JP2000271107A - Device, system and method for processing image, and storage medium - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an image processing device capable of abstracting the irradiation range more accurately by taking the symmetricalness of the irradiation range into consideration. SOLUTION: Abstracting means 112b and 112c abstract candidates for prescribed ranges (irradiation ranges) from images (radiation images) by their respective abstraction methods, and add reliability to them. If the reliability of an arbitrary end of the irradiation range abstracted by an arbitrary abstraction method is higher than a prescribed value, with the reliability of the end opposite to the arbitrary end being lower than the prescribed value, the coordinate of the opposite end is determined based on the coordinate with the reliability of the opposite end abstracted by another abstraction method being higher than the prescribed value.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to, for example, extracting a radiation irradiation area from a photographed image in order to perform image processing on a photographed image obtained by narrowing an irradiation area in radiography (such as X-ray). In addition, the present invention relates to a technique used in an apparatus or a system configured to determine a parameter used for image processing from the irradiation area, and particularly to an image processing apparatus that extracts the irradiation area in consideration of the symmetry of the irradiation area, The present invention relates to a computer-readable storage medium storing a system, an image processing method, and processing steps for executing the system.

[0002]

2. Description of the Related Art In recent years, with the advance of digital technology, for example, a photographed image obtained by photographing with radiation such as X-rays has been digitized, and image processing (gradation conversion processing or the like) has been performed on the digital image. Display on a display device (CRT or the like) or output on a film is performed.

In radiography, "irradiation area squeezing" which only irradiates only necessary areas is performed for humanitarian reasons and to prevent scattering from unnecessary areas and prevent a decrease in contrast. It is common to be done.
In addition, when performing image processing on a captured image, it is common to determine parameters used for image processing from the distribution of density values of the captured image, and to perform image processing based on the parameters (image processing parameters). It is.

However, when the irradiation area is not limited from the photographed image, information on an area outside the necessary area (region of interest), that is, unnecessary information, is also used for determining image processing parameters. There is a problem that processing cannot be performed. Therefore, it is necessary to extract an irradiation area from a captured image and determine an image processing parameter from information on only the irradiation area, that is, information on a region of interest.

[0005]

By the way, FIG.
It shows a captured image including the irradiation area as described above. In FIG. 10, “A” indicates an imaging region of the sensor where the radiation light transmitted through the subject is imaged,
“B” indicates the irradiation area, “D” indicates the center of the imaging area of the sensor, and “E” and “F” indicate the left and right ends of the irradiation area B. Therefore, generally, the irradiation area is narrowed down. Is performed vertically and horizontally around the center point D of the imaging region A. As a result, the ends E and F of the irradiation region B due to the irradiation region squeezing are symmetric with respect to the center point D.

However, in the conventional irradiation area extraction method, since the above-described symmetry of the irradiation area is not taken into account, for example, as shown in FIG. Etc.), there is a problem that when the subject C having a poor transmittance is placed, the extraction accuracy of the left end of the irradiation area is reduced.

Therefore, the present invention has been made to eliminate the above-mentioned drawbacks. Since the irradiation area can always be accurately extracted from a photographed image, optimal image processing can be performed. It is an object of the present invention to provide an image processing apparatus, an image processing system, an image processing method, and a storage medium in which processing steps for executing the same are readable by a computer.

[0008]

For such a purpose,
An image processing apparatus having a function of extracting a predetermined area from an image, comprising: an extraction unit that extracts the predetermined area based on the symmetry of the predetermined area.

[0009] The second invention is the above-mentioned first invention, wherein:
The image includes an image obtained by radiography, and the predetermined region includes a radiation irradiation region.

In a third aspect, in the first aspect,
The extraction means has a function of extracting the predetermined area by a plurality of extraction methods, and adds reliability to the extraction results obtained by the extraction methods.

[0011] In a fourth aspect based on the third aspect,
The extraction means determines an extraction result selected from the extraction results of the plurality of extraction methods as a final predetermined area based on a result of the comparison between the reliability and a predetermined value. .

[0012] In a fifth aspect based on the fourth aspect,
When the reliability of the extraction result by an arbitrary extraction method is equal to or less than the predetermined value, the extraction means determines the extraction result by another extraction method as a final predetermined area.

[0013] In a sixth aspect based on the third aspect,
The extraction means adds a reliability to each end constituting each predetermined region extracted by the plurality of extraction methods,
Based on the result of comparing the reliability of those ends with a predetermined value,
It is characterized in that each end constituting the final predetermined area is determined.

