Image data processing method, apparatus and device

Abstract

Embodiments of the present application disclose image data processing methods, devices and equipment. The method comprises: obtaining brightness information of each target point in the image data to be processed; determining mask weights corresponding to each target point according to the brightness information; performing brightness adjustment processing on the brightness information of each target point according to a preset dark area processing strategy to obtain dark area processing data corresponding to each target point, and performing full-channel adjustment processing on each target point according to a preset bright area processing strategy to obtain bright area processing data corresponding to each target point; determining fusion data corresponding to each target point according to the mask weights, the dark area processing data and the bright area processing data; and generating target image data based on the fusion data. By implementing the method of the embodiments of the present application, the brightness of the image data can be adaptively adjusted and processed, and the image data processing quality can be improved.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to image data processing methods, apparatus and equipment. Background Technology

[0002] Due to variations in ambient lighting during shooting or scanning, the resulting image data often suffers from uneven brightness distribution, loss of detail in dark areas, and overexposure in bright areas. For example, due to the narrow space and complex lighting conditions inside the oral cavity, the image data obtained from shooting or scanning is highly prone to problems such as uneven brightness distribution, loss of detail in dark areas, overexposure in bright areas, and color distortion. Dark areas deep within the oral cavity are prone to losing texture details, and highlight areas on the tooth surface may appear washed out and overexposed.

[0003] In existing technologies, gamma correction is used to adjust the brightness of image data. However, traditional gamma correction uses a single parameter to process the entire image data uniformly, which cannot perform differentiated optimization for different brightness areas. For example, there is the color distortion problem of single red-green-blue (RGB) gamma adjustment: although traditional full-image gamma correction in the RGB space can adjust the brightness, it is prone to generating color noise in dark areas because it performs power function transformation on three channels at the same time, resulting in abnormal color saturation and noise amplification, which cannot meet the requirements of high-quality image data processing. Summary of the Invention

[0004] This application provides an image data processing method, apparatus, and device that can adaptively adjust the brightness of image data to improve the quality of image data processing.

[0005] In a first aspect, embodiments of this application provide an image data processing method, which includes: Obtain the brightness information of each target point in the image data to be processed; The mask weights corresponding to each target point are determined based on the brightness information. According to the preset dark area processing strategy, the brightness information of each target point is adjusted to obtain the dark area processing data corresponding to each target point. According to the preset bright area processing strategy, the full channel adjustment is performed on each target point to obtain the bright area processing data corresponding to each target point. Based on the mask weights, the dark area processing data, and the bright area processing data, determine the fusion data corresponding to each of the target points; Target image data is generated based on the fused data.

[0006] In some embodiments, determining the fused data corresponding to each of the target points based on the mask weights, the dark area processing data, and the bright area processing data includes: The mask weight is determined as the bright area weight of the corresponding target point in the bright area processing data, and the dark area weight of the corresponding target point in the dark area processing data is determined based on the mask weight. Based on the bright area weight and the dark area weight, the dark area processing data and the bright area processing data are weighted and fused to obtain the fused data.

[0007] In some embodiments, obtaining the brightness information of each target point in the image data to be processed includes: The image data to be processed is converted from RGB space to a luminance-chrominance separated color space, which includes YCbCr space, HSV space or YCgCo space; The luminance channel data of the image data to be processed is extracted from the luminance-chrominance separated color space to obtain the luminance information.

[0008] In some embodiments, determining the mask weights corresponding to each target point based on the brightness information includes: Based on the brightness information, determine the brightness threshold and transition steepness coefficient corresponding to the image data to be processed; The mask weights corresponding to each target point are determined based on the brightness information, the brightness threshold, and the transition steepness coefficient.

[0009] In some embodiments, determining the brightness threshold and transition steepness coefficient corresponding to the image data to be processed based on the brightness information includes: Based on the brightness information, determine the median brightness, mean brightness, and variance of the brightness corresponding to the image data to be processed; The brightness threshold is determined based on the median brightness and the mean brightness. The transition steepness coefficient is determined based on the brightness variance and the preset base coefficient.

[0010] In some embodiments, determining the mask weights corresponding to each of the target points based on the brightness information, the brightness threshold, and the transition steepness coefficient includes: Based on a preset S-curve function, the mask weights corresponding to each target point are determined according to the brightness information, the brightness threshold, and the transition steepness coefficient. The S-curve function is: mask = 1. / (1+exp(-k×(Y-threshold))); Wherein, mask is the mask weight, k is the transition steepness coefficient, Y is the brightness information, and threshold is the brightness threshold.

[0011] In some embodiments, the step of performing brightness adjustment processing on the brightness information of each target point according to a preset dark area processing strategy to obtain dark area processing data corresponding to each target point, and performing full-channel adjustment processing on each target point according to a preset bright area processing strategy to obtain bright area processing data corresponding to each target point, includes: Obtain the dark area gamma correction coefficient and the bright area gamma correction coefficient corresponding to the image data to be processed; In a luminance-chrominance separated color space, the luminance information is adjusted according to the dark area gamma correction coefficient to obtain the dark area processing data. In the RGB space, each target point is adjusted across all channels according to the gamma correction coefficient of the bright area to obtain the initial brightness processing data corresponding to each target point. The initial brightness processing data is converted from RGB space to a luminance-chrominance separated color space to obtain the brightness area processing data.

[0012] In some embodiments, obtaining the dark area gamma correction coefficient and the bright area gamma correction coefficient corresponding to the image data to be processed includes: The median and mean brightness values ​​of the image data to be processed are determined based on the brightness information. The dark area gamma correction coefficient and the bright area gamma correction coefficient are determined based on the median brightness, the average brightness, the preset dark area gamma reference value, and the preset bright area gamma reference value.

