Product image acquisition method and device, computer equipment and storage medium

Abstract

The invention relates to the technical field of image recognition, in particular to a product image acquisition method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring image data of a product in a multiband spectrum; calculating spectral parameters of the product in different wavebands according to the image data of the product in the multiband spectrum; according to the spectral parameters of the product in different wavebands, generating a product synthetic image in a virtual illumination environment; and carrying out dynamic processing and compression processing on the product synthesis image, and carrying out distributed storage on the processed product synthesis image. By adopting the method, high-definition and multi-dimensional product display can be provided, so that the user experience is enhanced, and the decision-making efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of image acquisition technology, and in particular to a method, apparatus, computer equipment, computer-readable storage medium and computer program product for acquiring product images. Background Art

[0002] With the rapid development of the smart online platform for power grids, product pictures (images) have become the core element of product display and user experience. The quality, accuracy and loading speed of picture display directly affect the user's understanding experience. Users make product preference decisions by browsing product pictures on online platforms, so their requirements for product display are getting higher and higher. In order to provide a better experience, online platforms have begun to continuously improve the image shooting, processing, compression, distribution and display technology. However, although these improvements have made significant progress in image display, current technology still has many limitations, especially in terms of product detail display and image loading efficiency.

[0003] At present, the product image display technology used by most online platforms mainly relies on traditional static visible light images, and obtains the visual information of the product through a single shooting method. Although these methods can show the basic appearance of the product, they have great limitations in expressing materials, lighting conditions and hiding defects.

[0004] Therefore, there is an urgent need for a product image acquisition method, apparatus, computer device, computer-readable storage medium and computer program product that can provide high-definition, multi-dimensional product display to enhance user experience and improve decision-making efficiency. Summary of the invention

[0005] Based on this, it is necessary to provide a product image acquisition method, device, computer equipment, computer-readable storage medium and computer program product that can provide high-definition, multi-dimensional product display to enhance user experience and improve decision-making efficiency in response to the above-mentioned technical problems.

[0006] In a first aspect, the present application provides a method for acquiring a product image, comprising:

[0007] Obtain image data of products in multi-band spectra;

[0008] Calculating the spectral parameters of the product in different bands according to the image data of the product in the multi-band spectrum;

[0009] Generating a synthetic image of the product in a virtual lighting environment according to spectral parameters of the product in different bands;

[0010] The product composite image is dynamically processed and compressed, and the processed product composite image is distributedly stored.

[0011] In one embodiment, calculating the spectral parameters of the product in different bands according to the image data of the product in the multi-band spectrum includes:

[0012] Performing spectral separation processing on the image data of the product in the multi-band spectrum, calculating the reflectivity of each pixel point in different bands, and generating an independent reflection image in each band;

[0013] Generate a multi-band spectral image of the product based on the reflectivity of each pixel in different bands and the independent reflectance image in each band;

[0014] According to the image gray value of each pixel in the multi-band spectral image in different bands, the image texture roughness of the product in different bands is calculated.

[0015] In one embodiment, generating a product composite image in a virtual lighting environment according to spectral parameters of the product in different wavebands includes:

[0016] Build a physical lighting reflection model;

[0017] According to the physical illumination reflection model, the light source reflection intensity of the product is calculated under at least one virtual light source;

[0018] Calculating a physical illumination image of the product according to the light source reflection intensity of the product;

[0019] By generating a GAN (Generative Adversarial Network), the multi-band spectral image is amplified in quantity and enhanced in quality;

[0020] The quality-enhanced multi-band spectral image is fused with the physical illumination image to generate a product composite image.

[0021] In one embodiment, the dynamic processing and compression processing of the product composite image includes:

[0022] Dynamically identifying the resolution of the user device, scaling the product composite image to fit the size of the user device, and compressing the product composite image using an adaptive quantization compression algorithm;

[0023] Multi-level quality optimization is performed on the compressed product composite image to generate product composite images with different clarity.

[0024] In one embodiment, the distributed storage of the processed product composite image includes:

[0025] Dividing the product composite image into a plurality of file blocks, generating a hash value for each file block by a hash algorithm, and storing the hash value in different distributed storage nodes;

[0026] Counting the image access frequency of each of the product composite images, and migrating the product composite images to different storage levels of distributed storage nodes according to the image access frequency and a preset access frequency threshold;

[0027] A redundant copy is created for each of the product composite images, and the redundant copies are stored in different distributed storage nodes according to distributed storage rules, and the integrity of the redundant copies is regularly checked.