According to a seventh aspect, in the sixth aspect,
The above-mentioned extracting means is such that the reliability of an arbitrary end of the predetermined area obtained by the arbitrary extraction method is equal to or more than a predetermined value, and the reliability of the opposite end located at a position facing the arbitrary end is a predetermined value. In the following case, the coordinates of the opposite end are determined based on the coordinates of the opposite end to which the reliability equal to or more than a predetermined value is added among the opposite ends obtained by another extraction method. I do.

According to an eighth aspect based on the first aspect,
The extracting means adds reliability to the extraction result of each end of the predetermined area, and determines each end of the predetermined area based on a comparison result between the reliability of each end and a predetermined value. It is characterized by doing.

According to a ninth aspect, in the eighth aspect,
The extracting means may include, when the reliability of the arbitrary end is equal to or more than the predetermined value and the reliability of the opposing end located at a position facing the arbitrary end is equal to or less than the predetermined value, Are determined based on the coordinates of the arbitrary end.

A tenth aspect of the present invention is an image processing system in which a plurality of devices are communicably connected to each other, wherein at least one of the plurality of devices is connected to any one of the first to third embodiments.
9. It has the function of the image processing apparatus according to any one of 9.

An eleventh invention is an image processing method for inputting an image generated on the basis of a set center portion and extracting a predetermined region having symmetry from the image. The method is characterized by including a step of extracting the predetermined region based on the image characteristics of the image, because the left end is symmetrical based on the set center portion.

A twelfth invention is characterized in that, in the eleventh invention, the image is an image obtained by radiography, and the central portion is set based on an irradiation photograph.

In a thirteenth aspect based on the eleventh aspect, the extraction of the predetermined area is performed based on an edge portion in the image, and whether a right end and a left end obtained based on the edge portion are correct is determined. Is characterized by using the above symmetry to study

According to a fourteenth aspect, there is provided an image processing method having a plurality of different irradiation field recognition methods, wherein an image obtained by radiography is input, and the image is irradiated using the irradiation field recognition method. Performing field recognition, evaluating the irradiation field recognition result, and detecting an irradiation field in the image based on the evaluation result and the irradiation field recognition result.

According to a fifteenth aspect of the present invention, a computer readable storage medium stores the processing steps of the image processing method according to any one of claims 11 to 14.

[0023]

Embodiments of the present invention will be described below with reference to the drawings.

The present invention is applied to, for example, an X-ray imaging apparatus 100 as shown in FIG. This X-ray imaging apparatus 100
Has an X-ray imaging function while performing “irradiation area narrowing”. As shown in FIG. 1, an X-ray generation circuit 101 for generating X-rays and an X-ray
A two-dimensional X-ray sensor 104 on which line light is imaged,
A data collection circuit 105 for collecting captured images output from the line sensor 104, a preprocessing circuit 106 for performing preprocessing on the captured images collected by the data collection circuit 105, and a preprocessing performed by the preprocessing circuit 106 Image taken (original image)
And a main memory 109 for storing various information such as information and a processing program for executing various processing, and an operation panel 11 for giving instructions and various settings to the apparatus for executing X-ray imaging and the like.
0, an irradiation area processing circuit 112 for executing processing for extracting an irradiation area from a captured image (original image) subjected to preprocessing by the preprocessing circuit 106, and an irradiation area processing circuit 112
An image processing circuit 114 that performs image processing on a captured image (original image) that has been pre-processed by the pre-processing circuit 106 based on the processing result in step 1, and a captured image that has been subjected to image processing by the image processing circuit 114 And the like, and a CPU 108 for controlling the operation of the entire apparatus. The data collection circuit 105, the preprocessing circuit 106, the irradiation area processing circuit 112, the image processing circuit 114, the CPU 108, the main memory 109, operation panel 110, image display 111
Are connected to the CPU bus 115 so that they can exchange data with each other.

