JPH09138854A - Method and device for extracting area of picture - Google Patents

Abstract

PROBLEM TO BE SOLVED: To easily extract only a desired objective area from a picture constituted by means of various colors and patterns by extracting a connection area which has a picture element feature quantity extraction step and a step comparing the picture element feature quantity of a reference picture element with its nearby picture element feature quantity and further has uniform picture element feature quantity including the reference picture element. SOLUTION: A point in the objective area which is to be cut from the picture in picture data inputted from a picture input device 1 is designated by a position designation means 3. Position information on the designated reference picture element is stored in buffers 7 and 9, and the picture element feature quantity of the reference picture element is inputted to a buffer 6. One piece of data is read by a buffer 9 and 'TRUE' is set in mask picture data. The picture element feature quantity of the picture element near the picture element position which is previously judged is compared with reference point picture element feature quantity. When it is judged that masking is possible, the picture element position is inputted to the buffer 9. The judgment processing is continued until the buffer 9 becomes null.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a technique for extracting a necessary target region in an image, a technique for creating a mask for the target region, and a technique for cutting out the target region in various image processing apparatuses. A mask is a data that is used to cut out a partial area in an image and combine it with another image or to combine with a document, and specify in the pixel unit which pixel of the original image is required. Means

[0002]

2. Description of the Related Art Conventionally, this type of image area extracting apparatus has a brightness, hue, saturation, or RG of an area to be extracted.
The B value is specified, and only the pixels within a certain threshold range from the specified value are extracted.

An embodiment of a conventional image area extracting device will be described with reference to FIGS. 15 and 14.

An example of the conventional apparatus is an image input device 201 such as a scanner, a monitor 202 for displaying an image, and a position designating means 20 by which an operator designates a reference point in a target area.
4. Reference pixel value storage buffer 206 for storing pixel values of reference points, input image memory 203, mask image memory 20
7, threshold value processing means 205 for comparing the RGB value and pixel value of the reference point, and an output device 208 for outputting the generated mask data.

The image data input from the image input device 201 is held in the input image memory 203 and simultaneously displayed on the monitor 202. The operator wants to mask while looking at the image displayed on the monitor 202 (target area)
One of the points is designated as a reference point using the position designation means 204 (step A101). The position designating means 204 includes a mouse, a tablet, a keyboard and the like.
Next, the pixel value (R0, G0, B0) of the reference point is extracted from the input image memory 203, and the reference pixel value storage buffer 20
Put the data in 6 (step A102).

The image scanning position is reset to an initial value (step A103), the image in the input image memory 203 is used to scan the image from end to end, and the threshold value processing means 2 is used.
In 05, for each pixel value (r, g, b), (R
0, G0, B0) to determine whether to extract. For pixels determined to be extracted, TRUE is set in the mask image memory 207 at the corresponding position,
If not, FALSE is set (steps A104, A105, A106, A107, A108,
A109). After scanning to the end of the image, the contents of the mask image memory 207 are output to the output device 208, and the process ends. Generally, the contents of the mask image memory 207 are
There are two types, E and FALSE. Hereinafter, it is indicated that the pixel is extracted in the case of TRUE and is not extracted in the case of FALSE.

The threshold value processing means 205 uses a threshold value of Th as a threshold value (R0-Th <r <R
0 + Th) and (G0-Th <g <G0 + Th) and (B0-Th <b <B0 + Th), TRUE, and FALSE otherwise. Further, instead of RGB values, a method of performing threshold processing after converting to hue, saturation, and lightness values, or (R0-r) ² + (G0
-G) ² + (B0-b) ² <Th is used.

As another example of the conventional apparatus, Japanese Patent Laid-Open No. 4-3 is used.
29487, JP-A-5-28263 and the like.

[0009]

In the conventional image area extracting apparatus, if there is a pixel having the same color other than the area to be extracted, that area is also removed, so that the target area intended by the operator is accurate. There was a problem that it could not be extracted. In addition, there is a problem that the area cannot be extracted when the area to be extracted is composed of pixel patterns of a plurality of colors.

FIG. 12 shows a partial area 101 and a partial area 10.
2, a partial area 103 and a partial area 104. The pixel values in the partial areas 101, 102, and 103 are substantially equal to each other. The pixel values of the partial area 101 and other areas are significantly different. Partial area 10
Although the positions of 2 and the partial area 103 are distant from each other, the pixel values in the area are substantially the same. In addition, the partial region 10
4 is composed of a pattern of pixels of two colors, that is, the first color pixel 105 and the second color pixel 106.

