Image data processing method, image data processing device and image data processing system

Abstract

An image data processing method according to one embodiment of the present disclosure includes: obtaining first image data representing a hyperspectral image of an object photographed under first background light; generating first spectral data representing an estimated spectrum of the first background light based on the first image data; and generating second image data representing an image of the object illuminated by the second background light based on the first image data using second spectral data representing at least one type of spectrum of at least one second background light different from the first background light and the first spectral data.

Description

Technical Field

[0001] The present disclosure relates to an image data processing method, an image data processing device, and an image data processing system. Background Art

[0002] Using a multi-wavelength camera system such as a hyperspectral camera or a multispectral camera, the spectral information of the photographed image can be analyzed in detail.

[0003] Images captured by a camera contain both the object's reflected spectrum and the spectrum of the background light illuminating the object. For example, if the spectrum of the background light when an object is photographed differs from the spectrum of the background light in the environment in which a person visually perceives the object, the information perceived by a person when visually recognizing the object reflected in the image may differ from that perceived by the actual object.

[0004] Patent Document 1 discloses a color reproduction system that displays an image, color-converted by a server-side system, on a monitor device on a user-side system. This system provides a webpage with functionality that allows the user to select the type of lighting applied to displayed product images and changes the image's appearance accordingly. Furthermore, Patent Document 2 discloses a system that uses illumination information representing illumination within a specific building or illumination based on at least the weather in a specific region or location to perform illumination correction on a composite image containing information about tried-on clothing.

[0005] Prior art literature

[0006] Patent Literature

[0007] Patent Document 1: Japanese Patent Application Laid-Open No. 2009-124647

[0008] Patent Document 2: Japanese Patent Application Laid-Open No. 2005-248393 Summary of the Invention

[0009] Problems to be solved by the present invention

[0010] The present disclosure provides a method for improving color reproducibility of images provided to a user.

[0011] Means for solving problems

[0012] An image data processing method according to one embodiment of the present disclosure includes: obtaining first image data representing a hyperspectral image of an object photographed under a first background light; generating first spectral data representing an estimated spectrum of the first background light based on the first image data; and using at least one type of second spectral data representing a spectrum of at least one second background light different from the first background light and the first spectral data, generating at least one type of second image data representing an image of the object illuminated by the at least one second background light based on the first image data.

[0013] The general or specific aspects of the present disclosure may also be implemented through a system, device, method, integrated circuit, computer program, or computer-readable recording disk or other recording medium, or through any combination of a system, device, method, integrated circuit, computer program, and recording medium. Computer-readable recording media may include both volatile recording media and non-volatile recording media such as CD-ROM (Compact Disc-Read Only Memory). A device may also be composed of more than one device. In the case where a device is composed of more than two devices, the two or more devices may be configured in one device or separately in two or more separate devices. In this specification and claims, "device" may refer not only to one device, but also to a system composed of multiple devices.

[0014] Effects of the Invention

[0015] According to one aspect of the present disclosure, it is possible to improve the color reproducibility of an image provided to a user.

[0016] Additional benefits and advantages of one embodiment of the present disclosure are apparent from this specification and the accompanying drawings. Such benefits and / or advantages can be provided individually by the various embodiments and features disclosed in this specification and the accompanying drawings, and it is not necessary to obtain all of them in order to obtain one or more of them. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a diagram showing the configuration of a system in an exemplary embodiment.

[0018] Figure 2A This diagram shows an example of data for one pixel in an image including only general information in three wavelength bands: red, green, and blue.

[0019] Figure 2B This diagram shows an example of data for one pixel in a hyperspectral image in which each of the red, green, and blue bands is divided into three.

[0020] Figure 2CThis figure shows an example of a hyperspectral image in which each of the red, green, and blue bands is divided into more components.

[0021] Figure 3 This is a sequence diagram showing an example of the operations of the seller terminal, server, and user terminal and the flow of data.

[0022] Figure 4 This is a diagram showing an example of a web page displayed on a user terminal.

[0023] Figure 5 This is a flowchart showing an example of the operation executed by the processor of the server.

[0024] Figure 6 This is a diagram showing an example of an image displayed on a seller terminal.

[0025] Figure 7 This is a flowchart showing a specific example of the solar spectrum estimation process in step S530.

[0026] Figure 8 This is a schematic diagram showing the contents recorded in the solar spectrum database stored in the memory.

[0027] Figure 9 This is a flowchart showing a specific example of the illumination spectrum estimation process in step S550 .

[0028] Figure 10A This is a diagram showing an example of spectrum data of LED lighting.

[0029] Figure 10B This is a diagram showing an example of spectrum data of a fluorescent lamp.

[0030] Figure 10C This is a diagram showing an example of spectrum data of an incandescent lamp.

[0031] Figure 11 It is represented by a dotted box Figures 10A to 10C A diagram of three reference bands in an example of a spectrum is shown.

[0032] Figure 12 It is a flowchart which shows the operation of step S550 more specifically.

[0033] Figure 13 This is a flowchart showing a specific example of the test image generation process in step S570 .

[0034] Figure 14 This is a flowchart showing an example of processing executed by the processor of the seller terminal.

[0035] Figure 15 This is a sequence diagram showing another example of processing executed by the server and the user terminal.

[0036] Figure 16 This diagram shows an example of a system further including an operator terminal used by an operator operating a server.

[0037] Figure 17 This is a timing chart showing an overview of the operation in the modification example.

[0038] Figure 18 It is a timing chart showing an outline of the operation in another modification example.

[0039] Figure 19 This is a diagram showing a modified example in which the operator terminal also functions as a server.

[0040] Figure 20 It is a sequence diagram showing the operation of a system according to another modification. DETAILED DESCRIPTION

[0041] In the present disclosure, all or part of a circuit, unit, device, component or section, or all or part of a functional module in a block diagram, for example, can be performed by a semiconductor device, a semiconductor integrated circuit (IC), or one or more electronic circuits including an LSI (large scale integration). An LSI or an IC can be integrated into one chip or formed by combining multiple chips. For example, functional modules other than memory elements can also be integrated into one chip. Although referred to herein as an LSI or an IC, the name may be changed depending on the degree of integration, and a circuit may also be referred to as a system LSI, a VLSI (very large scale integration), or an ULSI (ultra large scale integration). A field programmable gate array (FPGA) programmed after the manufacture of the LSI or a reconfigurable logic device that can reconfigure the internal connection relationship of the LSI or set the circuit division within the LSI can also be used for the same purpose.

[0042] Furthermore, all or part of the functions or actions of a circuit, unit, device, component or part can also be executed by software processing. In this case, the software is recorded on one or more non-volatile recording media such as ROM, optical disk, hard disk drive, and when the software is executed by a processing device (processor), the functions determined by the software are executed by the processing device (processor) and peripheral devices. The system or device can also have one or more non-volatile recording media, a processing device (processor), and required hardware devices such as interfaces that record the software.