The irradiation area processing circuit 112 extracts the irradiation area in consideration of the symmetry of the irradiation area. The configuration of the irradiation region processing circuit 112 is the most characteristic configuration in this embodiment. For this reason, the irradiation area processing circuit 112 determines whether or not the captured image (original image) subjected to the pre-processing by the pre-processing circuit 106 has an image area which has been subjected to the irradiation processing. And a first irradiation area extraction circuit for extracting an irradiation area from the entire projection of the photographed image (original image) subjected to the pre-processing by the pre-processing circuit 106 based on the result of the judgment by the irradiation aperture presence / absence judgment circuit 112a. 112b and the final part from the end of the irradiation area of a plurality of lines (lines) of the photographed image (original image) subjected to the pre-processing by the pre-processing circuit 106 based on the determination result of the irradiation squeezing presence / absence determination circuit 112a. A second irradiation area extraction circuit 112c for determining the end and calculating the reliability of the end, an irradiation aperture determination circuit 112a, and a first irradiation area extraction circuit 1
12b, and a determination circuit 112d for determining and extracting the final irradiation area from the processing result of the second irradiation area extraction circuit 112c.

Therefore, the X-ray imaging apparatus 100 as described above
First, in the main memory 109, the CPU 10
The data and processing programs required for executing various processes in step 8 are stored in advance, and include a work memory for the CPU 108 to work with. Main memory 109
Here, for example, a processing program according to the flowcharts of FIGS.
Therefore, the CPU 108 reads out the above-described processing program and the like from the main memory 109 and executes the same, thereby controlling the operation of the entire apparatus as described below in accordance with the operation from the operation panel 110.

[Main processing: see FIG. 2]

Step S200: First, the X-ray generation circuit 1
Numeral 01 radiates the X-ray beam 102 to the inspection object 103. The X-ray beam 102 emitted from the X-ray generation circuit 101 passes through the subject 103 while attenuating, reaches the two-dimensional X-ray sensor 104, and is output as an X-ray image by the two-dimensional X-ray sensor 104. Is done. here,
The X-ray image output from the two-dimensional X-ray sensor 104 is, for example, a human body image. Next, the data collection circuit 105
Converts the X-ray image output from the two-dimensional X-ray sensor 104 into an electric signal and supplies it to the pre-processing circuit 106. The preprocessing circuit 106 performs preprocessing such as offset correction processing and gain correction processing on the signal (X-ray image signal) from the data collection circuit 105. This preprocessing circuit 10
The X-ray image signal pre-processed in 6 is used as an original image as C
Under the control of the PU 108, via the CPU bus 115,
The data is transferred to the main memory 109 and the irradiation area processing circuit 112, respectively. The irradiation area processing circuit 112 extracts an irradiation area from the transferred original image (target image) by executing processing in steps S201 to S204 described in detail below.

Step S205: Image processing circuit 114
Determines an image processing parameter used when performing image processing on a target image from the irradiation area extracted by the irradiation area processing circuit 112, and performs the image processing (gradation conversion processing or the like) using the parameter. . The target image processed by the image processing circuit 114 is displayed on the image display 111 or output on a film.

[Irradiation aperture determination processing (step S2)
01): See FIG. 3] Irradiation aperture determination circuit 112a
Is determined using an arbitrary determination method (for example, Japanese Patent Application No.
39102), whether or not the target image has an image area in which the irradiation area is narrowed down (hereinafter, a captured image in which the image area in which the irradiation area is narrowed down is referred to as an “image with irradiation area”) And an image that is not so is referred to as an "image without irradiation"). As an example of the determination method here, the following method is used.

Step S301: First, the maximum value of each pixel in the entire area of the target image is calculated. Specifically, for example, a cumulative histogram of all pixel values is created, and a predetermined point (upper 5% point or the like) is set as a maximum value. Alternatively, all pixel values are sorted, and a predetermined point (upper 5% point or the like) is set as a maximum value.

Steps S302 and S303: When determining whether or not to irradiate the left portion of the target image, next, as a characteristic value, a pixel value of a fixed ratio of the maximum value calculated in step S301 (for example, the maximum value A pixel value of 90% or more is calculated (step S302), and the pixel value of the left image end portion of the target image (for example, in the case of an image size of 168 × 168 pixels, “0” to “5” columns) Is calculated at the pixel portion of the image.

Step S304: and step S3
It is determined whether or not the appearance frequency calculated in step 03 is greater than a certain value Th1. If it is larger, it is determined that there is no left-side irradiation, and if not, it is determined that there is left-side irradiation.

As described above, it is determined whether or not the left portion of the target image has been irradiated, and the right, upper and lower portions are similarly determined as to whether or not there is the irradiated portion.

[First Irradiation Area Extraction Processing (Step S
202): See FIG. 4] First irradiation area extraction circuit 112b
Extracts the end of the irradiation area as follows.

