WO2007015384A1 - Area extracting device and area extracting program - Google Patents

Abstract

An area extracting device (1) for extracting an area of interest corresponding to a subject stably and accurately comprises a smoothing section (7) for creating a smoothed image by smoothing an input image, an initial area detecting section (8) for detecting an initial area including at least a part of the subject from the smoothed image according to the smoothed pixel values which the pixels in the smoothed image have, an area transforming section (9) for judging whether or not a contour adjoining pixel is a pixel of the area of interest constituting the area of interest on the basis of the smoothing pixel value which the contour adjoining pixel in the initial area has, varying at least either the size or shape of the initial area according to the judgment result, and shaping the transformed area, and an area integrating section (10) for detecting adjoining areas formed by adjoining transformed areas and shaping the area of interest by integrating the adjoining transformed areas according to the feature values indicating the features of the adjoining transformed areas among the adjoining areas.

Description

 Region extraction apparatus and region extraction program

 Technical field

 The present invention relates to a region extraction device and a region extraction program that extract an image region corresponding to an imaging target from an input image.

 Background art

 Conventionally, an image processing technique for extracting an image region corresponding to a specific imaging target from an image acquired by imaging with a digital camera or an imaging device provided in a microscope has been used in various fields. It has become an important technology (see, for example, Patent Documents 1 and 2).

 [0003] In the region extraction method disclosed in Patent Document 1, when extracting the outline of a person to be imaged from an image, a plurality of edge points are obtained using an edge detection filter, and adjacent edges are extracted. An edge line is formed by connecting points, and an edge line indicating an elliptical shape is detected as a contour of a person.

 [0004] With the contour extraction device disclosed in Patent Document 2, the contour of a desired object is extracted based on the theory of "snakes" using the energy minimization principle! . In other words, the contour model formed by a continuous line is initialized, and an energy evaluation function that quantitatively expresses the curvature and change state of the contour model, deviations of edges and gradients on the image, etc. is defined. The contour of the object is extracted by repeating the deformation of the contour model so as to minimize this energy evaluation function.

 [0005] Conventionally, in such a Snakes method, it is necessary for the operator to presume the contour model of the target object to be extracted, and to initially set the contour model so as to surround the target object. For this reason, when extracting multiple objects or extracting objects from multiple images, the contour model must be initialized for each object or image, which can be a daunting task. There was a problem that it took a lot of time and load.

[0006] On the other hand, in the contour extraction device disclosed in Patent Document 2, all the images in the image are displayed. It is necessary to initialize the contour model for each target object by initializing the contour model surrounding the extraction target and splitting the contour model into multiple parts when this contour model contacts or intersects during the deformation process. Instead, the contours of multiple objects are extracted.

 [0007] Patent Document 1: Japanese Patent Laid-Open No. 9138471

 Patent Document 2: JP-A-8-329254

 Disclosure of the invention

 Problems to be solved by the invention

 However, in the region extraction method described above, noise or the like in the image is erroneously detected as an edge point, or the edge line is interrupted when the edge point strength is weak. There is a problem that it is difficult to stably detect a desired contour.

 [0009] Further, the above-described contour extraction apparatus may not be able to extract a contour that is faithful to the target object when the shape of the target object changes or when there are a plurality of various target objects. was there. Furthermore, in this contour extraction device, the contour model is split when a contact or intersection of a plurality of line segments connecting the contour candidate points is detected, so that a plurality of objects are adjacent and the contour candidate points are detected. If this is not possible, the contour of each adjacent object cannot be extracted, and therefore there is a problem that each adjacent object cannot be identified.

 [0010] The present invention has been made in view of the above, and is not affected by noise or the like in an acquired image, and does not depend on the state of the imaging target such as deformation or adjacency. An object of the present invention is to provide an area extraction apparatus and an area extraction program that can stably and accurately extract an image area corresponding to the above.

 Means for solving the problem

[0011] In order to achieve the above object, an area extraction apparatus according to claim 1 is an area extraction apparatus that extracts a target area, which is an image area corresponding to an imaging target, from input images. Smoothing means for generating a smoothed image obtained by smoothing the image, and based on the smoothed pixel value of each pixel in the smoothed image, and at least the imaging target from the smoothed image. An initial region that detects an initial region that is an image region including a part of Based on the detection means and the smoothed pixel value of the contour neighboring pixels of the initial region, it is determined whether or not the contour neighboring pixels are target region pixels constituting the target region, and according to the determination result And an area deformation means for deforming at least one of the size and shape of the initial area to form the target area.

 [0012] In addition, an area extraction apparatus according to claim 2 smoothes the image by inputting it into an area extraction apparatus that extracts a target area that is an image area corresponding to an imaging target from input images. An image including at least a part of the imaging target from the smoothed image based on a smoothing unit that generates a smoothed image and a smoothed pixel value of each pixel in the smoothed image An initial region detecting means for detecting an initial region that is an area; an edge detecting means for generating an edge image that detects an edge included in the smoothed image; and the edge corresponding to a contour neighboring pixel of the initial region. Based on the edge pixel value of each pixel in the image, it is determined whether or not the pixel near the contour is a target region pixel constituting the target region, and the size of the initial region is determined according to the determination result. At least one of thickness and shape And a region deformation means for deforming the direction to form the target region.

 [0013] In the area extracting apparatus according to claim 3, in the above invention, the initial area detecting means detects each pixel having the smoothed pixel value larger than a predetermined value as the initial area. It is characterized by doing.

 [0014] In addition, in the above-described invention, the region extraction device according to claim 4 is characterized in that the initial region detection means has a predetermined distribution shape of the smoothed pixel value with respect to the pixel position in the smoothed image. A pixel group satisfying the above condition is detected as the initial region.

 [0015] In addition, the region extraction apparatus according to claim 5 is characterized in that, in the above invention, the initial region detection means detects, as the initial region, a pixel group having a convex distribution shape. To do.

[0016] Furthermore, in the region extraction device according to claim 6, in the above invention, the region deformation means is in the initial region among a series of adjacent pixels adjacent to the outside of the initial region. A pixel that satisfies a predetermined condition of the smoothed pixel value with respect to a contour pixel that forms a contour of the initial region is determined to be the target region pixel, and the initial region is set so as to capture the determined adjacent pixel. It is characterized by being deformed. [0017] Further, in the region extracting apparatus according to claim 7, in the above invention, the region modifying means is configured such that a pixel value difference of the smoothed pixel value between the adjacent pixel and the contour pixel is within a predetermined range. The adjacent pixels that are within are determined to be the target region pixels

[0018] Also, in the region extraction device according to claim 8, in the above invention, the region deformation means is located in the initial region among a series of adjacent pixels adjacent to the outside of the initial region. A pixel that satisfies the predetermined condition of the edge pixel value with respect to a contour pixel that constitutes a contour of the initial region is determined to be the target region pixel, and the initial region is modified so as to incorporate the determined adjacent pixel. It is characterized by doing.

 [0019] In addition, in the region extraction device according to claim 9, in the above invention, the region modification means includes a pixel value difference of the edge pixel value between the adjacent pixel and the contour pixel within a predetermined range. And determining that the adjacent pixel is the target region pixel.

[0020] Further, in the above-described invention, the region extracting device according to claim 10 is characterized in that the region deforming means includes the initial region out of a series of contour pixels in the initial region and constituting the contour of the initial region. A pixel that satisfies the predetermined condition for the smoothed pixel value between adjacent pixels outside the region is determined to be a pixel outside the target region, and the initial contour so as to remove the determined contour pixel. The region is deformed.

 [0021] Further, in the region extraction device according to claim 11, in the above invention, the region deformation means is configured such that a pixel value difference of the smoothed pixel value between the adjacent pixel and the contour pixel is within a predetermined range. It is characterized in that the contour pixel that is inside is determined to be a pixel outside the target region.

 [0022] Further, in the above invention, the region extracting device according to claim 12 is characterized in that the region deforming means includes the initial region out of a series of contour pixels in the initial region and constituting the contour of the initial region. A pixel whose edge pixel value satisfies a predetermined condition is determined to be a pixel outside the target region between adjacent pixels adjacent to the outside of the region, and the initial region is modified so as to remove the determined contour pixel It is characterized by doing.