[0013] In some embodiments, generating target image data based on the fused data includes: In a luminance-chrominance separated color space, candidate image data is generated based on the fused data; The candidate image data is converted from a luminance-chrominance separated color space to an RGB space to obtain the target image data.

[0014] In some embodiments, the image data to be processed is two-dimensional image data obtained by shooting or scanning; after generating target image data based on the fused data, the method further includes: A three-dimensional model is generated based on the target image data.

[0015] In some embodiments, the image data to be processed is two-dimensional image data or three-dimensional image data, the image data to be processed is acquired by one or more devices, and before acquiring the brightness information of each target point in the image data to be processed, the method further includes: In an oral cavity scanning scenario, the image data to be processed is acquired through scanning and / or 3D reconstruction. Alternatively, in high dynamic range scenarios, the image data to be processed can be acquired by shooting.

[0016] Secondly, embodiments of this application also provide an image data processing apparatus, comprising: The transceiver unit is used to acquire image data to be processed; A processing unit is configured to: acquire brightness information of each target point in the image data to be processed; determine mask weights corresponding to each target point based on the brightness information; perform brightness adjustment processing on the brightness information of each target point according to a preset dark area processing strategy to obtain dark area processing data corresponding to each target point; and perform full-channel adjustment processing on each target point according to a preset bright area processing strategy to obtain bright area processing data corresponding to each target point; determine fusion data corresponding to each target point based on the mask weights, the dark area processing data, and the bright area processing data; and generate target image data based on the fusion data.

[0017] Thirdly, embodiments of this application also provide a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-described method.

[0018] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program, the computer program including program instructions that, when executed by a processor, can implement the above-described method.

[0019] This application provides an image data processing method, apparatus, and device. The method includes: acquiring brightness information of each target point in image data to be processed; determining mask weights corresponding to each target point based on the brightness information; performing brightness adjustment processing on the brightness information of each target point according to a preset dark area processing strategy to obtain dark area processing data corresponding to each target point; performing full-channel adjustment processing on each target point according to a preset bright area processing strategy to obtain bright area processing data corresponding to each target point; determining fusion data corresponding to each target point based on the mask weights, the dark area processing data, and the bright area processing data; and generating target image data based on the fusion data. As can be seen, this embodiment of the application determines the mask weight based on the brightness information of the target point, thereby achieving objective division and continuous transition of bright and dark areas and avoiding color information interference. Moreover, this embodiment of the application adopts a differentiated processing strategy of adjusting the brightness of dark areas and adjusting the full channel of bright areas, which can improve the performance of bright areas while ensuring the color fidelity of dark areas. In addition, this embodiment of the application achieves smooth fusion of dark area processing data and bright area processing data through mask weight, eliminating boundary abrupt changes and artificial traces, making the image data enhancement effect natural and continuous, thereby improving the quality of image data processing. Attached Figure Description

[0020] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 A flowchart illustrating the image data processing method provided in an embodiment of this application; Figure 2 This is a schematic diagram of a sub-process of the image data processing method provided in the embodiments of this application; Figure 3 A schematic diagram illustrating the correspondence between brightness and mask weights provided in the embodiments of this application; Figure 4 Another schematic diagram illustrating the correspondence between brightness and mask weights provided in the embodiments of this application; Figure 5 Another schematic diagram illustrating the correspondence between brightness and mask weights provided in the embodiments of this application; Figure 6 A schematic diagram of a luminance mask is provided for an embodiment of this application; Figure 7 This is another schematic diagram of a sub-process of the image data processing method provided in the embodiments of this application; Figure 8This is another schematic diagram of a sub-process of the image data processing method provided in the embodiments of this application; Figure 9 A schematic block diagram of an image data processing apparatus provided in an embodiment of this application; Figure 10 A schematic block diagram of a computer device provided in an embodiment of this application. Detailed Implementation

[0022] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0023] It should be noted that any AI models, software tools, or components not belonging to this company appearing in the embodiments of this application are merely illustrative examples and do not represent actual use. All user personal information involved in the embodiments of this application has been obtained by authorized entities (who have known and consented) or fully authorized by all parties through various legal and compliant means. The collection, storage, use, processing, transmission, provision, and disclosure of the information, data, and signals involved all comply with relevant laws and regulations and do not violate public order and good morals.

[0024] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0025] It should also be understood that the terminology used in this application specification is for the purpose of describing particular embodiments only and is not intended to limit the application. As used in this application specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0026] It should also be further understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0027] This application provides an image data processing method, apparatus, and device.

[0028] The execution subject of this image data processing method can be the image data processing device provided in the embodiments of this application, or a computer device that integrates the image data processing device. The image data processing device can be implemented in hardware or software, and the computer device can be a terminal or a server. The terminal can be a scanning device, a smartphone, a tablet computer, a handheld computer, or a laptop computer, etc.

[0029] Figure 1 This is a schematic flowchart of the image data processing method provided in an embodiment of this application. Figure 1 As shown, the method includes the following steps S110-S150.

[0030] S110. Obtain the brightness information of each target point in the image data to be processed.

[0031] In this embodiment, the image data to be processed is the image data that needs to be optimized and adjusted. For example, it is the facial image data, oral image data, or both facial and oral image data of the target object. The target object is a user undergoing oral treatment, which includes, but is not limited to, restoration, veneer, orthodontics, and implants.

[0032] The image data to be processed can be scanned image data obtained in real time using scanning equipment (intraoral scanning equipment, extraoral scanning equipment, or facial scanning equipment, etc.) in an oral scanning scenario, or image data acquired by an imaging device (via scanner or camera) in a high dynamic range scenario. A high dynamic range scenario refers to a scenario where the brightness difference between the brightest and darkest areas of an image is extremely large, i.e., there are simultaneously overexposed highlight areas and deep shadow areas. Ordinary imaging equipment struggles to clearly present the details of both types of areas simultaneously, easily resulting in problems such as missing details in dark areas and overexposed, washed-out bright areas. In this case, the scanning or imaging device can be connected to the computer device provided in this application via wired or wireless connection. The computer device provided in this application can then perform real-time optimization processing on the image data to be processed sent by the scanning or imaging device.