Step S401: First, the projection fh (x) of the entire target image is set to the vertical length Lv of the target image,
With horizontal Lh and pixel data f (x, y),

[0037]

(Equation 1)

It is created by using the following equation (1).

Step S402: Next, step S30
The projection fh (x) created in 1 is converted to a constant d
Hold 2 (for example, 5mm)

[0040]

(Equation 2)

Smoothing is performed according to the following equations (2) to (4).

Step S403: Next, step S40
From the smoothing result f2 (x) at S2, the primary difference value S1
(X) with a difference distance d3 (for example, 7 mm)

[0043]

(Equation 3)

The calculation is performed using the following equation (5).

Step S404: Next, step S40
From the primary difference value S1 (x) calculated in step 3, the secondary difference value S2 (x) is

[0046]

(Equation 4)

Calculated using the following equation (6).

Step S405: The left and right ends El1 and Er1 of the irradiation area have the primary difference value S1 (x) calculated in step S403 and the secondary difference value S2 (x) calculated in step S404. ,

[0049]

(Equation 5)

The calculation is performed using the following equations (7) and (8).

[Extraction Process of Second Irradiation Area (Step S
203): See FIG. 5] Second irradiation area extraction circuit 112c
Extracts the end of the irradiation area as follows.

Step S500: First, the maximum value of each pixel in the entire area of the target image is calculated. Specifically, for example, a cumulative histogram of all pixel values is created, and a predetermined point (upper 5% point or the like) is set as a maximum value. Alternatively, all pixel values are sorted, and a predetermined point (upper 5% point or the like) is set as a maximum value. Then, a value obtained by multiplying the calculated maximum value by a constant (for example, 0.8) is set as the threshold Th2.

Step S502: Next, the target image 300
The projection of each area (hereinafter, referred to as a “projection area”) obtained by equally dividing the length Ly in the Y-axis direction by 40 at the distance d1 is calculated. For example, the projection Fn (x) of the n-th projection area has a pixel value f (x, y),

[0054]

(Equation 6)

The calculation is performed using the following equation (9).

Step S503: Next, the smoothing circuit 11
3c smoothes the one-dimensional row projection calculated in step S502 for each projection area. For example, the projection Fn (x) of the n-th projection area has a constant d2 (for example, 4 mm),

[0057]

(Equation 7)

Smoothing is performed using the following equations (10) and (11). "D2" in these equations (10) and (11)
And “h (x)” are represented by the above-described equation (4).

Step S504: Next, step S50
A primary difference value is obtained from the smoothing result for each projection area in step 3. For example, a primary difference value Sn (x) is obtained from the smoothed result F2n (x) of the n-th projection area.
With a difference distance d3 (for example, 7 mm)

[0060]

(Equation 8)

The calculation is performed using the following equation (12).

Step S505: Next, step S50
A secondary difference value is calculated from the primary difference value for each projection area calculated in step 4. For example, from the primary difference value Sn (x) of the n-th projection area to the secondary difference value SS
n (x)

[0063]

(Equation 9)

The calculation is performed using the following equation (13).

Step S506: Next, step S50
From the primary difference value calculated in step 4 and the next difference value calculated in step S505, a candidate point of the left end point of the irradiation area is calculated for each projection area. For example, a candidate point Eln at the left end point of the irradiation area of the n-th projection area
With the primary difference value Sn (x) and the secondary difference value SSn (x)
Has the length Lx of the target image in the X-axis direction,

[0066]

(Equation 10)

The calculation is performed using the following equations (14) and (15). Thereby, candidate points El of the left and right end points of the irradiation area are obtained.
As n and Ern, the coordinates where the secondary difference value SSn (x) is the minimum value in the positive and negative regions of the primary difference value Sn (x) are calculated.

Step S507: and step S5
For the candidate point of the end point of the irradiation area for each projection area calculated in 06, a determination is made using the threshold value Th2 calculated in step 500. For example, candidate points Eln, left and right end points of the irradiation area of the n-th projection area
About Ern,

[0069]

[Equation 11]

From the equations (16) and (17), the projection value Fn (E) of the coordinates of the candidate points Eln and Ern is obtained.
ln) is determined to be greater than or equal to a threshold Th2. Then, only the candidate points that satisfy the conditions of Expressions (16) and (17) are set as the candidate points on the left and right ends of the irradiation area of the target projection area. Thereby, for example, when the projection values Fn (Eln) and Fn (Ern) of the coordinates of the candidate points Eln and Ern at the left and right end points of the n-th projection area are equal to or larger than the threshold Th2, the candidate points Eln and Er
n is stored as the left end point candidate point of the irradiation area of the n-th projection area in the main memory 109.