[0023] Further, in the above invention, the region extraction device according to claim 13 is the region modification. The means is characterized in that the contour pixel in which a pixel value difference of the edge pixel value is within a predetermined range between the adjacent pixel and the contour pixel is determined to be a pixel outside the target region.

 [0024] Further, in the above-described invention, the region extracting device according to claim 14 is configured to determine whether the region deforming means is the target region pixel until the pixel value difference exceeds the predetermined range. This determination is repeated and the deformation of the initial region is repeated.

 [0025] Further, in the above-described invention, the region extracting device according to claim 15 is characterized in that the region deforming means is adjacent to the outside of one of the initial regions and adjacent to the outside of the other initial region. An adjacent pixel that satisfies the predetermined condition is determined to be the target region pixel.

 [0026] Further, in the above-described invention, the region extracting device according to claim 16 is characterized in that the region deforming means is adjacent to the outside of the initial region or a series of all adjacent pixels adjacent to the outside of the initial region. It is characterized in that it is determined whether or not the target region pixel is a power for each adjacent pixel of a predetermined ratio or more in a series of adjacent pixels.

 [0027] Further, in the above-described invention, the region extracting apparatus according to claim 17 is an adjacent region formed by an adjacent deformed region from among the deformed regions that are image regions as a result of deformation by the region deforming means. A region integration unit that detects a region group and integrates the adjacent deformation regions to form the target region based on a feature amount indicating a feature between adjacent deformation regions in the detected adjacent region group. Is further provided.

 [0028] In the region extraction device according to claim 18, in the above invention, the region integration unit calculates the feature amount and integrates the deformation regions based on the calculated feature amount. It is characterized by.

 [0029] In addition, in the region extraction device according to claim 19, in the above invention, the region integration unit is included in a deformation region different from the deformation region to be subjected to the intermediate force processing target of the contour neighboring pixels of each deformation region. It is characterized in that the adjacent region group is detected by detecting a pixel.

[0030] In addition, in the above invention, the region extracting apparatus according to claim 20 is the adjacent deformed region among the deformed regions which are image regions as a result of the deformation by the region deforming means. Is detected based on the smoothed pixel value of the boundary pixel indicating the boundary line between the deformation regions in the detected adjacent region group and the boundary neighboring pixels in the vicinity of the boundary line. It further comprises region integration means for calculating a feature amount indicating a feature between regions, and forming the target region by integrating the deformation regions in the adjacent region group based on the calculated feature amount. Features.

 [0031] In addition, in the above-described invention, the region extracting unit according to claim 21 is characterized in that the region integration means includes the smoothing function of each boundary pixel on the boundary line and a boundary neighboring pixel near the boundary pixel. The average value of the difference between the pixel values is calculated as the feature amount.

 [0032] Further, in the above-described invention, the region extracting apparatus according to claim 22 is an adjacent region formed by the adjacent deformed region from among the deformed regions that are image regions as a result of the deformation by the region deforming means. A region group is detected, and a feature between the deformation regions is shown based on the boundary pixel indicating the boundary line between the deformation regions in the detected adjacent region group and the edge pixel value of the boundary vicinity pixel near the boundary line. The image processing apparatus further includes a region integration unit that calculates a feature amount and integrates the deformation regions in the adjacent region group based on the calculated feature amount to form the target region.

 [0033] In addition, in the above-described invention, the region extraction unit according to claim 23 is characterized in that the region integration unit includes the edge pixels of the boundary pixels on the boundary line and the boundary neighboring pixels in the vicinity of the boundary pixels. The average value difference is calculated as the feature amount.

 [0034] Further, in the above-described invention, the region extracting device according to claim 24 is characterized in that the region integrating means includes a series of adjacent images adjacent to the outside of each deformation region in the detected adjacent region group. Scanning an element, and detecting an adjacent pixel adjacent to the outside of a deformation area different from the deformation area to be processed as the boundary pixel.

[0035] Further, the area extraction program according to claim 25 is provided with a region extraction device that extracts a target area, which is an image area corresponding to an imaging target, from an input image. In the region extraction program for extracting image data, the region extraction device causes the region extraction device to generate a smoothed image obtained by smoothing the image, and a smoothed pixel value of each pixel in the smoothed image. Accordingly, an initial region detection for detecting an initial region that is an image region including at least a part of the imaging target from the smoothed image. Based on the output procedure and the smoothed pixel value of each contour neighboring pixel of the initial region, it is determined whether or not each contour neighboring pixel is a target region pixel constituting the target region, And a region deformation procedure for deforming at least one of the size and shape of the initial region in accordance with the determination result to form the target region.

 [0036] Further, the region extraction program according to claim 26 provides the region extraction device for extracting a target region, which is an image region corresponding to the imaging target, from the input image. In the region extraction program for extracting a region, the region extraction device generates a smoothing procedure for generating a smoothed image obtained by smoothing the image, and the smoothed pixel value of each pixel in the smoothed image. Based on this, an initial region detection procedure for detecting an initial region that is an image region including at least a part of the imaging target from the smoothed image, and an edge included in the smoothed image is detected. Each edge neighboring pixel is determined to be the target area based on the edge detection procedure for generating the edge image and the edge pixel value of each pixel in the edge image corresponding to each edge neighboring pixel in the initial area. a configuration A region deformation procedure for determining whether or not the target region pixel is a force to be deformed, and deforming at least one of the size and shape of the initial region according to the determination result, and forming the target region. And

 The invention's effect

 [0037] According to the region extraction device and the region extraction program that are useful in the present invention, individual imaging is performed regardless of the state of the imaging target such as deformation and adjacency without being affected by noise or the like in the acquired image. The image area corresponding to the object can be stably and accurately extracted. Brief Description of Drawings

 FIG. 1 is a block diagram showing a configuration of a region extraction device according to a first exemplary embodiment of the present invention.

 FIG. 2 is a block diagram showing a detailed configuration of the region deforming section shown in FIG.

 FIG. 3 is a block diagram showing a detailed configuration of the area integration unit shown in FIG. 1.

 [FIG. 4-1] FIG. 41 is a diagram showing an example of an observation image input to the region extracting apparatus shown in FIG.

[Fig. 4-2] Fig. 4 2 shows the initial region detection image generated based on the observation image shown in Fig. 41. FIG.

 [Fig. 4-3] Fig. 4 3 shows a region deformation image generated based on the observation image shown in Fig. 41.

_[4 - _4] Figure 4-4 is a view to view the region integrating image generated on the basis of the observed image shown in FIG 1.

 FIG. 5 is a flowchart showing a processing procedure performed by the region extracting apparatus shown in FIG.

[FIG. 6-1] FIG. 6-1 is a diagram for explaining the processing method of the smoothing process shown in FIG.

 [FIG. 6-2] FIG. 6-2 is a diagram for explaining the processing method of the smoothing process shown in FIG.

 FIG. 7 is a diagram for explaining a processing method of the initial region detection processing shown in FIG.

 FIG. 8 is a flowchart showing a processing procedure for the region deformation processing shown in FIG.

 FIG. 9 is a diagram for explaining a processing method of the region transformation process shown in FIG.

 FIG. 10 is a flowchart of a process procedure of the area integration process shown in FIG.

 [FIG. 11] FIG. 11 is a diagram for explaining a processing method of the region integration processing shown in FIG.

 FIG. 12 is a block diagram showing a configuration of a region extracting device according to the second embodiment of the present invention.

 FIG. 13 is a block diagram showing a detailed configuration of the area deforming unit shown in FIG.

FIG. 14 is a block diagram showing a detailed configuration of the area integration unit shown in FIG.

FIG. 15 is a flowchart showing a processing procedure performed by the region extracting apparatus shown in FIG.

 FIG. 16 is a diagram showing an edge image generated by the edge detection process shown in FIG.

Explanation of symbols

 1, 21 region extractor

 2 Input section

 3, 23 Image processing section

4 Output section 6, 26 Control unit

 7 Smoothing part

 8 Initial area detector

 9, 29 Region transformation

 9a Sign section

 9b Contour detector

 9c, 29c Deformation judgment part

 9d End determination part

 10, 30 Area Integration Department

 10a Boundary detector

 10b, 30b feature quantity calculator

 10c Integrated judgment section

 31 Edge detector

 BEST MODE FOR CARRYING OUT THE INVENTION

 Hereinafter, preferred embodiments of a region extraction device and a region extraction program according to the present invention will be described in detail with reference to the accompanying drawings. Note that the present invention is not limited to the embodiments. In the drawings, the same portions are denoted by the same reference numerals.

