JP2856164B2 - Mask making method and image processing apparatus - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

[0001] 1. Field of the Invention [0002] The present invention relates to an image processing method and an image processing apparatus, and more particularly to an image processing method for generating mask information from an arbitrary area of a color image and an image processing apparatus having a mask creation function. .

[0002]

2. Description of the Related Art Conventionally, this type of image processing apparatus has been used for performing image processing on an arbitrary area of an image to create a mask.

As an example of a conventional mask making method, for example, Japanese Patent Application Laid-Open No. 2-284275 discloses a method of cutting out a predetermined shape such as a rectangle or a circle, and a method of using a pointing device such as a mouse to outline a region to be cut out. In order to solve the problem in the method of following, the feature information of the representative pixel of the mask target area is extracted, and the mask information is generated by detecting a pixel having the common feature information.
An image processing method has been proposed in which closed area processing is performed on the mask information.

[0004] As another example of a method for producing a mask,
For example, Japanese Patent Application Laid-Open No. 4-308980 discloses a method of generating a mask in an image processing for setting a non-inspection area of an arbitrary shape in an inspection area set by using a known function. A lightness threshold for generating a non-inspection mask of an unspecified shape in the inspection area is input, and in the input multi-tone image data, pixels having lightness equal to or less than the threshold are mask information. As a method, a method of deleting the inspection area from the inspection area has been proposed. The publication also proposes a mask creation method characterized in that the edge of the created mask is reduced into the mask region by an arbitrary number of pixels or enlarged outside the mask region.

[0005]

The above-mentioned conventional method has the following problems.

(1) As a first problem, Japanese Unexamined Patent Application Publication No. Hei 2 (1995) -1990 discloses that feature information of a representative pixel is extracted and mask information is generated by detecting pixels having the same feature information.
According to the method described in Japanese Patent No. 284275, a region desired by an operator is not always obtained as a mask.

The reason is that the obtained mask area varies in various ways depending on the RGB gradation state of the image. For example, in the case of an extreme image in which only the gradation of the R value of RGB changes stepwise over the entire screen and the values of G and B are close to “0” over the entire screen, the conventional method is used. When a mask is selected, there is a problem that the entire screen is selected as a mask area.

(2) A second problem is that a threshold value of brightness is input and pixels having brightness equal to or less than the threshold value are generated as mask information.
In the method disclosed in Japanese Patent Application No. 308980, in order to obtain a target mask area, it is necessary to perform an operation while repeatedly changing the threshold value and performing trial and error.

The reason is that when the threshold value is changed, the operator does not know in advance what mask area is to be selected. After changing the threshold value, the operator selects the mask area actually selected. This is because it is possible to confirm whether or not the target image area has been obtained for the first time by checking on the screen.

(3) The third problem is that, in the above-mentioned method of reducing the edge of the created mask by an arbitrary number of pixels into the mask area or expanding it outside the mask area, the mask is not always desired by the operator. That is, an area is not always obtained.

The reason is that the mask area desired by the operator is not always smaller or larger than the selected mask area by a certain number of pixels.

Accordingly, the present invention has been made in view of the above problems, and an object thereof is to create a mask region closer to a mask region desired by an operator as compared with a conventional mask creation method. , Image processing method and apparatus.

Another object of the present invention is to provide an image processing method and apparatus which can reduce the number of times of trial and error as much as possible, greatly reduce the number of times of repetitive processing, and create a mask area desired by an operator with a small number of operations. It is in.

[0014]

In order to achieve the above object, an image processing apparatus according to the present invention comprises a representative point selecting means (10 in FIG. 1) for selecting a certain point of an input image as a representative point.
2) and sample generation means (103 in FIG. 1) for generating a sample of the selected area of the image based on the representative point and displaying the sample in a list.
Sample selection means (104 in FIG. 1) for selecting an appropriate sample from a list of samples in the selected area;
A mask area determining unit (105 in FIG. 1) for creating a mask from the selected sample;

A second method for producing a mask and an image processing apparatus according to the present invention include a threshold change degree changing means (601 in FIG. 6) in addition to the first method for producing a mask and the image processing apparatus.

The method for producing a mask according to the present invention comprises the steps of (a)
Selecting a certain point as a representative point in the input image; and (b) generating a plurality of samples of the mask area by gradually changing a threshold value based on the representative point, and displaying a list of the generated samples. (C) selecting an appropriate sample from the sample list, and (d)
Generating a mask region based on the selected sample.

[0017]

Next, embodiments of the present invention will be described with reference to the drawings.

