region growing method by using this point can be performed FIGS 3A and 3B illustrate segmented class-maps

It is necessary to check whether a segmentation is performed well with respect to each region in the segmented class-maps and to represent the same as quantized values For this purpose, when J_k is the J-value obtained with respect to a k-region, and M_k is the number of pixel points of a k-th region, and N is the total number of pixel points in the class-map, the averaged J- value is calculated as

(equation 5)

The calculated values are represented as quantized values whether a segmentation is performed well with respect to each region in the segmented class-maps or not

In the case of the segmented class-map shown in FIG 3A, J is 0, on the other hand, in the case of the segmented class-map shown in FIG 3B, J is 0 05 That is, in the case of regions of a fixed number, especially in the case of better segmentation, the averaged J-value is small This occurs because the region contains a few uniformly distributed color classes in the case where a region is well segmented Accordingly, the averaged J-value is small

FIG 4A illustrates one image frame of a "container" as a test image and a test image segmented by the color image segmentation method according to the present invention Referring to FIG 4A, J of an image before segmentation is 0 232, but, J of the image after segmentation is 0 071 Also, it is evident that regions in the test image are well segmented

FIG 4B illustrates one image frame of a "foreman" as a test image and a test image segmented by the color image segmentation method according to the present invention Referring to FIG 4B, ./ of an image before segmentation is 0 238, but ,7 of the image after segmentation is 0 105 Also, it is evident that regions in the test image are well segmented FIG 4C illustrates one image frame of a "coast" as a test image and a test image segmented by the color image segmentation method according to the present invention Referring to FIG 4C, J of an image before segmentation is 0 494, but J of the image after segmentation is 0 093 Also, it is evident that regions in the test image are well segmented

FIG 4D illustrates one image frame of a "flower garden" as a test image and a test image segmented by the color image segmentation method according to the present invention Referring to FIG 4D, J of an image before segmentation is 0 435, but J of the image after segmentation is 0 088 Also, it is evident that regions in the test image are well segmented

FIG 4E illustrates one image frame of a "mother and daughter" as a test image and a test image segmented by the color image segmentation method according to the present invention Referring to FIG 4E, J of an image before segmentation is 0 438, but J of the image after segmentation is 0 061 Also, it is evident that regions in the test image are well segmented That is, as described referring to FIG 4A through 4E, J of the image segmented by the color image segmentation method according to the present invention is smaller than J of the image before segmentation

In the above embodiment, the calculation of a specific function is explained as an example, however, this is only for explanation The scope of the present invention defined in the appended claims is not limited to the embodiment, and it is obvious that one of ordinary skill in the art can use another modified function representing the degree of difference from the color of peripheral pixels Furthermore, the above color image segmentation method can be embodied in a computer program Codes and code segments composing the program can be easily inferred to by a skilled computer programmer in the art Also, the program can be stored in computer readable media, read and executed by a computer, and it can thereby realize the color image processing method The media can include magnetic media, optical media, and carrier waves

As described above, according to the present invention, a color image can be automatically segmented without user's assistance and is robust with respect to an input image containing noise

Industrial Applicability

In the above color image segmentation method according to the present invention, a robust segmentation is possible even when segmenting an image containing much noise or texture Furthermore, an automatic segmentation is possible without user's assistance such as segmentation performed manually by a user, therefore, the segmentation speed is high The color image segmentation method can be applied to object-based image processing such as that used in MPEG-7

Claims

What is claimed is

1 A color image segmentation method for segmenting a color image into a plurality of regions, comprising the steps of

(a) calculating a predetermined value representing the degree of difference from the color of peripheral pixels by using pixel values of an input image,

(b) obtaining a converted image by converting a calculated value into a value of a predetermined scale, and

(c) segmenting the converted image

2 The color image segmentation method according to claim 1 , wherein the step (c) segments the converted image based on a region growing method

3 The color image segmentation method according to at least one of claim 1 or claim 2, prior to the step (a), further comprising the step of (p-a) quantizing pixel values of an image into a predetermined number of representative pixel values, wherein the pixel values are quantized pixel values

4 The color image segmentation method according to claim 3, wherein the representative pixel values consist of 10-20 values

