JPH08123940A - Method and device for extracting picture area - Google Patents

Abstract

PURPOSE: To provide the picture area extracting device which easily correctly extracts an arbitrary area of a picture and subjects this extracted area to the picture processing like color correction or gradation correction. CONSTITUTION: A second large area in the picture is set roughly to a second area setting part 11, and a first relatively minute area in the second area is set to a first area setting part 9. The average value of picture parameters of picture elements in the first area set to the first area setting part 9 is calculated by a feature parameter calculation part 10, and upper and lower limit thresholds of the picture parameter allowing for a prescribed margin for area extraction are set by the user based on this obtained average value. Only picture elements whose picture parameter values are within the range determined by upper and lower limit threaholds out of picture elements in the second area set to the second area setting part 11 are extracted by an area extracting part 12.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image area extracting apparatus and an image area extracting method for extracting an arbitrary area of an image and performing image processing.

[0002]

2. Description of the Related Art Conventionally, various proposals have been made and carried out as a method for performing image processing by extracting an arbitrary region of an image. For example, as a first conventional example, there is a method of drawing an arbitrary rectangular area or circle with a mouse, extracting an image of only the enclosed area, and performing various kinds of image processing.

Further, as a second conventional example, there is a method of extracting a region while tracing the boundary of the region to be extracted with a mouse and performing various kinds of image processing. In addition, as Conventional Example 3, image brightness, saturation, hue, or chromaticity, R, G, B
There is a method in which an arbitrary image area is extracted by setting an appropriate threshold value for the value of and various kinds of image processing are performed.

[0004]

However, the above-mentioned conventional example 1 has a drawback that a region having a complicated shape cannot be extracted as a rectangle or a circle. Further, the above-mentioned conventional example 2
However, as in the first conventional example, there is a drawback in that it is difficult to extract a region having a complicated shape. Further, in the above-mentioned Third related example 4, there is a drawback that it takes time to set the threshold value and the region to be extracted cannot be correctly extracted in many cases.

Therefore, the present invention has been made in view of the above problems, and it is possible to easily and correctly extract an arbitrary area of an image and perform image processing such as color correction and gradation correction on the extracted area. It is an object of the present invention to provide an image area extracting device that can perform the operation.

[0006]

In order to achieve the above object, an image area extraction device according to a first aspect of the present invention provides a second area that roughly specifies a second area in an electronic imaged image.
Area designating means, first area designating means for designating a relatively small first area within the second area designated by the second area designating means, and first area designated by the first area designating means Calculating means for calculating the average value of the image parameters of the pixels in the inside, and based on the average value of the image parameters obtained by the calculating means, the upper limit of the image parameters in consideration of a predetermined margin for area extraction, and Setting means for setting a lower limit threshold value, and the upper and lower limit threshold values set by the setting means among the pixels in the second area designated by the second area designating means. It is characterized in that only pixels having an image parameter value within the range determined by are extracted.

Further, in the image area extracting apparatus according to the second aspect, the image parameter value is at least one of brightness, luminance, saturation, hue, or chromaticity, which is a parameter characterizing a pixel. It is defined by two.

Furthermore, an image area extracting device according to a third aspect of the invention is an image area extracting device for extracting a part of an electronic imaged image, and a second area which is a rough extraction range of the image is extracted. A second area setting step for setting, a first area setting step for setting a minute first area in the second area set by the second area setting step in order to specify a color serving as an extraction reference, and A calculation and display step of calculating and outputting the average value of the characteristic parameters of the pixels in the first area set by the first area setting step, and the second area based on the average value of the characteristic parameters of the first area Set a margin value for extracting the characteristic region in the, the average value of the characteristic parameter, based on the margin value, of the upper limit value and the lower limit value of the feature parameter serving as a reference of the characteristic region extraction A detection threshold value setting step of setting output threshold values, a selection input step of selecting and inputting an extraction parameter serving as a key for extracting a characteristic region in the second region, the detection threshold value and the extraction parameter, Area extraction step for extracting the characteristic area in the second area based on the above.

[0009]

In the image area extracting apparatus of the present invention, the second area is roughly specified by the second area specifying means in the electronic imaged image, and the second area is specified by the second area specifying means. A relatively small first area in the area is designated by the first area designating means. Further, the average value of the video parameters of the pixels in the first area designated by the first area designating means is calculated by the calculating means, and the area extraction is performed based on the average value of the video parameters obtained by the calculating means. The upper and lower thresholds of the video parameters are set by the setting means in consideration of a predetermined margin. Then, among the pixels in the second area designated by the second area designating means, pixels having an image parameter value within a range determined by the upper and lower threshold values set by the setting means. Only is extracted.

