Image processing system, image processor, imaging device, and processing method

Abstract

An apparatus, an image processing system, and a program are provided that measure a desired length of a subject included in a captured image with simpler operations. [Solution] In an image processing system 1 having a management server 10, an imaging device 40, an auction device 50, and a market 2 configured through a communication network, the management server 10 is equipped with a communication interface, a processor, an image processor 20, and a machine learning machine 30. The image processor 20 detects feature components of the captured image and identifies a distance measurement position corresponding to the subject based on the feature components of the captured image. The detection of feature components of the captured image includes edge detection. The distance measurement position may include at least a first point and a second point different from the first point. Furthermore, the distance measurement position may be a line segment including the first point and the second point different from the first point. The line segment may be straight or curved.

Description

[Technical field]

[0001] The present invention relates to an image processing system, an image processor, an imaging device, and a processing method. [Background technology]

[0002] 2. Description of the Related Art Conventionally, electronic cameras have been known that allow a user to easily grasp a subject and its size (length) in an image by photographing the subject (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2005-142938 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, the above-mentioned electronic camera has a problem in that it is not possible to automatically calculate the size of the subject.

[0005] Therefore, the present invention has been made in consideration of the above-mentioned problems, and aims to provide an image processing system, image processor, imaging device, and processing method that can measure the desired length of a subject contained in a captured image with simpler operations. [Means for solving the problem]

[0006] An image processing system according to a first aspect includes an image processor that detects a characteristic component of a captured image and identifies a distance measurement position according to a subject based on the characteristic component.

[0007] The image processor according to the second aspect includes at least one processor that detects a characteristic component of a captured image and identifies a distance measurement position according to a subject based on the characteristic component.

[0008] An imaging device according to a third aspect includes an image processor according to the second aspect, a camera, and a processor, and the image processor detects characteristic components of an image captured by the camera and identifies a distance measurement position corresponding to a subject based on the characteristic components.

[0009] The processing method according to the fourth aspect is executed by an image processing system including an image processor, detects a characteristic component of a captured image, and identifies a distance measurement position according to a subject based on the characteristic component. Effect of the Invention

[0010] According to one aspect of the present invention, it is possible to provide an image processing system, an image processor, an image capturing device, and a processing method that are capable of measuring a desired length of a subject included in a captured image with a simpler operation. [Brief description of the drawings]

[0011] [Figure 1] FIG. 1 is a diagram showing an example of the overall configuration of an image processing system 1 according to the first embodiment. [Diagram 2] FIG. 2 is a diagram illustrating an example of functional blocks of the management server 10 according to an embodiment. [Diagram 3] FIG. 3 is a diagram showing an example of functional blocks of the image processor 20 according to an embodiment. [Figure 4] FIG. 4 is a diagram for explaining an example of the function of the image processor 20 shown in FIG. [Diagram 5] FIG. 5 is a diagram for explaining an example of the function of the image processor 20 shown in FIG. [Figure 6] FIG. 6 is a diagram for explaining an example of the function of the image processor 20 shown in FIG. [Figure 7] FIG. 7 is a diagram illustrating an example of functional blocks of the machine learning machine 30 according to an embodiment. [Figure 8] FIG. 8 is a diagram illustrating an example of functional blocks of the management server 10 illustrated in FIG. [Figure 9]FIG. 9 is a diagram for explaining an example of the function of the imaging device 40 according to an embodiment. [Figure 10] FIG. 10 is a sequence diagram showing an example of the operation of the image processing system 1 according to the first embodiment. [Figure 11] FIG. 11 is a diagram showing an example of the overall configuration of an image processing system 1 according to the second embodiment. [Figure 12] FIG. 12 is a diagram showing an example of functional blocks of an imaging device 40 according to an embodiment. [Figure 13] FIG. 13 is a sequence diagram showing an example of the operation of the image processing system 1 according to the second embodiment. [Figure 14] FIG. 14 is a diagram showing an example of the overall configuration of an image processing system 1 according to the third embodiment. [Figure 15] FIG. 15 is a diagram showing an example of functional blocks of an imaging device 40 according to an embodiment. [Figure 16] FIG. 16 is a sequence diagram showing an example of the operation of the image processing system 1 according to the third embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] Hereinafter, embodiments will be described with reference to the drawings. In the following description of the drawings, the same or similar parts are denoted by the same or similar reference numerals.

[0013] However, it should be noted that the drawings are schematic and the ratios of the dimensions may differ from the actual ones. Therefore, the specific dimensions should be determined with reference to the following explanation. In addition, the drawings may include parts whose dimensional relationships or ratios differ from one another.

[0014] (First embodiment) The first embodiment will be described below with reference to FIGS.

[0015] Fig. 1 is a diagram showing an example of the overall configuration of an image processing system 1 according to the first embodiment. As shown in Fig. 1, the image processing system 1 according to the present embodiment includes a management server 10, an imaging device 40, an auction device 50, and a market 2 configured by a communication network.

[0016] In the image processing system 1 according to this embodiment, the management server 10 includes a communication interface 11, a processor 12, an image processor 20, and a machine learning device 30, as shown in FIG.

[0017] The communication interface 11 is configured to acquire an image captured by the camera 41 from the imaging device 40, using a wireless or wired line. The communication interface 11 is also configured to transmit a distance indicated by the distance measurement position acquired from the processor 12 to the imaging device 40, using a wireless or wired line.

[0018] The processor 12 is configured to identify a distance measurement position corresponding to a subject included in a captured image acquired by the communication interface 11 based on processing by the image processor 20, and to measure the distance indicated by the distance measurement position.

[0019] As shown in FIG. 3, the image processor 20 includes a processor 21 and a storage unit 22.

[0020] The processor 21 detects a characteristic component of the captured image acquired by the communication interface 11. The processor 21 may further identify a subject included in the captured image. The detection of the characteristic component includes edge detection. The processor 21 can detect edges of the captured image by applying various techniques. The various techniques may be techniques using first or second derivatives. Techniques using first derivatives include, for example, a Sobel filter and a Prewitt filter. Techniques using second derivatives include, for example, a Laplacian filter.

[0021] The processor 21 is also configured to specify a distance measurement position according to a subject included in the captured image, based on the detected characteristic components.

[0022] Here, the distance measurement position may include at least a first point and a second point different from the first point. Also, the distance measurement position may be a line segment including the first point and the second point different from the first point. The line segment may be a straight line or a curved line.

[0023] The processor 21 may specify a subject region (segmentation image) based on the detected feature components. An image showing a subject region is also called a segmentation image. The processor 21 may specify a contour of the subject based on the detected feature components.

[0024] Here, identifying a distance measurement position corresponding to a subject contained in an captured image based on a detected feature component may involve identifying a point on a subject area or on the contour of a subject that is located at specified coordinates with respect to the entire captured image or the subject area (segmentation image).

[0025] Furthermore, identifying a distance measurement position corresponding to a subject contained in an captured image based on a detected characteristic component may involve identifying a point or area that satisfies certain conditions and is located on the contour (or around the contour) of the subject.

[0026] Furthermore, identifying a distance measurement position according to a subject included in a captured image based on a detected feature component may be identifying a straight line connecting two points within a subject area (segmentation image) that satisfies a specific condition.

[0027] Furthermore, identifying a distance measurement position corresponding to a subject contained in an captured image based on a detected feature component may involve identifying a point located on a contour (or a periphery of the contour) that intersects with an extension of a line segment that follows at least a portion of the contour (or a periphery of the contour) of the subject identified based on the feature component.

[0028] The processor 21 may be configured to specify a distance measurement position according to the subject included in the captured image based on the detected feature components and the identified subject. For example, the processor 21 may determine a condition that the detected feature components should satisfy in order to specify the distance measurement position according to the identified subject.

[0029] For example, as shown in FIG. 4, when processor 21 determines that the subject included in the captured image is wearing a T-shirt, it may determine at least one of the following distance measurement positions: points 5 and 6 for measuring the length, points 1 and 9 (or points 2 and 10) for measuring the sleeve length, points 1, 5 and 9 (or points 2, 5 and 10) for measuring the shoulder length, points 3 and 4 for measuring the width (chest circumference), points 7 and 8 for measuring the waist (or waist circumference), and points 9 and 10 for measuring the shoulder width.

[0030] That is, as shown in Fig. 4, when a captured image includes an upper garment (i.e., when the subject is identified as showing an upper garment), the processor 21 may identify distance measurement positions so as to measure at least one dimension of the length, sleeve length, shoulder width (i.e., chest circumference), waist (i.e., waist circumference) and shoulder width based on the identified subject and the detected feature components. Note that the waist here refers to the circumference of the torso part of the upper garment that has the shortest distance.

[0031] 4, the X-axis corresponds to the left-right direction of the captured image, and the Y-axis corresponds to the up-down direction of the captured image. Alternatively, if the processor 21 can identify a subject included in the captured image, the X-axis may correspond to the left-right direction of the subject, and the Y-axis may correspond to the up-down direction of the subject.

[0032] 4, for example, points 1 and 2 are end points in the X-axis direction (left and right direction) of subject Z included in the captured image. That is, points 1 and 2 are points located above the tip of the sleeve (i.e., the tip of the sleeve on the shoulder side). Points 1 and 2 are examples of points on the subject region or on the subject's outline that are located at predetermined coordinates with respect to the entire captured image or the subject region (segmentation image).

[0033] Points 3 and 4 are points below the base of the sleeve (i.e., the base of the sleeve at the armpit). Points 3 and 4 are examples of points or areas that satisfy a specific condition and are located on the contour (or around the contour) of the subject. Here, the specific condition is that, at point 3, a feature component exists in the negative direction of the X-axis (leftward) and the negative direction of the Y-axis (downward). Here, the specific condition is that, at point 4, a feature component exists in the positive direction of the X-axis (rightward) and the negative direction of the Y-axis (downward).

[0034] Points 5 and 6 are the intersections of the perpendicular bisector L2 of the line connecting points 3 and 4 and the boundary line X1 of subject Z. That is, point 5 is a point located at the base of the collar and the center of subject Z, and point 6 is a point located at the tip of the hem and the center of subject Z. Points 5 and 6 are examples of points on the subject region or on the subject's contour that are located at specific coordinates with respect to the entire captured image or the subject region (segmentation image).

[0035] The line connecting points 7 and 8 is the line with the shortest distance among the lines connecting the end points of subject Z, which are in the negative direction (downward direction) of the Y axis relative to points 3 and 4, parallel to the X axis. The line connecting points 7 and 8 is an example of a line connecting two points in a subject region (segmentation image) that satisfies a specific condition. Here, the specific condition is the shortest distance.

[0036] Point 9 is the intersection of a line L4 passing through points 3 and 7 and the boundary line X1 of subject Z. Point 10 is the intersection of a line L5 passing through points 4 and 8 and the boundary line X1 of subject Z. In other words, points 9 and 10 are points located above the base of the sleeve (i.e., the base of the sleeve on the shoulder side). Points 9 and 10 are examples of points located on the contour (or the periphery of the contour) that intersect with an extension of a line segment along at least a part of the contour (or the periphery of the contour) of the subject identified based on the feature components.

[0037] In addition, if processor 21 determines that the subject included in the captured image is wearing a T-shirt, it may identify points 1 to 10 as distance measurement positions, but it may also identify points 1 to 10 based only on the detected characteristic components without determining that the subject is wearing a T-shirt.

[0038] Alternatively, as shown in FIG. 5, if the processor 21 determines that the subject included in the captured image represents trousers, it may determine at least one of points 1 to 14 as the distance measurement positions: points 1 and 5, or points 2 and 6, for measuring the rise length; points 1 and 3, or points 2 and 4, for measuring the inseam length; points 3 and 5, or points 4 and 6, for measuring the total length; points 1 and 14, as well as points 2 and 13, for measuring the thigh width (i.e., thigh circumference); points 5 and 6, for measuring the waist (i.e., waist circumference); points 7 and 8, as well as points 9 and 10, for measuring the knee width; and points 3 and 11, as well as points 4 and 12, for measuring the hem width.

[0039] That is, as shown in FIG. 5, when the captured image includes undergarments (i.e., when the subject is identified as showing undergarments), the processor 21 may identify a distance measurement position so that at least one of the dimensions of rise, inseam, total length, waist (i.e., waist circumference), thigh width (i.e., thigh circumference), knee width, and hem width is measured.

[0040] For example, in FIG. 5, points 4 and 12 (as well as points 3 and 11) are points located at both ends of the hem portion. Points 2 and 13 (as well as points 1 and 14) are points located at both ends of the portion corresponding to the wearer's thighs. Points 9 and 10 (as well as points 7 and 8) are points located at both ends of the portion corresponding to the wearer's knees. Points 5 and 6 are points located at both ends of the portion corresponding to the wearer's torso.

[0041] Alternatively, as shown in FIG. 6, when processor 21 determines that the subject included in the captured image represents a bag, it may identify at least one of points 1 and 2 for measuring the width at the bottom surface, points 2 and 3 for measuring the depth at the bottom surface, points 1 and 6 (or points 2 and 5, or points 3 and 4) for measuring the height, points 5 and 6 for measuring the width at the top surface, and points 4 and 5 for measuring the depth at the top surface as such distance measurement positions.

[0042] That is, as shown in Fig. 6, when a captured image includes a three-dimensional object (i.e., when the subject is identified as representing a three-dimensional object), the processor 21 may specify a distance measurement position so that at least one dimension of height, width, and depth is measured. Here, the three-dimensional object may include at least one of furniture, home appliances, and bags.

[0043] Alternatively, the processor 21 may be configured to identify points for measuring the height of a human or animal, or the size of a fish or plant.

[0044] The memory unit 22 is composed of a memory device including a RAM (Random Access Memory) or a ROM (Read Only Memory), or an auxiliary memory device such as a hard disk or flash memory, and is configured to store the distance measurement position identified by the processor 21.

[0045] As shown in FIG. 3, the machine learning machine 30 includes an acquisition unit 31, a processor 32, and a storage unit 33.

[0046] The acquisition unit 31 is configured to acquire the learning captured images and the names of the subjects corresponding to the learning captured images as pairs of input data and labels.

[0047] The processor 32 is configured to learn what a subject included in a captured image represents by performing learning using pairs of input data and labels as training data.

[0048] Here, the processor 32 may be configured to calculate the above-mentioned training data in a multi-layer structure, i.e., to generate a learned model for indicating what the subject contained in the captured image indicates by deep learning.

[0049] The memory unit 33 is composed of a memory device such as FRAM (Ferroelectric Random Access Memory) (registered trademark) or an auxiliary memory device such as a hard disk or flash memory, and is configured to store the trained model generated by the processor 32.

[0050] Furthermore, the processor 21 of the image processor 20 may be configured to identify what a subject included in a captured image represents, based on a trained model of the machine learning device 30.

[0051] Furthermore, the processor 12 of the management server 10 may be configured to measure, based on the distance measurement position identified by the image processor 20, the distance indicated by the distance measurement position.

[0052] For example, the processor 12 may be configured to measure at least one of the following dimensions when a captured image includes an upper garment: length, sleeve length, shoulder length, body width, waist, and shoulder width.

[0053] Specifically, the processor 12 may be configured to measure the distance between points 5 and 6 as the garment length dimension, as shown in Fig. 4. The processor 12 may also be configured to measure the distance between points 1 and 9 (and / or the distance between points 2 and 10) as the sleeve length dimension, as shown in Fig. 4.

[0054] The processor 33 may also be configured to measure the sleeve length dimension as the sum of the distance between points 1 and 9 and the distance between points 5 and 9 (and / or the sum of the distance between points 2 and 10 and the distance between points 5 and 9), as shown in FIG.

[0055] Processor 12 may also be configured to measure the distance between points 3 and 4 as the body width dimension, as shown in Fig. 4. Processor 33 may also be configured to measure the distance between points 7 and 8 as the waist dimension, as shown in Fig. 4. Processor 12 may also be configured to measure the distance between points 9 and 10 as the shoulder width dimension, as shown in Fig. 4.

[0056] Furthermore, the processor 12 may be configured to measure at least one of the dimensions of the rise, inseam, total length, waist, thigh width, knee width, and hem width when the captured image includes an undergarment.

[0057] Specifically, the processor 12 may be configured to measure the distance between point 1 and point 5 (and / or the distance between point 2 and point 6) as the rise dimension, as shown in FIG. 5. The processor 12 may be configured to measure the distance between point 1 and point 3 (and / or the distance between point 2 and point 4) as the inseam dimension, as shown in FIG. 5. The processor 12 may be configured to measure the distance between point 3 and point 5 (and / or the distance between point 4 and point 6) as the total length dimension, as shown in FIG. 5. The processor 12 may be configured to measure twice the distance between point 5 and point 6 as the waist dimension, as shown in FIG. The processor 12 may be configured to measure twice the distance between point 1 and point 14 (and / or the distance between point 2 and point 13) as the thigh width dimension, as shown in FIG. 5. The processor 12 may also be configured to measure the knee width dimension as twice the distance between points 7 and 8 (and / or the distance between points 9 and 10) as shown in Fig. 5. The processor 12 may also be configured to measure the hem width dimension as twice the distance between points 3 and 11 (and / or the distance between points 4 and 12) as shown in Fig. 5.

[0058] Furthermore, the processor 12 is configured to measure at least one dimension of the height, width, and depth when a three-dimensional object is included in the captured image.

[0059] Here, the distance indicated by the distance measurement position may be a distance connecting two points on the surface of a subject that is a three-dimensional object, or a distance connecting two points on the edge of a subject that can be regarded as a plane. Specifically, as shown in FIG. 6, the processor 12 may be configured to measure the distance between points 1 and 6 (and / or the distance between points 2 and 5, and the distance between points 3 and 4) as the height dimension. As shown in FIG. 6, the processor 12 may also be configured to measure the distance between points 1 and 2 as the width dimension. As shown in FIG. 6, the processor 12 may also be configured to measure the distance between points 2 and 3 as the depth dimension.

[0060] In addition, the processor 12 may be configured to measure the height of a human or an animal when the captured image includes the human or animal, or to measure the size of a fish or a plant when the captured image includes the fish or a plant.

[0061] Also, as shown in FIG. 8, the processor 12 may be configured to detect a manufacturer or brand from tag information included in the captured image, and identify the distance indicated by the distance measurement position from a size chart of the manufacturer or brand.

[0062] In the image processing system 1 according to the present embodiment, the imaging device 40 can list a target commodity on the market 2 that is configured by a communication network. In this case, the imaging device 40 may be, for example, a communication terminal such as a so-called smartphone or a portable communication terminal such as a tablet.

[0063] Here, the imaging device 40 is configured to input or select the captured image and the distance indicated by the distance measurement position as target product information in response to user operation, and upload the target product information including the captured image and the distance indicated by the distance measurement position onto the market 2, thereby allowing the target product to be listed.

[0064] In the image processing system 1 according to the present embodiment, the exhibition device 50 can exhibit the target commodity on the market 2 configured by a communication network. In such a case, the exhibition device 50 may be, for example, a laptop computer, a desktop computer, a smart speaker, or the like.

[0065] Here, the listing device 50 is configured to, in response to user operation, acquire the captured image and the distance indicated by the distance measurement position from the imaging device 40, input or select the captured image and the distance indicated by the distance measurement position as target product information, and upload the target product information including the captured image and the distance indicated by the distance measurement position onto the market 2, thereby listing the target product.

[0066] As shown in FIG. 9, the imaging device 40 and the auction device 5 may overlay the distance indicated by the distance measurement position on the captured image for measurement, and upload the captured image with the distance indicated by the distance measurement position overlaid onto the market 2 as target product information including the product image and the distance indicated by the distance measurement position.

[0067] FIG. 10 is a sequence diagram showing an example of the operation of the image processing system 1 according to the present embodiment.

[0068] As shown in FIG. 10, the imaging device 40 captures an image including a subject with the camera 41 in step S1001, and transmits the captured image to the management server 10 in step S1002.

[0069] In step S1003, the management server 10 identifies a distance measurement position corresponding to the subject included in the acquired captured image and measures the distance indicated by the distance measurement position, and in step S1005, transmits the measured distance indicated by the distance measurement position to the imaging device 40.

[0070] In step S1006, the imaging device 40 inputs or selects the captured image and the distance indicated by the distance measurement position as target product information in response to user operation, and in step S1007, uploads the target product information including the captured image and the distance indicated by the distance measurement position onto the market 2.

[0071] In step S1008, the target product information is put up for sale on the market 2.

[0072] According to the image processing system 1 of this embodiment, the image processor 20 provided in the management server 10 identifies a distance measurement position corresponding to the subject included in the captured image, thereby automatically measuring the desired dimensions of the subject included in the captured image.

[0073] Furthermore, according to the image processing system 1 of this embodiment, there is no need to provide an image processor in each imaging device 40, so that desired dimensions of a subject included in a captured image can be automatically measured easily using a portable communication terminal or the like.

[0074] Second embodiment Hereinafter, the second embodiment will be described with reference to FIGS. 11 to 13, focusing on the differences from the above-described first embodiment.

[0075] As shown in FIG. 11, in the image processing system 1 according to this embodiment, the image processor 20 is provided in an imaging device 40 rather than in a management server 10.

[0076] As shown in FIG. 12, the imaging device 40 includes a communication interface 41, a camera 42, a processor 43, and the image processor 20.

[0077] The communication interface 41 is configured to be able to communicate with the management server 10 and the communication network (market) 2 using a wireless or wired line, and the camera 42 is configured to be able to acquire captured images including a subject.

[0078] Similar to processor 12, processor 43 is configured to identify a distance measurement position corresponding to a subject contained in an image captured by camera 42 based on processing by image processor 20, and to measure the distance indicated by the distance measurement position.

[0079] As in the first embodiment, the image processor 20 is configured to identify what the subject represents based on the captured image captured by the camera 42 and detect characteristic components of the subject, and to identify a distance measurement position corresponding to the subject included in the captured image based on the identified subject and characteristic components.

[0080] FIG. 13 is a sequence diagram showing an example of the operation of the image processing system 1 according to the present embodiment.

[0081] As shown in FIG. 13, in step S2001, the management server 10 generates a trained model for indicating what the subject contained in the captured image indicates by learning using a pair of input data and a label as training data, and in step S2002, transmits the trained model to the imaging device 40.

[0082] In step S2002, the imaging device 40 identifies what the subject included in the captured image represents based on the received trained model and detects the characteristic components of the subject, identifies a distance measurement position corresponding to the subject included in the captured image based on the identified subject and the detected characteristic components, and measures the distance indicated by the distance measurement position in step S2003.

[0083] In step S2004, the imaging device 40 inputs or selects the captured image and the distance indicated by the distance measurement position as target product information in response to user operation, and in step S2005, uploads the target product information including the captured image and the distance indicated by the distance measurement position onto market 2.

[0084] In step S2006, the target product information is put up for sale on the market 2.

[0085] According to the image processing system 1 of this embodiment, the image processor 20 provided in the imaging device 40 identifies a distance measurement position corresponding to the subject included in the captured image, thereby making it possible to automatically measure the desired dimensions of the subject included in the captured image.

[0086] Third embodiment Hereinafter, the third embodiment will be described with reference to FIGS. 14 to 16, focusing on the differences from the first and second embodiments.

[0087] 14, in the image processing system 1 according to this embodiment, the image processor 20 and the machine learning device 30 are provided in an imaging device 40. Also, as shown in FIG 15, the imaging device 40 includes the image processor 20, the machine learning device 30, a communication interface 41, a camera 42, and a processor 43.

[0088] Here, the processor 43 may be configured to identify three-dimensional information of the surrounding environment and the position of the imaging device 40 based on an image captured by the camera 31, identify a distance from the imaging device 40 to the first point and a distance from the imaging device 40 to the second point based on the three-dimensional information of the surrounding environment, the position of the imaging device 40, the first point and the second point, and identify a distance from the first point to the second point based on the distance from the imaging device 40 to the first point and the distance from the imaging device 40 to the second point. That is, the processor 43 may be configured to measure the distance between each point (i.e., each distance estimation position) using, for example, a Virtual SLAM (Simultaneous Localization and Mapping) technique.

[0089] FIG. 16 is a sequence diagram showing an example of the operation of the image processing system 1 according to the present embodiment.

[0090] As shown in FIG. 16, in step S3001, the imaging device 40 generates a trained model for indicating what the subject included in the captured image indicates by learning using a pair of input data and a label as training data, and in step S3002, based on the trained model, identifies what the subject included in the captured image indicates and detects feature components of the subject, identifies a distance measurement position corresponding to the subject included in the captured image based on the identified subject and the detected feature components, and measures the distance indicated by the distance measurement position.

[0091] In step S3003, the imaging device 40 inputs or selects the captured image and the distance indicated by the distance measurement position as target product information in response to user operation, and in step S3004, uploads the target product information including the captured image and the distance indicated by the distance measurement position onto market 2.

[0092] In step S3005, the target product information is put up for sale on the market 2.

[0093] According to the image processing system 1 of this embodiment, the image processor 20 provided in the imaging device 40 identifies a distance measurement position corresponding to the subject included in the captured image, thereby making it possible to automatically measure the desired dimensions of the subject included in the captured image.

[0094] A program may be provided that causes a computer to execute each process performed by the imaging device 40, the management server 10, the image processor 20, and the machine learning machine 30. The program may be recorded in a computer-readable medium. Using the computer-readable medium, it is possible to install the program in the computer. Here, the computer-readable medium on which the program is recorded may be a non-transient recording medium. The non-transient recording medium is not particularly limited, and may be, for example, a recording medium such as a CD-ROM or a DVD-ROM.

[0095] The above describes the embodiments in detail with reference to the drawings, but the specific configuration is not limited to that described above, and various design changes, etc. are possible without departing from the spirit of the invention. [Explanation of symbols]

[0096] 1. Image processing system 2. Communication network (market) 10…Administration server 11...Communication interface 12…Processor 20...Image processor 21…Processor 22...Storage section 30...Machine learning machine 31…Acquisition part 32…Processor 33...Storage section 40...Imaging device 41...Communication interface 42...Camera 43…Processor 50…Exhibited equipment

Claims

1. Detecting characteristic components of the captured image; identifying a distance measurement position including at least a first point corresponding to the subject and a second point different from the first point based on the feature components; Identifying a position of the own device based on the captured image; determining a first distance from the determined position of the own device to the first point and a second distance from the determined position of the own device to the second point; measuring a distance indicated by the distance measurement position based on the first distance and the second distance; When the captured image includes tag information, detect a manufacturer or brand included in the tag information, and identify the distance indicated by the distance measurement position by referring to a size chart of the manufacturer or brand; Device.

2. Accepts user operations, Selecting the captured image and the distance indicated by the distance measurement position as target product information in response to the user operation; The device according to claim 1 , wherein the target product information including the selected captured image and the distance indicated by the distance measurement position is uploaded onto a marketplace formed by a communication network.

3. identifying a subject area included in the captured image based on the feature components; 2. The apparatus of claim 1.

4. The device according to claim 1 , wherein the distance indicated by the distance measurement position is a distance connecting two points on a surface of a three-dimensional object or a distance connecting two points on edges of an object that can be regarded as a plane.

5. The device according to any one of claims 1 to 4, wherein when the captured image includes a three-dimensional object, the distance measurement position is specified so that at least one dimension of height, width, and depth is measured.

6. A program that causes at least one processor to execute at least the following processes 1) to 7). 1) Processing to detect characteristic components of captured images 2) A process of identifying distance measurement positions including at least a first point corresponding to the subject and a second point different from the first point based on the feature components. 3) Processing for identifying the position of the own device based on the captured image 4) A process of determining a first distance from the determined position of the own device to the first point and a second distance from the determined position of the own device to the second point. 5) A process of measuring a distance indicated by the distance measurement position based on the first distance and the second distance. 6) Processing for detecting a manufacturer or brand included in tag information when the captured image includes tag information 7) A process of identifying the distance indicated by the distance measurement position by referring to a size chart of the manufacturer or brand.

Images