 [0041] (Embodiment 1)

 First, the region extraction apparatus and the region extraction program according to the first embodiment of the present invention will be described. FIG. 1 is a block diagram showing the configuration of the area extracting apparatus 1 according to the first embodiment. As shown in FIG. 1, the region extraction device 1 includes an input unit 2 that receives input of various types of information such as images, an image processing unit 3 that processes input images, and outputs various types of information such as image display. An output unit 4 to perform, a storage unit 5 for storing various information such as images, and a control unit 6 for controlling processing and operation of each unit of the region extraction device 1 are provided. The input unit 2, image processing unit 3, output unit 4 and storage unit 5 are electrically connected to the control unit 6.

The input unit 2 includes an imaging device realized by using an imaging lens, an imaging element such as a CCD, and an AZD converter, and acquires an observation image generated by imaging by the imaging device. Also, The input unit 2 includes an input key, a mouse, a touch panel, a switch, and the like, and receives input of various processing information to be processed by the area extraction device 1.

 [0043] Note that various types of imaging devices capable of generating digital images, such as a digital camera, a microscope, and a visual sensor, can be applied to the imaging device included in the input unit 2. The input unit 2 includes a communication interface such as USB or IEEE1394, or an interface corresponding to a portable storage medium such as a flash memory, a CD, a DVD, or a hard disk. You can get observation images.

 Here, it is assumed that the observation image input from the input unit 2 is, for example, an image obtained by imaging cells that have been stained with a fluorescent dye in a living tissue. In the observation image obtained by imaging the energetic cells, the corresponding part of the cell to which the dye has acted is observed brightly. The cell staining may be for staining the entire cell or for staining only a specific site such as a cell nucleus, actin, or cell membrane. In addition, the dye used for staining is not limited to fluorescent dyes, but makes the cell contrast clearer. In addition to contrast, any dye can be used as long as it does not alter the cell characteristics. Well ...

 [0045] Note that the observation image input from the input unit 2 may be an arbitrary form of image, such as a monochrome image, a color image, or a color difference image, as long as the image can be identified as a cell to be imaged. In addition, the imaging target captured in the observation image may be an arbitrary object such as an object such as a vehicle, a person, or an animal that need not be interpreted as being limited to cells. For example, in the case where a person is an imaging target, image data such that a portion where the imaging target exists on the image is captured with high contrast, such as an image showing a temperature distribution, can be used.

 The image processing unit 3 includes a smoothing unit 7, an initial region detection unit 8, a region deformation unit 9, and a region integration unit 10. The image processing unit 3 acquires and processes an observation image output from the input unit 2. Note that the observation image output from the input unit 2 can be acquired and stored by the storage unit 5, and the image processing unit 3 can acquire and process the observation image stored in the storage unit 5. it can.

[0047] The smoothing unit 7 acquires the observation image output from the input unit 2, and smoothes the observation image while preserving the structure of the pixel value distribution indicating a large pixel value change such as an edge in the image. This smoothness removes random noise in the observed image. In addition, the smoothing unit 7 generates a smoothed image as a result of smoothing the observation image. Output to shape 9 and area integration unit 10. Note that the smoothing unit 7 can also output and store the smoothed image to the storage unit 5 via the control unit 6.

 [0048] The initial region detection unit 8 has a large pixel value corresponding to the imaging target in the smoothed image based on the smoothness pixel value that is the pixel value of each pixel in the smoothed image acquired from the smoothing unit 7. An initial area that is a rough image area is detected. The initial region to be detected may be a region including only a part of the imaging target as long as it is a region including at least a part of the corresponding imaging target, or a region including the entire imaging target. However, the contour of the initial area to be detected does not intersect with the contour of the imaging target. The initial region detection unit 8 detects a strong initial region for each imaging target as an extraction target. In addition, the initial region detection unit 8 generates initial region data in which various feature amounts such as the position, shape, and area of each detected initial region are associated, and outputs the initial region data to the region deformation unit 9. Note that the initial region detection unit 8 can also output and store the generated initial region data to the storage unit 5 via the control unit 6.

 [0049] The region deforming unit 9 acquires the smoothed image from the smoothing unit 7 and the initial region data from the initial region detecting unit 8, and matches each initial region to the contour shape of the corresponding imaging target. It transforms so that Specifically, based on the smoothed pixel value of the contour neighboring pixel located in the vicinity of the contour of the initial region, the region deforming unit 9 determines whether or not this contour neighboring pixel is a pixel constituting the target region. Is determined. Then, at least one of the size and shape of the initial region is deformed according to the determination result, and the target region is formed as an image region that matches the contour shape of the imaging target.

 FIG. 2 is a block diagram showing a detailed configuration of the area deforming unit 9. As shown in FIG. 2, the region deforming unit 9 includes a labeling unit 9a, a contour detecting unit 9b, a deformation determining unit 9c, and an end determining unit 9d. The labeling unit 9a gives a unique region marker to each initial region in the smooth image. The contour detection unit 9b refers to the area marker provided by the labeling unit 9a, and detects adjacent pixels adjacent to the outside of each initial region as contour neighboring pixels. The deformation determination unit 9c determines whether each adjacent pixel is a target area pixel constituting the target area based on the smoothed pixel value, and deforms the initial area according to the determination result. A deformation area, which is an image area obtained as a result of deformation by the deformation determination unit 9c, is temporarily regarded as a target area.

[0051] The end determination unit 9d performs processing in the region deformation unit 9 according to the processing status of the deformation determination unit 9c. It is determined whether or not the power to end the reason. Further, when the end determination unit 9d determines the end of processing, the end determination unit 9d generates deformation region data in which various feature amounts such as the position, shape, and area of each deformation region are associated with each other, and outputs the deformation region data to the region integration unit 10. . The end determination unit 9d can also output and store the deformation area data in the storage unit 5 via the control unit 6.

 [0052] The region integration unit 10 acquires the smoothed image from the smoothing unit 7 and the deformation region data from the region deformation unit 9, and detects an adjacent region group formed by the adjacent deformation regions. Then, based on the feature amount indicating the feature between adjacent deformation areas in the detected adjacent area group, the adjacent deformation areas are integrated to form a final target area.

 FIG. 3 is a block diagram showing a detailed configuration of the region integration unit 10. As shown in FIG. 3, the region integration unit 10 includes a boundary detection unit 10a, a feature amount calculation unit 10b, and an integration determination unit 10c. The boundary detection unit 10a detects boundary pixels indicating boundary lines between adjacent deformation regions with reference to the region markers of the deformation regions. The feature amount calculation unit 10b calculates a feature amount between adjacent deformation regions corresponding to the boundary line based on the smoothed pixel values of the boundary pixel and the boundary vicinity pixel near the boundary line.

 [0054] The integrated determination unit 10c determines whether or not the adjacent deformation regions are integrated based on the feature amount calculated by the feature amount calculation unit 10b, and integrates the deformation regions according to the determination result. Then, the target area is formed. In addition, when the integration determination unit 10c completes the integration of the deformation region and ends the processing in the region integration unit 10, the integration determination unit 10c associates various feature amounts such as the position, shape, and area of each target region as a processing result Generate area data and output to output unit 4. At this time, the integration determining unit 10c regards the independent deformation area that has not been integrated as it is as the final target area, and outputs the deformation area data corresponding to the deformation area as the target area data. The integrated determination unit 10c can also output and store the target area data to the storage unit 5 via the control unit 6.

[0055] The output unit 4 includes a display device having a CRT, a liquid crystal display, etc., acquires the target area data output from the image processing unit 3, and displays it as image information and numerical information. In this display, the output unit 4 can display only one of image information and numerical information. Both can be displayed simultaneously or by switching. Note that the target area data output from the image processing unit 3 is acquired and stored by the storage unit 5. The output unit 4 may acquire and display the target area data stored in the storage unit 5. In addition to the target area data, the output section 4 can obtain observation images, smoothed images, initial area data, deformation area data, etc. from the image processing section 3 or the storage section 5 and display them. .

 The storage unit 5 is realized by using a ROM that stores various processing programs and the like, and a RAM that stores processing parameters, processing data, and the like for various processing. In particular, the storage unit 5 stores a program for causing the image processing unit 3 to execute processing, that is, a region extraction program for causing the region extraction device 1 to extract a target region from the observed image. The storage unit 5 may include a portable storage medium such as a flash memory, a CD, a DVD, and a hard disk as a removable storage unit.