[0043] Before describing specific embodiments of the present disclosure, an overview of the embodiments of the present disclosure will be described.

[0044] An image data processing method according to an exemplary embodiment of the present disclosure includes the following steps.

[0045] (1) First image data representing a hyperspectral image of an object photographed under first background light is acquired.

[0046] (2) Based on the first image data, first spectrum data representing the estimated spectrum of the first background light is generated.

[0047] (3) Using at least one type of second spectral data representing the spectrum of at least one second background light different from the first background light and the first spectral data, at least one type of second image data representing the image of the object illuminated by the at least one second background light is generated based on the first image data.

[0048] A “hyperspectral image” refers to an image that includes information of four or more wavelength bands per pixel. A hyperspectral image can be acquired, for example, by a hyperspectral camera that can acquire information of four or more wavelength bands per pixel.

[0049] According to the above configuration, first image data representing an image of an object under a first background light can be converted into second image data representing an image of the object under a second background light. This improves the color reproducibility of the image of the object. In particular, according to the above configuration, first spectral data representing an estimated spectrum of the first background light is generated based on the first image data. Thus, unlike conventional techniques, an image of the object under the second background light can be generated even when the spectrum of the first background light at the time the object was photographed is unknown.

[0050] In one embodiment, the at least one second background light may include a plurality of different second background lights. The at least one type of second image data may include a plurality of types of second image data. Each of the plurality of types of second image data may represent an image of the object illuminated by a respective second background light of the plurality of second background lights.

[0051] According to the above configuration, it is possible to generate images of the object under a plurality of types of second background light.

[0052] The plurality of second background lights may include sunlight and one or more artificial lighting lights.

[0053] According to the above configuration, it is possible to generate an image of an object under sunlight and one or more artificial lighting sources.

[0054] Generating the at least one type of second image data may also include: using the first spectral data to generate reflection spectrum data representing the reflection spectrum of the object based on the first image data; and using the reflection spectrum data and the at least one type of second spectral data to generate the at least one type of second image data.

[0055] Generating the first spectral data may also include: determining, based on the first image data, whether the hyperspectral image is photographed outdoors or indoors; and generating the first spectral data by performing different processing depending on whether the hyperspectral image is photographed outdoors or indoors.

[0056] According to the above configuration, the second image data can be generated by appropriate processing according to whether the hyperspectral image of the object is captured outdoors or indoors.

[0057] In the case where it is determined in the determination that the hyperspectral image is photographed outdoors, generating the first spectral data may also include: obtaining data representing at least one selected from the group consisting of date, time, location and weather when the hyperspectral image was photographed; obtaining spectral data of sunlight associated with at least one selected from the group consisting of date, time, location and weather; and recording the spectral data of sunlight as the first spectral data to a recording medium.

[0058] According to the above configuration, when a hyperspectral image of an object is captured outdoors, more appropriate second image data can be generated.

[0059] In the case where it is determined in the determination that the hyperspectral image is photographed indoors, generating the first spectral data may also include: estimating which artificial lighting light the first background light corresponds to based on spectral data of at least one predetermined reference band extracted from the first image data; and recording the spectral data of the artificial lighting light as the first spectral data to a recording medium.

[0060] According to the above configuration, when a hyperspectral image of an object is captured indoors, more appropriate second image data can be generated.

[0061] The at least one reference wavelength band may include a blue wavelength band and a green wavelength band.

[0062] According to the above configuration, spectrum data of artificial illumination light can be generated more accurately.

[0063] The at least one reference wavelength band may include a blue wavelength band, a green wavelength band, and a red wavelength band.

[0064] According to the above configuration, spectrum data of artificial illumination light can be generated more accurately.

[0065] The image data processing method may be executed by a server computer that provides a website for selling the object as a commodity via a network. The method may further include transmitting data of a web page including the at least one type of second image data to a user terminal used by a user of the website in response to a request from the user terminal.

[0066] Another exemplary embodiment of the present disclosure relates to an image data processing method executed by a server computer providing a website for selling products via a network. The method includes: obtaining first image data representing a hyperspectral image of a first product photographed under first background light; generating first spectral data representing an estimated spectrum of the first background light based on the first image data; using second spectral data representing at least one type of spectrum of at least one second background light different from the first background light and the first spectral data, generating at least one type of second image data representing an image of the first product illuminated by the at least one second background light based on the first image data; and, in response to a request from a user terminal used by a user of the website, transmitting data of a webpage including the at least one type of second image data to the user terminal.

[0067] According to the above configuration, images of goods such as clothing sold through e-commerce transactions can be properly processed and displayed on the user terminal. In e-commerce transactions, sometimes the impression of the goods displayed on the web page is different from the actual goods. For example, if the spectrum of the lighting used when the goods were photographed is significantly different from the spectrum of the background light in the environment in which the buyer uses the goods, the impression of the goods may be significantly different. According to the above configuration, before purchasing the goods, the user can confirm how the goods will look under the desired background light. Even if the spectrum of the background light when the goods were photographed is unknown, the image of the goods under the background light selected by the user can be displayed. This can improve user satisfaction.

[0068] Acquiring the first image data may also include receiving the first image data from a seller terminal used by a seller of the first product. The method may also include, after generating the at least one type of second image data, sending a request for approval of the at least one type of second image data to the seller terminal; and receiving data indicating approval of the at least one type of second image data from the seller terminal. After receiving the data indicating approval, the webpage data may be sent to the user terminal.

[0069] According to the above configuration, after the second image data is generated, the seller of the product can confirm the validity of the second image data. Only after the seller has approved it can the second image data be used on the web page. Therefore, for example, it is possible to prevent inappropriate second image data from being posted on the web page.

[0070] Sending the data of the web page to the user terminal may also include: sending the data of the first web page including the default image data of the first product to the user terminal in response to a first request from the user terminal; and sending the data of the second web page after replacing the default image data in the first web page with the at least one type of second image data, or adding the at least one type of second image data to the default image data in the first web page, in response to a second request from the user terminal.

[0071] According to the above configuration, for example, when a user browsing the first web page requests display of a second image that is an image of a product under a second background light, the second web page including the second image can be displayed.

[0072] The at least one second background light may include a plurality of second background lights. The first web page may include a display area for selecting one scene from a plurality of scenes associated with the plurality of second background lights.

[0073] According to the above configuration, the user can confirm the image under the second background light associated with the selected scene by selecting one scene from among the plurality of scenes.

[0074] The display area may include a plurality of areas each representing the plurality of scenes. In the display area, the plurality of areas may be displayed in an order corresponding to the number of times each of the plurality of scenes has been selected in the past on the website.