In the conventional image area extracting apparatus, an area such as the partial area 101 having a pixel value different from that of other areas can be extracted. However, partial area 1
When 02 is to be extracted, the partial area 1 having the same pixel value
There was a problem that 03 was also extracted at the same time. Further, with respect to a region formed by a pattern such as the partial region 104, in most cases, there is a problem that only one of the pixels of two colors can be extracted. Of course, if masking is performed using both the color of the first color pixel 105 and the second color pixel 106, extraction can be performed to some extent, but this not only imposes a burden on the operator, but also has a problem of extremely poor extraction accuracy. It was

[0012]

In order to solve the above problems, an image area extracting apparatus of the present invention comprises an input image memory for holding input image data, and a monitor for displaying the image data and the area extraction result. A position designation means for designating a target region to be extracted, a reference point feature amount storage buffer for holding a pixel feature amount of a reference point for region extraction, a reference point position storage buffer for holding a position of a reference point for region extraction, Neighbor pixel search means for searching the address of a pixel adjacent to a certain pixel,
A determined pixel storage buffer that stores pixels to be masked, a pixel feature amount comparison unit that compares the feature amounts of two pixels, a pixel feature amount extraction unit that calculates the feature amount of a certain pixel, and an area extraction result are held. And a mask image memory for performing the mask image processing.

The image area extraction method of the present invention further includes a step of designating a reference pixel in the target area to be extracted, and one or more different pixel feature amount extraction steps of extracting the feature amount of an arbitrary pixel, It is characterized by extracting a connected region having a uniform pixel feature amount including the reference pixel, which has a step of comparing the pixel feature amount of the reference pixel with the pixel feature amount in the vicinity thereof.

The principle of the image area extraction method and apparatus of the present invention will be described.

FIG. 4, FIG. 5, FIG. 7, and FIG. 8 are flow charts showing the principle of the present invention. 9 and 10 are enlarged views of the input image data. The image data is digitized by a scanner or the like, and each pixel is represented as a small rectangle surrounded by a grid in the figure.

The processing flow of the present invention will be described with reference to FIG. First, the operator designates a pixel in the target area to be extracted (step A1). The pixel designated by the operator is used as the reference pixel. Then, the position of the reference pixel is registered as the first determined pixel position (step A
2, A3), and at the same time, the pixel feature amount of the reference pixel is calculated (step A4). Next, a connected area extraction process is performed to extract the target area (step A5). In the connected area extraction processing, connected areas having a uniform pixel feature amount including the reference pixel are extracted. The connected region is a region formed by a set of adjacent pixels having substantially the same pixel feature amount. Further, the mask image data is expanded and contracted to correct the shape of the area (step A6). Finally, the mask image data is output (step A7).

The processing flow of the present invention will be described with reference to FIG. First, the operator designates a pixel in the target area to be extracted (step A21). The pixel designated by the operator is used as the reference pixel. Then, the position of the reference pixel is registered as the first determined pixel position (step A
22, A23), and the pixel feature amount of the reference pixel is calculated (step A24). Next, a connected area extraction process is performed to extract the target area (step A25). In the connected area extraction processing, connected areas having a uniform pixel feature amount including the reference pixel are extracted. The connected region is a region formed by a set of adjacent pixels having substantially the same pixel feature amount. Then, the obtained mask data is examined to determine whether or not the mask is normally created (step A25).

As an example of the mask creation determination result, it is possible to check whether or not n or more pixels of the mask TRUE have been extracted. n is usually 2, but a number larger than that may be used. In this case, when the number of TRUE is n or more, the mask creation is considered successful, and when the number is less than n, it is considered that the mask creation is unsuccessful. There is also a method of determining in advance how many times the feature amount should be changed before processing. Also, if all the pixel feature amount extraction means in the device have been executed,
Succeed and proceed to the next step.

When the mask is not normally created, the pixel feature amount to be used is changed (step A27), and the pixel feature amount of the reference pixel is calculated again (step A23).
Repeat from Mask creation result determination process (step A2
In 6), if it is determined that it has succeeded, the process proceeds to the next step. Next, the mask image data is subjected to expansion and contraction processing to correct the contour of the area (step A28). Finally, the mask image data is output (step A29).

Output data in the present invention is TRUE,
It is two types of mask data of FALSE, and in the case of TRUE, it indicates that it is an extraction region at that position of the input image, and in the case of FALSE, it indicates that it is not extracted. However, the output data is not limited to this, and the pixel value is TRUE and FALSE is 0 and 25.
There is a method of expressing it with a value of 5, or a method of mapping and outputting the pixel value of the input image to the position of TRUE.