[0033] Furthermore, the image data to be processed can also be image data pre-stored in a local or cloud database. In this case, the computer device retrieves the image data to be processed from the local or cloud database. In this embodiment, the image data to be processed can be two-dimensional image data or three-dimensional image data. Two-dimensional image data can be high-resolution photographs captured by a camera or image frames obtained from an oral scanner. Three-dimensional image data can be point cloud data or a mesh model obtained through three-dimensional reconstruction based on image frames obtained from an oral scanner.

[0034] The image data to be processed consists of multiple target points. If the image data to be processed is two-dimensional image data, the target points are pixels; if the image data to be processed is three-dimensional image data, the target points can be three-dimensional points. In some embodiments, step S110 specifically includes: converting the image data to be processed from RGB space to a luminance-chrominance separated color space, which includes YCbCr space, HSV space, or YCgCo space; extracting the luminance channel data of the image data to be processed in the luminance-chrominance separated color space to obtain luminance information.

[0035] Specifically, in the RGB color space, texture information is represented using R, G, and B channel values; YCbCr (brightness Y, blue difference Cb, red difference Cr) is a classic color model that separates brightness and chromaticity information, with brightness information represented by the Y channel data; HSV (hue, saturation, brightness value) is a color model that conforms to human visual perception, with brightness information represented by the V channel (Value channel data); YCgCo (brightness Y, green difference Cg, orange difference Co) is a computationally efficient and numerically stable brightness-chromaticity separation color model, with brightness information represented by the Y channel data.

[0036] This embodiment converts the image data to be processed from the RGB space to a YCbCr, HSV, or YCgCo type luminance-chrominance separation color space and extracts the luminance channel data to obtain luminance information. This achieves complete decoupling of luminance information and chrominance information, making the extraction of luminance information more direct, accurate, and unaffected by chrominance information, thus ensuring the accuracy of subsequent mask weight determination.

[0037] Taking the YCbCr color space as an example, this embodiment extracts luminance information based on the following formula: ycbcr = rgb2ycbcr(img); Y = ycbcr(:,:,1); The formula ycbcr = rgb2ycbcr(img) is used to convert image data in RGB space to an image in YCbCr color space. img is the image data to be processed (containing three channels: R, G, and B, with brightness and color coupled together). rgb2ycbcr() is a standard color space conversion function used to linearly transform the RGB three-channel values ​​to the YCbCr three-channel values. ycbcr is the output YCbCr format image data, containing three independent channels: Y, Cb, and Cr.

[0038] The formula Y = ycbcr(:,:,1) is used to extract the brightness information from the converted YCbCr image data to obtain the pure brightness matrix Y (which contains the brightness information of each target point).

[0039] S120. Determine the mask weights corresponding to each target point based on the brightness information.

[0040] In this embodiment, the mask weight is used to control the fusion ratio of bright area processing data and dark area processing data for each target point, avoiding visual discontinuities caused by hard segmentation, achieving adaptive partitioning and smooth transition based on brightness information, eliminating artificial traces at the boundaries between bright and dark areas, and ensuring that the image data enhancement effect is natural, continuous, accurate, and reliable. In some embodiments, please refer to... Figure 2 Specifically, the mask weights corresponding to each target point are determined through the following steps: S1201. Determine the brightness threshold and transition steepness coefficient corresponding to the image data to be processed based on the brightness information.

[0041] In this embodiment, the luminance median, luminance mean, and luminance variance corresponding to the image data to be processed are determined based on the luminance information; the luminance threshold is determined based on the luminance median and luminance mean; and the transition steepness coefficient is determined based on the luminance variance and a preset base coefficient.

[0042] Specifically, the luminance median, luminance mean, and luminance variance of luminance information of multiple target points in the image data to be processed are calculated. Then, the luminance threshold (threshold) is calculated based on a preset luminance threshold adaptive formula, and the transition steepness coefficient (k) is calculated based on a preset transition steepness coefficient adaptive formula.

[0043] The adaptive brightness threshold formula is: threshold = α × Y med +β×Y mean ; Where Ymed is the median brightness, Ymean is the mean brightness, and α and β can be preset or dynamically obtained weighting coefficients.

[0044] When α and β are adaptively and dynamically obtained weighting coefficients, α and β can be adapted based on the luminance variance and the proportion of dark areas: First, the luminance variance Y... var and the proportion of dark areas P dark Normalized to the [0,1] interval to eliminate the influence of dimensions, subsequent calculations are based on the normalized luminance variance Y. var and the proportion of dark areas P dark Perform the calculations for α and β: First, calculate the basic α(α) base The fundamental α is dominated by variance; the larger the variance, the larger α. The corresponding formula can be set as: α base= 0.5 + 0.4 ×Y var Then, adjust the dark area ratio: the more dark areas there are, the higher α should be. The corresponding formula can be α. correction =0.1×P dark Finally, based on the formula α=max(min((α base +α correction α is calculated from 0.5, 0.9, and 0.5, and the final α is limited to 0.5~0.9 to avoid extreme values.

[0045] When the image data has a large difference in brightness (Y) var =1), α base =0.9 (median weight fully increased); when the image data brightness is uniform (Y var =0), α base =0.5 (median base weight); the higher the proportion of dark areas (e.g., Y), the better. var =1), and α is increased by 0.1 to make the threshold more biased towards the median level of the dark area. Then β is calculated based on the formula β = 1-α.

[0046] The adaptive formula for the transition steepness coefficient is: k = k base / (Y var + eps); Where, k base Y is a preset base coefficient (e.g., set to 0.5). var The value represents the luminance variance, with eps being the minimum value to avoid a denominator of 0.

