KR20080095616A - Calculating method of actual size of object and system thereof - Google Patents

Abstract

A method of calculating actual size of an image and a system thereof are provided to calculate size of an interesting area quickly in a photographed image and estimate actual size of a diseased part more accurately when photographing the diseased part. An analysis processing unit receives information with regard to a target that a user wants to obtain to calculate actual size of an image through an input unit if the image obtained from a camera unit is transmitted to the analysis processing unit(S110). The number of pixels is obtained(S120). The number of pixels is divided by a maximum pixel number of an image provided from meta information in the camera unit, and multiplied by size of a photographing element to calculate image size of a target(S130).

Description

Calculating method of actual size of object and system

1 is a system configuration diagram for calculating the real size of an image according to an embodiment of the present invention.

2 is a flowchart illustrating a method of calculating a real size of an image according to a first exemplary embodiment of the present invention.

3 is a flowchart illustrating a method of obtaining the number of pixels involved in an object through an image segmentation technique.

4 is a flowchart illustrating a method of calculating a real size of an image according to a second exemplary embodiment of the present invention.

5 is a conceptual diagram illustrating a geometrical processing method applied to a second embodiment of the present invention.

6 is a flowchart illustrating a method of calculating a real size of an image according to a third exemplary embodiment of the present invention.

<Description of Symbols for Main Parts of Drawings>

100: camera unit 110: wireless transmission unit

120: imaging device 200: analysis processing unit

210: input unit 220: calculation processing unit

230: display unit

The present invention relates to a method and a system for calculating the real size of an image, and more particularly, to a method and a system for calculating the exact real size of an object of interest in an image taken with a digital camera.

In the medical field, there are many ways to know and treat a patient's condition. Among such methods, there is a medical assistance method that provides information on the depth of burn (degree of first degree, second degree burn, etc.) and the size of the affected area for the treatment of burn patients.

In the related art, a method of calculating the area of the affected area by applying a grid paper directly to the affected part of the burn patient, or photographing the affected area with an imager or the like and manually calculating the area through a general-purpose program such as Photoshop.

As described above, the method of manually calculating the area was difficult to calculate the accurate area, and the calculation time was cumbersome.

Accordingly, the present invention is to solve the above-mentioned disadvantages and problems of the prior art, the technical problem to be achieved by the present invention, the actual size of the image to be able to quickly process the size calculation of the region of interest in the photographed image It is to provide a calculation method and a system thereof.

Another object of the present invention is to provide a real size calculation method of an image capable of calculating an actual size of an ROI using meta information of a captured image.

In addition, another technical problem to be achieved by the present invention is to provide a method for calculating the actual size of an image capable of accurately measuring the actual area of the affected part in the medical field.

The objects of the present invention are not limited to the above-mentioned objects, and other objects which are not mentioned will be clearly understood by those skilled in the art from the following description.

According to an aspect of the present invention, there is provided a method for calculating the actual size of an object captured by an image, the method comprising: obtaining the number N of pixels involved in the object captured by the image; Dividing the number N of pixels involved in the object by the maximum number of pixels of the image, multiplying the size of the image pickup device to obtain the size of the image of the object captured on the image, and substituting the size of the image of the object into a lens formula Obtaining the actual size of the object.

Here, the maximum number of pixels of the image is preferably information obtained from meta information of the digital camera.

In the obtaining of the number N of pixels related to the object, the number N of pixels related to the object may be obtained using an image segmentation technique.

In this case, obtaining the number N of pixels involved in the object by using the image segmentation technique may include detecting a boundary of the object, and determining one or more pixels corresponding to the boundary and the boundary. It is preferable to include the step of constructing a binary image of the pixel to be 0.

The determining of the number N of pixels involved in the object may include measuring the number N of pixels involved in the object at least two times, and an average value according to each result value measured at least two times. The method may include calculating the number of pixels N involved in the object.

The method may further include correcting an error of an actual size resulting from the difference between the maximum number of pixels and the actual number of pixels of the image capturing device.