Here, the pixel feature amount in the present invention will be described. The pixel feature amount in the pixel X is V (X), and V (X) may be a single value or a plurality of values representing the feature of the pixel. Examples of the pixel feature amount are: -The pixel value is used as it is. Grayscale is used for gray images, and RGB values are used for color images. HSV value (hue, saturation, lightness value). Several calculation methods for obtaining these have been proposed in the past, and can be calculated from RGB values according to, for example, document [1]. In addition, XYZ value, L ^* a ^* b ^* value, L ^* u ^* v ^*
Values etc. can also be used. These are generally widely known by the standard established by CIE (International Commission on Illumination), and the calculation method is described in detail in the document [3] and the like. -Value obtained by applying a local filter in the vicinity of a pixel. A value obtained by operating a local filter after performing color conversion such as HSV and XYZ. and so on.

A method of applying a local filter to the vicinity of a pixel will be described with reference to FIG. Local filter 7
0 indicates a scene where the local filter is operated at the pixel position of interest 71. i represents the position in the x direction of the image, and j represents the position in the y direction. In the figure, the size of the local filter is 3
Although it is × 3, it is generally expressed by M × N, and its size is arbitrary. The pixel values at the positions i and j are I
Assuming that (i, j), when the 3 × 3 local filter is operated, its output I ′ (i, j) is I ′ (i, j) = I (i−1, j−1) * a. (1,1) + I (i, j-1) * a (1,2) + I (i + 1, j-1) * a (1,3) + I (i-1, j) * a (2,1) + I (i, j) * a (2,2) + I (i + 1, j) * a (2,3) + I (i-1, j + 1) * a (3,1) + I (i, j + 1) * a ( 3,2) + I (i + 1, j + 1) * a (3,3) (1). If there are three pixel values like RGB,
By applying a local filter to each of R, G, and B, three feature quantities R ′, G ′, and B ′ can be obtained.

One of the local filters effective in the present invention is a low frequency filter. The numerical values of the low-frequency filtering filter 72 shown in the figure are examples, and the low-frequency filtering filter referred to here is a filter that acts to filter only low spatial frequency components after Fourier transforming the image. Are collectively referred to. Such a low-frequency filtering filter can actually be represented as a local filter that weighted averages pixels around the pixel of interest. As an example of these, the low frequency filtering filter 72 is a local filter that takes a uniform average of peripheral pixels.

The low frequency filtering filter includes a first color pixel 105 and a second color pixel 10 such as the target area 104 in FIG.
This is effective for extracting a region in which 6 is repeated as a fine pattern. An area having such a pattern appears as a mixed color of both colors when displayed on a monitor. Therefore, in order to display an arbitrary color on a monitor with a limited number of colors such as 16 colors, such a color is often used. An image is created and used. For example, white and black patterns can represent gray tones, and red and blue patterns can represent purple.

The first color pixel 105 is red and the second color pixel 106 is
Is blue, and when displayed on a monitor
It looks almost purple. In order to reproduce this effect, a low frequency filter is used. The weighted average value of red and blue is obtained by using the low-frequency filtered component as the feature amount of a certain pixel of interest in the target region 104, which is almost the same as the purple pixel value. That is, by using the low-frequency filtering filter, it is possible to carry out the mask making work as a color as seen by a human, even in an area constituted by a fine pattern.

Other examples of effective local filters include a high frequency filter 73 and an edge strength extraction filter 74. The high frequency filter 73 in the figure,
The numerical values shown in the edge strength filter 74 are just examples, and some filters are described in the document [2] and the like. The high frequency filter and the edge strength extraction filter are effective for extracting regions having the same color but different textures.

Next, a connected area extracting process (step A5)
The contents of A25) will be described.

FIG. 7 shows an example of the connected area extracting process. First, all output mask image data is FALSE
(Step B1). One determined pixel position is read (step B2). Note that the location information item once read must be deleted from the registration. TRUE is set at the position of the determined pixel in the mask image (step B3). Next, a pixel in the vicinity of the determined pixel is acquired as a mask candidate pixel (step B4). For each mask candidate pixel, the pixel feature amount is compared with the reference pixel feature amount, and if maskable, the pixel position is registered as a determined pixel position (steps B5, B6, B).
7, B8). Then, the processing from step B2 is continued until there are no more judged pixels.

An example of a method of determining whether masking is possible will be described below. Assuming that N feature quantities are used, N reference pixel feature quantities are Vi = (V1, V2, V3 ... V
n), the feature amount of the target pixel is Xi = (X1, X2, X3
... Xn) can be represented. If the allowable range of each feature amount is Ti = (T1, T2, T3 ... Tn),
It can be judged by the following formula. -If all i from 1 to N are | Xi-
If Vi | <Ti is true, the pixel can be masked (TRUE), and if not FALSE, if the feature amount is an RGB pixel value, the R, G, and B values of the target pixel are From the value, it is TRUE if it is within a certain range, and FALSE otherwise.