 The control unit 6 is realized using a CPU or the like that executes various processing programs stored in the storage unit 5. In particular, the control unit 6 executes a region extraction program stored in the storage unit 5, and controls the processing and operation of each component included in the image processing unit 3 according to the region extraction program. The control unit 6 performs control to display the target area data output from the image processing unit 3 on the output unit 4 as image information and numerical information. Note that the control unit 6 can also perform control to acquire an observation image, a smoothed image, initial region data, deformation region data, target region data, and the like from the storage unit 5 and display them on the output unit 4.

 Here, a processing procedure performed by the region extraction device 1 will be described. FIG. 5 is a flowchart showing the processing procedure of the region extraction process in which the region extraction apparatus 1 processes and displays the observation image by the control unit 6 executing the region extraction program. FIGS. 41 to 44 are diagrams showing the processing results of the respective processing steps shown in FIG. 5, and are schematic diagrams showing an observation image, an initial region detection image, a region deformation image, and a region integration image in order. . However, FIG. 41 is also used to describe the smoothed image as the smoothed image processing result. The region integrated image shown in FIG. 4-4 is an image showing the target region finally determined as the region integration processing result, and is also the target region image as the region extraction processing result.

[0059] Each image shown in Figs. 4 2 to 4 4 is imaged by the control unit 6 based on the initial area data, the deformation area data, and the target area data, respectively. Although it is not necessarily an image to be generated, here is the region extraction process It is shown as a diagram for explaining the progress.

 As shown in FIG. 5, first, the input unit 2 captures a cell as an imaging target and acquires an observation image (step S101). In step S101, the input unit 2 acquires, as an observation image, an image obtained by imaging a plurality of cells, for example, as shown in FIG. 4-1. The input unit 2 outputs the acquired observation image to the smoothing unit 7.

 [0061] Next, the smoothing unit 7 performs a smoothing process to generate a smoothed image by smoothing the observation image acquired from the input unit 2 (step S103). In step S103, as shown in FIG. 41, the smoothing unit 7 performs smoothing while preserving the structure of the cell region in the observation image, and removes the smooth image from which noise and the like in the observation image are removed. Generate. The smoothing unit 7 outputs the generated smoothed image to the initial region detecting unit 8, the region deforming unit 9, and the region integrating unit 10.

 Subsequently, the initial region detection unit 8 detects an initial region corresponding to each cell from the smoothed image acquired from the smoothing unit 7, and generates initial region data of each detected initial region. Initial region detection processing is performed (step S105). In step S105, the initial region detection unit 8 detects an initial region including at least a part of each cell region, for example, as shown in FIG. The initial region detection unit 8 outputs the generated initial region data to the region deformation unit 9.

 [0063] Next, the region deforming unit 9 determines each initial region indicated by the initial region data acquired from the initial region detecting unit 8 based on the smoothed pixel value of the smoothed image acquired from the smoothing unit 7. Deformation is performed so as to match the contour shape of the imaging target, and region deformation processing for generating deformation region data of each deformation region as a deformation result is performed (step S107). In step S107, as shown in FIG. 43, the region deformation unit 9 forms a deformation region that matches the contour shape of each cell in the observation image as a result of expanding and deforming each initial region stepwise. . The region deformation unit 9 outputs the generated deformation region data to the region integration unit 10.

[0064] Subsequently, the region integration unit 10 detects the adjacent region group based on the smoothed pixel value of the smoothed image acquired from the smoothing unit 7, and the feature amount between the adjacent deformation regions in the adjacent region group. Based on the calculated feature value, adjacent deformation regions are integrated with each other, and region integration processing for generating target region data as a result of integration is performed (step S109). In step S109, the region integration unit 10 in the region deformation image shown in FIG. 4-3, for example. Adjacent deformation areas TA5 and TA6 are integrated into a target area OA5 as shown in Figure 4-4. Further, the region integration unit 10 regards the independent deformation regions TA1 to TA4 that are not integrated as the final target regions ΟΑ1 to ΟΑ4, respectively, and generates target region data for each target region. The region integration unit 10 outputs the generated target region data to the output unit 4.

Next, the output unit 4 displays at least one of image information and numerical information based on the target region data output from the region integration unit 10 as an extraction result of the region extraction process (step S111). In step S111, the output unit 4 displays the target region image as shown in FIG. 44 when displaying the extraction result as image information. At this time, the output unit 4 displays, for each area marker associated with the target area, for example, each pixel value in the target area has the same value, each pixel has the same color, or the target area has been unified. And so on.

 [0066] After step S111, the control unit 6 ends the series of region extraction processing. However, the control unit 6 can repeatedly perform the processing of steps S101 to S111 until, for example, instruction information for ending predetermined processing is received. Further, instead of acquiring the observation image from the input unit 2 in step S101, the observation image stored in the storage unit 5 can be acquired and the processing in step S103 and subsequent steps can be executed. Furthermore, instead of processing steps S101 to S109, step S111 can be executed based on the target area data stored in the storage unit 5. In addition to the target area data, step S111 can also be executed based on the observed image, smoothed image, initial area data, area deformation data, and the like.

 [0067] Next, the details of each process will be described with respect to steps S103 to S109 shown in FIG. First, in step S103, the smoothing unit 7 refers to a neighboring 5 × 5 pixel pattern PA centered on the target pixel OP, which is a pixel to be processed in the observed image, as shown in FIG. 5 X 5 pixel pattern Based on the variance and average value of the pixel values calculated for each given 3 X 3 pixel pattern in the PA !, set the smoothed pixel value of the pixel of interest OP

That is, the smoothing unit 7 divides the 5 × 5 pixel pattern PA into, for example, nine 3 × 3 pixel patterns PA1 to PA9 as shown in FIG. A variance value of pixel values of a plurality of selected pixels indicated by diagonal lines is calculated for each of ~ PA9. And The smoothing unit 7 extracts the 3 × 3 pixel pattern indicating the smallest variance value, calculates the average value of the pixel values of the selected pixels in the extracted 3 × 3 pixel pattern, and pays attention to the calculated average value. Set as the smooth pixel value of pixel OP.

 [0069] The smoothing unit 7 smoothes the observation image by setting the smoothed pixel value for each pixel constituting the observation image. It is not necessary to limit the pixel pattern referred to corresponding to the target pixel OP to 5 × 5 pixels, and the number of pixels to be referred to may be increased or decreased. In addition, the number of pixels in each pixel pattern may be increased or decreased without having to limit each pixel pattern to be divided within the pixel pattern to be referenced to 3 × 3 pixels.

 [0070] Furthermore, the smoothing method by the smoothing unit 7 need not be interpreted as being limited to the method described above. For example, the smoothed pixel value of the target pixel may be calculated by referring to the pixel value of each neighboring pixel within a predetermined range with respect to the target pixel and calculating an average value weighted at the center. Alternatively, the smooth pixel value may be set using the k-nearest neighbor method. That is, k pixels having a pixel value closest to the pixel value of the target pixel are extracted from neighboring pixels within a predetermined range with respect to the target pixel, and an average value of the pixel values of the extracted pixels is calculated. The smooth pixel value of the target pixel may be used.

 Further, the smoothed pixel value may be set using a selection averaging method. That is, an edge within a predetermined range with respect to the target pixel may be detected, and an average value of pixel values of neighboring pixels along the detected edge direction may be calculated to obtain the smoothed pixel value of the target pixel. Furthermore, smoothing may be performed using a known filter such as a median filter or a bilateral filter.

 Next, the initial region detection process in step S 105 will be described. In step S 105, the initial region detection unit 8 detects, as an initial region, each pixel having a smoothed pixel value larger than a predetermined value from each pixel constituting the smoothed image. At this time, the initial region detection unit 8 determines whether or not the smoothness pixel value is larger than a predetermined value for each pixel, and determines that the pixel determined to be large is a value of “1” and is not large. A value of “0” is set for the pixel. Then, a set of pixels for which “1” is set is detected as an initial region.