In addition, the present invention is a method for obtaining the actual size of the object imaged on the image, comprising the steps of arranging the start pixel and the end pixel of the length to be measured of the object imaged on the image on the coordinates displayed on the horizontal axis and the vertical axis, Obtaining a number of pixels (I, J) for each of the horizontal lines formed by the intersection of the horizontal axis and the vertical axis and the start pixel, and the vertical lines formed by the intersection of the intersection pixel and the end pixel; And calculating a size of the horizontal line and the vertical line with respect to the size of the image of the object by referring to a J value, the maximum number of pixels of the image, and the size of the image pickup device, and the horizontal line and the vertical line. Calculating the actual size of the object by substituting the magnitude of the direction line into the Pythagorean theorem and lens formula. There.

In this case, obtaining the sizes of the horizontal line and the vertical line with respect to the size of the image of the object, respectively, dividing I by the horizontal maximum pixel number of the image, multiplying the horizontal size of the image pickup device, Obtaining the size of the vertical line with respect to the size of the object by dividing the size of the horizontal line with respect to the size of the image, dividing the J by the maximum number of pixels in the vertical direction of the image, and multiplying the vertical size of the image pickup device. It may include a step.

On the other hand, the actual size calculation system of the image according to the present invention for achieving the above object, the camera unit on which the meta information, the image received from the camera unit is received, and inputs the information on the object captured in the image And an analysis processor for calculating and outputting the actual size of the object.

Here, the camera unit preferably includes a wireless transmission unit of an ultra wideband (UWB) wireless communication method.

The analysis processor may calculate an actual size of the object by applying a lens formula based on an input unit to receive information about the object in the image transmitted from the camera unit, the number of pixels involved in the object, and the meta information. It may include a calculation processing unit.

Here, the calculation processing unit divides the number N of pixels involved in the object by the maximum number of pixels of the image, multiplies the size of the image pickup device, obtains the size of the image of the object imprinted on the image, and calculates the size of the image of the object. It is desirable to calculate the actual size of the object by substituting the lens formula.

Details of the above object and technical configuration of the present invention and the resulting effects thereof will be more clearly understood from the following detailed description based on the accompanying drawings.

First, FIG. 1 is a diagram illustrating a system configuration for calculating a real size of an image according to an exemplary embodiment.

As shown in FIG. 1, a system for calculating a real size of an image according to an exemplary embodiment of the present invention receives a camera unit 100 for acquiring an image and information about an object for which an actual size is to be obtained from the image. And an analysis processor 200 for calculating and outputting the actual size of the object.

The camera unit 100 includes a wireless transmitter 110 and an imaging device 120. In this case, the imaging device 120 may be a charge coupled device (CCD) or a complementary metal oxide semiconductor (CMOS) image sensor.

On the other hand, the camera unit 100 is a digital camera (DSC; Digital Still Cameras) format, and carries the standard information called the meta information (Exif; Exchangeable image file format) for handling the captured image in another system.

The basic image of the DSC is largely in JPEG (ISO / IEC 10918-1) compression standard format or TIFF Rev. It is stored in the uncompressed standard format of 6.0, which consists of a basic substructure called the Image File Directory (IFD), which contains various tags and their corresponding values. In particular, there is a sub-IFD (SubIFD) specifically allocated for the meta information in the first IFD (IFD0; main image information), and these tags contain various information such as the manufacturer, product name, shooting time, and shooting method of the digital camera. have.

In embodiments of the present invention, a method of calculating an actual size of a photographing target using some information of the meta information is adopted.

Specifically, information on the distance to the object (SubjectDistance; d), the focal length (FocalLength; f), the horizontal maximum pixel number (ExifImageWidth; w), and the vertical maximum pixel number (ExifImageWidth; h) Can be used.

In addition, the wireless transmitter 110 transmits an image captured by a wireless communication method to the analysis processor 200, and transmits a large amount of digital data through a wide spectrum frequency at low power in a short range. It is desirable to use ultra wideband (UWB) wireless communication.