The state of actual processing will be described with reference to FIG. The reference pixel 53 (pixel indicated by A in the figure) is
It is registered in advance as the first determined pixel position 54. After setting TRUE to the first determined pixel position 54 in the mask image data, the four neighboring pixels, a, b, c, and d, are acquired as the mask candidate pixels, and the respective pixel feature amounts V (a), V (b), V (c), V (d)
Is compared with the reference pixel feature amount V (A). If the feature amount is close to the reference pixel value, it is a maskable pixel and is registered as a determined pixel. In this example, a, b, c, d
All are registered in the judged pixels.

Next, it is assumed that the pixel read from the determined pixel buffer is c. Since c is located at the second determined pixel position 55, TRUE is set to the second determined pixel position 55 of the mask image memory. The mask candidate pixels in the vicinity of the pixel c are A, e, f, and g, but A is not registered because it is already registered in the mask image. e,
Comparing the feature amounts of f and g, e and f become TRUE and can be masked, but g is out of the target area, so F
Become ALSE. In this way, the target region including the reference pixel can be extracted by expanding the search pixel from the vicinity of the reference pixel.

Another connected area extraction process (step A)
5, A25) is shown in FIG. First, all output mask image data is initialized to FALSE (step B20). One determined pixel position is read (step B21). The input image is searched in the -X direction from the determined pixels to find the pixel that becomes the boundary of the target area (step B
22), and the boundary pixel is set as the scan pixel p (step B23). Next, TRUE is set at the position of the scan pixel in the mask image (step B24). Next, it is determined whether or not the adjacent pixel P1 in the + Y direction of the scan pixel can be masked (step B25), and if maskable, p1 is determined only when the adjacent pixel in the -X direction of p1 cannot be masked. Register as a pixel (step B
26). Next, the adjacent pixel p2 in the −Y direction of the scan pixel
Is maskable (step B27), and if maskable, p2 is registered as a determined pixel (step B28) only when a pixel adjacent to p2 in the -X direction is not maskable.

Next, it is judged whether or not adjacent pixels in the + X direction of the scan pixel can be masked (step B29). If maskable, the scan pixel is incremented in the + X direction (step B30), and the process returns to step B24. If masking is not possible, the processing from step B21 is repeated for the next determined pixel. This is continued until there are no judged pixels.

The state of actual processing will be described with reference to FIG. The reference pixel 63 (pixel indicated by A in the figure) is
It is registered in advance as the first determined pixel position 64. When searching in the −X direction from the first determined pixel position 64, the boundary pixel p is first found. Therefore, p is a scan pixel. After setting the mask data of the position of the scan pixel to TRUE, it is investigated whether or not the p1 pixel on it is maskable. However, since p1 is outside the target area, the process proceeds to the next step, and it is investigated whether or not p2 pixels under the scan pixels can be masked. Since p2 is within the target area, the adjacent pixel in the -X direction of p2 is examined next. Then
Adjacent pixels in the -X direction of p2 are FALSE outside the target area.
Therefore, the condition is met and the pixel is registered as a determined pixel.

Since the adjacent pixel q in the + X direction of the scan pixel p can also be masked, it is understood that the upper and lower pixels are similarly examined and q1 is registered as the determined pixel. When the process proceeds as described above, another boundary pixel r is eventually reached, and the process for one line ends. Thus, FIG.
It can be seen that in the mask determination processing method (1), one determined image is stored for each line, and the processing can be performed at extremely high speed.

Next, expansion / contraction processing (steps A6 and A2)
8) will be described.

The expansion processing is processing for thickening the area by one pixel, and the contraction processing is processing for thinning the area by one pixel. This process is also described in the document [4].

In the present invention, the mask image is TRUE.
Since the input mask image is f (i, j) and the output mask image is g (i, j), it can be expressed as follows. -Expansion: f (i, j) or its 4 vicinity (8 vicinity)
Is TRUE, g (i, j) = TRU
E. Other than that, g (i, j) = FALSE. Contraction: f (i, j) or its 4 neighborhoods (8 neighborhoods)
Is FALSE, g (i, j) = FAL
SE. Other than that, g (i, j) = TRUE Here, 4 neighborhoods refer to 4 adjacent pixels on the left, right, top and bottom of the pixel, and 8 neighborhoods indicate 8 in the top, bottom, left, right and diagonal directions of the pixel.
Two adjacent pixels. In the present invention, expansion and contraction are performed N times to remove fine irregularities and holes in the region.