Step S508: Steps S502 to S507 are performed on all the projection areas 1 to 40.
Is determined. If the result of this determination is that processing has not yet been completed, processing returns to step S502, and the above-described processing of steps S502 to S507 is executed for the next (n + 1) th projection area. Then, after completing the processing for all the projection areas, the process proceeds to the next step S509.

Step S509: After the processing for all of the projection areas 1 to 40 is completed, the overlap Nl (x) and Nr (x) of the candidate points Eln and Ern at the left and right ends of the respective projection areas are set to a constant d4 (for example, 1
0mm)

[0073]

(Equation 12)

The calculation is performed using the following equations (18) and (19). Then, the candidate points E at the left and right ends of the final irradiation area
l2, Er2 having the overlaps Nl (x) and Nr (x) calculated by the equations (18) and (19),

[0075]

(Equation 13)

The calculation is performed using the following equations (20) and (21).

Step S510: Also, assuming that the total number of candidate points at the left and right ends is Nl, Nr, the equations (20) and (21)
Final candidate points El2 and Er at the left and right ends calculated by
2 reliability Cl, Cr,

[0078]

[Equation 14]

The calculation is performed using the following equations (21) and (22).

Steps S511 to S516: It is determined whether or not the reliability Cl and Cr of the final candidate points El2 and Er2 at the left and right ends calculated in step S510 are each larger than a predetermined threshold Th3. If the reliability Cl is greater than the threshold Th3, the flag flg21 is set to "
1 is set, otherwise, “0” is set, and if the reliability Cr is larger than the threshold Th3, “1” is set in the flag flg2r, otherwise, “0” is set. set.

As described above, the left and right ends of the irradiation area are calculated, and the upper and lower ends are similarly calculated.

[Final Determination of Irradiation End (Step S20)
4): See FIG. 6] The determination circuit 112e finally determines the end of the irradiation area as follows. For the sake of simplicity, the determination of the left and right ends of the irradiation area will be described here. The processing for the upper and lower ends is the same as the process for determining the left and right ends, so the details are omitted.

Step S601: First, it is determined whether or not the result of determination by the irradiation / non-exposure circuit 112b indicates that irradiation is not performed at both the left and right ends of the target image.

Step S604: If the result of determination in step S601 is "no irradiation at both the left and right ends of the target image", the final left and right ends El,
Er is set to El = 0 and Er = Lh, respectively. That is, the left and right end portions are determined as the left and right end portions of the imaging region of the sensor.

Steps S602, S603, S605-
S607: If the result of determination in step S601 is not "no irradiation at both the left and right ends of the target image", it is determined whether or not there is irradiation at both the left and right ends of the target image (step S602) As a result, if both the left and right ends are present, a “both ends squeezing process” described later is executed (step S605). On the other hand, if the right and left ends are not present, it is determined whether or not the left end of the target image is irradiated with the squeeze (step S60).
3) As a result, if there is only the left end, the “left end squeezing process” described later is executed (step S60).
6) If not, the “right end squeezing process” described later is executed (step S607). In the processing in steps S605 to S607, the flag flg set in steps S511 to S516 of the above-described [second irradiation area extraction processing (step S203): see FIG. 5] is referred to.

[Double-end squeezing process (step S60)
5): See FIG. 7]

Step S701: First, flgl2 = 1
And whether or not f1gr2 = 1, that is, the reliability Cl of the candidate point El2 at the left end of the irradiation area is greater than the threshold Th3, and the reliability C2 of the candidate point Er2 at the right end of the irradiation area is greater than the threshold Th3. It is determined whether it is larger.

Step S702: As a result of the determination in step S701, candidate points El2 and Er at the left and right ends of the irradiation area are obtained.
2 are both greater than the threshold Th3, the final left and right end portions El and Er are respectively set to the candidate points E and
12 and Er2.

Step S703: As a result of the determination in step S701, candidate points El2 and Er at the left and right ends of the irradiation area are obtained.
If both the reliability C1 and C2 are not larger than the threshold Th3, it is determined whether flgr2 = 1, that is, whether the reliability C2 of the candidate point Er2 at the right end of the irradiation area is larger than the threshold Th3. Determine.

Step S704: If the reliability C2 of the candidate point Er2 at the right end of the irradiation area is larger than the threshold Th3 as a result of the determination at step S703, the final right end E
r is determined as the candidate point Er2.

Step S705: In order to determine the left end, the candidate point El2 (the second candidate point) is set to the above-mentioned [First Irradiation Area Extraction Processing (Step S202): See FIG. 4] step. Using the left and right ends El1 and Er1 (first candidate points) of the irradiation region obtained in S405,

[0092]

(Equation 15)

It is determined whether or not conditional expression (24) is satisfied.

Steps S706 and S707: Step S
If the result of the determination in 705 satisfies the conditional expression (24), the final left end El is determined to be the candidate point El2 (second candidate point); otherwise, the final left end E1 is determined.
1 is determined as a candidate point El1 (first candidate point).

Step S708: On the other hand, step S70
As a result of the determination in step 3, when the reliability C2 of the candidate point Er2 at the right end of the irradiation area is not larger than the threshold Th3, and when the reliability Cl of the candidate point El2 at the left end of the irradiation area is larger than the threshold Th3. So the final left end E
1 is determined as a candidate point El2.

Step S709: In order to determine the right end, the candidate point Er2 (the second candidate point) is converted to the step of the above-described [First Irradiation Area Extraction Processing (Step S202): See FIG. 4]. Using the left and right ends El1 and Er1 (first candidate points) of the irradiation region obtained in S405,

[0097]

(Equation 16)

It is determined whether or not conditional expression (25) is satisfied.

Steps S710 and S711: Step S
If the result of the determination in 709 is that conditional expression (25) is satisfied, the final right end Er is determined to be the candidate point Er2 (second candidate point); otherwise, the final right end E is determined.
r is determined as a candidate point Er1 (first candidate point).

[Left end squeezing process (step S60)
6): See FIG. 8]

Step S801: First, the final right end Er is set to Er = Lh (the right end is determined to be the right end of the photographing area of the sensor).

Step S802: Next, flgl2 = 1
, That is, the candidate point El at the left end of the irradiation area.
It is determined whether or not the reliability Cl of 2 is larger than the threshold Th3.

Steps S803 and S804: Step S
As a result of the determination at 802, a candidate point El2 at the left end of the irradiation area
Is larger than the threshold Th3, the final left end El is determined to be El = El2 (second candidate point) (step S804). Otherwise, the final left end El is determined. It is determined that El = El1 (first candidate point) (step S803).

[Right end squeezing process (step S60)
7): See FIG. 9]

Step S901: First, the final left end El is set to Er = 0 (the left end is determined to be the left end of the photographing area of the sensor).

Step S902: Next, flgr2 = 1
, That is, the candidate point Er at the right end of the irradiation area
It is determined whether or not the reliability C2 of No. 2 is larger than the threshold Th3.

Steps S903 and S904: Step S
As a result of the determination in Step 902, a candidate point Er2 at the right end of the irradiation area
Is greater than the threshold Th3, the final right end Er is determined to be Er = Er2 (second candidate point) (step S904). Otherwise, the final right end Er is determined. It is determined that Er = Er1 (first candidate point) (step S903).

As described above, in the present embodiment, the irradiation region is drawn by focusing on the symmetry of the irradiation region, so that the irradiation region can be extracted with higher accuracy. Also, at this time, an evaluation based on reliability is added to the end of the irradiation region acquired as a candidate point, and the final end of the irradiation region is determined based on this evaluation. End point candidates with a high evaluation can be reflected on end point candidates with a low evaluation. In this case, the irradiation area is more accurately drawn by selecting, as the other end point, the end point closest to the coordinates at the symmetric position of the candidate with a high evaluation (candidate of the end point) among the plurality of end point candidates. can do. Further, since the first irradiation area extraction circuit 112b is configured to create a projection of the entire target image, it is possible to accurately extract, as the irradiation area end, an end where the edge structure appears most as a whole. . In the second irradiation area extraction circuit 112c, a projection of a plurality of areas is created, and in a region where an X-ray image is strongly applied to an end of the irradiation area, the edge structure of the end is made clear and used. Due to the configuration, even if the image has an area where the X-rays are strongly applied, such as a through area (an area where the X-rays directly hit the sensor surface), exists at the end of the irradiation area. An irradiation area can be accurately extracted. In addition, the second irradiation region extraction time 112c is configured to introduce the above-described reliability when extracting the irradiation region end portion candidate. Therefore, it is necessary to objectively evaluate the accuracy of the extraction result. Can be. For this reason, for example, even if the image in which relatively strong X-rays are applied to the end of the irradiation area is the target image, if the evaluation (reliability) of the extraction result of the second irradiation area extraction 112c is high, The extraction result of the second irradiation area extraction circuit 112c is used for determining a final endpoint; otherwise, the extraction result of the first irradiation area extraction circuit 112b is used for determining a final endpoint. Thus, a complementary effect can be obtained, and the irradiation region can be extracted with higher accuracy.