[0047] The physical meaning of k is that the larger the k value, the narrower the transition region and the steeper the transition between bright and dark areas; the smaller the k value, the wider the transition region and the smoother the blending.

[0048] This embodiment abandons the method of manually setting brightness thresholds and transition steepness coefficients in existing solutions. Instead, it extracts the brightness statistical features (such as mean, median, variance, etc.) and visual features (such as the proportion of bright and dark areas) of image data to establish an adaptive calculation model. This enables the automatic assignment of the two parameters, allowing the algorithm to adapt to image data with different brightness distributions (such as overly dark, overexposed, and uniformly bright image data).

[0049] S1202. Determine the mask weights corresponding to each target point based on brightness information, brightness threshold, and transition steepness coefficient.

[0050] Specifically, based on a preset S-curve function, the mask weights corresponding to each target point are determined according to brightness information, brightness threshold, and transition steepness coefficient. The S-curve function is as follows: mask = 1. / (1+exp(-k×(Y-threshold))); Where mask is the mask weight, k is the transition steepness coefficient, Y is the brightness information, and threshold is the brightness threshold. Specifically, mask, k, and Y in this formula are represented as matrices, and the corresponding matrices contain the mask weight, transition steepness coefficient, and brightness information of all target points, respectively.

[0051] Specifically, when the value of the brightness information is less than the brightness threshold, the mask weight approaches 0, and the corresponding pixels are processed mainly using the dark area processing strategy. When the value of the brightness information is greater than the brightness threshold, the mask weight approaches 1, and the corresponding pixels are processed mainly using the bright area processing strategy.

[0052] Among them, the correspondence between brightness and mask weights is as follows when the brightness threshold (threshold=0.5) is fixed and different k values ​​are different: Figure 3 As shown; with a fixed k value (k=20) and different brightness thresholds, the correspondence between brightness and mask weights is as follows: Figure 4 As shown; in the case of a typical S-curve (k=20, fixed threshold=0.5), the correspondence between brightness and mask weight is as follows. Figure 5 As shown; Figure 6 This is a schematic diagram of the luminance mask when k=30 and the fixed threshold=0.6. The horizontal and vertical positions of the left box in the diagram represent the pixel coordinates of the image data. The color bars on the right range from 0.1 to 0.9, which intuitively show the range of mask weight values. Black indicates that the mask weight is close to 0 (dark area, mainly using dark area to process data), white indicates that the mask weight is close to 1 (bright area, mainly using bright area to process data), and gray gradient indicates that the mask weight is smoothly transitioned between 0 and 1 (blending area).

[0053] In this embodiment, the brightness threshold is used to control the boundary between bright and dark areas, and the transition steepness coefficient is used to control the steepness of the transition area.

[0054] S130. According to the preset dark area processing strategy, the brightness information of each target point is adjusted to obtain the dark area processing data corresponding to each target point. According to the preset bright area processing strategy, the full channel adjustment is performed on each target point to obtain the bright area processing data corresponding to each target point.

[0055] In this embodiment, completely different processing strategies are designed to address the visual characteristics and processing challenges of bright and dark areas in image data. For dark areas, only the brightness information is adjusted according to the dark area processing strategy (e.g., only the Y channel of the image data in the YCbCr space is adjusted) to protect the details in the dark areas from loss. For bright areas, the image data to be processed is processed in full-channel RGB according to the bright area processing strategy. This step adapts to the different visual needs of bright and dark areas and achieves a precise balance between color fidelity, detail protection and brightness enhancement.

[0056] In some embodiments, please refer to Figure 7 Step S130 includes: S1301. Obtain the dark area gamma correction coefficient and bright area gamma correction coefficient corresponding to the image data to be processed.

[0057] In some embodiments, the dark area gamma correction coefficient and the bright area gamma correction coefficient can be obtained through the following steps: determining the median and mean brightness values ​​corresponding to the image data to be processed based on the brightness information; and determining the dark area gamma correction coefficient and the bright area gamma correction coefficient based on the median brightness value, the mean brightness value, a preset dark area gamma reference value, and a preset bright area gamma reference value.

[0058] Specifically, based on the overall brightness characteristics of the image data, the system adapts and combines the median and mean brightness values ​​(reflecting the overall brightness of the image data) to automatically adjust parameter values: If the overall image data is too dark (e.g., the value of the mean brightness divided by the median brightness is less than a preset threshold (e.g., 128)), the system reduces the first preset value based on the dark area gamma reference value to obtain the dark area gamma correction coefficient, and reduces the second preset value based on the bright area gamma reference value to obtain the bright area gamma correction coefficient; if the overall image data is overexposed (e.g., the value of the mean brightness divided by the median brightness is much higher than the preset threshold), the system increases the third preset value based on the dark area gamma reference value to obtain the dark area gamma correction coefficient, and increases the fourth preset value based on the bright area gamma reference value to obtain the bright area gamma correction coefficient; if the image data has uniform brightness, the system maintains both the dark area gamma reference value and the bright area gamma reference value.

[0059] In other embodiments, the dark area gamma correction coefficient and the bright area gamma correction coefficient can also be obtained according to user settings (adjusted as needed) or preset fixed values.

[0060] In this embodiment, the dark area gamma correction coefficient and the bright area gamma correction coefficient are used to control the enhancement intensity of the dark area and the bright area, respectively.

[0061] S1302. In the luminance-chrominance separation color space, adjust the luminance information of each area according to the dark area gamma correction coefficient to obtain dark area processing data.

[0062] The dark area processing strategy provided in this embodiment only adjusts the luminance channel while keeping the chroma channel unchanged, avoiding excessive compression of chroma information. It can improve the brightness and visibility of dark areas while avoiding problems such as color shift, color distortion and noise amplification in dark areas. It preserves the original texture, edge and detail information of the dark areas to the greatest extent, achieving high-quality enhancement of dark areas without loss of detail.