It should be noted that the value set for each pixel according to the determination result need not be limited to “1” and “0”, as long as the determination result can be determined, other numerical values, alphabets, symbols, etc. Even with Good. The predetermined value used as a criterion for determining the smoothness pixel value may be a fixed value for all pixels in the smoothness image, but the position of the pixel to be determined in the smoothness image The variation value may be in accordance with the smoothness pixel value or the like. Alternatively, the predetermined value may be a value obtained by using a known method such as a discriminant analysis method, which may be an average pixel value in a pixel block of a predetermined size! /.

 Further, the initial region detection method by the initial region detection unit 8 need not be interpreted as being limited to the method described above. For example, as shown in FIG. 7, it may be possible to detect a pixel group whose smoothed pixel value distribution shape satisfies a predetermined condition as an initial region. More specifically, this distribution shape is convex. A pixel group may be detected as the initial region. Here, FIG. 7 shows the distribution shape of the smoothed pixel value, where the horizontal axis indicates the pixel position in the smoothed image, and the vertical axis indicates the smoothed pixel value.

 For example, as shown in FIG. 7, the initial region detection unit 8 refers to pixels P2 and P3 that are symmetrically separated by a predetermined distance D with respect to the target pixel P1. Then, when compared with the average pixel value v23 of the pixel values V2 and v3 of the pixels P2 and P3, when the pixel value vl of the pixel of interest P1 is large, the pixel of interest P1 is detected as a pixel constituting the initial region. By repeating this detection process over the entire smoothed image, the initial region detection unit 8 can detect an initial region as a pixel group in which the distribution shape of the smoothed pixel values is convex.

 In addition, the initial region detection unit 8 is not limited to the case where the distribution shape of the smooth pixel value is convex, and detects, for example, a pixel group having a local maximum local distribution value as the initial region. Also good. Note that the initial region detection method by the initial region detection unit 8 is not limited to the method described above, and various methods can be applied.

 Next, the region deformation process in step S 107 will be described. FIG. 8 is a flowchart showing the processing procedure of the area transformation process. As shown in FIG. 8, first, the labeling unit 9a performs a labeling process for assigning a unique region marker to each initial region detected by the initial region detection unit 8 (step S121). Here, the region marker given by the marker 9a may be any notation using numbers, alphabets, symbols, etc. as long as it is unique.

Subsequently, the contour detection unit 9b detects a contour pixel indicating the contour of each initial region, and further detects an adjacent pixel that is a pixel adjacent to the contour pixel (step S123). Deformation judgment The unit 9c determines whether or not each detected adjacent pixel is a pixel constituting the target region, and deforms the initial region according to the determination result (step S125). Thereafter, the end determination unit 9d determines whether or not the force has deformed the initial region in step S125 (step S127).

) o

 [0079] When the initial region is deformed (step SI 27: Yes), the control unit 6 repeats the processing from step S123. On the other hand, when the initial area is not deformed (step S 127: No), the control unit 6 determines whether or not the force has processed all the initial areas (step S 129). If yes (step S129: No), repeat the process from step S123 for the initial area. If all have been processed (step S129: Yes), the control unit 6 causes the end determination unit 9d to output the deformation area data, and then returns to step S107.

 [0080] In step S123, the contour detection unit 9b refers to the area marker given by the marker 9a, and detects a series of pixels adjacent to the outside of each initial area as an adjacent pixel. In other words, the contour detection unit 9b searches for pixels that have not been assigned a region marker to determine whether or not a region marker has been added to pixels adjacent in the vertical, horizontal, and diagonal directions. In this case, the pixel to be processed is detected as an adjacent pixel. In this way, the contour detection unit 9b detects, as shown in FIG. 9, for example, a series of pixels indicated by diagonal lines adjacent to the outside of the initial area IA1 as adjacent pixels.

 Here, FIG. 9 is a schematic diagram illustrating an initial region detection image, and is a diagram in which a part of the initial region is enlarged and displayed. In the figure, each rectangular area indicates a pixel, and areas IA1 and IA2 surrounded by thick lines indicate a part of different initial areas.

[0082] In step S125, the deformation determination unit 9c satisfies the predetermined condition for the smoothed pixel value between the adjacent pixels in the initial region and the contour pixels constituting the contour of the initial region among a series of adjacent pixels. The added pixel is determined to be a target region pixel, and the initial region is expanded and deformed so as to capture the determined adjacent pixel. More specifically, the deformation determination unit 9c calculates a pixel value difference between the smoothed pixel values between the adjacent pixel and the contour pixel, and if the calculated pixel value difference is within a predetermined range, the deformation determination unit 9c The pixel is determined to be a target area pixel. Then, the modification is performed so that the adjacent pixel determined to be the target region pixel is taken into the initial region. The initial area The same area marker as that of the initial area is newly given to the adjacent pixels captured in.

 [0083] Further, the deformation determination unit 9c calculates a pixel value difference of the smoothness pixel value between the adjacent pixel and the contour pixel, and when the calculated pixel value difference exceeds a predetermined range, Neighboring pixels are not taken into the initial area. Further, when the adjacent pixel is adjacent to a plurality of different initial regions, the deformation determination unit 9c does not use the adjacent pixel as a pixel to be taken into the initial region. In other words, the deformation determination unit 9c determines that an adjacent pixel that is adjacent to only one initial region and whose calculated pixel value difference is within a predetermined range is a target region pixel, and takes it into the initial region. Let it be a pixel.

 [0084] The deformation determination unit 9c performs such processing in step S125 on a series of all adjacent pixels detected by the contour detection unit 9b. However, the deformation determination unit 9c can be executed only for adjacent pixels of a predetermined ratio or more in a series of adjacent pixels. For example, it can be executed only for each adjacent pixel separated by a predetermined interval. It is.

 For example, for the initial region IA1 shown in FIG. 9, the deformation determination unit 9c calculates a pixel value difference between the pixel PxO as the adjacent pixel and the pixels Pxl to Px3 as the contour pixels. If the pixel value difference is within the predetermined range, the pixel PxO is determined to be the target region pixel. More specifically, the deformation determination unit 9c determines that the pixel value differences between the pixels PxO and the pixel Pxl, the pixel PxO and the pixel Px2, and the pixel Pχθ and the pixel Px3 are all within a predetermined range. The pixel PxO is determined to be the target area pixel.

 Then, the deformation determination unit 9c performs the same determination processing for all adjacent pixels indicated by diagonal lines, and then takes each adjacent pixel determined to be the target region pixel in the initial region IA1. The initial area IA1 is expanded and deformed so that Note that the deformation determination unit 9c does not use the pixels Px4 to Px6 adjacent to the two initial areas IA1 and IA2 as pixels to be captured in any of the initial areas.

Here, the deformation determination unit 9c performs the determination process only on adjacent pixels separated by one pixel, for example, indicated by a circle among the adjacent pixels indicated by diagonal lines in the initial area IA1. You can also. In this case, the determination as to whether or not the non-processed adjacent pixel that is not marked with a ○ is a target region pixel is made based on, for example, the discrimination result for the neighboring pixel marked with a close ○. It is good to estimate. By reducing the adjacent pixels to be processed in this way, it is possible to reduce the processing load and processing time in the region deformation processing.

 [0088] It should be noted that in the determination process of whether or not the force is the target region, the deformation determination unit 9c has all the pixel value differences among the plurality of pixel value differences calculated for the adjacent pixels to be processed within a predetermined range. In addition to a certain case, for example, when a pixel value difference of a predetermined number or more or a predetermined ratio is within a predetermined range, the pixel to be processed is determined to be a target region pixel.

 In step S 127, the end determination unit 9 d determines the end or continuation of the region deformation process for the initial region to be processed depending on whether or not the initial region has been deformed in the immediately preceding step S 125. Here, if the initial region is deformed immediately before, it is highly necessary to deform the initial region, and it is determined that the region deformation process is to be continued. On the other hand, if the initial region is not deformed, the necessity of further deforming the initial region is low, and the end of the region deformation process is determined.

 In this way, the region deforming unit 9 determines whether or not each adjacent pixel is a target region pixel until the pixel value difference calculated by the deformation determining unit 9c exceeds a predetermined range, and this Based on the determination result, the initial region is repeatedly deformed.

 [0091] Here, the region deformation process is repeated until the initial region is no longer deformed, that is, until there are no adjacent pixels to be captured in the initial region. However, the present invention is limited to this. For example, when the number of adjacent pixels captured in the initial area is less than a predetermined number, or when the area deformation process is repeated a predetermined number of times, the area deformation process can be ended.