In the explanation of the operation so far, it has been explained that the operator designates one pixel as the reference pixel, but when the operator designates a plurality of pixels, the above-mentioned action is repeated a plurality of times, The results can be integrated. The manner in which the masks are integrated will be described with reference to FIG. In the input image example 110, the operator tried to extract the target area 116, but at first, only the A area 111 could be extracted. Therefore, the A area 111 is saved, and then the B area 112 is extracted and integrated with the A area 111. In this way, if the E regions 115 and so on are integrated at any time, all the target regions 116 can be extracted.

An example of such processing will be described with reference to FIG. When the area extraction is completed for one reference pixel, the data in the mask image memory is not output, but is transferred to the second mask image memory (step C3). Then, the area extraction result is displayed on the monitor (step C4), and the next instruction from the operator is awaited. When the next reference point is designated by the operator, the area extraction process is performed again, and the result is integrated with the previous result held in the second mask image memory (step C2). If there is an end instruction from the operator, the mask image data is output and the process ends.

[0041]

BEST MODE FOR CARRYING OUT THE INVENTION An image area extracting apparatus according to an embodiment of the present invention will be described below with reference to the drawings. FIG. 1 is a block diagram showing an embodiment of an image area extracting device of the present invention. FIG. 2 is a block diagram showing another embodiment of the image area extraction device of the present invention. FIG. 3 is a block diagram showing an embodiment of pixel feature amount extraction means in the image area extraction device of the present invention.

The first embodiment of the present invention is an image input device 1 such as a scanner or a camera, a monitor 2 for displaying an image,
An input image memory 4 for holding image data, a position designation means 3 for designating a target area, a reference point feature amount storage buffer 6 for storing the feature amount of a reference point, and a reference point for storing the position of the reference point. The position storing buffer 7, the neighboring pixel searching means 8 for calculating the address of the neighboring pixel, the determined pixel position storing buffer 9, the mask image memory 5, the data output device 10 such as a hard disk, and the pixel feature amount are compared. Pixel feature amount comparison means 11 and pixel feature amount extraction means 12
And a CPU 15 for controlling each module.

The second embodiment of the present invention has the pixel feature amount extraction means 12 which is the pixel accumulation extraction means 40 in the first embodiment.

The third embodiment of the present invention is different from the pixel feature amount extracting means in the second embodiment in that a color converting means 4 is further provided.
The pixel feature amount extraction unit 12 having a configuration in which 4 is added is included.

In the fourth embodiment of the present invention, the pixel feature quantity extracting means 12 is constructed by adding a low frequency filtering means 41 to the pixel feature quantity extracting means in the second and third embodiments.
Having.

The fifth embodiment of the present invention replaces the pixel feature amount extraction means 12 of the first embodiment with N (N is 2 or more).
A plurality of pixel feature amount extracting means 21 and different mask feature result determining means 22.

In the sixth embodiment of the present invention, a pixel value extracting means 40 is used instead of the pixel feature quantity extracting means 12 of the first embodiment.
And a plurality of pixel feature amount extracting means 21 including a pixel value extracting means 40 and a second pixel feature amount extracting means 24 having a low frequency filtering means 41, and mask creation. It is composed of the result judging means 22.

The seventh embodiment of the present invention is the first embodiment,
In addition to the components of the second embodiment, the third embodiment, the fourth embodiment, the fifth embodiment, and the sixth embodiment, the mask area expanding means 13 and the mask area contracting means 14 are provided. .

An eighth embodiment of the present invention is the first embodiment,
In addition to the components of the second embodiment, the third embodiment, the fourth embodiment, the fifth embodiment, the sixth embodiment and the seventh embodiment, a second mask image memory 26 and The mask area integrating means 27 is provided.

The operation of the first, second, third and fourth embodiments of the present invention will be described with reference to FIG. 4, FIG. 7 and FIG.

Image data is input from the image input device 1 to the input image memory 4 and displayed on the monitor 2. The image input device 1 is not only an image pickup device such as a scanner or a camera, but also
It is assumed to include a device that acquires images from a database connected by a network. The operator designates a point in the target area to be cut out from the image by the position designation means 3 such as a mouse and a keyboard (step A).
1).

Position information (x) of the designated point (reference pixel)
The coordinates, y coordinate) are first stored in the reference point position storage buffer 7 (step A2). Then, the position information of the reference point is also stored in the determined pixel position storage buffer 9 (step A3).

Next, the pixel feature amount of the reference pixel is extracted by the pixel feature amount extraction means 12, and the output value is put into the reference point feature amount storage buffer 6 (step A4). The method of implementing the pixel feature amount extraction means 12 has already been described in the section of operation. Examples include one that outputs the RGB value of the pixel, one that outputs the hue, saturation, and lightness value, and one that applies a local filter to neighboring pixels.