[0010]

Embodiments of the present invention will be described below with reference to the drawings. FIG. 1 is a block diagram showing the configuration of an image area extracting apparatus according to an embodiment of the present invention.

In this image area extracting apparatus, image data is input to a workstation (hereinafter referred to as WS) 1 which executes desired image processing on digital image data and controls each connected part. A scanner 2 for converting into digital data, a mouse 3 and a keyboard 4 for inputting characteristic parameters for image area extraction and specifying an image area, a characteristic parameter for displaying an image and extracting an image area, etc. A monitor television 5 for displaying, a printer 6 for outputting a display image after execution of image processing, and an external storage device 7 for storing digital image data and the like for writing and reading them with the WS 1 are respectively connected. .

FIG. 2 is a block diagram schematically showing the internal structure of the WS1. In the image memory 8 storing digital image data inside the WS 1, in order to calculate characteristic parameters such as hue (H), saturation (S), and lightness (B) which are references in the entire image. Is connected to a first area setting unit 9, and the first area setting unit 9 further calculates a characteristic parameter calculation unit that calculates the characteristic parameter from the image data set by the first area setting unit 9. 10 are connected.

The image memory 8 stores the second image data.
A second area setting unit 11 for setting an area is connected, and the second area setting unit 11 is further connected to the second area setting unit 11.
A region extracting unit 1 for extracting a desired region from the second region of the image set by
2 are connected.

In practice, since the functions of the above blocks are executed by software, not all the hardware configurations described above actually exist. FIG. 3 is a flow chart showing the operation of the image area extracting apparatus according to the embodiment of the present invention.
The operation of this image area extracting apparatus will be described based on the display examples of the monitor television 5 at the time of the operations shown in FIGS.

As shown in FIG. 4A, the image input by the scanner 2 or the like is displayed on the monitor television 5.
First, the button of the mouse 3 is clicked to specify the upper left corner of the rectangle to be set. Then, when you move mouse 3,
The mouse index moves so as to follow this, and a rectangle whose diagonal corner is the upper left corner and the current position of the mouse index is drawn. Therefore, the button on the mouse 3 is clicked to specify the lower right corner so as to surround the area to be extracted. The second area 21 is set by the above-described known input method (step S1). The input method as described above is performed when the switch 22 shown in FIG. 4C is selected.

Here, the switches 22 to 22 shown in FIG.
Reference numeral 24 is a switch for selecting an input form when setting the second area 21. As described above, the switch 22 sets the area by the mouse 3 in a rectangular shape, the switch 23 sets the area by the mouse 3 in a circle, and the switch 24 sequentially moves the mouse 3 to move an arbitrary image in the image. Select a point to make a closed area and set the area. The switch 25 will be described later. Each of the switches 22 to 25 is selected by moving the mouse index on the display area and clicking the button of the mouse 3.

Next, when the switch 25 shown in FIG. 4B is selected, the switches 22 and 25 shown in FIG. 5C are selected.
Is displayed, and the window shown in FIG. 5B is displayed.

Next, the rectangular area shown in FIG. 5A, which is set by the same procedure as when setting the second area 21, is the same as the rectangular area shown in FIG.
By moving the mouse index to the panel switch "STD_COL" shown in (b) and clicking the mouse 3, it is registered as the first area 26 (step S2).

Next, the average value (R bar, G bar, B bar) of each component of red (R), green (G), and blue (B) of each pixel belonging to the first area 26 is calculated, and this is calculated. The standard color (R
Bar, G bar, B bar) 27 (step S3).

Next, as shown in FIG. 6A, the reference color 2
7 is displayed on the window so that it can be visually confirmed (step S4). Next, the hue (H) of the reference color 27,
The saturation (S) and the brightness (B) are obtained, and as shown in FIG. 6A, the values of the hue (H), the saturation (S), and the brightness (B) are displayed in the display field 28 on the left side of the window. (Step S5).

Next, the hue of the reference color 27 is H0 and the saturation is S
0, the brightness is B0, and with these values as a reference, the lower limit threshold THL and the upper limit threshold THH (THL ≦ TH
H), the lower threshold TSL and the upper threshold T of the saturation
SH (TSL ≦ TSH) and the lower limit threshold value TB of brightness
L and the upper threshold TBH (TBL ≦ TBH) are set respectively. HUE, SATUR, BR shown in FIG.
IT is a slider for setting an upper threshold value and a lower threshold value of hue, saturation, and brightness, respectively. The index (∇) is set by moving the mouse index near the index (∇) and clicking the mouse 3 to move the index (∇) to the position of the mouse index. The set upper and lower threshold values are displayed in the display field 29 on the right side of the window (step S6).