[0092] In the region deformation process described above, the deformation determination unit 9c expands and deforms the initial region by newly taking in adjacent pixels, but conversely, the initial region force is also applied to the contour pixels. By removing, the initial region can be contracted and deformed. In this case, when the pixel value difference between the adjacent pixel and the contour pixel is within a predetermined range, the contour pixel is determined to be a pixel outside the target region. When the initial region is contracted and deformed in this way, the initial region detection unit 8 detects the initial region so as to individually include the region corresponding to each imaging target. Further, in the region deformation process described above, it is determined whether or not the adjacent pixel is a pixel constituting the target region and the initial region is expanded and deformed. However, instead of the adjacent pixel, the initial region is changed to the initial region. It is also possible to detect pixels separated from the outline of the region by a predetermined distance and determine whether the detected pixel is a pixel constituting the target region, thereby expanding and deforming the initial region. When the initial region is contracted and deformed, instead of the contour pixel, the initial region contour is also used as a pixel separated from the initial region by removing the pixel and the contour pixel from the initial region. The region can be contracted and deformed.

 Next, the region integration processing in step S 109 will be described. FIG. 10 is a flowchart showing the processing procedure of the region integration processing. As shown in FIG. 10, first, the boundary detection unit 1 Oa detects an adjacent region group based on the deformation region data (step S141), and detects boundary pixels in the adjacent region group (step S143). . Subsequently, the feature amount calculation unit 10b calculates a feature amount between adjacent deformation regions in the adjacent region group (step S145). After that, the integration determination unit 10c determines whether or not the calculated feature amount is smaller than the predetermined value (step S1 47), and if it is smaller than the predetermined value (step S147: Yes), the adjacent deformation regions are integrated. (Step S149).

 [0095] Then, the control unit 6 determines whether or not the force has processed all the deformation areas (step S151), and when all the deformation areas have not been processed (step S151: No), The process from step S141 is repeated. If all are processed (step S1 51: Yes), the control unit 6 outputs the target area data from the integrated determination unit 10c, and then returns to step S109. If it is determined in step S147 that the feature amount is not smaller than the predetermined value (step S147: No), the integration determination unit 10c does not integrate the deformation area, and the control unit 6 determines in step S151. I do.

[0096] In step S141, the boundary detection unit 10a refers to the contour neighboring pixels of the deformation region, and detects the neighboring region group from the contour neighboring pixels by detecting pixels adjacent to the deformation region different from the deformation region. To detect. More specifically, the boundary detection unit 10a scans a series of adjacent pixels that are adjacent to the outside of the deformation area, and detects pixels having an area marker of a deformation area different from the deformation area around the adjacent pixels. In this case, it is determined that this deformation area is adjacent to another deformation area, and a set of these deformation areas is detected as an adjacent area group. [0097] In step S143, the boundary detection unit 10a scans a series of adjacent pixels that are adjacent to the outside of the deformation area, and is adjacent to the pixels included in the deformation area different from the deformation area from among the scanned adjacent pixels. Adjacent pixels are detected as boundary pixels between adjacent deformation regions. More specifically, when scanning the adjacent pixels, the boundary detection unit 10a refers to the area markers included in the eight pixels adjacent in the vertical and horizontal directions and in the oblique direction for each adjacent pixel, and detects pixels having different area markers. If it is detected, the adjacent pixel to be processed is determined as a boundary pixel and detected.

 [0098] In step S145, the feature amount calculation unit 10b sandwiches the boundary pixel with respect to each boundary line detected in step S143 based on the smoothness pixel values of the boundary pixel and the boundary neighboring pixels. To calculate the feature amount between adjacent deformation regions. More specifically, the feature amount calculation unit 10b calculates the average value of the smoothed pixel value difference between the boundary pixel and the boundary vicinity pixel located in the vicinity of the boundary pixel as the feature amount between the adjacent deformation regions. To do. Here, for example, a pixel that is a predetermined number of pixels away from the boundary pixel to be processed in the normal direction of the boundary line is selected as the boundary neighboring pixel.

 [0099] The feature amount calculation unit 10b, for example, as shown in FIG. 11, is predetermined in the normal direction of the boundary line A—B of the adjacent deformation areas AR1, AR2, and on the opposite side from the boundary line A—B. Set curves Α, -Β ', A "— Β" separated by the number of pixels. Then, for each boundary pixel on the boundary line Α—Β, the pixel of the smoothed pixel value between the pixel on the curve A′—B ′ and the pixel on the curve Α “—Β” corresponding to the normal direction. Each value difference is calculated. The feature amount calculation unit 10b calculates such a pixel value difference for all the boundary pixels on the boundary line A—B, and calculates an average value of all the calculated pixel value differences between the feature regions AR1 and AR2. Calculate as

 [0100] Note that the feature quantity calculation unit 10b can calculate not only the average value but also statistics such as the maximum value, the minimum value, and the standard deviation of the pixel value difference as the feature quantity. In addition, the feature amount calculation unit 10b calculates the feature amount based on the pixel value difference between the smoothness pixel values. For example, the feature amount calculation unit 10b calculates the feature amount based on the intersection angle of the contour lines of adjacent deformation regions. Can also be calculated.

[0101] In step S149, the integration determining unit 10c integrates adjacent deformed regions in the adjacent region group when it is determined in step S147 that the feature amount is smaller than a predetermined value. At this time, the integrated determination unit 10c selects one of the area markers of the adjacent deformation areas. The other area marker is rewritten by the other area marker. The determination in step S147 is based on the fact that when the feature amount is small, the change between adjacent deformation areas is small and can be regarded as the same deformation area.

 [0102] As described above, in the region extraction device 1 and the region extraction program according to the first embodiment, the input observation image is first subjected to smoothing processing, and based on the smoothed image, Therefore, the target area can be extracted stably and with high accuracy without being affected by noise included in the observation image.

 [0103] Further, in the region extraction device 1 and the region extraction program according to the first embodiment, a pixel group in which the size, distribution shape, etc. of the smoothed pixel values satisfy a predetermined condition is detected as the initial region. Therefore, for example, even when a plurality of target areas are adjacent to each other, it is possible to reliably detect individual initial areas corresponding to the target areas.

 [0104] Furthermore, in the region extraction device 1 and the region extraction program according to the first embodiment, a series of all adjacent pixels adjacent to the outside of the initial region to be used, or a predetermined ratio or more of the series of adjacent pixels. Since the initial region is deformed based on each adjacent pixel to form the target region, even if the shape of the imaging target changes, the contour shape of the imaging target is highly accurate regardless of the state of the imaging target. It is possible to extract the target area that matches the target.

 [0105] In addition, in the region extraction device 1 and the region extraction program according to the first embodiment, the initial region detection unit 8 detects the initial region corresponding to each imaging target, and the region deformation unit 9 uses each initial region. Since the deformed area is formed by deforming the area, and the deformed area is integrated by the area integration unit 10 to form the target area, the number of images to be imaged, the position, etc. are specified in advance. The target area can be extracted automatically without the need for setting.

[0106] Although the region extraction device 1 according to the first embodiment has been described as including the region integration unit 10 that integrates adjacent deformation regions, it is not necessary to integrate adjacent deformation regions. If the imaging target is not handled, it is not always necessary. Even when the region integration unit 10 is provided, the region integration processing may be omitted according to predetermined instruction information, for example. When region integration processing is not performed in this way, region transformation processing Each subsequent deformation area may be regarded as a target area, and the area extraction result may be obtained using the deformation area data as the target area data.

 [0107] Further, in the area extraction device 1 and the area extraction program according to the first embodiment, the area integration process is described as being executed after the area deformation process. However, the area integration process is incorporated into the area deformation process. You may make it perform. In this case, the region deforming unit 9 may detect adjacent initial regions as needed in the process of sequentially deforming each initial region, and perform region integration processing at the detected stage.

 [Embodiment 2]

 Next, a second embodiment of the present invention will be described. In the first embodiment described above, the region deformation processing and the region integration processing are performed based on the smooth smooth image. However, in the second embodiment, an edge included in the smooth smooth image is detected. Based on the detected edge detection image, perform region transformation processing and region integration processing based on V!