The analysis processor 200 may further include an input unit 210 that receives information about an object for which an actual size is to be obtained from an image transmitted from the camera unit 100, the number of pixels related to the object, and the meta information. A calculation processor 220 for calculating an actual size of the object by applying a lens formula to the display unit, and a display unit 230 for outputting the actual size of the object obtained by the calculation processor 220.

Here, the input unit 210 may receive information about the object in various ways, for example, selection of a location through a user's mouse click or a change to standard information previously stored in the analysis processing unit 200. Alternatively, information about the object may be input through a target identification according to a movement or a wavelet technology that is well known.

In addition, the calculation processing unit 220 divides the number of pixels involved in the object by the maximum number of pixels of the received image, multiplies the size of the image pickup device 120 to obtain the size of the image of the object captured in the image, and The actual size of the subject may be calculated by substituting the subject's image size into the lens formula.

Here, the size of the imaging device 120 means a size corresponding to the maximum number of pixels of the video.

Specific embodiments of the real area calculation in the system for calculating the real size of the image described above will be described in detail with reference to the flowcharts of FIGS. 2 to 4 and 6.

First, a method for calculating the real size of an image according to the first embodiment of the present invention will be described with reference to the flowcharts of FIGS. 2 and 3.

2 is a flowchart illustrating a method for calculating the real size of an image according to the first embodiment of the present invention, and FIG. 3 is a flowchart illustrating a method of obtaining the number of pixels involved in an object through an image segmentation technique.

As shown in FIG. 2, first, when an image obtained from the camera unit 100 is transmitted to the analysis processing unit 200, the analysis processing unit 200 determines an actual size of the image through the input unit 210. Receive information on the target to obtain (S110).

In step S110, the information about the object may be input in various ways. For example, the user may click on a user's mouse to select a location or change or move the standard information previously stored in the analysis processing unit 200. According to the object identification, or through a well-known wavelet (wavelet) technology can receive information about the object.

Next, the number of pixels (named N) involved in the object is obtained (S120).

In this case, the number N of pixels involved in the object may be calculated using an image segmentation technique.

Specifically, a method of obtaining the number N of pixels related to the object through the image segmentation technique, as shown in FIG. The contour of the object is detected using information extracted from the feature information, the change of the feature information, the motion prediction of the object, or the wavelet technology, and the boundary of the object is detected (S121).

Next, a binary image is configured by setting the boundary of the object and the pixel within the boundary to 1 (white), and setting the corresponding pixel to 0 (black) (S122). .

Then, since the sum (or the number of 1s) of all the pixel values of the binary image is the number of pixels involved in the area of the object, the sum of all pixel values of the binary image is obtained to determine the number of pixels involved in the object. (N) can be obtained (S123).

Next, the number N of pixels related to the object obtained is divided by the maximum number of pixels w and h of the image provided from the meta information mounted on the camera unit 100, and the size W of the image pickup device. Multiply by H) to obtain the size of the image of the object captured in the image (S130).

In detail, the size B of the target image may be obtained through Equation 1 below.

Here, Bw represents the size in the horizontal direction of the object, and Bh represents the size in the vertical direction of the object. N is the number of pixels involved in the length of the object, W is the horizontal size of the imaging device, and H is the vertical size of the imaging device.

W is the maximum number of pixels in the horizontal direction of the image, and h is the maximum number of pixels in the vertical direction of the image.

On the other hand, the maximum number of pixels (w, h) of the image can be provided as meta information of the digital camera, the size (W, H) of the image pickup device is the size corresponding to the maximum number of pixels (w, h) of the image Assume that

In general, there may be a difference between the maximum number of pixels and the actual number of pixels in the image. In the first embodiment of the present invention, it is assumed that the difference between the maximum number of pixels and the actual number of pixels is not large. Although the size of the device is assumed to be the size corresponding to the maximum number of pixels of the image, when a separate correction is required, the description thereof will be described later.

Therefore, since the area Bs of the target image is a value obtained by multiplying the size Bw in the horizontal direction by the size Bh in the vertical direction, it can be expressed by Equation 2 below.

Here, Bs represents the area of the image of the object. N 'is the number of pixels involved in the area of the object.

Next, the actual size A of the object may be obtained by substituting the size B of the object into a lens formula (S140).

Specifically, the actual size A of the object may be obtained through Equation 3 below.

Here, Aw represents the actual size of the object in the horizontal direction, Ah represents the actual size of the object in the longitudinal direction, and As represents the actual area of the object.

N is the number of pixels involved in the length of the object, and N 'is the number of pixels involved in the area of the object. W is the horizontal size of the imaging device, and H is the vertical size of the imaging device. W is the maximum number of pixels in the horizontal direction of the image, and h is the maximum number of pixels in the vertical direction of the image.

D is the distance to the object and f is the focal length.

Equation 3 is a formula derived using the data obtained from the meta information and the lens formula, and the calculation derivation process according to this will be described in detail as follows.

In general, the lens formula for calculating the size of an object with respect to the size of an image is expressed by Equation 4 below.

Here, A is the size of the object, B is the size of the image, f is the focal length, and a represents the distance from the lens center to the object.

On the other hand, in the embodiment of the present invention, if a distance from the center of the lens to the end boundary of the lens is negligibly smaller than the distance to the object, a is the working distance (d) which is the distance from the end boundary of the lens to the object You can think of it as.

Here, d may be provided from the meta information.

Therefore, if the following symbols are defined for the width (width) and height (length) of the object in Equation 4 above, and the relationship between f and d is listed, the following Equation 5 can be expressed.

Here, Wo represents the width of the object and Wi represents the width of the image. In addition, Ho represents the height of the object and Hi represents the height of the image.

An image formed on the image pickup device includes a plurality of pixels. If the width of a single pixel is wi and the height of a single pixel is hi, Equation 5 may be expressed as Equation 6 below.

In addition, the width W and the height H of the image pickup device having different images have unique values for each digital camera product. The size W and H of the image pickup device and w, which are obtained from the meta information after photographing, By using the value of h, the width and height (wi, hi) of the single pixel can be obtained, from which Equation 6 can be represented by Equation 7 below.

In addition, assuming that the area of the object exists on a plane, the area So of the object has a relationship with the small area of the object so and the single pixel area si that can be inferred by Equation 7 above. It may be expressed as Equation 8 below.

? Denoted by Equations 6 to 8 means the number of pixels involved in the area of the object to be measured.

That is, the number of pixels involved in the area of the object is expressed as N ', the width of the object (Wo) is displayed in the horizontal direction actual size (Aw) of the object, and the height (Ho) of the object is expressed in the vertical direction actual size of the object. If expressed as (Ah) and the area So of the object is expressed as the actual area As of the object, Equations 7 and 8 may be finally expressed by Equation 3 above.

Next, a method for calculating the real size of an image according to the second embodiment of the present invention will be described with reference to the flowchart of FIG. 4 and FIG. 5.

4 is a flowchart illustrating a method of calculating the real size of an image according to a second embodiment of the present invention, and FIG. 5 is a conceptual diagram illustrating a geometric processing method applied to the second embodiment of the present invention.

First, as shown in FIG. 4, when an image obtained from the camera unit 100 is transmitted to the analysis processing unit 200, the analysis processing unit 200 determines an actual size of the image through the input unit 210. Receive information on the target to obtain (S210).

Next, the position of the pixel is determined by arranging the start pixel and the end pixel of the length to be measured of the object captured on the image on the coordinates indicated by the horizontal axis (i) and the vertical axis (j) (S220).

For example, in FIG. 5, it is assumed that the start pixel P is disposed on the coordinates P (i1, j1) and the end pixel K is disposed on the coordinates K (i2, j2).

Next, the pixel number I involved in the horizontal length where the intersection point O formed by the i-axis and the j-axis orthogonal to the start pixel P meet is obtained. In the same manner, the number of pixels J involved in the longitudinal length at which the intersection point O and the end pixel K meet is obtained (S230).

In this case, it is preferable to obtain the I and J by measuring the I and J at least twice each, and deriving an average value according to each result value measured at least twice.