An example of the pixel feature amount extraction means 12 will be described with reference to FIG. In FIG. 3, inputs are all pixel addresses (pixel positions), and outputs are pixel feature amounts. The pixel feature amount extraction means 30 is a pixel value extraction means 40.
This is the simplest configuration example consisting of only, and returns a pixel value when a pixel address is input.

The pixel feature amount extraction means 31 comprises a pixel value extraction means 40 and a low frequency filtering means 41. The low frequency filtering means 41 applies a local filter such as the low frequency filtering filter 72 of FIG. 11 to the vicinity of the input pixel.

The pixel feature amount extraction means 32 comprises a pixel value extraction means 40 and an edge strength extraction means 42. The edge strength extraction means 42 is the edge strength extraction filter 74 of FIG.
A local filter like the one described above acts on the vicinity of the input pixel.

The pixel feature amount extracting means 33 comprises a pixel value extracting means 40 and a high frequency filtering means 43. The high frequency filtering means 43 causes a local filter such as the high frequency filtering filter 73 of FIG. 11 to act in the vicinity of the input pixel.

The pixel feature amount extraction means 34 comprises a pixel value extraction means 40 and a color conversion means 44. The color conversion means 44 is
The RGB values are HSV (hue (H), saturation (S), lightness (V)) values, or XYZ values, L ^* a ^* b ^* values, L ^*.
It is a module that converts u ^* v ^* values. A method for converting to an HSV value is known by reference [1] and the like. Further, a method of converting into XYZ, L ^* a ^* b ^* , L ^* u ^* v ^* values is also known from literature [3] and the like.

The pixel feature amount extraction means 35 comprises a pixel value extraction means 40, a color conversion means 44, and a low frequency filtering means 41, and outputs the value after color conversion after the low frequency filtering operation as a feature amount. .

Next, the mask image memory 5 is initialized by FALSE (step B1). Next, one determined pixel position is read from the determined pixel position storage buffer 9 (step B2). At this time, the read position information item must be deleted from the determined pixel position storage buffer 9. Therefore, the determined pixel position storage buffer 9 can be mounted as a stack. TRUE is set to the determined pixel position in the mask image memory 5 (step B
3).

The neighboring pixel searching means 8 is used to calculate the addresses of the pixels in the vicinity of the pixels which have been judged as mask candidate pixels (step B4). A pixel feature amount is calculated from the address of the mask candidate pixel by using the pixel feature amount extraction means 12, and the feature amount at that point and the contents of the reference point feature amount storage buffer 6 are compared by the pixel feature amount comparison means 11 to obtain the mask. It is determined whether it is possible (step B6).

As an example of the pixel feature quantity comparison means 11, as already described in the section of the operation, masking is possible if the feature quantity of the pixel is within a certain range from the feature quantity of the reference pixel, and it is not. In that case, there is a means to make masking impossible.

If it is determined that masking is possible, the pixel position is input to the determined pixel position storage buffer 9. The determination process of whether or not the neighboring pixels can be masked is continued until the determined pixel position storage buffer 9 becomes empty. The obtained mask image data is held in the mask image memory 5 and saved in the data output device 10 such as a hard disk.

Further, in the present embodiment, the above step B
Instead of the processing of 1 or less, the processing of step B20 or less can be performed.

First, the mask image memory 5 is initialized by FALSE (step B20). Next, one determined pixel position is read from the determined pixel position storage buffer 9 (step B21). At this time, the read position information item must be deleted from the determined pixel position storage buffer 9. A search is made in the -X direction from the determination pixel position obtained by using the neighboring pixel search means 8 and the pixel feature amount extraction means 12.
A boundary pixel of the target area is found, and the pixel is set as a scan pixel (steps B22 and B23).

TRUE is set at the position of the scan pixel in the mask image memory 5 (step B24). Using the neighboring pixel search means 8, the address of the adjacent pixel p1 in the + Y direction of the scan pixel is calculated, and the pixel feature amount extraction means 12 is calculated.
To extract the pixel feature amount. The feature quantity at that point and the contents of the reference point feature quantity storage buffer 6 are compared by the image feature quantity comparison means 11 to determine whether masking is possible (step B6). If it is determined that masking is possible, it is determined whether or not the adjacent pixel in the -X direction of the adjacent pixel is maskable. If the adjacent pixel in the -X direction is not maskable, p1 is input to the determined pixel position storage buffer 9. To do. Similar processing is performed for the adjacent pixel p2 in the −Y direction of the scan pixel. These processes are continued until the determined pixel position storage buffer 9 becomes empty.