FIG. 1 is a functional block diagram showing the configuration of a mask creating method according to the first embodiment of the present invention. Referring to FIG. 1, an embodiment of the present invention includes an image input unit 101, a representative point selecting unit 102, a sample generating unit 103, a sample selecting unit 104, and a mask area determining unit 105. Have been.

The image input means 101 converts the image signal into RGB
Inputs quantized image data such as a signal.

The representative point selecting means 102 inputs a certain point on the image using a pointing device such as a mouse on the display screen and stores the point as a representative point.

The sample generating means 103 generates a plurality of samples of the mask region in which the threshold value is changed stepwise based on the input image data and the representative points, and displays a list on the screen.

The sample selection means 104 selects a sample closest to the mask area desired by the operator from among the samples listed on the screen.

The mask area determining means 105 creates mask information based on the sample selected by the operator.

FIG. 2 is a diagram showing an example of mask samples listed by the sample generating means 103. In FIG. Based on the representative point 201 input by the operator, the obtained mask area 202 is obtained by changing the threshold value r stepwise as r = 1, 2, 3,. , 205 (see FIGS. 2A, 2B, and 2C).

FIG. 3 is a block diagram showing the configuration of an embodiment of the image processing apparatus according to the present invention. The image processing apparatus according to the present embodiment includes a system bus 300, a display controller 310, a display 311, and a CPU 3.
20, the memory 330, and the keyboard controller 34
0, keyboard 341 and mouse controller 350
, A mouse 351, a disk controller 360,
And a fixed disk 361.

The fixed disk 361 stores image data 362 used by the image processing apparatus and an image processing program 363 processed by the CPU 320. The image processing program 363 is developed and processed in the memory 330 as necessary.

The image data 362 is input from an image scanner 371 or the like via a scanner controller 370. Note that, instead of the image scanner, an image input device such as a digital camera, a video capture, or a CD-ROM can be used instead.

The operator can input threshold information from the keyboard 341 and representative points and sample list selection information from the mouse 351. The input information can be input from the keyboard controller 340 or the mouse. The data is stored in the memory 330 by the controller 350. Note that a pointing device such as a tablet can be used instead of a mouse.

The image processed by the CPU 320 and the sample of the mask are displayed on the display 311 via the display controller 310.

FIG. 4 is a diagram for explaining an example showing the above-mentioned mask generating method according to the embodiment of the present invention more specifically, and is a flowchart showing a processing flow of the example.

Referring to FIG. 4, first, in the maximum sample number setting process of step 401, the sample generation means 103
The maximum number of samples created by (see FIG. 1) is set as a constant N.

In the image input processing in step 402, image data input in advance from a scanner or other image input devices and stored in the fixed disk device 361 is developed as image data F on a memory.

Step 403 is a process of inputting a representative point (representative point input process), in which a representative point C is input from a pointing device such as a mouse.

In step 404, the threshold value is initialized, and the value of the threshold value r is initialized to "1".

In the mask sample generation processing in the next step 405, for the pixel Pn (n = 1, 2,...) In F, the distance | CP in the RGB color space between the representative points C and Pn
A set of pixels Pn where n | is equal to or smaller than the threshold value r is created as a mask region M (r).

The distances in the RGB color space are as follows: the RGB components of C are (RC, GC, BC), and the RGB components of Pn are (RP,
GP, BP) is obtained by the following equation (1).

Step 406 is a mask sample display process. The mask area M (r) generated in the mask sample generation process of step 405 is displayed on the display 311.

Step 407 updates the threshold value, and increases the value of r by "1".

Step 408 is a process for judging the condition for terminating the sample preparation. The value of r is compared with the value of N. If r.ltoreq.N, the process branches to a loop process to generate the next sample. If so, end the loop.

Next, in the sample selection process of step 409, the mask area M which the operator considers most appropriate from the list of samples displayed on the display.
Select (x).

Finally, in the mask determination processing of step 410, mask information is generated based on the mask area M (x) selected by the operator.

FIG. 6 is a block diagram showing a configuration of a mask making method according to the second embodiment of the present invention.

Referring to FIG. 6, the mask forming method according to this embodiment further includes a threshold change degree changing means 601 in addition to the configuration of the above-described embodiment shown in FIG.

In the threshold change degree changing means 601,
The degree of change of the threshold value when creating a mask sample is gradually narrowed each time the operator selects a sample, so that a more detailed mask area can be obtained.

FIG. 5 is a flowchart showing the operation of the example for explaining the second embodiment of the present invention more specifically.

In the initialization processing of step 501, the maximum value R at which the threshold value changes, the maximum number of samples N to be created,
The threshold r = 0 and the degree of change d = R / N of the threshold are initialized.