[0028] In one embodiment, the step of acquiring image data of a product in a multi-band spectrum includes:

[0029] A spectral imaging device is used to perform a multi-band spectral scan on the product; wherein the band types of the spectral imaging device include a visible light band, a near infrared band, a far infrared band, and an ultraviolet band.

[0030] In a second aspect, the present application further provides a product image acquisition device, comprising:

[0031] Obtain image data of products in multi-band spectra;

[0032] Calculating the spectral parameters of the product in different bands according to the image data of the product in the multi-band spectrum;

[0033] Generating a synthetic image of the product in a virtual lighting environment according to spectral parameters of the product in different bands;

[0034] The product composite image is dynamically processed and compressed, and the processed product composite image is distributedly stored.

[0035] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0036] Obtain image data of products in multi-band spectra;

[0037] Calculating the spectral parameters of the product in different bands according to the image data of the product in the multi-band spectrum;

[0038] Generating a synthetic image of the product in a virtual lighting environment according to spectral parameters of the product in different bands;

[0039] The product composite image is dynamically processed and compressed, and the processed product composite image is distributedly stored.

[0040] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0041] Obtain image data of products in multi-band spectra;

[0042] Calculating the spectral parameters of the product in different bands according to the image data of the product in the multi-band spectrum;

[0043] Generating a synthetic image of the product in a virtual lighting environment according to spectral parameters of the product in different bands;

[0044] The product composite image is dynamically processed and compressed, and the processed product composite image is distributedly stored.

[0045] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0046] Obtain image data of products in multi-band spectra;

[0047] Calculating the spectral parameters of the product in different bands according to the image data of the product in the multi-band spectrum;

[0048] Generating a synthetic image of the product in a virtual lighting environment according to spectral parameters of the product in different bands;

[0049] The product composite image is dynamically processed and compressed, and the processed product composite image is distributedly stored.

[0050] The above-mentioned product image acquisition method, device, computer equipment, computer-readable storage medium and computer program product can more comprehensively capture the physical characteristics of the product, such as material, transparency, reflectivity, etc., by acquiring image data of the product in a multi-band spectrum, thereby providing a more realistic product display. It can display the appearance of the product under different lighting conditions, reduce the visual error caused by lighting changes, and improve the user's understanding of the actual appearance of the product. The generated synthetic image can provide a high-definition and multi-dimensional product view to enhance the user's visual experience. Dynamic processing and compression processing can optimize the loading speed of the image, reduce the user's waiting time, and improve the user experience. Users can quickly make more accurate decisions with more detailed product image information. Multi-dimensional product display can help users identify and select products that meet their needs more quickly and improve decision-making efficiency. The product synthetic image processed by distributed storage can reduce storage costs and improve storage efficiency. Dynamic compression processing can provide images of different clarity according to the user's network conditions and device performance, and optimize the transmission and loading efficiency of images. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0052] FIG1 is a diagram showing an application environment of a method for acquiring product images in one embodiment;

[0053] FIG2 is a schematic diagram of a process of a method for acquiring product images in one embodiment;

[0054] FIG3 is a schematic diagram of a process of obtaining a product image in another embodiment;

[0055] FIG4 is a structural block diagram of a device for acquiring product images in one embodiment;

[0056] FIG. 5 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0058] The product image acquisition method provided in the embodiment of the present application can be applied in the application environment shown in FIG1 . The terminal 102 communicates with the server 104 via a network. The data storage system can store data that the server 104 needs to process. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers.

[0059] The image data of the product in the multi-band spectrum is obtained through the terminal 102; the server 104 calculates the spectral parameters of the product in different bands according to the image data of the product in the multi-band spectrum; a composite image of the product is generated in a virtual lighting environment according to the spectral parameters of the product in different bands; the composite image of the product is dynamically processed and compressed, and the processed composite image of the product is distributedly stored.

[0060] The terminal 102 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart car devices, projection devices, etc. Portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. Head-mounted devices may be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. The server 104 may be an independent physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides cloud computing services.

[0061] In an exemplary embodiment, as shown in FIG2 , a method for obtaining a product image is provided, which is described by taking the method applied to the server in FIG1 as an example, and includes the following steps S202 to S208 . Among them:

[0062] Step S202, obtaining image data of the product in a multi-band spectrum.

[0063] Specifically, a specialized hyperspectral imaging device is used to scan the product. The product is spectrally scanned across multiple bands to obtain its reflection or emission characteristics in each band. The original multi-band spectral data is obtained through the hyperspectral imaging device. This data contains the reflectance information of the product in each band and is the basis for subsequent analysis and image generation.

[0064] In a specific embodiment, obtaining image data of a product in a multi-band spectrum includes: using a spectral imaging device to perform a multi-band spectral scan on the product; wherein the band types of the spectral imaging device include a visible light band, a near infrared band, a far infrared band, and an ultraviolet band.