[0063] Taking the YCbCr color space as an example, this embodiment performs brightness adjustment based on the following formula: y dark = Y.^y γ ; % Adjust only the brightness channel ycbcr dark (:,:,1) = y dark ; Wherein, formula y dark = Y.^y γ Used to adjust brightness information, y dark Y represents the adjusted brightness information, and Y represents the brightness information before adjustment. γ The dark area gamma correction coefficient is given by the formula ycbcr. dark (:,:,1) = y dark This is used to replace the luminance channel data in the ycbcr color space with adjusted luminance information while keeping the chrominance information unchanged. In this embodiment, the dark area processing data includes adjusted luminance data and chrominance information. Specifically, ycbcr in the formula... dark Specifically, Y is represented as a matrix, with each matrix containing the adjusted brightness information and brightness information for all target points. This embodiment allows adjustment of only the Y channel, preserving details in dark areas.

[0064] S1303. In RGB space, adjust each target point in full channel according to the gamma correction coefficient of the bright area to obtain the initial brightness processing data corresponding to each target point.

[0065] S1304. Convert the initial brightness processing data from RGB space to a luminance-chrominance separation color space to obtain the brightness area processing data.

[0066] The bright area processing strategy provided in this embodiment adjusts the RGB full channel of the bright area, which can simultaneously optimize the brightness and color performance of the bright area, enhance the transparency and layering of the bright area, and complement the strategy of adjusting the brightness of the dark area only. While ensuring that the dark area is not distorted, the overall image data has natural colors and rich details. The comprehensive optimization of the bright area performance results in a better visual effect.

[0067] Taking the YCbCr color space as an example, this embodiment performs full-channel adjustment processing based on the following formula: rgb bright =img.^rgb γ % Full channel RGB adjustment ycbcr bright =rgb2ycbcr(rgb bright ); Wherein, the formula rgb bright = img.^rgbγ Used for full-channel RGB adjustment of the image data (img) in RGB space. γ For bright areas, gamma correction coefficients, RGB bright The initial data for brightness processing is given by the formula ycbcr. bright =rgb2ycbcr(rgb bright This is used to convert initial luminance processing data in RGB space to bright area processing data in YCbCr space. bright This ensures that the data format for bright area processing and dark area processing is unified for subsequent processing. rgb2ycbcr is a standard color space conversion function used to convert image data from RGB space to YCbCr space.

[0068] S140. Based on the mask weights, dark area processing data, and bright area processing data, determine the fusion data corresponding to each target point.

[0069] This embodiment achieves adaptive weighted fusion of dark area processing data and bright area processing data through mask weights, which allows image data to transition smoothly and continuously between bright and dark areas, achieving seamless transition, eliminating abrupt boundaries (hard boundaries) and artificial traces, while taking into account the fidelity of dark area details and the color optimization of bright area, thus improving the overall enhancement quality and naturalness of image data.

[0070] In some embodiments, please refer to Figure 8 Step S140 includes the following steps: S1401. Determine the mask weight as the bright area weight of the corresponding target point in the bright area processing data, and determine the dark area weight of the corresponding target point in the dark area processing data based on the mask weight.

[0071] S1402. Based on the bright area weight and the dark area weight, perform weighted fusion processing on the dark area processing data and the bright area processing data to obtain fused data.

[0072] Specifically, for each target point, the weight mask obtained in step S120 is used as the bright area weight, and then 1-mask is used as the dark area weight; then, based on the obtained bright area weight and dark area weight, the dark area processing data and the bright area processing data are subjected to weighted fusion processing.

[0073] Taking the YCbCr color space as an example, this embodiment performs weighted fusion processing on the dark area processing data and the bright area processing data based on the following formula: ycbcr out = mask.×ycbcr bright +(1-mask).×ycbcr dark ; Among them, ycbcr out To fuse the data, mask represents the weight of bright areas, 1-mask represents the weight of dark areas, and ycbcr bright Data processing for bright areas, ycbcr dark For processing data in dark areas, specifically, ycbcr in the formula... out , mask, 1-mask, ycbcr bright and ycbcr dark Specifically, this is represented by a matrix, which contains the fused data of all target points, the weights of bright areas, the weights of dark areas, the data processed by bright areas, and the data processed by dark areas.

[0074] The weighted fusion process in this embodiment is performed in a luminance-chrominance separated color space.

[0075] S150. Generate target image data based on fused data.

[0076] Specifically, in a luminance-chrominance separated color space, candidate image data is generated based on the fused data; the candidate image data is then converted from the luminance-chrominance separated color space to the RGB space to obtain the target image data.

[0077] This embodiment generates candidate image data in a luminance-chrominance separation color space, which ensures that the enhancement and fusion process is precise and controllable, and that details and colors are not distorted. Then, by converting to the RGB space, target image data with standard format, natural color, and excellent visual effect can be obtained, which meets the requirements for image data display and output.

[0078] Taking the YCbCr color space as an example, the candidate image data is converted from the YCbCr color space to the RGB space based on the following formula: Output = ycbcr2rgb(ycbcr out ); Where Output is the final output RGB format target image data, and ycbcr2rgb is the standard color space inverse conversion function, which converts the image data from YCbCr space to RGB space. out The candidate image data is generated from the matrix corresponding to the fused data.

[0079] In this embodiment, the fused YCbCr space image data is converted to the RGB color space using the standard inverse conversion formula to obtain RGB format target image data that can be displayed and output normally, thus completing the overall image data enhancement process.

[0080] Furthermore, in some embodiments, the image data to be processed is two-dimensional image data obtained by shooting or scanning. After step S150, the method further includes: generating a three-dimensional model based on the target image data.