That is, according to the embodiment of the present invention, when extracting a predetermined area (a symmetric irradiation area caused by squeezing irradiation and photographing from left, right, upper and lower portions) from an image (radiation image, etc.), the predetermined area is extracted. Since the predetermined area is extracted in consideration of the symmetry (for example, using the property that the irradiation area is likely to be symmetric), the predetermined area such as the irradiation area can be more accurately extracted. Specifically, for example, an image obtained by performing irradiation area squeezing and X-ray imaging is used.
When extracting an irradiation area from the image, a candidate as a predetermined area is extracted by a plurality of extraction methods. And
Reliability (evaluation) is added to the extraction result (the left, right, upper, and lower end points of the irradiation area) by each extraction method. The final irradiation area is determined based on the reliability, whereby the candidate of the endpoint with high reliability can be reflected on the candidate of the endpoint with low reliability. In addition, after determining a candidate of a highly reliable end point among a plurality of end point candidates, an end point at a position opposed to the end point is closest to a coordinate at a symmetric position of coordinates of the highly reliable end point. By determining it as the end point of the coordinates, the irradiation area can be drawn with higher accuracy. Therefore, the irradiation area can always be accurately extracted from an image such as a radiation image. Therefore, by determining an image processing parameter for performing image processing from such an accurate extraction result, it is possible to perform optimal image processing and output a good image. this is,
In particular, it is effective for X-ray photography and the like.

It is to be noted that an object of the present invention is to provide a storage medium storing program codes of software for realizing the functions of the host and terminal of the above-described embodiment to a system or an apparatus, and to provide a computer (a computer) of the system or the apparatus. It is needless to say that the present invention can also be achieved by a CPU or an MPU) reading and executing a program code stored in a storage medium. In this case, the program code itself read from the storage medium implements the functions of the present embodiment, and the storage medium storing the program code constitutes the present invention. ROM, as a storage medium for supplying the program code,
Floppy disk, hard disk, optical disk, magneto-optical disk, CD-ROM, CD-R, magnetic tape,
A non-volatile memory card or the like can be used. By executing the program code read out by the computer, not only the functions of the present embodiment are realized, but also the OS and the like running on the computer perform actual processing based on the instructions of the program code. It goes without saying that a part or all of the above is performed and the function of the present embodiment is realized by the processing. Further, after the program code read from the storage medium is written to a memory provided in an extension function board inserted into the computer or a function extension unit connected to the computer, the function extension is performed based on the instruction of the program code. It goes without saying that a CPU or the like provided in the board or the function expansion unit performs part or all of the actual processing, and the processing realizes the functions of the present embodiment.

[0111]

As described above, according to the present invention, it is possible to satisfactorily extract a predetermined region having symmetry in an image, and to properly extract an appropriate irradiation field from an image obtained by radiography. Can be detected.

[Brief description of the drawings]

FIG. 1 is a block diagram illustrating a configuration of an X-ray imaging apparatus to which the present invention has been applied.

FIG. 2 is a flowchart illustrating a main process of an irradiation area extraction circuit in the X-ray imaging apparatus.

FIG. 3 is a flowchart illustrating an irradiation aperture determination process of the main process.

FIG. 4 is a flowchart illustrating a first irradiation area extraction process of the main process.

FIG. 5 is a flowchart illustrating a second irradiation area extraction process of the main process.

FIG. 6 is a flowchart for explaining an irradiation end final determination process of the main process.

FIG. 7 is a flowchart for explaining a process of squeezing both ends of the irradiation end final determination process.

FIG. 8 is a flowchart illustrating a left end squeezing process of the irradiation end final determination process.

FIG. 9 is a flowchart for explaining a right end squeezing process of the irradiation end final determination process.

FIG. 10 is a diagram for explaining the symmetry of an irradiation area.