5 The color image segmentation method according to at least one of claim 1 or claim 2 or claim 4, prior to the step (a), further comprising the steps of

(p-a-1 ) defining a predetermined window containing a center pixel, and (p-a-2) calculating a predetermined value representing the degree of difference from the color of peripheral pixels with respect to pixels in a defined window 6 The color image segmentation method according to claim 3, prior to the step (a), further comprising the steps of

(p-a-1 ) defining a predetermined window containing a center pixel, and (p-a-2) calculating a predetermined value representing the degree of difference from the color of peripheral pixels with respect to pixels in a defined window

7 The color image segmentation method according to at least one of claim 1 or claim 2, wherein the step (a) comprises the steps of (a-1 ) defining a window B which is centered at a pixel p and has a size of d x d when d is a positive integer, and

(a-2) classifying a pixel position Z, into a C number of classes when i is a number between 1 and C, and Z, is a set of all pixels in the window B, and

(a-3) obtaining a J-value with respect to each pixel in a class-map as

S_B S_τ ύ,

J w

S w, S_a

where m, is the average of positions of N, data points in class Z„ c S_τ = ∑ || - m and S„ = ∑ S, = ∑ \\= - m_t \ zeZ <^{= 1} zeZ,

8 The color image segmentation method according to claim 3, wherein the step (a) comprises the steps of

(a-1 ) defining a window B which is centered at a pixel p and has a size of d x d when d is a positive integer, and

(a-2) classifying a pixel position Z, into a C number of classes when i is a number between 1 and C, and Z, is a set of all pixels in the window B, and (a-3) obtaining a J-value with respect to each pixel in a class-map as _{B τ H}

J s w, 'w

where m, is the average of positions of N, data points in class Z„ c S_τ = ∑ ll- - w||² and .- = ∑ 5, = ∑ ||— - m. reZ ι = l 2<EZ,

9 The color image segmentation method according to claim 4, wherein the step (a) comprises the steps of

(a-2) classifying a pixel position Z, into a C number of classes when i is a number between 1 and C, and Z, is a set of all the pixels in the window B, and

(a-3) obtaining a J-value with respect to each pixel in a class-map as

r, _T , w

J = ^~^ = _w S_w

where m, is the average of positions of N, data points in class Z„ c l|2 S_τ - ∑ | - mf and S_lt = ∑ S, = ∑ || - w, || zeZ '^{= 1} zeZ,

10 The color image segmentation method according to claim 5, wherein the step (a) comprises the steps of

(a-1 ) defining a window B which is centered at a pixel p and has a size of d x d when d is a positive integer, and (a-2) classifying a pixel position Z, into a C number of classes when i is a number between 1 and C, and Z, is a set of all pixels in the window B, and

(a-3) obtaining a J-value with respect to each pixel in a class-map as

where m, is the average of positions of N, data points in class Z„

S_τ = ∑l - m and S_ιv = ∑ S, = ∑ \\=- m.

?eZ reZ,

11 The color image segmentation method according to claim 6, wherein the step (a) comprises the steps of

(a-2) classifying a pixel position Z, into a C number of classes when i is a number between 1 and C, and Z, is a set of all pixels in the window B, and (a-3) obtaining a J-value with respect to each pixel in a class-map as

_j _ ^B _ ^T '-V _w S_w

where m, is the average of positions of Λ/, number of data points of class Z„

^sτ = Σ

26Z l^{z ~ m}\\^{2 and S} _"- ^{= , = 1 = 2} Σ^eZ, Ik ^{■ m},

12 The color image segmentation method according to claim 7, wherein the d is an integer inclusive of and between 3 and 10

13 The color image segmentation method according to claim 8, wherein the d is an integer inclusive of and between 3 and 10

14 The color image segmentation method according to claim 9, wherein the d is an integer inclusive of and between 3 and 10

15 The color image segmentation method according to claim 10, wherein the d is an integer inclusive of and between 3 and 10

16 The color image segmentation method according to claim 11 , wherein the d is an integer inclusive of and between 3 and 10

5

17 The color image segmentation method according to at least one of claim 1 or claim 2, wherein the predetermined scale is a gray scale having values between 0 and 255