[0065] Among them, the visible light band: This is the spectrum range that the human eye can perceive, and is usually used to show the appearance and color of the product.

[0066] Near-infrared band: can provide information about the material and chemical composition of the product, which is useful for identifying certain materials and detecting the internal structure of the product.

[0067] Far infrared: Radiation can penetrate certain materials and is used to detect thermal properties or deep structure of products.

[0068] UV Band: The UV band is useful for detecting the fluorescence reaction of certain materials or identifying subtle features of a product, such as the underlying pigment of a painting.

[0069] In each band, the device captures image data of the product, which can then be used to analyze the physical and chemical properties of the product, as well as generate multispectral images.

[0070] In this embodiment, through this multi-band spectral scanning technology, richer product information can be obtained than traditional single-band imaging, providing more accurate data support for product analysis and display.

[0071] Step S204, calculating the spectral parameters of the product in different bands according to the image data of the product in the multi-band spectrum.

[0072] Specifically, for each band of the image, the reflectance of each pixel is calculated. Based on the calculated reflectance, the spectral parameters of the product are extracted. These parameters may include but are not limited to:

[0073] Spectral reflectance: The reflectance of each band reflects the product's ability to reflect light in that band.

[0074] Spectral absorptivity: the product’s ability to absorb light in different wavelengths.

[0075] Spectral transmittance: the ability of a product to transmit light in different wavelengths.

[0076] In a specific embodiment, calculating the spectral parameters of the product in different bands according to the image data of the product in the multi-band spectrum includes:

[0077] Perform spectral separation on the product's image data in multi-band spectra, calculate the reflectivity of each pixel in different bands, and generate independent reflection images in each band;

[0078] Generate a multi-band spectral image of the product based on the reflectivity of each pixel in different bands and the independent reflectance image in each band;

[0079] According to the image gray value of each pixel in the multi-band spectral image in different bands, the image texture roughness of the product in different bands is calculated.

[0080] Specifically, first, the image data of the product in the multi-band spectrum is processed to separate the mixed spectral data into the data of each independent band. This step usually involves image processing technology to ensure that the data of each band is accurately separated.

[0081] For each band of data, the reflectivity of each pixel is calculated. Reflectivity refers to the reflectivity of the product surface to light of a specific wavelength, usually calculated by comparing the intensity of incident light and the intensity of reflected light.

[0082] Based on the calculated reflectivity, independent reflection images are generated for each band. These images show the reflection characteristics of the product in different bands and provide a basis for further analysis.

[0083] The multi-band spectral image of the product is synthesized by using the reflectivity and independent reflection images of each pixel in different bands. This synthetic image can be a simple overlay or based on more complex algorithms, such as physical model-based rendering technology, to show the comprehensive performance of the product in multiple bands.

[0084] According to the image grayscale value of each pixel in the multi-band spectral image in different bands, the image texture roughness of the product in different bands is calculated. Texture roughness is a parameter that describes the texture details and changes in an image. It can be calculated by statistical methods such as variance or standard deviation, or by using more advanced texture analysis algorithms. These spectral parameters and the calculation results of texture roughness can help analyze the physical and chemical properties of the product, such as material, transparency, reflectivity, etc. This multi-dimensional spectral information can be used to provide a more detailed and realistic product display, enhance the user experience, and help users make more accurate purchasing decisions.

[0085] In this embodiment, through this process, the data provided by the hyperspectral imaging technology can be fully utilized, the characteristics of the product can be deeply explored, and scientific and accurate data support can be provided for various applications.

[0086] Step S206, generating a product composite image in a virtual lighting environment according to the spectral parameters of the product in different bands. As shown in FIG3 , it includes:

[0087] Step S302, constructing a physical illumination reflection model;

[0088] Step S304, calculating the light source reflection intensity of the product under at least one virtual light source according to the physical light reflection model;

[0089] Step S306, calculating a physical illumination image of the product according to the light source reflection intensity of the product;

[0090] Step S308, amplifying the quantity and enhancing the quality of the multi-band spectral image by generating an adversarial network (GAN);

[0091] Step S310: Fusing the multi-band spectral image after quality enhancement with the physical illumination image to generate a product composite image.

[0092] Specifically, building a virtual lighting environment can include simulating natural light, indoor light, or lighting under specific conditions. This environment can be implemented through a physical lighting model, such as the Phong reflection model, which takes into account the direction and intensity of the light source and the reflective characteristics of the product surface.