The image input processing in step 502 and the representative point input processing in step 503 are the same as those in FIG. 4, and a description thereof will be omitted.

In the threshold value updating process in step 504,
The threshold r is increased by d. The mask sample generation processing in step 505 and the mask sample display processing in step 506 are the same as steps 405 and 406 shown in FIG.

In the sample preparation end condition determination processing in step 507, if r ≦ R, the flow branches to a loop to generate the next sample. If r> R, the loop ends. Further, the sample selection processing in step 508 is the same as step 409 in FIG.

In the detailed selection branching process of step 509,
The operator inputs whether or not he or she wants to select a more detailed mask. If “Yes”, the process branches to sample preparation condition update processing 510.

In the sample preparation condition updating process in step 510, the threshold value desired by the operator is considered to be larger than x−d and smaller than x + d. The value R is initialized to x + d, and d = ((x + d)-(x-d)) / N = 2d / N.

By these initialization, it is possible to efficiently obtain a sample in which the threshold value is changed in more detail. Note that the mask determination processing in step 511 is the same as step 410 in FIG. 4, and a description thereof will be omitted.

[0053]

As described above, according to the present invention,
The following effects are obtained.

(1) The first effect is that a mask area closer to an operator's desired mask area can be created as compared with the conventional mask creation method.

The reason is that, in the present invention, by selecting from a plurality of mask samples in which the threshold value is changed stepwise, there is a high possibility that a mask closer to the purpose of the operator exists. is there.

(2) The second effect is that a desired mask area of an operator can be created with a small number of operations without performing trial and error as much as possible.

The reason is that, in the present invention, the operator can know in advance the mask area to be obtained by using the mask sample displayed on the screen, so that unnecessary trial and error operations can be omitted. Because it becomes.

[Brief description of the drawings]

FIG. 1 is a functional block diagram illustrating a configuration of a mask creating method according to a first embodiment of the present invention.

FIG. 2 is a diagram for describing the first embodiment of the present invention, and is a diagram illustrating an example of a sample displayed by a sample generation unit.

FIG. 3 is a block diagram showing an embodiment of the image processing apparatus of the present invention.

FIG. 4 is a flowchart illustrating a processing procedure according to an embodiment of the present invention.

FIG. 5 is a flowchart illustrating a processing procedure according to a second embodiment of the present invention.

FIG. 6 is a diagram showing a configuration of a mask creating method according to a second embodiment of the present invention in functional blocks.

[Explanation of symbols]

 Reference Signs List 101 image input means 102 representative point selecting means 103 sample generating means 104 sample selecting means 105 mask area determining means 201 representative point 202 mask area 203 r = 1 sample 204 r = 2 sample 205 r = 3 sample 300 system bus 310 Display controller 311 Display 320 CPU 330 Memory 340 Keyboard controller 341 Keyboard 350 Mouse controller 351 Mouse 360 Disk controller 361 Fixed disk device 362 Image data 363 Image processing program 370 Scanner controller 371 Image scanner 401 Maximum sample number setting processing 402 Image input processing 403 Representative Point input processing 404 Initial threshold value substitution processing 405 Mask sample generation processing 406 Mask sample display processing 407 Threshold update processing 408 Sample creation end condition determination processing 409 Sample selection processing 410 Mask determination processing 501 Initialization processing 502 Image input processing 503 Representative point input processing 504 Threshold update processing 505 Mask sample generation processing 506 Mask sample display processing 507 Sample preparation end condition judgment processing 508 Sample selection processing 509 Detailed selection branch processing 510 Sample preparation condition update processing 511 Mask determination processing 601 Threshold change degree changing means

Continuation of front page (58) Field surveyed (Int.Cl. ⁶ , DB name) G06T 5/00

Claims (4)

(57) [Claims] (A) selecting a certain point as a representative point in an input image; and (b) generating a plurality of samples of a mask region by changing a threshold value stepwise based on the representative point. Displaying the generated sample list; (c) selecting an appropriate sample from the sample list; and (d) generating a mask region based on the selected sample. A method for producing a mask, characterized in that: 2. The method according to claim 1, wherein, when generating the sample of the mask area by changing the threshold value in a stepwise manner, control is performed so as to change the degree of change of the threshold value. The mask creation method described. 3. A means for inputting an image, means for selecting a certain point in the input image as a representative point, and generating a plurality of samples of a mask area by changing a threshold value stepwise based on the representative point. Means for displaying the generated sample list; means for selecting an appropriate sample from the displayed sample list; and means for generating a mask area based on the selected sample. An image processing apparatus comprising: 4. The image processing apparatus according to claim 3, further comprising means for controlling the degree of change by changing the threshold value.