[0075] According to the above configuration, it is possible to realize a highly convenient network display, for example, a scene with a greater number of times a product is selected is displayed at a higher position.

[0076] The second request may be received when a scene is selected from the plurality of scenes. The second webpage may further include image data of at least one second product determined based on the number of times it is displayed in combination with the selected scene. Alternatively, the second webpage may further include image data representing at least one second product illuminated by a second background light associated with the selected scene from among the plurality of second background lights.

[0077] According to the above configuration, images of other products that are expected to be of interest to the user can be displayed on the second web page. This allows the user to be aware of other products that match the scene selected by the user.

[0078] Acquiring the first image data may also include receiving the first image data from a seller terminal used by a seller of the first product. Generating the first spectral data may also include determining whether the first background light can be determined based on spectral data of at least one predetermined reference band extracted from the first image data; and, if the first background light cannot be determined, transmitting instruction data to the seller terminal to capture the hyperspectral image of the product under background light different from the first background light.

[0079] According to the above configuration, when the first background light cannot be determined, the seller can be notified of this fact and prompted to recreate the first image data.

[0080] The at least one reference wavelength band may include a blue wavelength band. The determination may include determining that the first background light cannot be determined if an amount of the component belonging to the blue wavelength band included in the spectrum data of the at least one reference wavelength band is less than a reference value.

[0081] The commodity may be clothing. The commodity is not limited to clothing, and may be any commodity such as furniture, automobiles, and electrical appliances.

[0082] The present disclosure also includes an image data processing device including a computer for executing any one of the above methods, and a computer program for causing a computer to execute any one of the above methods.

[0083] A computer-readable recording medium according to one embodiment of the present disclosure stores a program for processing image data, which, when executed by the computer, performs the following steps: obtaining first image data representing a hyperspectral image of an object photographed under a first background light; generating first spectral data representing an estimated spectrum of the first background light based on the first image data; and generating at least one type of second image data representing an image of the object illuminated by the at least one second background light based on the first image data, using second spectral data representing at least one type of spectrum of at least one second background light different from the first background light and the first spectral data.

[0084] A computer-readable recording medium according to one embodiment of the present disclosure stores a program for processing image data. When executed by a computer, the program performs the following steps: obtaining first image data representing a hyperspectral image of a first product photographed under first background light; generating first spectral data representing an estimated spectrum of the first background light based on the first image data; using second spectral data representing at least one type of spectrum of at least one second background light different from the first background light and the first spectral data to generate, based on the first image data, at least one type of second image data representing an image of the first product illuminated by the at least one second background light; and transmitting, in response to a request from a user terminal used by a user of the website, data of a web page including the at least one type of second image data to the user terminal.

[0085] Another embodiment of the present disclosure includes an image data processing system comprising an image processing computer and a server computer providing a website for selling products via a network. The image processing computer acquires first image data representing a hyperspectral image of the product photographed under first background light, generates first spectral data representing an estimated spectrum of the first background light based on the first image data, and generates, based on the first image data, at least one type of second spectral data representing a spectrum of at least one second background light different from the first background light, and the first spectral data, at least one type of second image data representing an image of the product illuminated by the at least one second background light. The server computer transmits webpage data including the at least one type of second image data to a user terminal of the website in response to a request from the user terminal.

[0086] According to the above configuration, the above service can be provided even when the image processing computer that converts the first image data into the second image data is different from the server computer that transmits the web page data to the user terminal.

[0087] Hereinafter, the embodiments of the present disclosure will be described in detail. In addition, the embodiments described below all represent general or specific examples. The numerical values, shapes, constituent elements, configuration positions and connection methods of constituent elements, steps, order of steps, etc. shown in the following embodiments are examples, and are not intended to limit the present disclosure. In addition, among the constituent elements in the following embodiments, constituent elements that are not recorded in the independent claims representing the highest concepts are described as arbitrary constituent elements. In addition, each figure is a schematic diagram and is not necessarily a strict illustration. Furthermore, in each figure, the same reference numerals are given to substantially the same or similar constituent elements, and repeated descriptions are sometimes omitted or simplified.

[0088] (Implementation Method 1)

[0089] Figure 1 This diagram shows the configuration of a system according to this embodiment. The system includes a seller terminal 100, a server 200 (server computer), and a user terminal 300. Server 200 is connected to seller terminal 100 and user terminal 300 via a network such as the Internet. Server 200 is also connected to a weather server 500 via the Internet or other network.

[0090] Server 200 functions as a data processing device that executes the data processing method disclosed herein. Server 200 also functions as a web server that generates data for websites selling products such as clothing and furniture. Examples of clothing and furniture include clothing, shoes, bags, wallets, accessories, clocks, and fashion accessories.

[0091] Server 200 includes processor 202, memory 203, and communication interface 204. Processor 202 executes the processing described below by executing a computer program stored in memory 203. Server 200 generates website data in response to a request from user terminal 300 and provides it to user terminal 300.

[0092] The seller terminal 100 is a computer used by sellers to sell products posted on the website provided by the server 200. The seller can be a company, a store, or an individual. In the case where the server 200 provides a network service such as a free market website or an auction website, the seller can also be an individual. The operator providing the network service itself can also be a seller.

[0093] The seller terminal 100 can be any computer, such as a smartphone, tablet computer, or personal computer. In this embodiment, the seller terminal 100 includes a camera 101, which is a hyperspectral camera; a processor 102; a memory 103; a communication interface 104; and a display 105. In this embodiment, the camera 101 is built into the seller terminal 100; however, it can also be an external component of the seller terminal 100.

[0094] Camera 101 is an imaging device capable of acquiring hyperspectral images. A hyperspectral image is an image containing information on more wavelength bands than the typical three bands of red, green, and blue. One example of a hyperspectral image is an image containing information on four or more wavelength bands. Another example of a hyperspectral image is an image containing information on ten or more wavelength bands. In this specification, the wavelength band of visible light is defined as 380 nm to 750 nm, the wavelength band of blue is defined as 380 nm to 500 nm, the wavelength band of green is defined as 500 nm to 600 nm, and the wavelength band of red is defined as 600 nm to 750 nm.

[0095] Figure 2A This diagram shows an example of data for one pixel in an image including only general information in three wavelength bands: red (R), green (G), and blue (B). Figure 2B This diagram shows an example of data for one pixel in a hyperspectral image in which each of the red, green, and blue bands is divided into three. Figure 2C The figure shows an example of a hyperspectral image in which each band of red, green, and blue is divided into more components. The camera 101 in this embodiment obtains, for example, a hyperspectral image in which each pixel has Figure 2B or Figure 2C The camera 101 may include a hyperspectral image sensor capable of acquiring data of four or more wavelength bands within the visible light band for each pixel, and an optical system including one or more lenses.