[0093] Use physical lighting models (such as the Phong model) to calculate the lighting effect of each point on the product surface under specific lighting conditions. This involves calculating lighting effects such as diffuse reflection, specular reflection, and highlights.

[0094] Create a virtual light source library that contains light source parameters of different types and conditions. These parameters can be used to simulate various actual lighting environments, such as sunlight, fluorescent lamps, incandescent lamps, etc.

[0095] Artificial intelligence (AI) models, such as the generative adversarial network (GAN) in the convolutional neural network (CNN), are used to amplify the quantity and enhance the quality of multi-band spectral images to generate higher quality images.

[0096] The AI-enhanced image is combined with the lighting effects calculated by the physical lighting model to generate the final product composite image. This composite image should accurately reflect the appearance of the product under specific lighting conditions.

[0097] In this embodiment, through this process, synthetic images of products in various virtual lighting environments can be generated. These images can provide a richer and more realistic product display than traditional static visible light images, thereby improving the user's shopping experience and decision-making efficiency.

[0098] Step S208, dynamically process and compress the product composite image, and distribute the processed product composite image.

[0099] In a specific embodiment, the product composite image is dynamically processed and compressed, including:

[0100] Dynamically identify the resolution of the user's device, scale the product composite image to fit the size of the user's device, and compress the product composite image using an adaptive quantization compression algorithm;

[0101] Multi-level quality optimization is performed on the compressed product composite image to generate product composite images with different clarity.

[0102] Specifically, the system needs to be able to identify or predict the screen resolution of the user's device. This can be achieved through user agent string analysis, device information provided by the client, or a preset list of device resolutions. Based on the identified device resolution, the system scales the product composite image to a size suitable for the user's device display. This step ensures that the image can be displayed at the optimal size on different devices, avoiding images that are too large or too small from affecting the user experience.

[0103] The scaled product composite image is compressed using an adaptive quantization compression algorithm. This algorithm dynamically adjusts the compression ratio based on the image content and quality requirements to reduce the file size while maintaining image quality. Adaptive compression means that the algorithm analyzes the image content and identifies which parts can withstand a higher compression ratio without significantly reducing visual quality and which parts need to maintain a higher quality.

[0104] In order to adapt to different users' network conditions and device performance, the system needs to generate product composite images with different clarity levels. This usually involves creating multiple versions of the image, each with a different resolution and compression level. For example, you can create a low-resolution version for environments with poor network conditions, a high-resolution version for environments with good network conditions, and a retina screen optimized version for devices with high pixel density.

[0105] The system needs to dynamically select the most appropriate image version for loading and display based on the user's network speed and device performance. This can be achieved through technologies such as network condition detection and device performance evaluation. To increase loading speed, the system may cache commonly used image versions on the user's device or edge server. In addition, it can also predict and preload the image version that may be needed based on user behavior.

[0106] In this embodiment, through these steps, the processing and compression of the product composite image is intended to optimize the transmission efficiency and storage efficiency of the image, while ensuring a high-quality user experience under different devices and network conditions. This dynamic processing and compression strategy is crucial to improving the performance and user satisfaction of the online platform.

[0107] In a specific embodiment, distributed storage of the processed product composite image includes:

[0108] Divide the product composite image into multiple file blocks, generate a hash value for each file block through a hash algorithm, and store the hash value in different distributed storage nodes;

[0109] Count the image access frequency of each product composite image, and migrate the product composite image to different storage levels of distributed storage nodes according to the image access frequency and the preset access frequency threshold;

[0110] Create redundant copies for each product composite image, store the redundant copies in different distributed storage nodes through distributed storage rules, and regularly perform integrity checks on the redundant copies.

[0111] Specifically, file segmentation and hash value generation include:

[0112] File chunking refers to dividing a large product composite image into multiple smaller file chunks. Doing so can improve storage efficiency, allow for parallel processing and transfer, and more flexible storage management.

[0113] The application of hash algorithm refers to using hash algorithm to generate a unique hash value for each file block. This hash value is equivalent to the "fingerprint" of the file block, which is used to identify and retrieve the file block.

[0114] The generated hash values ​​and corresponding file blocks are stored in different distributed storage nodes. This distributed storage can improve data reliability and access speed because the data is replicated and stored on multiple geographically dispersed servers.

[0115] The system needs to track and count the access frequency of each product composite image, which can be achieved through log analysis, counters or other monitoring tools. Based on the access frequency of the image and the preset access frequency threshold, the system will automatically migrate the image to different levels of storage nodes. For example, frequently accessed images may be migrated to faster storage media (such as SSD), while infrequently accessed images may be migrated to lower-cost, slower storage media (such as HDD or cloud storage).