ιo 18 The color image segmentation method according to claim 3, wherein the predetermined scale is a gray scale having values between 0 and 255

19 The color image segmentation method according to claim 4, is wherein the predetermined scale is a gray scale having values between 0 and

255

20 The color image segmentation method according to claim 5, wherein the predetermined scale is a gray scale having values between 0 and

20 255

21 The color image segmentation method according to claim 6, wherein the predetermined scale is a gray scale having values between 0 and 255

25

22 The color image segmentation method according to claim 7, wherein the predetermined scale is a gray scale having values between 0 and 255

30 23 The color image segmentation method according to claim 8, wherein the predetermined scale is a gray scale having values between 0 and

255.

24. The color image segmentation method according to claim 9, wherein the predetermined scale is a gray scale having values between 0 and s 255.

25. The color image segmentation method according to claim 10, wherein the predetermined scale is a gray scale having values between 0 and 255. 0

26. The color image segmentation method according to claim 11 , wherein the predetermined scale is a gray scale having values between 0 and 255.

s 27. The color image segmentation method according to claim 12, wherein the predetermined scale is a gray scale having values between 0 and 255.

28. The color image segmentation method according to claim 13, 0 wherein the predetermined scale is a gray scale having values between 0 and

255.

29. The color image segmentation method according to claim 14, wherein the predetermined scale is a gray scale having values between 0 and 255. 5

30. The color image segmentation method according to claim 15, wherein the predetermined scale is a gray scale having values between 0 and 255.

0 31. The color image segmentation method according to claim 16, wherein the predetermined scale is a gray scale having values between 0 and

255.

32. An object-based color image processing method for processing a color image according to a color image segmentation method, wherein the color image segmentation method comprises the steps of:

(a) calculating a predetermined value representing the degree of difference from the color of peripheral pixels using pixel values of an input image;

(b) obtaining a converted image by converting a calculated value into a value of a predetermined scale; and

(c) segmenting the converted image.

33. The color image processing method according to claim 32, wherein the color image processing method complies with the MPEG-7 s standard.

34. A color image segmentation method for segmenting a color image into a plurality of regions, comprising the steps of:

(a) quantizing pixel values of an image into a predetermined number of 0 representative pixel values;

(b) calculating a predetermined value representing the degree of difference from the color of pixels in a predetermined size window using quantized representative pixel values;

(c) obtaining a converted image by converting a calculated value into 5 a value of a predetermined scale; and

(d) segmenting the converted image using a segmentation method based on a region growing method.

35. The color image segmentation method according to claim 34, o wherein the step (a) comprises the steps of:

(a-1 ) defining a window B which is centered at a pixel p and has a size of d x d when d is a positive integer; and

(a-2) classifying a pixel position Z, into a C number of classes when i is a number between 1 and C, and Z, is a set of all pixels in the window B; and

(a-3) obtaining a J-value with respect to each pixel in a class-map as:

r _ °B _ * *~ o_{w w}

where m, is the average of positions of /V, data points in class Z„

36. The color image segmentation method according to claim 35, wherein d is an integer inclusive of between 3 and 10.

37. The color image segmentation method according to one of claim 34 to claim 36, wherein the predetermined scale is a gray scale having values between 0 and 255.

38. A medium for storing program codes performing a color image segmentation method for segmenting a color image into a plurality of regions, wherein the color image segmentation method comprises the steps of:

(a) quantizing pixel values of an image into a predetermined number of representative pixel values;

(c) obtaining a converted image by converting a calculated value into a value of a predetermined scale; and

39. The medium according to claim 38, wherein the step (a) comprises the steps of:

(a-1 ) defining a window B which is centered at a pixel p and has a size of d x d when d is a positive integer; and (a-2) classifying a pixel position Z, into a C number of classes when i is a number between 1 and C, and Z, is a set of all pixels in the window B; and

(a-3) obtaining a J-value with respect to each pixel in a class-map as:

where m, is the average of positions of Λ/, data points in class Z„

S_τ =

40. The medium according to claim 39, wherein d is set as an integer inclusive of and between 3 and 10.

41. The medium according to one of claim 38 to claim 40, wherein the predetermined scale is a gray scale having values between 0 and 255.