That is, in this embodiment, among the pixels in the second area 21, the values of the hue (H), the saturation (S), and the brightness (B) within the range of the upper limit threshold and the lower limit threshold. Only those pixels with are extracted. Therefore, the difference DH = H−H0, between the (H, S, B) of the pixel where the mouse index is located in the second area 21 and the (H0, S0, B0) of the reference color.
If DS = S-S0 and DB = B-B0 can be visually confirmed, it becomes easy to set the upper limit threshold and the lower limit threshold. For this reason, as shown in FIG. 6A, the X for the pixel at the position of the mouse index on the image is displayed at the lower left of the window.
The coordinates (X) and Y coordinates (Y) are displayed in the display column 30, and the above (DH, DS, DB) are displayed in the display column 31.

Here, depending on the image, there are cases where a desired region can be extracted only by the hue (H). However, a desired area may not be correctly extracted unless AND conditions for hue (H), saturation (S), and brightness (B) are created. That is, when the area is extracted only by the hue (H), the hue (H) of each pixel of the second area 21 is extracted only the pixel satisfying the condition of THL ≦ H ≦ THH. Further, when extracting a region by hue (H) and brightness (B), only pixels satisfying THL ≦ H ≦ THH and TBL ≦ B ≦ TBH are extracted. As described above, it is necessary to determine which combination of hue (H), saturation (S), and brightness (B) to extract a pixel, and the extraction condition. Therefore, the lower panel switch "H" in FIG.
The mouse index is moved to the panel switch of "S" or "B" to be selected, and the button of the mouse 3 is clicked to select them (step S7). If the panel switch is clicked an even number of times, the selection will be canceled. Further, this example shows a case where pixels are extracted under two AND conditions of hue (H) and brightness (B).

Next, when the panel switch "OK" in the lower part of the window shown in FIG. 6A is clicked, the respective pixels of the second area 21 are set in step S6. It is calculated whether or not it is within the range between the upper limit threshold and the lower limit threshold. Then, only pixels that meet the above extraction conditions are extracted (step S8).

Next, as shown in FIG. 6C, the extracted area is displayed in the window (step S9). In reality, the extracted region is displayed in green, but in order to make it easy to understand, it is indicated by hatching in FIG. 6C. In this example of extraction, only the skin color, which is the skin part, was intended to be extracted, but part of the clothes, which is the other part, was also extracted.
This is because the hue (H) and the brightness (B) of clothes are close to the skin color and cannot be separated from the skin color well.

In order to solve this problem, in setting the second area, the mouse 3 is sequentially moved to the area setting, an arbitrary point of the image is designated to form a closed area, and the area is set in an arbitrary shape. Mode, that is, Fig. 4
The switch 24 shown in (b) is selected. Then, the second area 32 is set so as not to include clothes, and the above step S
FIG. 7 shows that the skin color part is extracted by performing the same calculation as in FIG.
It is the display shown in (c). It can be seen that the skin color part has been accurately extracted.

Next, it is judged whether or not there is a problem in the extracted area (step S10), and if there is no problem, desired image processing is performed on the extracted area (step S1).
1). On the other hand, if there is a problem in the extracted area, the above operation is repeated.

FIG. 8 shows the image processing in step S11. This image processing is applied to R, G, B in the extracted area.
Color conversion is performed. By moving the index (Δ) with reference to the slider 0 point shown in FIG. 8D, the ratio of each component of R, G, B is changed to perform color conversion.
FIG. 8B is a window that displays an image after color conversion. After that, this processing ends. The display image after the image processing is output by the printer 6 or stored in the external storage device 7.

In this embodiment, hue, saturation and lightness are used as the characteristic parameters, but the present invention is not limited to this, and chromaticity and R, G and B brightness may be used.
Further, in the present embodiment, an example in which the mouse 3 is used for inputting, setting, and selecting is shown, but this is not limited to the mouse 3, and the keyboard 4 or other input means may be used.

As described above, according to this embodiment,
Since a desired area of the image can be accurately extracted, it is convenient not only to perform image processing such as color conversion and gradation conversion on the extracted area, but also to cut out or combine the images.

If only the method of setting an area in an arbitrary shape is not used and the calculation in step S8 is not performed, the boundary becomes unnatural even if an effort is made to extract only the skin color portion. There is a drawback that it often happens. However, in this embodiment, there is no such unnaturalness.