[0116] To improve data reliability and fault tolerance, the system creates redundant copies for each product composite image. These redundant copies are stored on different storage nodes according to distributed storage rules to ensure that when a node fails, the data can still be recovered from other nodes. The integrity of the stored redundant copies is regularly checked to ensure that the data is not lost or damaged due to hardware failure, data corruption, etc.

[0117] In this embodiment, through the distributed storage strategy, large-scale product composite image data can be effectively managed, the access efficiency and reliability of data can be improved, and the storage cost can be reduced. This is especially important for e-commerce platforms that need to process and store large amounts of image data, because they need to ensure that users can quickly access high-quality product images no matter when and where.

[0118] In the above-mentioned product image acquisition method, by acquiring the image data of the product in a multi-band spectrum, the physical characteristics of the product, such as material, transparency, reflectivity, etc., can be more comprehensively captured, thereby providing a more realistic product display. It can display the appearance of the product under different lighting conditions, reduce the visual error caused by lighting changes, and improve the user's understanding of the actual appearance of the product. The generated synthetic image can provide a high-definition and multi-dimensional product view, enhancing the user's visual experience. Dynamic processing and compression processing can optimize the loading speed of the image, reduce the user's waiting time, and improve the user experience. Users can quickly make more accurate decisions with more detailed product image information. Multi-dimensional product display can help users identify and select products that meet their needs more quickly and improve decision-making efficiency. The product synthetic image processed by distributed storage can reduce storage costs and improve storage efficiency. Dynamic compression processing can provide images of different clarity according to the user's network conditions and device performance, and optimize the transmission and loading efficiency of images.

[0119] The most detailed embodiment of this application is:

[0120] 1. Obtain image data of the product in multi-band spectra and calculate the spectral parameters of the product in different bands;

[0121] 1.1. Use hyperspectral imaging equipment to perform multi-band spectral scanning on the product. The hyperspectral imaging equipment covers the following bands: visible light band, near infrared band, far infrared band and ultraviolet band;

[0122] 1.2. After obtaining the original multi-band spectral data, the images of each band are spectrally separated, and the reflectance of each pixel in different bands is calculated to generate an independent reflection image in each band. The spectral reflectance is calculated by the following formula:

[0123] ;

[0124] in, is the reflectivity at wavelength λ, is the reflection intensity of the product surface at this wavelength, is the incident light intensity;

[0125] 1.3. Generate multispectral images based on the spectral reflectance data of different bands, and calculate the texture roughness of the image of each band as the texture feature:

[0126] ;

[0127] Where T is the texture roughness, n is the number of bands, is the gray value of the midpoint (x, y) in the i-th band image. The texture feature is combined with the image reflectivity to form the image feature.

[0128] 2. Generate product synthetic images in a virtual lighting environment;

[0129] 2.1. Construct a physical lighting model;

[0130] Calculate the light source reflection intensity based on the Phong reflection model:

[0131] ;

[0132] in, is the reflected light intensity, is the incident light intensity, L is the light source direction vector, N is the product surface normal vector, is the diffuse reflectance, is the specular reflection coefficient, V is the sight direction vector, B is the reflected light direction vector, and a is the highlight index;

[0133] 2.2. Build a virtual light source library;

[0134] After the physical illumination model is established, a virtual light source library is created based on typical scenes, covering a variety of illumination conditions such as natural light, artificial light, and special ambient light. The light source is specifically set according to the user's choice or the actual environment. The illumination parameters are selected from the virtual light source library and input into the physical illumination model. The reflected light intensity of each pixel of the multispectral image is calculated, and a physical illumination image is generated based on the reflected light intensity.

[0135] 2.3. Dynamic synthesis of lighting conditions based on AI models;

[0136] A convolutional neural network is constructed to input image features to enhance the multispectral images, and a generative adversarial network (GAN) is used to amplify the quantity and enhance the quality of multi-band spectral images through the generation network and the discriminant network. The quality-enhanced multi-band spectral images are fused with the physical illumination images to generate a synthetic image of the product.

[0137] 3. Dynamically process and compress product synthetic images;

[0138] 3.1. Dynamically identify the resolution of the user's device, scale the width and height of the product composite image to the display size of the user's device, use an adaptive quantization compression algorithm to compress the product composite image, and perform quality inspection on the compressed image to ensure that the compression effect meets the visual standards;

[0139] 3.2. Perform multi-level quality optimization on the compressed images, generate product composite images in different resolutions, detect the network speed of the user's device, and select the product composite image with the appropriate resolution to load and display.

[0140] 4. Distributed storage of product composite images;

[0141] 4.1. Divide the product composite image into multiple file blocks, generate a hash value for each file block through a hash algorithm, and store the hash value in different distributed storage nodes. When distributed to the distributed storage nodes, compare the hash value of the file block with the hash value of the existing file in the storage node to avoid repeated storage of the same file block;

[0142] 4.2. Count the access frequency of each product's synthetic image and set the access frequency threshold. According to the image access frequency and the access frequency threshold, migrate the image to different storage layers of the distributed storage node, including high-speed storage layer, medium-speed storage layer and low-speed storage layer;

[0143] 4.3. Create redundant copies for each image, store them on different storage nodes according to the distributed storage rules, mark them as copies, and perform integrity checks on the redundant copies regularly.

[0144] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0145] Based on the same inventive concept, the embodiment of the present application also provides a product image acquisition device for implementing the product image acquisition method involved above. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above method, so the specific limitations in one or more product image acquisition device embodiments provided below can refer to the limitations of the product image acquisition method above, and will not be repeated here.

[0146] In an exemplary embodiment, as shown in FIG4 , a product image acquisition device is provided, comprising:

[0147] An image data acquisition module 402 is used to acquire image data of a product in a multi-band spectrum;

[0148] The parameter calculation module 404 is used to calculate the spectral parameters of the product in different bands according to the image data of the product in the multi-band spectrum;

[0149] An image synthesis module 406, used to generate a synthetic image of the product in a virtual lighting environment according to the spectral parameters of the product in different bands;

[0150] The image processing and storage module 408 is used to perform dynamic processing and compression processing on the product composite image, and to perform distributed storage on the processed product composite image.

[0151] In an exemplary embodiment, the parameter calculation module 404 is specifically used to perform spectral separation processing on the image data of the product in the multi-band spectrum, calculate the reflectivity of each pixel point in different bands, and generate an independent reflection image in each band; generate a multi-band spectral image of the product according to the reflectivity of each pixel point in different bands and the independent reflection image in each band; calculate the image texture roughness of the product in different bands according to the image grayscale value of each pixel point in the multi-band spectral image in different bands.

[0152] In an exemplary embodiment, the image synthesis module 406 is specifically used to construct a physical lighting reflection model; calculate the light source reflection intensity of the product under at least one virtual light source according to the physical lighting reflection model; calculate the physical lighting image of the product according to the light source reflection intensity of the product; amplify the quantity and enhance the quality of the multi-band spectral image by generating an adversarial network GAN; fuse the multi-band spectral image after quality enhancement with the physical lighting image to generate a product synthetic image.

[0153] In an exemplary embodiment, the image processing and storage module 408 is specifically used to dynamically identify the resolution of the user device, scale the product composite image to adapt to the size of the user device, and compress the product composite image using an adaptive quantization compression algorithm; perform multi-level quality optimization on the compressed product composite image to generate product composite images of different clarity.

[0154] In an exemplary embodiment, the image processing and storage module 408 is specifically used to divide the product composite image into multiple file blocks, generate a hash value for each file block through a hash algorithm, and store the hash value in different distributed storage nodes; count the image access frequency of each product composite image, and migrate the product composite image to different storage levels of the distributed storage node according to the image access frequency and a preset access frequency threshold; create redundant copies for each product composite image, store the redundant copies in different distributed storage nodes through distributed storage rules, and regularly perform integrity checks on the redundant copies.

[0155] In an exemplary embodiment, the image data acquisition module 402 is specifically used to use a spectral imaging device to perform a multi-band spectral scan on the product; wherein the band types of the spectral imaging device include a visible light band, a near infrared band, a far infrared band, and an ultraviolet band.

[0156] Each module in the above-mentioned product image acquisition device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module.

[0157] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG5. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store image data of the product in a multi-band spectrum and processed product composite images. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a product image acquisition method is implemented.

[0158] Those skilled in the art will understand that the structure shown in FIG. 5 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0159] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0160] Obtain image data of products in multi-band spectra;

[0161] Calculating the spectral parameters of the product in different bands according to the image data of the product in the multi-band spectrum;

[0162] Generating a synthetic image of the product in a virtual lighting environment according to spectral parameters of the product in different bands;

[0163] The product composite image is dynamically processed and compressed, and the processed product composite image is distributedly stored.

[0164] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0165] Performing spectral separation processing on the image data of the product in the multi-band spectrum, calculating the reflectivity of each pixel point in different bands, and generating an independent reflection image in each band;

[0166] Generate a multi-band spectral image of the product based on the reflectivity of each pixel in different bands and the independent reflectance image in each band;

[0167] According to the image gray value of each pixel in the multi-band spectral image in different bands, the image texture roughness of the product in different bands is calculated.