[0096] Processor 102 controls the operation of seller terminal 100 by executing programs stored in memory 103. For example, processor 102 transmits hyperspectral image data of a product captured by camera 101 to server 200 via communication interface 104. Processor 102 also causes display 105 to display an image of an application used to upload hyperspectral image data.

[0097] Hyperspectral image data may include a timestamp indicating the date and time of capture. The seller terminal 100 may be equipped with a GPS (Global Positioning System) receiver. The seller terminal 100 may also include in the uploaded data data indicating the location (e.g., latitude and / or longitude) measured by the GPS receiver. This data on the time and location of capture can be used by the server 200 to estimate the solar spectrum when capturing images outdoors.

[0098] The user terminal 300 is a computer used by a user who wants to purchase a product posted on a website provided by the server 200. In practice, there may be multiple users and multiple user terminals 300, but Figure 1 , only one of the plurality of user terminals 300 is shown as a representative example. The user terminal 300 may be any computer such as a smartphone, a tablet computer, or a personal computer. The user terminal 300 includes a processor 302 , a memory 303 , a communication interface 304 , and a display 305 .

[0099] Processor 302 controls the operation of user terminal 300 by executing a program stored in memory 303. In response to a user operation, processor 302 requests web page data from server 200. Processor 302 displays an image based on the data obtained from server 200 on display 305.

[0100] The weather server 500 is a server that records weather data at various locations at various dates and times. The server 200 can obtain weather data at the date and time and location where the hyperspectral image was generated from the weather server 500.

[0101] Figure 3 This is a sequence diagram showing an example of the operation and data flow of the seller terminal 100, the server 200, and the user terminal 300. Figure 3 , which describes an overview of the operation of the system of this embodiment.

[0102] The seller uses camera 101, a hyperspectral camera, to generate a hyperspectral image of the product they wish to sell (step S101). The seller uploads the hyperspectral image data using seller terminal 100. This image data is referred to as "first image data." Furthermore, the background light in the environment where the product is photographed is referred to as "first background light." This first background light can be either artificial lighting or sunlight.

[0103] Server 200 obtains the uploaded first image data. Next, server 200 estimates the spectrum of the first background light based on the first image data (step S201). A specific example of the operation of estimating the spectrum of the first background light will be described later. Server 200 generates first spectral data representing the estimated spectrum of the first background light. Server 200 stores the generated first spectral data in a storage medium such as memory 203.

[0104] Next, server 200 uses the first spectral data to generate product reflectance spectrum data from the first image data (step S202). For example, the product reflectance spectrum data can be generated by dividing the wavelength value of each pixel in the first image data by the corresponding wavelength value in the first spectral data.

[0105] Next, the server 200 uses the reflection spectrum data and the spectrum data of one or more virtual background lights recorded in advance in a recording medium such as the memory 203 to generate second image data representing the image of the above-mentioned product under each virtual background light (step S203). The virtual background light is referred to as the "second background light" and the spectrum data of the virtual background light is referred to as the "second spectrum data". Here, the virtual background light refers to the background light associated with the scene that can be selected by the purchasing user on the website provided by the server 200. The selectable scenes may include, for example, outdoor (daytime), outdoor (evening), indoor (warm color LED), indoor (daylight color LED), or indoor (fluorescent light) scenes. Therefore, the virtual background light may include, for example, sunlight, LED lighting, fluorescent light, or incandescent light.

[0106] If the server 200 generates the second image data corresponding to each scene, it will send a request for approval for each second image data to the seller terminal 100. If the seller terminal 100 receives the request, it will display an image based on each second image data and an image for selecting whether to approve each second image data on the display 105. These images can be displayed immediately after the hyperspectral image is uploaded or after a period of time. The seller performs an approval operation on the second image data of each scene in accordance with the instructions of the displayed image (step S102). If the seller approves, the seller terminal 100 sends data indicating approval of the second image data to the server 200. After receiving the data indicating approval, the server 200 posts the product on the sales webpage and starts accepting purchases.

[0107] The user can then purchase the product. If the user requests access to the product's sales webpage (step S301), the server 200 transmits the data for the webpage to the user terminal 300. If the user terminal 300 selects a product (step S302), the server 200 transmits the data for the webpage including default image data for the product. The default image data may be, for example, the first image data uploaded by the seller terminal 100, or data obtained by processing the first image data. An image for selecting one of multiple scenes may be displayed on the display 305 of the user terminal 300 along with the product image. If the user selects a scene (step S303), the user terminal 300 requests the server 200 for the data for the webpage including image data associated with the selected scene. In response to the request, the server 200 transmits the data for the webpage in which the default image data is replaced with the second image data corresponding to the selected scene. Alternatively, the server 200 transmits the data for the webpage in which the second image data corresponding to the selected scene is added to the default image data. The user terminal 300 receives the data and displays the image of the requested scene on the display 305 .

[0108] Figure 4 This figure shows an example of a web page displayed on user terminal 300. The web page in this example includes multiple images 810 showing examples of clothing styles selected by the user, and a display area 820 for multiple selectable scenes. The multiple scenes in this example include outdoor (daytime), outdoor (evening), indoor (warm LED), indoor (daylight LED), indoor (fluorescent light), and indoor (incandescent light). If the user selects one of the multiple scenes, image 810 changes to reflect the selected scene. The layout of the web page and the displayed content are not limited to the example shown. For example, each scene is not limited to text and can also be displayed as thumbnails. Multiple scenes can be set based on time and location, for example. In addition to the scenes shown, scenes such as outdoor (nighttime) or a party can also be selected. Depending on the selected scene, not only the color tone of image 810 but also the background itself can change. If the image data for the background and the image data for the person wearing the clothing are recorded separately, the combination of the background and the person can be arbitrarily changed.

[0109] Server 200 may also change the order of scenes in the multiple-scene display area 820 according to the selected product. For example, the multiple scenes may be displayed in an order corresponding to the number of times each scene has been selected by multiple users for that product on the website in the past. Alternatively, scenes with the highest number of past selections for each product may be displayed higher in the display, or the second image data associated with the most frequently selected scene may be displayed by default. This display allows users to identify popular combinations of scenes and products.

[0110] The data of the web page sent by the server 200 when the user selects a scene may also include the image of at least one other product. For example, an image of the at least one other product under the virtual background light corresponding to the selected scene may be added. The at least one other product may be a product that the user has selected in the past, or may be determined based on the user's Internet search history. In addition, the at least one other product may also be determined based on the number of times it is displayed in combination with the selected scene. For example, the data of the web page may also include image data of one or more other products that have been displayed the most times in combination with the selected scene. Such images of other products may be, for example Figure 4 The image 830 shown can be displayed as a recommended product on the side or below the screen. Through such a display, the user can easily know other popular products that match the selected scene. Figure 4 In the example shown, only one image 830 is displayed for other products. By pressing the triangle marks displayed in the upper right and upper left corners of image 830, image 830 is replaced with images of other candidate products. Alternatively, a method of displaying multiple images of other products on a single screen may be employed.

[0111] exist Figure 3 In the example shown, after generating the second image data for various scenes, server 200 transmits a request to seller terminal 100 for approval of the second image data. However, this approval process can also be omitted. In this case, the second image data generated in step S203 is used directly for the image posted on the website. In this example, server 200 generates the second image data in step S203 before posting it on the website. This is not limiting; server 200 can also generate the second image data after the user selects a scene in step S303.

[0112] Next, the operation of the server 200 in this embodiment will be described in more detail.

[0113] Figure 5This is a flowchart showing an example of the operation executed by the processor 202 of the server 200. In this example, the server 200 executes Figure 5 The processing of steps S510 to S590 is shown below. The operation of each step is described below.

[0114] In step S510 , the server 200 receives first image data representing a hyperspectral image of a product photographed under first background light from the seller terminal 100 .

[0115] Next, the server 200 determines whether the product is photographed outdoors or indoors based on the received first image data. The server 200 estimates the spectrum data of the first background light by performing different processing depending on whether the product is photographed outdoors or indoors. Figure 5 In the example shown, server 200 first determines in step S520 whether the image was taken outdoors based on the content of the first image data. If this determination is yes, the process proceeds to step S530. If this determination is no, the process proceeds to step S540, where server 200 further determines, based on the content of the first image data, whether the image was taken indoors. If this determination is yes, the process proceeds to step S550. If this determination is no, the process proceeds to step S590.

[0116] In step S590, the server 200 sends a notification indicating an error that the photographic environment cannot be determined to the seller terminal 100. The server 200 may also send not only the notification but also instruction data to prompt the seller terminal 100 to photograph the product in a different environment. If the seller terminal 100 receives the instruction data, it displays an image prompting the seller to photograph the product in a different environment on the display 105. For example, Figure 6 As shown, a message such as "Unable to confirm the background light. Please shoot again before a white wall, etc." can be displayed. In addition, the content of the message may simply instruct to reshoot or to change the shooting location.

[0117] In steps S520 and S540, a predetermined image recognition algorithm can be used to determine, based on the first image data, whether the photography was performed outdoors or indoors. For example, if objects existing outdoors, such as the sky, clouds, trees, buildings, vehicles, roads, mountains, or rivers, are identified in the image, it can be determined that the photography was performed outdoors. In addition, if objects mainly existing indoors, such as walls, electrical appliances, carpets, or furniture, are identified in the image, it can be determined that the photography was performed indoors. Alternatively, it is also possible to estimate whether the photography was performed outdoors based on the overall brightness and / or color tone of the image. The server 200 can determine whether the photography was performed outdoors or indoors based on the various factors mentioned above. In addition, for example, a learning model trained by a machine learning algorithm can be applied to the first image data to determine whether the photography was performed outdoors or indoors.

[0118] If the server 200 determines that the image was taken outdoors, it estimates the spectrum of sunlight as background light in step S530. On the other hand, if the server 200 determines that the image was taken indoors, it estimates the spectrum of illumination light as background light in step S550.

[0119] Figure 7 : is a flowchart showing a specific example of the solar spectrum estimation process in step S530. Step S530 includes Figure 7 The processing of steps S531 to S535 is shown.

[0120] In step S531, server 200 determines the date and time of the photo capture based on the timestamp of the uploaded hyperspectral image. In step S532, server 200 determines the location of the photo capture based on the location data obtained by the GPS receiver. In step S533, server 200 accesses meteorological server 500 to determine the date, time, and weather conditions at the location of the photo capture. The order of steps S531 to S533 can also be reversed. In step S534, server 200 references a database pre-stored in memory 203 to obtain solar spectrum data corresponding to the determined date, time, location, and weather conditions. Next, in step S535, server 200 stores the obtained solar spectrum data in memory 203 as an estimated background spectrum.

[0121] Figure 8This is a diagram showing the contents recorded in the solar spectrum database stored in the memory 203. The database in this example associates the combination of the shooting date, time, location, and weather with the solar spectrum data. Such data is pre-recorded in the memory 203 or other recording media. By referring to such a database, the server 200 can obtain the solar spectrum data corresponding to the shooting date, time, location, and weather. In addition, Figure 8 For ease of understanding, the spectrum data is shown as a graph, but in reality, the data representing the intensity of each wavelength is recorded. Figure 8 In the example, the location data is recorded roughly for each city, but the data may be recorded for each area smaller than each city.

[0122] Figure 9 : is a flowchart showing a specific example of the illumination spectrum estimation process in step S550. Step S550 includes Figure 9 The processing of steps S551 to S557 is shown. By extracting features from the spectrum of an object or background in an image, the spectrum of illumination light serving as background light in a room can be estimated.

[0123] In step S551, server 200 selects a portion of the acquired hyperspectral imagery estimated to be close to white. For example, a region of a background or object estimated to be close to white can be selected. Whether or not the image is close to white can be determined based on the ratio of components in the three wavelength bands of red, green, and blue. For example, a red object has extremely low reflectivity for blue and green components, thus providing insufficient information for estimating the spectrum of the illumination light. On the other hand, sufficient information for estimating the spectrum of the illumination light can be obtained from regions where the reflectivity components are non-zero across the entire range of 400 nm to 700 nm, which is visible to humans. In particular, objects with minimal reflectivity fluctuations in the visible range can provide a highly accurate estimate of the spectrum of the illumination light.

[0124] In step S552, the server 200 extracts (1) a 440-460 nm component, (2) a 540-560 nm component, and (3) a 600-650 nm component from the data of one or more pixels in the selected area. These three wavelength bands are hereinafter referred to as "reference wavelength bands."

[0125] In step S553, server 200 determines whether all three reference band components are present. For example, server 200 determines whether the average value of each reference band value for the plurality of pixels included in the area selected in step S551 exceeds a predetermined threshold for any reference band. If this determination is positive, the process proceeds to step S554. If this determination is negative, the process proceeds to step S557.

[0126] Step S557 is the same process as the above-mentioned step S590. In step S557, the server 200 sends a notification to the seller terminal 100 indicating that the background light cannot be determined. The server 200 may also send not only the notification but also instruction data to prompt the seller terminal 100 to change the background image. For example, the server 200 may also send instruction data to the seller terminal 100 to prompt the seller to take pictures of the product in different environments. If the seller terminal 100 receives the instruction data, it will display an image on the display 105 prompting the seller to take pictures of the product in different environments. For example, the server 200 may also send instruction data to the seller terminal 100 to prompt the seller to take pictures of the product in different environments. Figure 6 The message shown is displayed on the display 105. The content of the message may be a simple instruction to retake the picture or an instruction to change the shooting location.

[0127] If data for all components (1) to (3) is available, the process proceeds to step S554, where server 200 refers to the spectral data for multiple illumination lights stored in memory 203 to determine the type of illumination light. The spectrum of illumination light has characteristics corresponding to the illumination method, so by capturing these characteristics from the hyperspectral data, the type of illumination light can be determined. Furthermore, in step S555, server 200 estimates the color temperature corresponding to the determined illumination light. Details of this process are described below.

[0128] Spectral data for multiple types of lighting is pre-stored in memory 203. Examples of lighting types include LED lighting, fluorescent lighting, and incandescent lighting. Spectral shapes vary depending on the light emission method, so general spectral data can be pre-stored for each type of lighting. Alternatively, data for multiple types of lighting can be pre-stored for each type of lighting, corresponding to the manufacturer's model.

[0129] Figures 10A to 10C 2 is a diagram showing an example of spectrum data of illumination light stored in the memory 203 . Figure 10A An example of spectrum data for LED lighting is shown. Figure 10B This shows an example of spectrum data of a fluorescent lamp. Figure 10C An example of spectrum data of an incandescent lamp is shown. In the memory 203, except Figures 10A to 10C In addition to the spectra shown, data on spectra of other types of light sources, such as halogen bulbs, may also be recorded.

[0130] Figure 11 It is represented by a dotted box Figures 10A to 10CThe diagram shows the three reference wavelength bands mentioned above in the example of the spectrum shown. LED lighting generates white light by using blue light from a blue LED to excite phosphors (yellow and red). As a result, the light from LED lighting has a blue peak and a green to red peak. In most cases, the blue peak is caused by the 440nm to 460nm emission from the GaN semiconductor LED, the green to yellow peak is caused by the emission from the YAG-based phosphor, and the red peak is caused by the 600nm to 650nm emission from the CASN-based phosphor. Color temperature adjustment is performed by adjusting the ratio of these three wavelength bands. If there is a peak in the blue wavelength band of 440nm to 460nm and a bottom of the spectrum near 480nm, the lighting can be estimated as LED lighting. In addition, the color temperature can also be estimated based on the components of the green wavelength band of 530nm to 550nm and the red wavelength band of 600nm to 650nm.

[0131] Fluorescent lamps are composed of a combination of broadband and narrowband phosphors. They exhibit a peak around 440nm, originating from the phosphor's emission. This characteristic is similar to LED lighting, but differs from LED lighting in that they also exhibit a sharp peak around 550nm, originating from the phosphor's emission. This peak is detected by comparing the amount of components between 540nm and 560nm with those at surrounding wavelengths, enabling identification of illumination light as fluorescent.

[0132] Incandescent lamps have a characteristic of having no peak and increasing spectral intensity as the wavelength increases. The ratio of components in four wavelength bands, namely the 440nm to 460nm and 540nm to 560nm bands and their surrounding wavelength bands, can be used to distinguish between LED lighting, fluorescent lamps, and incandescent lamps.

[0133] Furthermore, by also taking into account the red component between 600 nm and 650 nm, the accuracy of the estimation is improved, particularly with regard to incandescent lamps.

[0134] exist Figure 9 In step S556 , after the server 200 estimates the type and color temperature of the lighting, it stores the estimated spectrum data of the lighting light in the memory 203 .

[0135] In addition, in this embodiment, the wavelength bands of 440nm to 460nm, 540nm to 560nm, and 600nm to 650nm are selected as three reference wavelength bands, and the spectrum of the illumination light is estimated based on the components of these wavelength bands, but this is only an example. Figure 12 As shown in FIG, the band from 600 nm to 650 nm is excluded from the reference band. Figure 12In the example, in step S552, only the components from 440nm to 460nm and the components from 540nm to 560nm are extracted. Furthermore, in step S553, a determination is made as to whether both the components from 440nm to 460nm and the components from 540nm to 560nm are present. As in this example, even by considering only information regarding the blue and green wavelength bands, it is possible to estimate the type and color temperature of the lighting in most cases. Alternatively, only the blue wavelength band may be set as the reference wavelength band. Alternatively, if the amount of blue spectrum components included in the spectrum data for the reference wavelength band is less than a reference value, it may be determined that the first background light cannot be determined.

[0136] Refer again Figure 5 If the background light spectrum is estimated through the processing of step S530 or S550, server 200 generates a test image for each scene in step S570. The test image data is transmitted to seller terminal 100. If the seller approves the test image, server 200 records the test image data for each scene, i.e., the second image data, to a recording medium such as memory 203 in step S580.

[0137] Figure 13 This is a flowchart illustrating a specific example of the test image generation process in step S570. After estimating the background light spectrum, server 200 calculates the absolute reflectance spectrum of the target product (step S571). Server 200 uses the estimated background spectrum to normalize the hyperspectral image of the product. Specifically, server 200 divides the value of each wavelength for each pixel in the hyperspectral image of the product by the value of the corresponding wavelength in the estimated background spectrum to generate reflectance spectrum data for the product. This reflectance spectrum is referred to as the "absolute reflectance spectrum."

[0138] Next, the server 200 obtains spectrum data of the virtual background light of each scene from the memory 203 (step S572 ).

[0139] Next, server 200 generates a test image for each scene using the calculated product reflectance spectrum and the obtained virtual background spectrum for each scene (step S573). Specifically, server 200 calculates the value of each pixel in the test image of the scene by multiplying the value of each wavelength in the product reflectance spectrum by the value of the corresponding wavelength in the virtual background spectrum.

[0140] Once test images for each scene have been generated, server 200 transmits the test image data to seller terminal 100, acting as the uploader (step S574). Upon receiving the test image data, seller terminal 100 displays the test image on display 105, along with a screen asking whether the seller approves the test image. The seller selects whether to approve based on the displayed information. If the seller selects whether to approve, seller terminal 100 transmits data indicating the approval result to server 200.

[0141] The server 200 determines whether the approval result is received from the seller terminal 100 (step S575). In the case of receiving the approval result, the server 200 determines whether the test data is approved (step S576). In the case of approval, the server 200 sets the test image of each scene to the image actually used in the website (step S577). In this case, it is determined that the estimation of the background spectrum and the calculation of the absolute reflectance spectrum of the product are correct, and the generated test image is adopted. In the case of non-approval, the server 200 sends data indicating re-shooting to the seller terminal 100 (step S578). In this case, it is considered that the estimation of the background spectrum is wrong. Therefore, it can also be compared with Figure 5 Step S590 and Figure 9 Similarly, in step S557 shown, data indicating an error display, a reshoot instruction, an instruction to change the shooting location, or an instruction to shoot in front of a white wall is transmitted to the seller terminal 100.

[0142] Figure 14 1 is a flowchart showing an example of the processing performed by the processor 102 of the seller terminal 100 in this embodiment. In this example, the seller terminal 100 first obtains the data of the hyperspectral image generated by the camera 101 from the memory 103 in step S610. If the upload instruction operation is accepted from the seller in step S620, the seller terminal 100 uploads the image data to the server 200 (step S630). Next, the seller terminal 100 waits until a test image is sent from the server 200 (step S640). If the test image is received, the seller terminal 100 displays the test image and an approval confirmation screen (step S650). As described above, the test images that are candidate images for each scene generated by the server 200 and the screen for selecting whether to approve each test image are displayed on the display 105. In step S660, if the seller selects whether to approve, the seller terminal 100 sends the approval result to the server 200 (step S670).

[0143] Furthermore, after step S630, if server 200 cannot estimate the background spectrum for the uploaded image, a notification indicating this fact may be transmitted from server 200. In this case, for example, an instruction prompting re-shooting may be displayed on display 105. Furthermore, if, in step S660, the user selects a selection indicating that they do not approve the test image, an instruction prompting re-shooting may also be displayed on display 105 after step S670, for example.

[0144] Figure 15 3 is a sequence diagram showing another example of the processing executed by the server 200 and the user terminal 300. In this example, after the purchasing user selects a scene, the server 200 generates second image data corresponding to the selected scene.

[0145] First, the user terminal 300 displays a web page (step S731). The user who wants to make a purchase selects the desired product and scene on the web page (step S732). The server 200 obtains image data associated with the selected product and scene from the memory 203 (step S721). This image data may include, for example, image data of a background suitable for the scene. Next, the server 200 obtains spectral data of the background light corresponding to the selected scene from the memory 203 (step S722). The server 200 also obtains the reflectance spectrum data of the product calculated in advance using the above-mentioned method from the memory 203 (step S723). The server 200 uses the data obtained in steps S721 to S723 to generate image data of the product and scene to be displayed (step S724). In step S724, the server 200 first generates image data of the product to be displayed by multiplying the reflectance spectrum data by the spectral data of the background light of the selected scene for each pixel. This image data is combined with the image data obtained in step S721 to generate image data of the selected product and scene. The user terminal 300 displays the product and the scene image based on the data transmitted from the server 200 (step S733 ).

[0146] As described above, according to this embodiment, even when the background lighting at the time of product photography is unknown, the displayed image can be appropriately corrected to suit the scene selected by the user. This allows the user to confirm how the product will appear in the desired scene before purchasing. This prevents potential issues such as discrepancies between the displayed product image and the actual product.

[0147] (Variation)

[0148] Next, several modifications of this embodiment will be described.

[0149] Figure 164 is a diagram showing an example of a system further including an operator terminal 400 used by an operator operating the server 200. The operator terminal 400 is a computer including a processor 402, a memory 403, a display 405, and a communication interface 404. Figure 17 is a timing diagram showing an overview of the actions in this modification. Figure 17 As shown, in this example, the approval operation after the seller terminal 100 uploads the hyperspectral image to the server 200 is performed not by the seller terminal 100 but by the operator terminal 400. In this way, the generation of the second image data and the subsequent approval can also be performed by the same operator.

[0150] In addition, you can also Figure 18 As shown, the processing of steps S201 to S203 is performed on the operator terminal 400, and the generated second image data is uploaded to the server 200 providing the network service. Alternatively, only steps S201 and S202 of steps S201 to S203 may be performed on the operator terminal 400, the generated product reflectance spectrum data may be uploaded to the server 200, and the second image may be generated (step S203) on the server 200. Alternatively, only step S201 of steps S201 to S203 may be performed on the operator terminal 400, the generated first spectrum data may be uploaded to the server 200 along with the first image, and the calculation of the product reflectance spectrum (step S202) and the generation of the second image (step S203) may be performed on the server 200.

[0151] Figure 19 This figure shows a modified example in which the operator terminal 400 also functions as the server 200. As in this example, instead of providing a dedicated server, the network service described above may be provided using the operator terminal 400 which is a general-purpose computer such as a personal computer.

[0152] In the above examples, the seller terminal 100 is used by a user different from the operator operating the network service, but this is not limited to this method. There are also cases where the operator operating the network service sells products. In this case, the seller terminal 100 is used by the operator.

[0153] Figure 20 This is a timing diagram showing the operation of the system according to another modification. Figure 1The structure shown is the same, but the operation of the server 200 is different. After the server 200 in this example generates the second image data of each scene in step S203, it determines the state of the product, determines the price or the discount rate relative to the list price, and notifies the seller terminal 100 of the determination result in step S910. Based on the reflectance spectrum of the product calculated in step S202, the server 200 determines the quality of the material, scratches, aging, etc. of the product. For example, the data of the products and reflectance spectra sold in the past are recorded in advance in a recording medium such as the memory 203 in association with the prices. Based on this accumulated data, the state of the product shown in the uploaded image can be determined and the appropriate price can be estimated. The state and price of the product can also be determined, for example, using a learning model pre-trained by a machine learning algorithm. Based on the huge amount of data accumulated in the past, the state and appropriate price of the product shown in the uploaded image can be automatically determined.

[0154] The judgment result is fed back to the seller terminal 100. The seller decides whether to accept the suggested price (step S920). At this time, it can also be set to be able to input whether the judgment result indicating the material / scratches / usage feeling is correct or not. The input result of correctness or not can also be recorded in the memory 203 of the server 200 and displayed as reference information when the user to purchase reads it. In addition, a mechanism can also be set up for the user to purchase to evaluate the seller's judgment result of whether it is correct or not. In this way, it is also possible to monitor whether the seller has made an inappropriate evaluation of his own products.

[0155] This specification primarily describes an example of applying the disclosed image processing technology to images of products sold through online shopping. However, the disclosed technology is not limited to such product images and can be applied to hyperspectral images of any object.

[0156] Industrial Applicability

[0157] The technology disclosed herein can be used, for example, to process hyperspectral images of articles. The technology disclosed herein can be used, for example, to process images of goods sold through online shopping using a network such as the Internet.

[0158] Description of reference numerals:

[0159] 100 seller terminals

[0160] 101 Camera

[0161] 102 processors

[0162] 103 Memory

[0163] 104 Communication Interface

[0164] 105 Display

[0165] 200 Server

[0166] 202 processor

[0167] 203 Memory

[0168] 204 Communication Interface

[0169] 300 user terminals

[0170] 302 processor

[0171] 303 Memory

[0172] 304 Communication Interface

[0173] 305 Display

[0174] 400 Operator Terminal

[0175] 402 Processor

[0176] 403 Storage

[0177] 404 Communication Interface

[0178] 500 Weather Server

Claims

1. A method for processing image data, comprising: acquiring first image data representing a hyperspectral image of an object photographed under first background light; extracting spectrum data of at least one reference band from the first image data; estimating the first background light based on the spectrum data of the at least one reference wavelength band extracted from the first image data, thereby acquiring first spectrum data representing the estimated spectrum of the first background light; as well as At least one type of second spectral data representing a spectrum of at least one second background light different from the first background light and the first spectral data are used to generate at least one type of second image data representing an image of the object illuminated by the at least one second background light based on the first image data.

2. The method according to claim 1, The at least one second background light includes a plurality of second background lights that are different from each other, The at least one type of second image data includes a plurality of types of second image data. Each of the plurality of types of second image data represents an image of the object illuminated by each of the plurality of second background lights.

3. The method according to claim 2, The plurality of second background lights include sunlight and one or more artificial lighting lights.

4. The method according to any one of claims 1 to 3, Generating the at least one type of second image data includes: generating, using the first spectrum data, reflection spectrum data representing a reflection spectrum of the object based on the first image data; as well as The at least one type of second image data is generated using the reflection spectrum data and the at least one type of second spectrum data.

5. The method according to any one of claims 1 to 3, Obtaining the first spectrum data includes: determining, based on the first image data, whether the hyperspectral image is taken outdoors or indoors; as well as The first spectral data is generated by performing different processing depending on whether the hyperspectral image is captured outdoors or indoors.

6. The method according to claim 5, If it is determined in the determination that the hyperspectral image is taken outdoors, Acquiring the first spectrum data further includes: Acquiring data representing at least one selected from the group consisting of date, time, location, and weather when the hyperspectral image was captured; Obtaining sunlight spectrum data associated with at least one selected from the group consisting of date, time, location, and weather; as well as The spectrum data of the sunlight is recorded as the first spectrum data in a recording medium.

7. The method according to claim 5, If it is determined in the determination that the hyperspectral image is taken indoors, Acquiring the first spectrum data further includes: estimating, based on the spectrum data of the at least one reference wavelength band, which type of artificial lighting light the first background light corresponds to; as well as The spectrum data of the artificial illumination light is recorded in a recording medium as the first spectrum data.

8. The method according to claim 7, The at least one reference wavelength band includes a blue wavelength band and a green wavelength band.

9. The method according to claim 7, The at least one reference band includes a blue band, a green band, and a red band.

10. The method according to claim 1, The hyperspectral image includes information of at least four bands.

11. A method for processing image data, executed by a server computer that provides a website for selling goods via a network, the method comprising: acquiring first image data representing a hyperspectral image of a first product photographed under first background light; extracting spectrum data of at least one reference band from the first image data; estimating the first background light based on the spectrum data of the at least one reference wavelength band extracted from the first image data, thereby acquiring first spectrum data representing the estimated spectrum of the first background light; generating, based on the first image data, at least one type of second image data representing an image of the first product illuminated by the at least one second background light, using at least one type of second spectral data representing a spectrum of at least one second background light different from the first background light and the first spectral data; as well as In response to a request from a user terminal used by a user of the website, data of a web page including the at least one type of second image data is transmitted to the user terminal.

12. The method according to claim 11, Acquiring the first image data includes receiving the first image data from a seller terminal used by a seller of the first product, The method further comprises: After generating the at least one type of second image data, transmitting a request for approval of the at least one type of second image data to the seller terminal; and receiving data indicating approval of the at least one type of second image data from the seller terminal, After receiving the data indicating the approval, the data of the web page is sent to the user terminal.

13. The method according to claim 11 or 12, Sending the data of the webpage to the user terminal includes: In response to a first request from the user terminal, transmitting data of a first web page including default image data of the first product to the user terminal; as well as In response to the second request from the user terminal, data of the second web page is sent to the user terminal, which is obtained by replacing the default image data in the first web page with the at least one type of second image data, or by adding the at least one type of second image data to the default image data in the first web page.

14. The method according to claim 13, The at least one second background light includes a plurality of second background lights, The first web page includes: A display area for selecting one scene from a plurality of scenes associated with the plurality of second backlights.

15. The method according to claim 14, The display area includes a plurality of areas respectively representing the plurality of scenes, In the display area, the plurality of areas are displayed in an order corresponding to the number of times each of the plurality of scenes has been selected in the website in the past.

16. The method according to claim 14, When one scene is selected from the plurality of scenes, the second request is received, The second web page also includes: Image data of at least one second product is determined based on the number of times the product is displayed in combination with the selected scene.

17. The method according to claim 14, When one scene is selected from the plurality of scenes, the second request is received, The second web page also includes: Image data representing at least one second product illuminated by a second background light associated with the selected scene among the plurality of second background lights.

18. The method according to claim 11 or 12, Acquiring the first image data includes receiving the first image data from a seller terminal used by a seller of the first product, Acquiring the first spectrum data further includes: determining whether the first background light can be determined based on the spectrum data of the at least one reference wavelength band; as well as If the first background light cannot be determined, instruction data for prompting the seller terminal to capture the hyperspectral image of the product under background light different from the first background light is transmitted.

19. The method according to claim 18, The at least one reference band includes a band belonging to blue, The determination includes: When the amount of the component belonging to the blue wavelength band included in the spectrum data of the at least one reference wavelength band is smaller than a reference value, it is determined that the first background light cannot be identified.

20. The method according to claim 11 or 12, The first product is clothing.

21. The method of claim 11, The hyperspectral image includes information of at least four bands.

22. An image data processing device comprising a computer for executing the method according to any one of claims 1 to 21.

23. A computer program product comprising a computer program for causing a computer to perform the method according to any one of claims 1 to 21.

24. An image data processing system comprising: image processing computers; and A server computer provides a website for selling products via the Internet. The image processing computer performs: obtaining first image data representing a hyperspectral image of the product photographed under a first background light, extracting spectrum data of at least one reference band from the first image data, estimating the first background light based on the spectrum data of the at least one reference wavelength band extracted from the first image data, thereby acquiring first spectrum data representing the estimated spectrum of the first background light; generating, based on the first image data, at least one type of second image data representing an image of the product illuminated by the at least one second background light, using at least one type of second spectral data representing a spectrum of at least one second background light different from the first background light and the first spectral data; The server computer transmits data of a web page including the at least one type of second image data to the user terminal in response to a request from the user terminal used by the user of the website.

Images