 FIG. 12 is a block diagram showing a configuration of the area extracting device 21 according to the second embodiment of the present invention. As shown in FIG. 12, the region extraction device 21 includes an image processing unit 23 and a control unit 26 instead of the image processing unit 3 and the control unit 6 based on the configuration of the region extraction device 1. Further, the image processing unit 23 includes a region deformation unit 29 and a region integration unit 30 instead of the region deformation unit 9 and the region integration unit 10 based on the configuration of the image processing unit 3, and a new edge detection unit 31. Equipped.

 FIGS. 13 and 14 are block diagrams showing detailed configurations of the region deforming unit 29 and the region integrating unit 30, respectively. As shown in FIG. 13, the region deforming unit 29 includes a deformation determining unit 29c instead of the deformation determining unit 9c based on the configuration of the region deforming unit 9. As shown in FIG. 14, the region integration unit 30 includes a feature amount calculation unit 30b instead of the feature amount calculation unit 10b based on the configuration of the region integration unit 10. The other configuration of the region extracting device 21 is the same as that of the first embodiment, and the same components are denoted by the same reference numerals.

[0111] The edge detection unit 31 acquires the smoothed image output from the smoothing unit 7, detects the edge included in the acquired smoothed image by filtering, and generates an edge image indicating the detected edge To do. The edge detection unit 31 detects an edge using, for example, a Sobel filter, a Laplacian filter, or a pre-witt filter. In addition, the edge detection unit 31 generates the generated error. The wedge image is output to the region transformation unit 29 and the region integration unit 30. The edge detection unit 31 can also output and store the edge image in the storage unit 5 via the control unit 26.

 The area deforming unit 29 executes the same process as the area deforming unit 9. However, the area deforming unit 29 acquires the edge image from the edge detecting unit 31 using the area deforming unit 29c, instead of the area deforming unit 9 acquiring the smoothed image from the smoothing unit 7 using the deformation determining unit 9c. In addition, instead of the region deforming unit 9 performing the process of determining whether or not the image is the target region image based on the smoothed pixel value by the deformation determining unit 9c, the region deforming unit 29 is replaced by the deformation determining unit 29c. Based on the edge pixel value possessed by each pixel in the edge image, it is determined whether or not the pixel is the target region pixel.

 The area integration unit 30 executes the same processing as that of the area integration unit 10. However, instead of the region integration unit 10 acquiring the smoothed image from the smoothing unit 7 by the feature amount calculation unit 10b, the region integration unit 30 receives the edge image from the edge detection unit 31 by the feature amount calculation unit 30b. get. In addition, instead of the region integration unit 10 calculating the feature amount between adjacent deformation regions based on the smoothed pixel value by the feature amount calculation unit 10b, the region integration unit 30 uses the feature amount calculation unit 30b. The feature amount is calculated based on the edge pixel value.

 Here, a processing procedure performed by the region extraction device 21 will be described. FIG. 15 is a flowchart showing a processing procedure of region extraction processing in which the region extraction device 21 processes and displays an observation image by the control unit 26 executing the region extraction program. FIG. 16 is a schematic diagram showing an edge image generated by the edge detection unit 31 as a result of the edge detection process shown in FIG. FIG. 16 shows an example of an edge image generated from the smooth wrinkle image shown in FIG. 4-1.

 As shown in FIG. 15, first, the input unit 2, the smoothing unit 7, and the initial region detecting unit 8 acquire observation images in the same manner as in steps S101 to S105 shown in FIG. Step S1 61), smoothing process (step S163) and initial area detection process (step S165)

[0116] Next, the edge detection unit 31 performs edge detection processing for detecting an edge of the smooth image obtained from the smoothing unit 7 and generating an edge image (step S167). In step S167, the edge detection unit 31 performs the smoothed image shown in FIG. 4-1, for example, as shown in FIG. The edge of each cell region in the image is detected and imaged. The edge detection unit 31 outputs the generated edge image to the region deformation unit 29 and the region integration unit 30. Note that the processing order of step S167 and step S165 may be exchanged.

 [0117] Subsequently, the region transformation unit 29, the region integration unit 30 and the output unit 4 sequentially perform region transformation processing (step S169) and region integration processing in the same manner as steps S107 to S111 shown in FIG. (Step S171) and display of extraction results (Step S173) are performed, and then the control unit 26 ends a series of region extraction processing.

 [0118] However, in step S169, the area deforming unit 29 does not perform the process of determining whether or not the pixel is the target area pixel based on the smoothness pixel value in step 107, but based on the edge pixel value. This determination process is performed. That is, the deformation determination unit 29c determines that a pixel satisfying a predetermined condition for an edge pixel value with respect to a contour pixel from a series of adjacent pixels adjacent to the outside of the initial region is a target region pixel. The initial area is expanded and deformed so as to capture the adjacent pixels. More specifically, the deformation determination unit 29c calculates the pixel value difference of the edge pixel value between the adjacent pixel and the contour pixel, and when the calculated pixel value difference is within a predetermined range, the adjacent pixel Is determined to be a target area pixel.

 [0119] Further, the deformation determination unit 29c calculates a pixel value difference of the edge pixel value between the adjacent pixel and the contour pixel, and if the calculated pixel value difference exceeds the predetermined range, the deformation determination unit 29c sets the initial region. Do not use pixels to capture. Furthermore, when the adjacent pixel is adjacent to a plurality of different initial regions, the deformation determination unit 29c does not regard the adjacent pixel as a pixel that is taken into the initial region. In other words, the deformation determination unit 29c determines that an adjacent pixel that is adjacent to only one initial region and has a calculated pixel value difference within a predetermined range is a target region pixel, and incorporates it into the initial region. Let it be a pixel.

 [0120] It should be noted that the deformation determination unit 29c can also shrink and deform the initial region by removing the contour pixels, similarly to the deformation determination unit 9c.

[0121] On the other hand, in step S171, the region integration unit 30 calculates this feature amount based on the edge pixel value instead of calculating the feature amount between adjacent deformation regions based on the smoothed pixel value in step S109. Is calculated. That is, the feature amount calculation unit 30b sandwiches the boundary pixel based on the edge pixel values of the boundary pixel and the boundary neighboring pixel. A feature amount between adjacent deformation regions is calculated. More specifically, the feature amount calculation unit 30b calculates the average value of the difference between the edge pixel values of the boundary pixel and the boundary vicinity pixel located in the vicinity of the boundary pixel as the feature amount between the adjacent deformation regions. To do.

 [0122] It should be noted that, similarly to the region extraction device 1, the region extraction device 21 does not necessarily include the region integration unit 30 when it is not necessary to integrate adjacent deformation regions or when an adjacent imaging target is not handled. It does not have to be. Further, even when the area integration unit 30 is provided, for example, the area integration processing may be omitted according to predetermined instruction information.

 [0123] As described above, in the region extracting device 21 and the region extracting program according to the second embodiment, the initial region is deformed and the deformed region is integrated based on the edge pixel value. Therefore, it is possible to shape and extract a target region that more precisely matches the contour shape of the imaging target.

 Note that the pixel values such as the smooth gradation pixel value and the edge pixel value used in the region extraction device according to the first and second embodiments described above include a luminance value, a gray value, a gradation value, an intensity value, and the like. included . In particular, the edge pixel value includes an edge strength value indicating the strength of the detected edge. The region extraction apparatus according to the first and second embodiments can appropriately select and process various values of the medium value that uses the pixel value according to the form of the input observation image.

 Industrial applicability

As described above, the region extraction device and the region extraction program according to the present invention are useful for the region extraction device and the region extraction program that extract the image region corresponding to the imaging target from the input image. In particular, it is suitable for an area extraction apparatus and an area extraction program that stably and highly accurately extract image areas corresponding to individual imaging targets.