[0168] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0169] Build a physical lighting reflection model;

[0170] According to the physical illumination reflection model, the light source reflection intensity of the product is calculated under at least one virtual light source;

[0171] Calculating a physical illumination image of the product according to the light source reflection intensity of the product;

[0172] By generating a GAN (Generative Adversarial Network), the multi-band spectral image is amplified in quantity and enhanced in quality;

[0173] The quality-enhanced multi-band spectral image is fused with the physical illumination image to generate a product composite image.

[0174] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0175] Dynamically identifying the resolution of the user device, scaling the product composite image to fit the size of the user device, and compressing the product composite image using an adaptive quantization compression algorithm;

[0176] Multi-level quality optimization is performed on the compressed product composite image to generate product composite images with different clarity.

[0177] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0178] Dividing the product composite image into a plurality of file blocks, generating a hash value for each file block by a hash algorithm, and storing the hash value in different distributed storage nodes;

[0179] Counting the image access frequency of each of the product composite images, and migrating the product composite images to different storage levels of distributed storage nodes according to the image access frequency and a preset access frequency threshold;

[0180] A redundant copy is created for each of the product composite images, and the redundant copies are stored in different distributed storage nodes according to distributed storage rules, and the integrity of the redundant copies is regularly checked.

[0181] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0182] A spectral imaging device is used to perform a multi-band spectral scan on the product; wherein the band types of the spectral imaging device include a visible light band, a near infrared band, a far infrared band, and an ultraviolet band.

[0183] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0184] Obtain image data of products in multi-band spectra;

[0185] Calculating the spectral parameters of the product in different bands according to the image data of the product in the multi-band spectrum;

[0186] Generating a synthetic image of the product in a virtual lighting environment according to spectral parameters of the product in different bands;

[0187] The product composite image is dynamically processed and compressed, and the processed product composite image is distributedly stored.

[0188] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0189] Performing spectral separation processing on the image data of the product in the multi-band spectrum, calculating the reflectivity of each pixel point in different bands, and generating an independent reflection image in each band;

[0190] Generate a multi-band spectral image of the product based on the reflectivity of each pixel in different bands and the independent reflectance image in each band;

[0191] According to the image gray value of each pixel in the multi-band spectral image in different bands, the image texture roughness of the product in different bands is calculated.

[0192] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0193] Build a physical lighting reflection model;

[0194] According to the physical illumination reflection model, the light source reflection intensity of the product is calculated under at least one virtual light source;

[0195] Calculating a physical illumination image of the product according to the light source reflection intensity of the product;

[0196] By generating a GAN (Generative Adversarial Network), the multi-band spectral image is amplified in quantity and enhanced in quality;

[0197] The quality-enhanced multi-band spectral image is fused with the physical illumination image to generate a product composite image.

[0198] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0199] Dynamically identifying the resolution of the user device, scaling the product composite image to fit the size of the user device, and compressing the product composite image using an adaptive quantization compression algorithm;

[0200] Multi-level quality optimization is performed on the compressed product composite image to generate product composite images with different clarity.

[0201] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0202] Dividing the product composite image into a plurality of file blocks, generating a hash value for each file block by a hash algorithm, and storing the hash value in different distributed storage nodes;

[0203] Counting the image access frequency of each of the product composite images, and migrating the product composite images to different storage levels of distributed storage nodes according to the image access frequency and a preset access frequency threshold;

[0204] A redundant copy is created for each of the product composite images, and the redundant copies are stored in different distributed storage nodes according to distributed storage rules, and the integrity of the redundant copies is regularly checked.

[0205] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0206] A spectral imaging device is used to perform a multi-band spectral scan on the product; wherein the band types of the spectral imaging device include a visible light band, a near infrared band, a far infrared band, and an ultraviolet band.

[0207] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0208] Obtain image data of products in multi-band spectra;

[0209] Calculating the spectral parameters of the product in different bands according to the image data of the product in the multi-band spectrum;

[0210] Generating a synthetic image of the product in a virtual lighting environment according to spectral parameters of the product in different bands;

[0211] The product composite image is dynamically processed and compressed, and the processed product composite image is distributedly stored.

[0212] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0213] Performing spectral separation processing on the image data of the product in the multi-band spectrum, calculating the reflectivity of each pixel point in different bands, and generating an independent reflection image in each band;

[0214] Generate a multi-band spectral image of the product based on the reflectivity of each pixel in different bands and the independent reflectance image in each band;

[0215] According to the image gray value of each pixel in the multi-band spectral image in different bands, the image texture roughness of the product in different bands is calculated.