Subsequently, the sizes of the horizontal line and the vertical line with respect to the size of the image of the object are obtained by referring to the I and J values, the maximum number of pixels of the image and the size of the image pickup device (S240).

Specifically, the size of the horizontal line with respect to the size of the target image may be obtained by dividing I by the horizontal maximum pixel number w of the image and multiplying the horizontal size W of the image pickup device. In the same manner, the size of the vertical line with respect to the size of the image of the object may be obtained by dividing J by the maximum number of pixels h in the vertical direction of the image and multiplying the vertical size H of the image pickup device.

Next, the magnitude of the horizontal line and the vertical line are substituted into the Pythagorean theorem to obtain the size of the image of the length to be measured (named D), and substituted into the lens formula to substitute the actual size of the object (A (D)) can be obtained (S250).

Specifically, using the Pythagorean theorem, the size D of the length to be measured may be calculated by Equation 9 below.

Substituting Equation 9 into the lens formula, the actual size A (D) of the object may be calculated by Equation 10 below.

or,

As described above, in the second embodiment of the present invention, the actual size of the object may be obtained by a geometric processing method.

Meanwhile, Equations 9 and 10 used in the method for calculating the real size of the image according to the second embodiment may be equally derived from the above-described equations and lens formulas in the first embodiment of the present invention. The detailed description thereof will be omitted.

Next, a method for calculating a real size of an image according to a third embodiment of the present invention will be described with reference to the flowchart of FIG. 6.

6 is a flowchart illustrating a method of calculating a real size of an image according to a third exemplary embodiment of the present invention.

As shown in FIG. 6, first, when an image acquired from the camera unit 100 is transmitted to the analysis processing unit 200, the analysis processing unit 200 determines an actual size of the image through the input unit 210. Receive information on the target to obtain (S310).

Next, the number N of pixels involved in the object is measured at least twice (S320).

At this time, the number N of pixels involved in the object is measured at least twice, but it is preferable to measure the number of times so that the measurement error is not large.

Next, an average value according to each result value measured two or more times is derived to obtain the number N of pixels involved in the object (S330).

Subsequently, the obtained number of pixels N related to the object is divided by the maximum number of pixels (w, h) of the image provided from the meta information of the camera unit 100, and the size (W, H) of the imaging device is divided. Multiplying to obtain the image size (B) of the subject imaged on the image (S340).

Next, the actual size A of the object may be obtained by substituting the size B of the object into a lens formula (S350).

Meanwhile, in the third embodiment of the present invention, all the steps except for the above steps S320 and S330 are the same as those of the first embodiment of the present invention, and thus a detailed description thereof is omitted.

In addition, an error correction step may be further performed as matters applicable to the first to third embodiments of the present invention.

Specifically, the size (W, H) of the image pickup device means a size corresponding to the actual number of pixels, but generally, there is a difference between the maximum number of pixels and the actual number of pixels of the image pickup device.

For example, assuming that the maximum number of pixels of an image pickup device of a specific company product is 7.4 million pixels, and that the actual number of pixels is 7.2 million pixels, the embodiment of the present invention calculates the size of the specific image pickup device to a size corresponding to the maximum number of pixels. Fields contain approximately 2.7% area measurement error.

That is, it is preferable to perform error correction that requires to consider the area of the imaging device as small as 2.7%.

This means that 1.64% of the width and the height are measured to be large, assuming square pixel pixels. Therefore, the actual length of the final object is corrected by multiplying 0.9836 times the result of calculating the actual size (A) of the object. Can be determined by value.

In addition, to correct the area, an area error of 2.7% may be applied, and the corrected value may be determined as the actual area value of the final object by multiplying the calculated result of the actual size A by 0.973 times.

As those skilled in the art to which the present invention pertains may implement the present invention in other specific forms without changing the technical spirit or essential features, the embodiments described above should be understood as illustrative and not restrictive in all aspects. Should be. The scope of the present invention is shown by the following claims rather than the detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalents should be construed as being included in the scope of the present invention. do.