The operation of the fifth and sixth embodiments of the present invention will be described with reference to FIGS. 5, 7 and 8.

This embodiment is the same as the first embodiment in the former part, and uses the first feature amount extraction means 23 as the pixel feature amount extraction means. Once the mask image data can be created, the mask creation result determination means 22 is used to check the contents of the mask image memory. The mask creation result determination means 22 determines whether the region extraction has been completed with a good result, or whether the region extraction has been executed using all the pixel feature amounts designated in advance. If the mask creation result determining means 22 determines that the failure has occurred, the first pixel feature amount extracting means 23 is replaced with the second pixel feature amount extracting means 24, and the process is repeated from step A23. If the mask creation result determining unit 22 determines that the data is successful, the data held in the mask image memory 5 is saved in the data output device 10 such as a hard disk, and the process ends.

If the mask creation result judging means 22 judges that the image data of the next mask can be created, it is judged to be successful by using the third pixel feature quantity extracting means this time. The process is repeated until it is done.

As an example of the mask creation result judging means 22, there is one that checks whether the number of pixels of TRUE is n or more, and succeeds if it is n or more and fails if it is less than n. Further, if all the N pixel feature amount extraction means implemented in the embodiment have been used, it is assumed that all the determinations are successful and the processing is forcibly ended.

The operation of the seventh embodiment of the present invention will be described with reference to FIGS. 4 and 5.

In this embodiment, in the first embodiment and the second embodiment, the mask area expanding means 13 and the mask area contracting means 14 are used to hold the data in the mask image memory 5 immediately before outputting the data. The expansion / contraction process is performed on the existing region data. As an example of processing, an expansion process is first performed m times on a region having mask data of TRUE to remove irregularities and small holes, and then a contraction process is performed m.
Repeat (m is an arbitrary integer of 1 or more).

The operation of the eighth embodiment of the present invention will be described with reference to FIG. In the present embodiment, before outputting the mask image data in the above embodiment, the data is once held in the second mask image memory 26 (step C3). Further, the data in the mask image memory 5 is displayed on the monitor 2 as the area extraction result, and the operator's next instruction is awaited (steps C4 and C5). Then, when the operator instructs to extract the area again, the process returns to the area extraction processing C1 and continues the processing.

Then, the new area extraction result in the mask image memory 5 is integrated with the data held in the second image memory 26 by the mask area integration processing 27 (step C2). As an example of the mask area integration processing 27, for each pixel, if either is TRUE, TRU
A process such as E may be performed. If TRUE = 1,
If FALSE = 0, this process is equivalent to ORing both.

The integrated data is held in the mask image memory 5 and simultaneously transferred to the second mask image memory 26 again. And the result is displayed on the monitor 2 again,
Wait for operator instructions. When the operator issues an end instruction, the contents of the mask image data 5 are output to the data output device 10 and the process ends (step C7).

[0076]

As described above, the image area extraction apparatus of the present invention can only connect areas (areas composed of a set of adjacent pixels having substantially the same pixel feature amount) including the reference point designated by the operator. The effect is that it can be extracted. As a result, even if the target area 102 of FIG. 12 is designated, the problem that the target area 103 is erroneously extracted does not occur.

Further, since the present apparatus processes only the connection area, there is an effect that the processing speed is improved as compared with the conventional apparatus.

Further, in the device using the low frequency filtering filter for the pixel feature amount, there is an effect that it is possible to extract a region constituted by a pattern like the target region 104 in FIG.

[Brief description of the drawings]

FIG. 1 is a block diagram showing an embodiment of an image area extraction device of the present invention.

FIG. 2 is a block diagram showing an embodiment of an image area extraction device of the present invention.

FIG. 3 is a block diagram showing an embodiment of pixel feature amount extraction means in the image area extraction device of the present invention.

FIG. 4 is a flowchart of an image area extraction method of the present invention.

FIG. 5 is a second flowchart of the image area extraction method of the present invention.

FIG. 6 is a third flowchart of the image area extraction method of the present invention.

FIG. 7 is a flowchart of connected region extraction processing in the image region extraction method of the present invention.

FIG. 8 is a second flowchart of the connected area extraction processing in the image area extraction method of the present invention.

FIG. 9 is an explanatory diagram of connected region extraction processing.

FIG. 10 is an explanatory diagram of second connected area extraction processing.

FIG. 11 is an explanatory diagram of a local filter.

FIG. 12 is an example of an input image.

FIG. 13 is an example of an input image.

FIG. 14 is a block diagram showing an embodiment of a conventional image area extraction device.

FIG. 15 is a flowchart of a conventional image area extraction method.