[0081] Specifically, the target image data of each frame of two-dimensional image data is obtained by optimizing the multi-frame two-dimensional image data obtained by shooting or scanning, and then a three-dimensional model is generated based on the multi-frame target image data.

[0082] In this embodiment, constructing a three-dimensional model using an optimized two-dimensional image can significantly improve the texture realism of the three-dimensional reconstruction.

[0083] In some embodiments, if the image data to be processed is a three-dimensional point cloud or a mesh model, then by optimizing each three-dimensional point based on this application, three-dimensional point cloud data or three-dimensional models with more realistic textures can also be obtained.

[0084] In some embodiments, the image data to be processed can be a two-dimensional image or three-dimensional data acquired by a device in a bright or dark environment. Based on the image data processing method of this application, a model with more realistic texture and more consistent brightness can be obtained. For example, if the image data to be processed can be model data acquired by an intraoral scanner, the image data processing method of this application can avoid uneven brightness distribution, loss of details in dark areas, overexposure in bright areas, color distortion, loss of texture details in dark areas, and whitening and overexposure in the highlight areas of the tooth surface due to the narrow space inside the oral cavity and complex lighting conditions, and can obtain a three-dimensional oral cavity model with more realistic texture and more consistent brightness.

[0085] In some embodiments, the image data to be processed can be two-dimensional images or three-dimensional data acquired by multiple different devices. Based on the image data processing method of this application, the texture and brightness of the data acquired by multiple devices can be made more consistent, and a three-dimensional model that integrates the data acquired by multiple devices can also be obtained. For example, if the image data to be processed can be model data acquired from a facial scanner, an intraoral scanner, or an extraoral scanner, the image data processing method of this application can avoid the inconsistency in texture between the scanned oral cavity model and facial model caused by differences in scanning devices and imaging methods, as well as different ambient light inside and outside the mouth. A facial model and oral cavity model with globally consistent texture, natural transition, and alignment integration can be obtained.

[0086] In summary, this application embodiment determines the mask weight based on the brightness information of the target point, achieving objective division and continuous transition of bright and dark areas, avoiding color information interference. Moreover, this application embodiment adopts a differentiated processing strategy of adjusting the brightness of dark areas and adjusting the full channel of bright areas, which can improve the performance of bright areas while ensuring the color fidelity of dark areas. In addition, this application embodiment achieves smooth fusion of dark area processing data and bright area processing data through mask weight, eliminating boundary abrupt changes and artificial traces, making the image data enhancement effect natural and continuous, thereby improving the image data processing quality and obtaining more realistic and consistent 3D point cloud data or 3D models.

[0087] Figure 9 This is a schematic block diagram of an image data processing apparatus provided in an embodiment of this application. Figure 9 As shown, corresponding to the above image data processing method, this application also provides an image data processing apparatus 900. This image data processing apparatus 900 includes a unit for performing the above image data processing method, and can be configured in a terminal such as a desktop computer, tablet computer, or laptop computer. Specifically, please refer to... Figure 9 The image data processing apparatus 900 includes a transceiver unit 901 and a processing unit 902, wherein: Transceiver unit 901 is used to acquire image data to be processed; The processing unit 902 is used to acquire the brightness information of each target point in the image data to be processed; determine the mask weight corresponding to each target point according to the brightness information; perform brightness adjustment processing on the brightness information of each target point according to a preset dark area processing strategy to obtain dark area processing data corresponding to each target point; and perform full-channel adjustment processing on each target point according to a preset bright area processing strategy to obtain bright area processing data corresponding to each target point; determine the fusion data corresponding to each target point according to the mask weight, dark area processing data, and bright area processing data; and generate target image data based on the fusion data.

[0088] In some embodiments, when the processing unit 902 performs the step of determining the fused data corresponding to each target point based on the mask weight, dark area processing data, and bright area processing data, it is specifically used for: The mask weights are determined as the bright area weights of the corresponding target points in the bright area processing data, and the dark area weights of the corresponding target points in the dark area processing data are determined based on the mask weights. Based on the weights of bright and dark areas, the data processed in dark areas and the data processed in bright areas are weighted and fused to obtain the fused data.

[0089] In some embodiments, when the processing unit 902 performs the step of acquiring the brightness information of each target point in the image data to be processed, it is specifically used for: The image data to be processed is converted from RGB space to a luminance-chrominance separated color space, which includes YCbCr space, HSV space or YCgCo space; The luminance channel data of the image data to be processed is extracted in the luminance-chrominance separation color space to obtain luminance information.

[0090] In some embodiments, when the processing unit 902 performs the step of determining the mask weights corresponding to each target point based on the brightness information, it is specifically used for: Determine the brightness threshold and transition steepness coefficient corresponding to the image data to be processed based on the brightness information; The mask weights for each target point are determined based on brightness information, brightness threshold, and transition steepness coefficient.

[0091] In some embodiments, when the processing unit 902 performs the step of determining the brightness threshold and transition steepness coefficient corresponding to the image data to be processed based on the brightness information, it is specifically used for: Based on the brightness information, determine the median brightness, mean brightness, and variance of the brightness corresponding to the image data to be processed; The brightness threshold is determined based on the median and mean brightness values. The transition steepness coefficient is determined based on the luminance variance and the preset base coefficient.

[0092] In some embodiments, when the processing unit 902 performs the step of determining the mask weights corresponding to each target point based on brightness information, brightness threshold, and transition steepness coefficient, it is specifically used for: Based on a preset S-curve function, the mask weights corresponding to each target point are determined according to brightness information, brightness threshold, and transition steepness coefficient. The S-curve function is as follows: mask = 1. / (1+exp(-k×(Y-threshold))); Where mask is the mask weight, k is the transition steepness coefficient, Y is the brightness information, and threshold is the brightness threshold.

[0093] In some embodiments, when the processing unit 902 performs the steps of adjusting the brightness information of each target point according to a preset dark area processing strategy to obtain dark area processing data corresponding to each target point, and adjusting the full channel of each target point according to a preset bright area processing strategy to obtain bright area processing data corresponding to each target point, the processing unit 902 is specifically used for: Obtain the dark area gamma correction coefficient and bright area gamma correction coefficient corresponding to the image data to be processed; In a luminance-chrominance separated color space, brightness adjustment processing is performed on each brightness information according to the dark area gamma correction coefficient to obtain dark area processing data; In the RGB space, each target point is adjusted across all channels according to the gamma correction coefficient of the bright area to obtain the initial brightness processing data corresponding to each target point. The initial luminance processing data is converted from RGB space to luminance-chrominance separated color space to obtain luminance processing data.

[0094] In some embodiments, when the processing unit 902 performs the step of acquiring the dark area gamma correction coefficient and the bright area gamma correction coefficient corresponding to the image data to be processed, it is specifically used for: Determine the median and mean brightness values ​​of the image data to be processed based on the brightness information. The dark area gamma correction coefficient and the bright area gamma correction coefficient are determined based on the median brightness, the average brightness, the preset dark area gamma reference value, and the preset bright area gamma reference value.

[0095] In some embodiments, when performing the step of generating target image data based on fused data, the processing unit 902 is specifically used for: In a luminance-chrominance separated color space, candidate image data is generated based on the fused data; The candidate image data is converted from the luminance-chrominance separated color space to the RGB space to obtain the target image data.

[0096] In some embodiments, after performing the steps of processing image data to be processed as two-dimensional image data obtained by shooting or scanning, and generating target image data based on fused data, the processing unit 902 is further configured to: Generate a 3D model based on the target image data.

[0097] In some embodiments, when performing the step of acquiring image data to be processed, the transceiver unit 901 is specifically used for: In oral cavity scanning scenarios, image data to be processed is acquired through scanning; Alternatively, in high dynamic range scenarios, image data to be processed can be acquired through photography.

[0098] In summary, the image data processing apparatus 900 provided in this application determines the mask weight based on the brightness information of the target point, thereby achieving objective division and continuous transition of bright and dark areas and avoiding color information interference. Moreover, this application adopts a differentiated processing strategy of adjusting the brightness of dark areas and adjusting the full channel of bright areas, which can improve the performance of bright areas while ensuring the color fidelity of dark areas. In addition, this application achieves smooth fusion of dark area processing data and bright area processing data through mask weight, eliminating boundary abrupt changes and artificial traces, making the image data enhancement effect natural and continuous, thereby improving the quality of image data processing and obtaining more realistic and consistent three-dimensional point cloud data or three-dimensional models.

[0099] It should be noted that those skilled in the art can clearly understand that the specific implementation process of the above-mentioned image data processing device and each unit can be referred to the corresponding description in the foregoing method embodiments. For the sake of convenience and brevity, it will not be repeated here.

[0100] The aforementioned image data processing device can be implemented as a computer program, which can, for example... Figure 10 It runs on the computer device shown.

[0101] Please see Figure 10 , Figure 10 This is a schematic block diagram of a computer device 1000 provided in an embodiment of this application. The computer device 1000 can be a terminal or a server. The terminal can be an electronic device with communication functions, such as a smartphone, tablet, laptop, desktop computer, personal digital assistant, or wearable device. The server can be a standalone server or a server cluster composed of multiple servers.

[0102] See Figure 10 The computer device 1000 includes a processor 1002, a memory, and a network interface 1005 connected via a system bus 1001. The memory may include a non-volatile storage medium 1003 and internal memory 1004.

[0103] The non-volatile storage medium 1003 may store an operating system 10031 and a computer program 10032. The computer program 10032 includes program instructions that, when executed, cause the processor 1002 to perform an image data processing method.

[0104] The processor 1002 provides computing and control capabilities to support the operation of the entire computer device 1000.

[0105] The internal memory 1004 provides an environment for the execution of the computer program 10032 in the non-volatile storage medium 1003. When the computer program 10032 is executed by the processor 1002, the processor 1002 can execute an image data processing method.

[0106] This network interface 1005 is used for network communication with other devices. Those skilled in the art will understand that... Figure 10 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device 1000 to which the present application is applied. The specific computer device 1000 may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0107] The processor 1002 is used to run the computer program 10032 stored in the memory to acquire the brightness information of each target point in the image data to be processed. Determine the mask weights corresponding to each target point based on the brightness information; The brightness information of each target point is adjusted according to the preset dark area processing strategy to obtain the dark area processing data corresponding to each target point. The full-channel adjustment is performed on each target point according to the preset bright area processing strategy to obtain the bright area processing data corresponding to each target point. Based on the mask weights, dark area processing data, and bright area processing data, determine the fusion data corresponding to each target point; Target image data is generated based on fused data.

[0108] It should be understood that in the embodiments of this application, the processor 1002 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0109] It will be understood by those skilled in the art that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program includes program instructions and can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the process steps of the embodiments of the above methods.

[0110] Therefore, this application also provides a storage medium. This storage medium can be a computer-readable storage medium. The storage medium stores a computer program, wherein the computer program includes program instructions. When executed by a processor, the program instructions cause the processor to perform the following steps: Obtain the brightness information of each target point in the image data to be processed; Determine the mask weights corresponding to each target point based on the brightness information; The brightness information of each target point is adjusted according to the preset dark area processing strategy to obtain the dark area processing data corresponding to each target point. The full-channel adjustment is performed on each target point according to the preset bright area processing strategy to obtain the bright area processing data corresponding to each target point. Based on the mask weights, dark area processing data, and bright area processing data, determine the fusion data corresponding to each target point; Target image data is generated based on fused data.

[0111] The storage medium can be any computer-readable storage medium capable of storing program code, such as a USB flash drive, portable hard drive, read-only memory (ROM), magnetic disk, or optical disk.

[0112] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

[0113] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of each unit is merely a logical functional division, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.

[0114] The steps in the methods of this application embodiment can be adjusted, merged, or deleted according to actual needs. The units in the apparatus of this application embodiment can be merged, divided, or deleted according to actual needs. Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0115] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a terminal, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application.

[0116] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An image data processing method, characterized in that, include: Obtain the brightness information of each target point in the image data to be processed; The mask weights corresponding to each target point are determined based on the brightness information. According to the preset dark area processing strategy, the brightness information of each target point is adjusted to obtain the dark area processing data corresponding to each target point. According to the preset bright area processing strategy, the full channel adjustment is performed on each target point to obtain the bright area processing data corresponding to each target point. Based on the mask weights, the dark area processing data, and the bright area processing data, determine the fusion data corresponding to each of the target points; Target image data is generated based on the fused data.

2. The method according to claim 1, characterized in that, The step of determining the fused data corresponding to each of the target points based on the mask weights, the dark area processing data, and the bright area processing data includes: The mask weight is determined as the bright area weight of the corresponding target point in the bright area processing data, and the dark area weight of the corresponding target point in the dark area processing data is determined based on the mask weight. Based on the bright area weight and the dark area weight, the dark area processing data and the bright area processing data are weighted and fused to obtain the fused data.

3. The method according to claim 1, characterized in that, The step of obtaining the brightness information of each target point in the image data to be processed includes: The image data to be processed is converted from RGB space to a luminance-chrominance separated color space, which includes YCbCr space, HSV space or YCgCo space; The luminance channel data of the image data to be processed is extracted from the luminance-chrominance separated color space to obtain the luminance information.

4. The method according to claim 1, characterized in that, Determining the mask weights corresponding to each target point based on the brightness information includes: Based on the brightness information, determine the brightness threshold and transition steepness coefficient corresponding to the image data to be processed; The mask weights corresponding to each target point are determined based on the brightness information, the brightness threshold, and the transition steepness coefficient.

5. The method according to claim 4, characterized in that, The step of determining the brightness threshold and transition steepness coefficient corresponding to the image data to be processed based on the brightness information includes: Based on the brightness information, determine the median brightness, mean brightness, and variance of the brightness corresponding to the image data to be processed; The brightness threshold is determined based on the median brightness and the mean brightness. The transition steepness coefficient is determined based on the brightness variance and the preset base coefficient.

6. The method according to claim 4, characterized in that, The step of determining the mask weights corresponding to each of the target points based on the brightness information, the brightness threshold, and the transition steepness coefficient includes: Based on a preset S-curve function, the mask weights corresponding to each target point are determined according to the brightness information, the brightness threshold, and the transition steepness coefficient. The S-curve function is: mask = 1. / (1+exp(-k×(Y-threshold))); Wherein, mask is the mask weight, k is the transition steepness coefficient, Y is the brightness information, and threshold is the brightness threshold.

7. The method according to claim 1, characterized in that, The process of adjusting the brightness information of each target point according to a preset dark area processing strategy to obtain dark area processing data corresponding to each target point, and performing full-channel adjustment processing on each target point according to a preset bright area processing strategy to obtain bright area processing data corresponding to each target point, includes: Obtain the dark area gamma correction coefficient and the bright area gamma correction coefficient corresponding to the image data to be processed; In a luminance-chrominance separated color space, the luminance information is adjusted according to the dark area gamma correction coefficient to obtain the dark area processing data. In the RGB space, each target point is adjusted across all channels according to the gamma correction coefficient of the bright area to obtain the initial brightness processing data corresponding to each target point. The initial brightness processing data is converted from RGB space to a luminance-chrominance separated color space to obtain the brightness area processing data.

8. The method according to claim 7, characterized in that, The step of obtaining the dark area gamma correction coefficient and bright area gamma correction coefficient corresponding to the image data to be processed includes: The median and mean brightness values ​​of the image data to be processed are determined based on the brightness information. The dark area gamma correction coefficient and the bright area gamma correction coefficient are determined based on the median brightness, the average brightness, the preset dark area gamma reference value, and the preset bright area gamma reference value.

9. The method according to claim 1, characterized in that, The generation of target image data based on the fused data includes: In a luminance-chrominance separated color space, candidate image data is generated based on the fused data; The candidate image data is converted from a luminance-chrominance separated color space to an RGB space to obtain the target image data.

10. The method according to claim 1, characterized in that, The image data to be processed is two-dimensional image data obtained by shooting or scanning; after generating target image data based on the fused data, the method further includes: A three-dimensional model is generated based on the target image data.

11. The method according to claim 1, characterized in that, The image data to be processed is two-dimensional image data or three-dimensional image data, and the image data to be processed is acquired by one or more devices. Before acquiring the brightness information of each target point in the image data to be processed, the method further includes: In an oral cavity scanning scenario, the image data to be processed is acquired through scanning and / or 3D reconstruction. Alternatively, in high dynamic range scenarios, the image data to be processed can be acquired by shooting.

12. An image data processing apparatus, characterized in that, include: The transceiver unit is used to acquire image data to be processed; The processing unit is used to acquire the brightness information of each target point in the image data to be processed; The mask weights corresponding to each target point are determined based on the brightness information. Brightness adjustment processing is performed on the brightness information of each target point according to a preset dark area processing strategy to obtain dark area processing data corresponding to each target point. Similarly, full-channel adjustment processing is performed on each target point according to a preset bright area processing strategy to obtain bright area processing data corresponding to each target point. Based on the mask weights, the dark area processing data, and the bright area processing data, fusion data corresponding to each target point is determined. Target image data is generated based on the fusion data.

13. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the image data processing method as described in any one of claims 1-11.

Images