[0216] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0217] Build a physical lighting reflection model;

[0218] According to the physical illumination reflection model, the light source reflection intensity of the product is calculated under at least one virtual light source;

[0219] Calculating a physical illumination image of the product according to the light source reflection intensity of the product;

[0220] By generating a GAN (Generative Adversarial Network), the multi-band spectral image is amplified in quantity and enhanced in quality;

[0221] The quality-enhanced multi-band spectral image is fused with the physical illumination image to generate a product composite image.

[0222] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0223] Dynamically identifying the resolution of the user device, scaling the product composite image to fit the size of the user device, and compressing the product composite image using an adaptive quantization compression algorithm;

[0224] Multi-level quality optimization is performed on the compressed product composite image to generate product composite images with different clarity.

[0225] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0226] Dividing the product composite image into a plurality of file blocks, generating a hash value for each file block by a hash algorithm, and storing the hash value in different distributed storage nodes;

[0227] Counting the image access frequency of each of the product composite images, and migrating the product composite images to different storage levels of distributed storage nodes according to the image access frequency and a preset access frequency threshold;

[0228] A redundant copy is created for each of the product composite images, and the redundant copies are stored in different distributed storage nodes according to distributed storage rules, and the integrity of the redundant copies is regularly checked.

[0229] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0230] A spectral imaging device is used to perform a multi-band spectral scan on the product; wherein the band types of the spectral imaging device include a visible light band, a near infrared band, a far infrared band, and an ultraviolet band.

[0231] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0232] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0233] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0234] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the present application. It should be noted that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for acquiring a product image, characterized in that: The method comprises: Obtain image data of products in multi-band spectra; Calculating the spectral parameters of the product in different bands according to the image data of the product in the multi-band spectrum; Generating a synthetic image of the product in a virtual lighting environment according to spectral parameters of the product in different bands; The product composite image is dynamically processed and compressed, and the processed product composite image is distributedly stored.

2. The method according to claim 1, characterized in that The step of calculating the spectral parameters of the product in different bands according to the image data of the product in the multi-band spectrum includes: Performing spectral separation processing on the image data of the product in the multi-band spectrum, calculating the reflectivity of each pixel point in different bands, and generating an independent reflection image in each band; Generate a multi-band spectral image of the product based on the reflectivity of each pixel in different bands and the independent reflectance image in each band; According to the image gray value of each pixel in the multi-band spectral image in different bands, the image texture roughness of the product in different bands is calculated.

3. The method according to claim 2, characterized in that Generating a product composite image in a virtual lighting environment according to the spectral parameters of the product in different bands includes: Build a physical lighting reflection model; According to the physical illumination reflection model, the light source reflection intensity of the product is calculated under at least one virtual light source; Calculating a physical illumination image of the product according to the light source reflection intensity of the product; By generating a GAN (Generative Adversarial Network), the multi-band spectral image is amplified in quantity and enhanced in quality; The multi-band spectral image after quality enhancement is fused with the physical illumination image to generate a product composite image.

4. The method according to claim 1, characterized in that: The step of dynamically processing and compressing the product composite image comprises: Dynamically identifying the resolution of the user device, scaling the product composite image to fit the size of the user device, and compressing the product composite image using an adaptive quantization compression algorithm; Multi-level quality optimization is performed on the compressed product composite image to generate product composite images with different clarity.

5. The method according to claim 1, characterized in that The distributed storage of the processed product composite image includes: Dividing the product composite image into a plurality of file blocks, generating a hash value for each file block by a hash algorithm, and storing the hash value in different distributed storage nodes; Counting the image access frequency of each of the product composite images, and migrating the product composite images to different storage levels of distributed storage nodes according to the image access frequency and a preset access frequency threshold; A redundant copy is created for each of the product composite images, and the redundant copies are stored in different distributed storage nodes according to distributed storage rules, and the integrity of the redundant copies is regularly checked.

6. The method according to claim 1, characterized in that The step of acquiring image data of a product in a multi-band spectrum includes: A spectral imaging device is used to perform a multi-band spectral scan on the product; wherein the band types of the spectral imaging device include a visible light band, a near infrared band, a far infrared band, and an ultraviolet band.

7. A product image acquisition device, characterized in that: The device comprises: An image data acquisition module is used to acquire image data of the product in a multi-band spectrum; A parameter calculation module, used for calculating the spectral parameters of the product in different bands according to the image data of the product in the multi-band spectrum; An image synthesis module, used to generate a product synthetic image in a virtual lighting environment according to spectral parameters of the product in different bands; The image processing and storage module is used to dynamically process and compress the product composite image, and to perform distributed storage on the processed product composite image.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images