[Explanation of Codes] 1 image input device 2 monitor 3 position designation means 4 input image memory 5 mask image memory 6 reference point feature amount storage buffer 7 reference point position storage buffer 8 neighborhood pixel search means 9 determined pixel storage buffer 10 data output Device 11 Pixel feature amount comparison unit 12 Pixel feature amount extraction unit 13 Mask region expansion unit 14 Mask region contraction unit 15 CPU 21 Multiple pixel feature amount extraction unit 22 Mask creation result determination unit 23 First pixel feature amount extraction unit 24 2 Th pixel feature amount extraction means 25 Nth pixel feature amount extraction means 26 Second mask image memory 27 Mask area integration means 30 Pixel feature amount extraction means 31 Pixel feature amount extraction means 32 Pixel feature amount extraction means 33 Pixel feature amount Extraction means 34 Pixel feature amount extraction means 35 Pixel feature amount extraction means 40 Pixel value extraction Outputting means 41 Low frequency filtering means 42 Edge strength extracting means 43 High frequency filtering means 44 Color conversion means 50 Enlarged image 51 Target area 52 Contour of target area 53 Reference pixel 54 First determined pixel position 55 Second determined pixel position 60 Enlarged Image 61 Target Area 62 Outline of Target Area 63 Reference Pixel 64 First Determined Pixel Position 65 Second Determined Pixel Position 66 Third Determined Pixel Position 70 Local Filter 71 Target Pixel Position 72 Low Frequency Filtering Filter 73 High Frequency Filtering Filter 74 Edge Strength Extraction Filter 100 Input Image Example 101 Target Area 102 Target Area 103 Target Area 104 Target Area 105 1st Color Pixel 106 2nd Color Pixel 110 Input Image Example 111 A Area 112 B Area 113 C Area 114 D Area 115 E area 116 Target area 201 Image input Location 202 Monitor 203 thresholding means 204 position specifying means 205 the input image memory 206 reference pixel location buffer 207 mask image memory 208 output device

Claims (10)

[Claims] 1. A step of designating a reference pixel in a target region to be extracted, one or more different pixel feature amount extraction steps of extracting a feature amount of an arbitrary pixel, a pixel feature amount of a reference pixel and its vicinity. An image area extraction method for extracting a connected area having a uniform pixel feature amount including a reference pixel, the method including a step of comparing with a pixel feature amount. 2. A step of designating a reference pixel in a target region to be extracted, one or more different pixel feature amount extraction steps of extracting a feature amount of an arbitrary pixel, a pixel feature amount of a reference pixel and its vicinity. A method for extracting a region of an image, which comprises a step of comparing with a pixel feature amount and a step of integrating target regions extracted by a plurality of reference pixels. 3. An input image memory for holding input image data, a monitor for displaying the image data and the area extraction result,
There are a position designating unit that designates a target region to be extracted, a reference point feature amount storage buffer that holds a pixel feature amount of a reference point for region extraction, and a reference point position storage buffer that holds a position of a reference point for region extraction. A neighboring pixel search means for searching an address of a pixel adjacent to a pixel, a determined pixel storage buffer for storing a pixel to be masked, a pixel feature amount comparison means for comparing feature amounts of two pixels, and a feature amount of a certain pixel An image area extracting device, comprising: a pixel feature amount extracting means for calculating the pixel extraction amount; and a mask image memory holding an area extraction result. 4. The pixel feature amount extraction means includes a pixel value extraction means for extracting a pixel value.
The image area extraction device described. 5. The image area extraction device according to claim 3, wherein the pixel feature amount extraction means includes pixel value extraction means for extracting pixel values and color conversion means for color conversion. . 6. The image area extraction device according to claim 4, wherein the pixel feature amount extraction means further comprises low frequency filtering means. 7. N (n is 2 or more) different pixel feature amount extraction means and mask creation result determination means for determining an area extracted using one type of pixel feature amount. The image area extraction device according to claim 3, 8. A first pixel feature amount extraction means having a pixel value extraction means for extracting a pixel value in place of the pixel feature amount extraction means, and both the pixel value extraction means and the low frequency filtering means. 4. The image area extraction device according to claim 3, further comprising a second pixel feature amount extraction means and a mask creation result determination means for determining an area extracted using one type of pixel feature amount. . 9. A mask area expanding means for thickening the area by one pixel and a mask area contracting means for thinning the area by one pixel. The image area extraction device described. 10. A second mask image memory for holding a previous area extraction result, and a mask area integrating means for integrating the contents of the mask image memory and the second mask image memory. 9. The image area extraction device according to claim 3, 4, 5, 6, 7 or 8.