Claims

The scope of the claims

 [1] In an area extraction device that extracts a target area, which is an image area corresponding to an imaging target, from input images,

 Smoothing means for generating a smoothed image obtained by smoothing the image;

 Based on the smoothed pixel value of each pixel in the smoothed image, the initial region detection is performed to detect an initial region that is an image region including at least a part of the imaging target from the smoothed image. Means,

 Based on the smoothed pixel value of the contour neighboring pixels of the initial region, it is determined whether or not the contour neighboring pixels are target region pixels constituting the target region, and according to the determination result, A region deforming means for deforming at least one of the size and shape of the initial region to form the target region;

 An area extracting apparatus comprising:

 [2] In an area extraction device that extracts a target area, which is an image area corresponding to an imaging target, from input images,

 Smoothing means for generating a smoothed image obtained by smoothing the image;

 An initial region detecting means for detecting an initial region that is an image region including at least a part of the imaging target from the smoothed image based on a smoothed pixel value of each pixel in the smoothed image. When,

 An edge detection means for generating an edge image in which an edge included in the smooth image is detected;

 Based on the edge pixel values of the pixels in the edge image corresponding to the contour neighboring pixels of the initial region, it is determined whether or not the contour neighboring pixels are target region pixels constituting the target region. Region deforming means for determining, and deforming at least one of the size and shape of the initial region in accordance with the determination result to form the target region;

 An area extracting apparatus comprising:

[3] The region extracting device according to claim 1 or 2, wherein the initial region detecting means detects each pixel having the smoothed pixel value larger than a predetermined value as the initial region.

[4] The initial region detecting means detects, as the initial region, a pixel group in which a distribution shape of the smoothed pixel value with respect to a pixel position in the smoothed image satisfies a predetermined condition. Item 1. The region extraction device according to item 1 or 2.

 5. The area extracting apparatus according to claim 4, wherein the initial area detecting means detects a pixel group having a convex distribution shape as the initial area.

 [6] The region deforming means may include the smooth smoothing between contour pixels in the initial region and constituting the contour of the initial region among a series of adjacent pixels adjacent to the outside of the initial region. The region extracting apparatus according to claim 1, wherein a pixel whose pixel value satisfies a predetermined condition is determined as the target region pixel, and the initial region is modified so as to capture the determined adjacent pixel.

 [7] The region deforming means determines that the adjacent pixel whose pixel value difference between the smoothed pixel values is within a predetermined range between the adjacent pixel and the contour pixel is the target region pixel. The region extracting apparatus according to claim 6, wherein:

 [8] The region deforming means may include the edge between a series of adjacent pixels adjacent to the outside of the initial region and a contour pixel that is in the initial region and forms a contour of the initial region. 3. The region extraction device according to claim 2, wherein a pixel whose pixel value satisfies a predetermined condition is determined as the target region pixel, and the initial region is modified so as to capture the determined adjacent pixel. .

 [9] The region deforming means determines that the adjacent pixel in which a pixel value difference of the edge pixel value is within a predetermined range between the adjacent pixel and the contour pixel is the target region pixel. 9. The region extracting apparatus according to claim 8, wherein

 [10] The region deforming means is configured to smooth the smoothing between adjacent pixels adjacent to the outside of the initial region among a series of contour pixels that are in the initial region and form the contour of the initial region. 2. The region extraction according to claim 1, wherein a pixel whose pixel value satisfies a predetermined condition is determined to be a pixel outside the target region, and the initial region is modified so as to remove the determined contour pixel. apparatus.

[11] The region modifying means determines that the contour pixel in which a pixel value difference between the smoothed pixel values is within a predetermined range between the adjacent pixel and the contour pixel is a pixel outside the target region. 11. The region extraction device according to claim 10, wherein the region extraction device is separate.

 [12] The region deforming means includes the edge between the adjacent pixels adjacent to the outside of the initial region among a series of contour pixels in the initial region and constituting the contour of the initial region. The region extraction according to claim 2, wherein a pixel whose pixel value satisfies a predetermined condition is determined to be a pixel outside the target region, and the initial region is modified so as to remove the determined contour pixel. apparatus.

 [13] The region modification means determines that the contour pixel in which a pixel value difference of the edge pixel value is within a predetermined range between the adjacent pixel and the contour pixel is a pixel outside the target region. The region extracting apparatus according to claim 12, wherein:

 [14] The region modifying means repeats the determination of whether or not the pixel is the target region pixel and the deformation of the initial region until the pixel value difference exceeds the predetermined range. The region extraction device according to any one of 9, 11 and 13.

 [15] The region deforming means may include adjacent pixels that are adjacent to the outside of one of the initial regions and are not adjacent to the outside of the other initial region, and that satisfy the predetermined condition. The region extraction device according to claim 6, wherein the region extraction device is discriminated as being.

 [16] The region deformation means, for a series of all adjacent pixels adjacent to the outside of the initial region, or for each adjacent pixel of a predetermined ratio or more of a series of adjacent pixels adjacent to the outside of the initial region, 16. The region extracting apparatus according to claim 6, wherein whether or not the force is a target region pixel is determined.

 [17] An adjacent region group formed by the adjacent deformed regions is detected from the deformed regions that are image regions as a result of the deformation by the region deforming means, and adjacent deformations in the detected adjacent region group are detected. Based on the feature amount indicating the feature between the regions, the region further includes a region integration unit that forms the target region by integrating the adjacent deformation regions. The region extraction device according to one.

 18. The area extracting apparatus according to claim 17, wherein the area integrating unit calculates the feature amount and integrates the deformed regions based on the calculated feature amount.

[19] The region integration means may change the deformation of the processing target from the pixels near the contour of each deformation region. 19. The area extracting apparatus according to claim 17, wherein the adjacent area group is detected by detecting pixels included in a deformation area different from the area.

[20] An adjacent region group formed by the adjacent deformed regions is detected from each deformed region that is an image region as a result of deformation by the region deforming means, and between the deformed regions in the detected adjacent region group. A feature amount indicating a feature between the deformation regions is calculated based on the smooth pixel value of the boundary pixel indicating the boundary line and the boundary vicinity pixel near the boundary line, and based on the calculated feature amount 2. The area extracting apparatus according to claim 1, further comprising area integration means for forming the target area by integrating the deformation areas in the adjacent area group.

 [21] The region integration unit calculates, as the feature amount, an average value of the difference between the smoothed pixel values of each boundary pixel on the boundary line and a boundary vicinity pixel near each boundary pixel. 21. The region extraction device according to claim 20.

 [22] An adjacent region group formed by the adjacent deformed regions is detected from among the deformed regions that are image regions as a result of the deformation by the region deforming means, and between the deformed regions in the detected adjacent region group. A feature amount indicating a feature between the deformation regions is calculated based on the edge pixel value of the boundary pixel indicating the boundary line and the boundary pixel near the boundary line, and based on the calculated feature amount, 3. The area extracting apparatus according to claim 2, further comprising area integration means for integrating the deformation areas in the adjacent area group to form the target area.

 [23] The region integration means calculates, as the feature amount, an average value of the difference between the edge pixel values of each boundary pixel on the boundary line and a boundary neighboring pixel in the vicinity of each boundary pixel. The region extracting apparatus according to claim 22.

 [24] The region integration unit scans a series of adjacent pixels adjacent to the outside of each deformation region in the detected adjacent region group, and adjacent pixels outside the deformation region different from the deformation region to be processed. The region extracting apparatus according to any one of claims 20 to 23, wherein: is detected as the boundary pixel.

[25] Region extraction for causing a region extraction device that extracts a target region, which is an image region corresponding to an imaging target, from the input image to extract the target region from the middle of the image In the program

 In the region extraction device,

 A smoothing procedure for generating a smoothed image obtained by smoothing the image;

 An initial region detection procedure for detecting an initial region that is an image region including at least a part of the imaging target from the smoothed image based on a smoothed pixel value of each pixel in the smoothed image. When,

 Based on the smoothed pixel value of each contour neighboring pixel in the initial region, it is determined whether or not each contour neighboring pixel is a target region pixel constituting the target region, and according to the determination result. An area deformation procedure for deforming at least one of the size and shape of the initial area to form the target area;

 A region extraction program characterized by causing

 In an area extraction program for causing a region extraction device that extracts a target region, which is an image region corresponding to an imaging target, from an input image to extract the target region from the middle of the image,

 In the region extraction device,

 A smoothing procedure for generating a smoothed image obtained by smoothing the image;

 An initial region detection procedure for detecting an initial region that is an image region including at least a part of the imaging target from the smoothed image based on a smoothed pixel value of each pixel in the smoothed image. When,

 An edge detection procedure for generating an edge image in which an edge included in the smooth image is detected;

 Whether each pixel near the contour is a target region pixel constituting the target region based on an edge pixel value of each pixel in the edge image corresponding to each pixel near the contour in the initial region An area deformation procedure for forming the target area by deforming at least one of the size and shape of the initial area according to the determination result;

 A region extraction program characterized by causing