[Explanation of symbols]

 REFERENCE SIGNS LIST 100 X-ray imaging apparatus 101 X-ray generation circuit 102 X-ray beam 103 subject 104 two-dimensional X-ray sensor 105 data collection circuit 106 preprocessing circuit 108 CPU 109 main memory 110 operation panel 111 image display 112 irradiation area processing circuit 112 a irradiation irradiation Presence / absence determination circuit 112b First irradiation area extraction circuit 112c Second irradiation area extraction circuit 112d Determination circuit 114 Image processing circuit 115 CPU bus

 ──────────────────────────────────────────────────続 き Continued on the front page F term (reference) 4C093 AA01 AA16 AA22 CA04 CA06 CA09 EA12 EB17 FD01 FD03 FD09 FD13 FF07 FF16 FF19 FF20 FF28 5B057 AA08 BA03 CA12 CA16 CB12 CB16 CE05 DA08 DB02 DC16 DC23

Claims (15)

[Claims] 1. An image processing apparatus having a function of extracting a predetermined area from an image, comprising: an extraction unit that extracts the predetermined area based on symmetry of the predetermined area. . 2. The image processing apparatus according to claim 1, wherein the image includes an image obtained by radiography, and the predetermined area includes a radiation irradiation area. 3. The method according to claim 1, wherein the extraction means has a function of extracting the predetermined area by a plurality of extraction methods, and adds reliability to an extraction result by the extraction methods. Image processing device. 4. The extraction means determines an extraction result selected from each of the extraction results of the plurality of extraction methods as a final predetermined area based on a result of the comparison between the reliability and a predetermined value. The image processing apparatus according to claim 3, wherein: 5. The method according to claim 1, wherein the extracting unit determines an extraction result obtained by another extraction method as a final predetermined area when reliability of the extraction result obtained by the arbitrary extraction method is equal to or less than the predetermined value. The image processing apparatus according to claim 4, wherein 6. The extraction means adds reliability to each end constituting each of the predetermined regions extracted by the plurality of extraction methods, and compares the reliability of the ends with a predetermined value. 4. The image processing apparatus according to claim 3, wherein each of the ends constituting the final predetermined area is determined based on the following. 7. The extraction means according to claim 1, wherein the reliability of an arbitrary end of the predetermined area obtained by the arbitrary extraction method is equal to or more than a predetermined value, and the extraction of the opposing end located at a position facing the arbitrary end is performed. When the reliability is equal to or less than a predetermined value, the coordinates of the opposite end are determined based on the coordinates of the opposite end to which the reliability equal to or more than the predetermined value is added among the opposite ends obtained by another extraction method. The image processing apparatus according to claim 6, wherein: 8. The extraction means adds reliability to the extraction result of each end of the predetermined area, and based on a result of comparison between the reliability of each end and a predetermined value, the extraction of the predetermined area. 2. The image processing apparatus according to claim 1, wherein each end is determined. 9. The method according to claim 1, wherein the reliability of the arbitrary end is equal to or more than the predetermined value, and the reliability of the opposing end located at a position facing the arbitrary end is equal to or less than the predetermined value. The image processing apparatus according to claim 8, wherein the coordinates of the opposite end are determined based on the coordinates of the arbitrary end. 10. An image processing system in which a plurality of devices are communicably connected to each other, wherein at least one of the plurality of devices is the image processing apparatus according to claim 1. An image processing system having the following functions. 11. An image processing method for inputting an image generated based on a set center portion and extracting a predetermined region having symmetry from the image, wherein a right end and a left end of the predetermined region are the same as the above. An image processing method, comprising: extracting the predetermined region based on image characteristics of the image by being symmetrical based on the set center portion. 12. The image processing method according to claim 11, wherein the image is an image obtained by radiation imaging, and wherein the central portion is set based on an irradiation imaging aperture. 13. The method according to claim 1, wherein the extraction of the predetermined region is performed based on an edge portion in the image, and the symmetry is used to determine whether a right end and a left end obtained based on the edge portion are correct. The image processing method according to claim 11, wherein: 14. An image processing method having a plurality of different irradiation field recognition methods, wherein an image obtained by radiography is input, and irradiation field recognition is performed on the image using the irradiation field recognition method. An image processing method comprising: evaluating a result of the irradiation field recognition; and detecting an irradiation field in the image based on the evaluation result and the irradiation field recognition result. 15. A storage medium, wherein the processing steps of the image processing method according to claim 11 are stored in a computer-readable manner.