Therefore, using the real-size calculation method of the image provided by the present invention, it is possible to quickly calculate the size of the ROI in the captured image, and calculate the actual size of the ROI using the meta information of the captured image. . In addition, in the medical field, the present invention has an advantage of more accurately measuring the actual area of the affected area during imaging of the affected part.

Claims (15)

In the method of obtaining the actual size of the object captured in the image, Obtaining a number N of pixels related to an object captured in the image; Dividing the number N of pixels involved in the object by the maximum number of pixels of the image and multiplying the size of an image pickup device to obtain a size of an image of the object captured in the image; And And calculating the actual size of the object by substituting the size of the image of the object into a lens formula. In claim 1, And the maximum number of pixels of the image is information obtained from meta information of a digital camera. In claim 1, Obtaining the number N of pixels involved in the object, A method of calculating the real size of an image, characterized by obtaining the number of pixels N involved in the object by using an image segmentation technique. In claim 3, The step of obtaining the number N of pixels involved in the object by using the image segmentation technique, Detecting a boundary of the object; And And constructing a binary image in which the boundary and one pixel corresponding to the boundary and one pixel other than the pixel are set to zero. In claim 1, Obtaining the number N of pixels involved in the object, Measuring the number of pixels N involved in the object at least twice; And And obtaining the number of pixels (N) involved in the object by deriving an average value according to each result value measured two or more times. In claim 1, And correcting an error of an actual size resulting from the difference between the maximum number of pixels and the actual number of pixels of the image capturing device taking the image. In the method of obtaining the actual size of the object captured in the image, Arranging a start pixel and an end pixel of a length to be measured of the object captured in the image on coordinates indicated by horizontal and vertical axes; Obtaining a number of pixels (I, J) for each of the horizontal lines formed by the intersection of the horizontal axis and the vertical axis and the start pixel and the vertical line formed by the intersection of the intersection pixel and the end pixel; Obtaining sizes of the horizontal line and the vertical line with respect to the size of the image of the object by referring to the I and J values, the maximum number of pixels of the image, and the size of the image pickup device; And And substituting the magnitudes of the horizontal line and the vertical line into Pythagorean theorem and lens formula to obtain the actual size of the object. In claim 7, Obtaining the size of the horizontal line and the vertical line with respect to the size of the image of the object, Dividing I by the horizontal maximum pixel number and multiplying the horizontal size of the image pickup device to obtain the size of the horizontal line with respect to the size of the image of the object; And Dividing J by the maximum number of pixels in the vertical direction of the image and multiplying the vertical size of the image pickup device to obtain the size of the vertical line with respect to the size of the image of the object. . In claim 7, Obtaining the actual size of the object by substituting the magnitude of the horizontal line and the vertical line into Pythagorean theorem and lens formula,

or,

The real size calculation method of an image, characterized in that the calculation according to the equation. In claim 7, Obtaining the number of pixels (I, J) for the horizontal line and the vertical line, And measuring I and J at least twice, and deriving an average value according to each result value measured at least twice to obtain I and J. In claim 7, And correcting an error of an actual size resulting from the difference between the maximum number of pixels and the actual number of pixels of the image capturing device taking the image. A camera unit for loading meta information; And And an analysis processing unit which receives the image captured by the camera unit, receives information on the object captured by the image, and calculates and outputs the actual size of the object. In claim 12, The camera unit, a real-size calculation system of the image, characterized in that it comprises a wireless transmission unit of ultra wideband (UWB) wireless communication. In claim 12, The analysis processing unit, An input unit for receiving information on an object from an image received from the camera unit; And And a calculation processor configured to calculate an actual size of the object by applying a lens formula based on the number of pixels (N) involved in the object and the meta information. The method of claim 14, The calculation processing unit, Divide the number N of pixels involved in the object by the maximum number of pixels in the image, multiply the size of an image pickup device to obtain the size of the image of the object captured in the image, and substitute the size of the image of the object in a lens formula to The actual size calculation system of the image, characterized in that to calculate the actual size of the image.

Images