According to the above embodiment of the present invention, the following configuration can be obtained. (1) Calculation means for calculating the value of at least one characteristic parameter representing the characteristics of the image, setting means for setting the upper or lower threshold value of the characteristic parameter based on the characteristic parameter value, and each of the images An image area extracting apparatus comprising: an extracting unit that extracts only an area in which the value of the characteristic parameter of the pixel has a predetermined value according to the threshold value. (2) Computation means for computing a characteristic parameter associated with the first area of the image, setting means for setting an upper or lower threshold value of the characteristic parameter based on the characteristic parameter value, and each area of the image An image area extracting device for extracting an area only from a pixel in which the characteristic parameter value of the pixel has a predetermined value according to the threshold value. (3) Setting means for setting different first and second areas in the image, calculating means for calculating characteristic parameters associated with the first area, and the characteristic parameters based on the characteristic parameter values. Setting means for setting an upper limit or lower limit threshold value, and extracting means for extracting a region of only pixels having the characteristic parameter value of each pixel in the second region having a predetermined value according to the threshold value. An image area extraction device characterized by being provided. (4) The image region extraction device according to (1) to (3), wherein the characteristic parameter is one of hue, saturation, and lightness, or a combination thereof. The parameter is one of chromaticity and lightness, or a combination of the two, and the image region extracting apparatus according to (1) to (3) above. (6) Roughly the second among the electronic images.
A second area designating step of designating an area, a first area designating step of designating a relatively small first area within the second area designated by the second area designating step, and a first area designating step A calculation step of calculating an average value of video parameters of pixels in the designated first region,
A setting step of setting upper and lower thresholds of the video parameter in consideration of a predetermined margin for area extraction based on the average value of the video parameter obtained by the calculation step; and the second area. Of the pixels in the second region designated in the designating step, region extraction for extracting only pixels having a video parameter value within the range determined by the upper and lower threshold values set in the setting step. An image area extraction method comprising:

[0033]

As described above, according to the present invention, it is possible to easily and correctly extract an arbitrary area of an image and perform image processing such as color correction and gradation correction on the extracted area. An image area extraction device can be provided.

[Brief description of drawings]

FIG. 1 is a block diagram showing a configuration of an image area extraction device according to an embodiment.

FIG. 2 is a block diagram schematically showing an internal configuration of WS1 of the embodiment.

FIG. 3 is a flowchart showing the operation of the image area extraction device of the embodiment.

FIG. 4 is a display example at the time of setting the second area in the image area extracting apparatus of the embodiment.

FIG. 5 is a display example when the first area is set in the image area extracting apparatus of the embodiment.

FIG. 6 is a display example at the time of setting a threshold value and extracting an area in the image area extracting apparatus of the embodiment.

FIG. 7 is a display example when setting another second area, extracting an area, and the like in the image area extracting apparatus of the embodiment.

FIG. 8 is a display example at the time of image processing in the image area extraction device of the embodiment.

[Explanation of symbols]

1 ... work station (WS), 2 ... scanner, 3 ...
Mouse, 4 ... Keyboard, 5 ... Monitor TV, 6 ... Printer, 7 ... External storage device, 8 ... Image memory, 9 ... First area setting section, 10 ... Feature parameter calculation section, 11 ... Second area setting section, 12 ... Region extraction unit, 21 ... Second region, 22,
23, 24, 25 ... Switch, 26 ... First area, 27 ...
Reference color, 28, 29, 30, 31 ... Display column, 32 ... Second
region.

─────────────────────────────────────────────────── ─── Continuation of the front page (51) Int.Cl. ⁶ Identification code Office reference number FI technical display location 9365-5H G06F 15/62 322 B 9061-5H 15/70 330 Z

Claims (3)

[Claims] 1. A second area designating means for roughly designating a second area in an electronic image, and a relatively small first area within the second area designated by the second area designating means. First area designating means for designating one area, computing means for computing an average value of video parameters of pixels in the first area designated by the first area designating means, and the video image obtained by the computing means. Setting means for setting the upper and lower thresholds of the video parameter in consideration of a predetermined margin for area extraction based on the average value of the parameters, and the setting means is specified by the second area specifying means. Among the pixels in the second area, only the pixels having the image parameter value within the range determined by the upper and lower thresholds set by the setting means are extracted. Detection device. 2. The image parameter value is defined by at least one of lightness, luminance, saturation, hue, or chromaticity, which is a parameter that characterizes a pixel. The image area extraction device according to 1. 3. An image area extracting device for extracting a part of an electronic imaged image, wherein a second area setting step of setting a second area which is a rough extraction range of the image, and a color serving as an extraction reference. A first area setting step of setting a minute first area in the second area set by the second area setting step, and a first area set by the first area setting step. A calculation and display step of calculating and outputting the average value of the characteristic parameters of the pixels and setting a margin value for extracting the characteristic area in the second area based on the average value of the characteristic parameters of the first area. , A detection threshold value that determines the detection threshold values of the upper limit value and the lower limit value of the feature parameter that is the reference of feature region extraction, based on the average value of the feature parameter and the margin value. A constant step, a selection input step of selectively inputting the extracted parameters that are key for extracting a feature region of the second region, on the basis of the above detection threshold and the extraction parameters,
A region extraction step of extracting a feature region in the second region, the image region extraction method comprising: