A color matching method, device, electronic device, storage medium and program product

Abstract

Embodiments of the present application disclose a color matching method and device, electronic equipment, a storage medium and a program product. The color matching method comprises: when it is detected that toner of an image forming device cannot present a target color of an image, taking at least one visual characteristic as a numerical constraint condition of an optical color space, generating at least one alternative color of the image, and making the alternative color consistent with the target color in the visual characteristic; and determining a printing color matching of the image based on the alternative color selected by a user. The embodiments of the present application can improve the image printing quality.

Description

Technical Field

[0001] This application relates to the field of image forming technology, and in particular to a color matching method, apparatus, electronic device, storage medium, and program product. Background Technology

[0002] When the remaining amount of toner, ink, or other toner in an image forming apparatus is low, image quality deterioration may occur, such as low concentration and low saturation. This is especially true for color printers, where toners of different colors are usually consumed at different rates. Therefore, when the remaining amount of toner for a certain color is low, the image quality printed by the image forming apparatus will be poor and will be difficult to meet user needs. Summary of the Invention

[0003] This application addresses some of the deficiencies mentioned in the background art by providing a color matching method, apparatus, electronic device, storage medium, and program product.

[0004] In a first aspect, embodiments of this application provide a color matching method, including: When it is detected that the toner of the image forming apparatus cannot reproduce the target color of the image, at least one visual characteristic is used as a numerical constraint condition in the optical color space to generate at least one alternative color of the image, such that the alternative color is consistent with the target color in the visual characteristic. The printing color scheme of the image is determined based on the alternative colors selected by the user.

[0005] In one embodiment of the first aspect, the method further includes: Based on the alternative colors selected by the user, the user's visual preference is determined, which is used to characterize the degree of attention the user pays to the visual characteristics. Based on the visual preference, at least one secondary color of the image is generated, such that the secondary color conforms to the visual preference.

[0006] In one embodiment of the first aspect, the method further includes: Based on the alternative colors selected by the user, the user's visual preference is determined, which is used to characterize the degree of attention the user pays to the visual characteristics. Based on the visual preference, a color characteristic file or color gamut mapping table is constructed, which is used to generate alternative colors that conform to the visual preference.

[0007] In one embodiment of the first aspect, before using at least one visual characteristic as a numerical constraint on the optical color space, the method includes: The at least one visual characteristic is obtained, wherein the at least one visual characteristic includes at least one of color fidelity, light and dark contrast intensity, and color vividness.

[0008] In one embodiment of the first aspect, before the detection that the toner of the image forming apparatus cannot render the target color of the image, the method includes: Obtain the remaining toner level in the image forming apparatus; Based on the remaining amount of toner, determine whether the toner is sufficient to reproduce the target color of the image.

[0009] In one embodiment of the first aspect, generating at least one alternative color for the image by using at least one visual characteristic as a numerical constraint in the optical color space includes: Based on the color gamut features of the image, a first dimension data is generated, which includes data for characterizing color fidelity, contrast intensity, and color vividness. Obtain the first dimension data correction coefficient corresponding to the visual characteristics and toner balance; Based on the first dimension data and the first dimension data correction coefficient, a second dimension data that satisfies the numerical constraints is determined. The second dimension data includes data used to characterize color fidelity, contrast intensity, and color vividness. The candidate colors are generated based on the second dimension data.

[0010] In one embodiment of the first aspect, determining the second dimension data based on the first dimension data and the first dimension data correction coefficient includes: Obtain the second-dimensional data correction coefficient corresponding to the user; The second dimension data is determined based on the first dimension data, the first dimension data correction coefficient, and the second dimension data correction coefficient.

[0011] In one embodiment of the first aspect, obtaining the second-dimensional data correction coefficient corresponding to the user includes: Using a neural network model, the second dimension data correction coefficient is generated based on the user behavior profile tensor. The user behavior profile tensor includes adjustment time, association scheme, adjustment dimension, and adjustment value. The neural network model is trained based on sample data, which includes historical user behavior profile tensors and their dimension data correction coefficient labels.

[0012] In one embodiment of the first aspect, before determining the print color scheme of the image based on the alternative colors selected by the user, the method further includes: At least one of the alternative colors is displayed in the user interface for the user to select; Get the alternative color selected by the user.

[0013] In one embodiment of the first aspect, before determining the print color scheme of the image based on the alternative colors selected by the user, the method further includes: At least one of the alternative colors is displayed in the user interface for the user to adjust; The alternative colors are adjusted according to the user's settings.

[0014] Secondly, embodiments of this application provide a color matching device, including: A generation module is used to generate at least one alternative color of the image when it is detected that the toner of the image forming apparatus cannot reproduce the target color of the image, using at least one visual characteristic as a numerical constraint condition of the optical color space, so that the alternative color is consistent with the target color in the visual characteristic. A determination module is used to determine the print color scheme of the image based on the alternative colors selected by the user. Thirdly, embodiments of this application provide an electronic device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of any of the methods described above. Fourthly, a computer-readable storage medium having a computer program / instructions stored thereon, which, when executed by a processor, implement the steps of any of the methods described above. Fifthly, a computer program product includes a computer program / instructions that, when executed by a processor, implement the steps of any of the methods described above.

[0015] According to an embodiment of this application, a color matching method, apparatus, electronic device, storage medium, and program product generate at least one alternative color for an image by using at least one visual characteristic as a numerical constraint condition in an optical color space when the toner of an image forming apparatus is detected to be unable to reproduce the target color of an image. This alternative color is visually consistent with the target color. Based on the alternative color selected by the user, the printing color scheme of the image is determined, thereby making the printing color scheme of the image visually match the image, improving the image printing quality, and meeting the user's needs. Attached Figure Description

[0016] The above and other objects, features, and advantages of this application will become more apparent from the more detailed description of the embodiments of this application in conjunction with the accompanying drawings. The accompanying drawings are used to provide a further understanding of the embodiments of this application and form part of the specification. They are used together with the embodiments of this application to explain this application and do not constitute a limitation thereof. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0017] Figure 1 This is a schematic diagram of an application scenario provided in an embodiment of this application.

[0018] Figure 2 This is a flowchart of a color matching method provided in an embodiment of this application.

[0019] Figure 3 This is a flowchart of generating a secondary color in a color matching method provided in an embodiment of this application.

[0020] Figure 4 This is a flowchart illustrating the construction of a color characteristic file or color gamut mapping table in a color matching method provided in an embodiment of this application.

[0021] Figure 5 This is a flowchart illustrating the determination of whether a toner can render the target color of an image in a color matching method provided in this application embodiment.

[0022] Figure 6 This is a flowchart illustrating the generation of alternative colors in a color matching method provided in an embodiment of this application.

[0023] Figure 7 This is a flowchart of generating the first dimension data in a color matching method provided in an embodiment of this application.

[0024] Figure 8 This is a flowchart illustrating the determination of second-dimensional data in a color matching method provided in an embodiment of this application.

[0025] Figure 9 This is a flowchart illustrating the generation of a default correction scheme in a color matching method provided in an embodiment of this application.

[0026] Figure 10 This is a flowchart illustrating the generation of alternative correction schemes in a color matching method provided in an embodiment of this application.

[0027] Figure 11 This is a flowchart illustrating the process of obtaining the candidate colors selected by the user in a color matching method provided in an embodiment of this application.

[0028] Figure 12 This is a user interface diagram of a color matching method provided in an embodiment of this application.

[0029] Figure 13 This is a flowchart of adjusting alternative colors in a color matching method provided in an embodiment of this application.

[0030] Figure 14 This is another user interface diagram in a color matching method provided in an embodiment of this application.

[0031] Figure 15 This is another user interface diagram of a color matching method provided in the embodiments of this application.

[0032] Figure 16 This is a user interaction flowchart of a color matching method provided in an embodiment of this application.

[0033] Figure 17 This is a block diagram of a color matching device provided in an embodiment of this application.

[0034] Figure 18 This is a schematic diagram of a computer program product provided in an embodiment of this application.

[0035] Figure 19 This is a hardware block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0036] To make the objectives, technical solutions, and advantages of this application more apparent, exemplary embodiments according to this application will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this application, and not all embodiments of this application. It should be understood that this application is not limited to the exemplary embodiments described herein.

[0037] To facilitate understanding, specific application scenarios will be illustrated below.

[0038] See Figure 1 This is a schematic diagram illustrating an application scenario provided by an embodiment of this application. For example... Figure 1 As shown, this application scenario includes an image forming apparatus 101. It should be noted that the image forming apparatus described herein is merely an exemplary description and should not be construed as limiting the scope of protection of this application. For example, an image forming apparatus includes, but is not limited to, printers, copiers, fax machines, scanners, and multifunction printers that integrate printing, copying, faxing, and scanning functions, whose function is to print images or text on an imaging medium using laser imaging capabilities.

[0039] Example 1: See Figure 2 A color matching method, including: S201, when it is detected that the toner of the image forming apparatus cannot present the target color of the image, at least one visual characteristic is used as a numerical constraint condition of the optical color space to generate at least one alternative color of the image, so that the alternative color is consistent with the target color in terms of visual characteristics.

[0040] In this step, "target color" refers to the color that the image forming apparatus should produce when printing the image. When the toner remaining in the image forming apparatus is low, or when there is no toner remaining for a certain color, image quality deterioration may occur, causing the toner in the image forming apparatus to be unable to reproduce the target color of the image. This application embodiment can employ relevant detection methods to detect whether the toner in the image forming apparatus is unable to reproduce the target color of the image. For example, it can detect the remaining toner in the ink cartridge and determine whether the toner in the image forming apparatus is unable to reproduce the target color of the image based on the remaining amount.

[0041] In this step, "visual characteristics" refers to features of visual perception dimensions such as color fidelity, contrast intensity, and color vividness. "At least one visual characteristic" can be specified by the system or by the user. At least one visual characteristic can be obtained before using it as a numerical constraint in the optical color space; this at least one visual characteristic includes at least one of color fidelity, contrast intensity, and color vividness.

[0042] In this step, "optical color space" refers to a color space constructed based on the principle of optical perception, including the Red-Green-Blue (RGB) color space and the Hue-Saturation-Value (HSV) color space, which is different from the printing color space based on the principle of pigment mixing.

[0043] In this step, visual characteristics serve as numerical constraints in the optical color space. The purpose is to ensure that the candidate color and the target color maintain visual consistency. These visual characteristics, acting as numerical constraints in the optical color space, constrain the relationship between the candidate and target colors in terms of visual characteristics, ensuring their consistency. For example, the ratio of the candidate color to the target color in a corresponding visual characteristic is greater than a preset ratio. This preset ratio can be set according to requirements. For instance, taking a certain visual characteristic as an example, it is set to 0.95 in a medium toner state and 0.7 in a low toner state. It should be understood that states such as medium toner and low toner can be determined using relevant methods. For example, 20%-40% toner remaining is considered medium toner, and 0%-20% toner remaining is considered low toner. The implementation method is not limited. In some cases, the numerical constraints can also constrain the value of the candidate color, for example, constraining the value of the candidate color in a corresponding visual characteristic to be greater than a preset threshold. It should be understood that if a candidate color and a target color are visually identical or deviate from each other within a set range, the candidate color and the target color can be considered to be visually consistent. This set range can be determined according to requirements. For example, when the toner in the image forming apparatus cannot reproduce the target color of the image, visual characteristics can be added to the model used to generate the candidate color as numerical constraints in the optical color space, so that the candidate color generated by the model conforms to the numerical constraints in the optical color space corresponding to the "visual characteristics".

[0044] Taking color fidelity as an example, if a user has a requirement for color fidelity, the color fidelity should not be significantly reduced when generating alternative colors. The color fidelity of the image should be preserved as much as possible, so that the color fidelity of the alternative colors is consistent with that of the target colors. It is permissible to reduce the intensity of brightness contrast and the vividness of colors. Then, "at least one visual characteristic as a numerical constraint condition of optical color space" can include the numerical constraint condition corresponding to the color fidelity of the alternative colors being consistent with that of the target colors. For example, when toner is scarce, the alternative colors are equal to (or greater than) a first preset ratio of color fidelity of the target colors. This first preset ratio can be set to 0.95. It is understandable that when toner is scarce, the numerical constraint condition corresponding to the color fidelity of the alternative colors being consistent with that of the target colors can be reduced, and the alternative colors can be equal to (or greater than) a second preset ratio of color fidelity of the target colors.

[0045] Visual characteristics can be specified by the system or by the user.

[0046] For example, the user specifies at least one visual characteristic. Taking the system specifying color fidelity, contrast intensity, and color vividness as visual characteristics, and using these three factors as numerical constraints in the optical color space, candidate colors for the image are generated. That is, color fidelity is used as the numerical constraint in the optical color space to generate the first candidate color of the image; contrast intensity is used as the numerical constraint in the optical color space to generate the second candidate color; and color vividness is used as the numerical constraint in the optical color space to generate the third candidate color. The first, second, and third candidate colors are all provided as candidate colors for the user to choose from, facilitating the selection of candidate colors under various visual characteristic requirements.

[0047] For example, the user specifies at least one visual characteristic, which serves as a numerical constraint in the optical color space to generate candidate colors for the image. For instance, if the user prioritizes color vibrancy, they specify color vibrancy as a numerical constraint in the optical color space to generate candidate colors for the image. It should be understood that, compared to other methods of generating candidate colors, this application adds at least one visual characteristic as a numerical constraint in the optical color space, ensuring that the generated candidate colors are visually consistent with the target color, thus better meeting user needs. It should also be understood that the generated candidate colors are those that the toner cannot reproduce the target color of the image, thus compensating for the poor print quality caused by the toner's inability to reproduce the target color.

[0048] It should be understood that when generating alternative colors, numerical constraints can be added to the relevant alternative color generation method. Based on these numerical constraints, alternative colors are generated so that the alternative colors and the target colors are visually consistent during the alternative color generation process.

[0049] S202, determine the printing color scheme of the image based on the alternative colors selected by the user.

[0050] The user can select a candidate color from the various candidate colors of the image generated in step S201. The printing color scheme of the image is determined based on the candidate color selected by the user. When a candidate color is determined, a relevant printing color scheme determination method can be used to determine the printing color scheme of the image. The image forming apparatus prints the image according to the determined printing color scheme.

[0051] One color matching method according to an embodiment of this application, when the toner of the image forming apparatus cannot present the target color of the image, uses at least one visual characteristic as a numerical constraint condition of the optical color space to generate at least one alternative color of the image, so that the alternative color is consistent with the target color in terms of visual characteristics, so that when the image forming apparatus prints an image based on the color matching method of this embodiment, the image quality can better meet the user's needs.

[0052] When the toner in an image forming device cannot reproduce the target color of an image, users sometimes focus more on dimensions such as the saturation and contrast of alternative colors. Suppose a user knows that toner for a certain color is insufficient and needs to use an alternative color. Theoretically, to save toner, saturation can be reduced; for colors like pure red and deep blue, reducing saturation means reducing toner consumption for that color. Alternatively, brightness can be increased; increasing brightness means the overall image becomes lighter, reducing the consumption of all colors. If a user wants to print a document containing both an image background and text, and their goal is to read the text clearly, they will tend to reduce saturation rather than increase brightness. Increasing brightness would make the text less legible, but the user is more concerned with the text than the color. For example, in a complex image where the foreground and background are not clearly defined and easily blend together, the user is more concerned with ensuring the output image does not significantly reduce contrast; relatively speaking, the user can tolerate a reduction in saturation.

[0053] On the other hand, users generally lack color knowledge. For example, they might only perceive things like "text is hard to read" or "the foreground and background of an image are blurred," but they don't know how to adjust them. Therefore, users cannot adjust values ​​on the User Interface (UI). Or, even if users have such professional knowledge, they might prefer a more effortless method.

[0054] Therefore, in the embodiments of this application, when generating alternative colors, alternative images can be generated that emphasize different visual characteristic dimensions. Emphasizing different dimensions means ensuring that this dimension does not deteriorate too much, but tolerating the deterioration of other dimensions. For example, contrast represents the pixel difference between the brightest and darkest areas. If this dimension is emphasized, it is necessary to ensure that the difference between the bright and dark areas of the generated image is not reduced too much compared to the original image.

[0055] In one embodiment, the multiple alternative colors displayed on the user interface imply different user focus dimensions, which can represent: alternative colors that maintain contrast as much as possible, alternative colors that maintain color fidelity as much as possible, alternative colors that maintain saturation as much as possible, etc. Users can choose the one they find acceptable.

[0056] In one implementation, see Figure 3 Color matching methods also include: S301, based on the alternative colors selected by the user, determine the user's visual preference, which is used to characterize the degree of attention the user pays to visual characteristics.

[0057] Based on the candidate colors selected by the user, the visual characteristics of those colors can be determined. Based on these visual characteristics, the user's visual preferences can be determined. For example, if the selected color is a satisfactory option for the user, the focus on the visual characteristics corresponding to that color is increased, building upon the user's existing visual preferences. Conversely, if the selected color is an unsatisfactory option for the user, the focus on the visual characteristics corresponding to that color is decreased, building upon the user's existing visual preferences.

[0058] S302, based on visual preference, generate at least one secondary color for the image, such that the secondary color conforms to the visual preference.

[0059] Based on the determined visual preferences, a secondary color can be regenerated to better match those preferences.

[0060] The "secondary color" in this step is provided for user selection and is an alternative color to the candidate color generated in step S201. At least one secondary color for the image can be generated by using visual characteristics corresponding to visual preferences as numerical constraints in the optical color space. For example, if a user selects a candidate color with high color fidelity from multiple candidate colors as their preferred option, this indicates a high level of user focus on color fidelity; visual preference reflects this focus. Based on this visual preference, at least one secondary color for the image can be generated again using color fidelity as a numerical constraint in the optical color space, thus making the generated secondary color more likely to meet the user's needs.

[0061] In this step, the numerical constraints of the visual characteristics corresponding to visual preferences can be adjusted, and a secondary color can be generated based on the adjusted numerical constraints. The generation process of the secondary color can refer to the generation process of the alternative colors. Taking the alternative color selected by the user as a satisfactory alternative solution as an example, the user prefers the visual characteristics corresponding to the selected alternative color, indicating that their attention to this visual characteristic is relatively high. Assuming that the visual characteristic corresponding to the alternative color is color fidelity, and the initial setting is a first preset ratio of the color fidelity of the alternative color to the target color, when the user's visual preference indicates a high level of attention to color fidelity, this first preset ratio can be increased by a set value or by a set ratio. The image color is regenerated based on the increased first preset ratio as the secondary color. This secondary color can be offered as another alternative color for the user to choose from, further increasing the probability that the secondary color better meets the user's needs.

[0062] In one implementation, see Figure 4 The methods also include: S401, based on the alternative colors selected by the user, determine the user's visual preference, which is used to characterize the degree of attention the user pays to visual characteristics.

[0063] S402, Based on visual preferences, construct a color profile file or color gamut mapping table. The color profile file or color gamut mapping table is used to generate alternative colors that conform to visual preferences.

[0064] Based on visual preferences, a color characteristic file or color gamut mapping table is constructed so that when used as a candidate color, the candidate color better matches the user's preferences. In this step, visual preferences are used to characterize the user's level of attention to visual characteristics. When constructing the color characteristic file or color gamut mapping table based on visual preferences, constraints corresponding to the visual characteristics that the user focuses on are determined based on visual preferences. The color characteristic file or color gamut mapping table is then constructed based on these constraints, ensuring that the interpolation and expansion of the color characteristic file or color gamut mapping table conform to the constraints. In one embodiment, see [link to implementation details]. Figure 5 Before detecting that the toner of the image forming apparatus cannot reproduce the target color of the image, the method includes: S501, Obtain the remaining amount of toner in the image forming apparatus.

[0065] S502, based on the remaining amount of toner, determines whether the toner can reproduce the target color of the image.

[0066] In this embodiment, the ability of the toner to render the target color of the image is determined based on the remaining amount of toner. Specifically, a threshold for the remaining toner amount can be set. When the remaining amount of toner is lower than this threshold, it is determined that the toner cannot render the target color of the image, achieving a fast and accurate determination.

[0067] The remaining toner level can be detected by the toner level acquisition module. Specifically, the remaining toner level can be obtained through the toner level acquisition interface provided by the printer.

[0068] In one implementation, see Figure 6 Based on numerical constraints of at least one visual characteristic in the optical color space, at least one alternative color for an image is generated, including: S601, based on the color gamut features of the image, generates first-dimensional data, which includes data used to characterize color fidelity, contrast intensity, and color vividness.

[0069] In this step, image processing identifies the image input by the user and generates the first dimension data based on the color gamut features of the image.

[0070] The first dimension data belongs to dimensional data. Dimensional data is a quantitative description of the color gamut feature HSV value of an image, which is used by users to measure the feature intensity of an image in three directions: color, contrast, and saturation. Assuming the original HSV values ​​are hue (H), saturation (S), and lightness (V) (with values ​​ranging from H∈[0, 360°], S∈[0, 100%], V∈[0, 100%]), the transformed dimensional data includes color fidelity (Kcolor), contrast intensity (Kcon), and vividness (Ksat) (all ranging from [0, 1]). Color fidelity (Kcolor) is the user's measure of the feature intensity of the image in the color direction, contrast intensity (Kcon) is the user's measure of the feature intensity of the image in the contrast direction, and vividness (Ksat) is the user's measure of the feature intensity of the image in the saturation direction.

[0071] This step generates the first dimension data based on the color gamut features of the image, that is, converting the color gamut features of the image into dimensional data.

[0072] For example, see Figure 7 First-dimensional data can be generated using a convolutional neural network (CNN), which includes: S701, Image Preprocessing.

[0073] The user-input image is preprocessed, which may include resizing and color format conversion. For example, resizing may involve adding borders to convert the pixel ratio of the original image to 244×244 pixels; color format conversion may involve converting the image's color format to RGB.

[0074] S702, extract color gamut features.

[0075] CNNs are used to extract color gamut features. Specifically, CNNs can be used to identify image types and then extract HSV values ​​as color gamut features based on those image types. Image types can be portrait, landscape, or text. CNNs for image type identification can be trained using samples, which include images, image types, and other relevant data.

[0076] The following are examples of color gamut features for different types of images: Portrait: Statistical analysis of the mean HSV values ​​of skin-colored regions (e.g., H=20°~30°, S=15~25%, V=70~90%). landscape: Statistics on sky (H=200°~240°, S=50~70%), vegetation (H=80°~140°, S=40~60%), and buildings (H= HSV distribution (0°~30°, S=10-30%); Word: The HSV distribution of the text region (H=0°~10°, S=0~10%, V=80~100%) was statistically analyzed.

[0077] S703 converts color gamut features into dimensional data.

[0078] The color gamut features of an image are converted into dimensional data. After the conversion, the first dimension data can be obtained, including Kcolor conversion, Kcon conversion and Ksat conversion.

[0079] Kcolor conversion: The closer H is to the target hue (skin tone in a portrait, H = 20~30°), the larger Kcolor is; The conversion formula is: Kcolor=1- ; H represents the theoretical hue. Most natural skin tones have an H value between 20° and 30°; for ease of calculation, a value of 25° can be used.

[0080] H tolerance is the maximum allowable deviation of H for a given image type. An H deviation > 10° will result in a noticeable color cast, so a value of 10° is acceptable. When the deviation exceeds the tolerance, the color is completely distorted (Kcolor = 0).

[0081] Kcon conversion: Kcon is determined by the dynamic range of saturation (S) and lightness (V). The greater the variation in S and V, the stronger the contrast, and the higher the Kcon.

[0082] The conversion formula is: ); Smax is the maximum value of S in the image; Smin is the minimum value of S in the image; for example, sky S=80%, shadow S=20%, Smax Smin=60%; Vmax is the maximum value of V in the image; Vmin is the minimum value of V in the image; for example, highlights V=90%, shadows V=30%, and Vmax... Vmin=60%); Ksat conversion: Ksat is determined by the absolute value of the saturation S. The higher S is, the higher Ksat is.

[0083] Transformation model: ; Taking portrait scenes as an example: Assuming the user selects an image, the extracted HSV color gamut features are as follows: H=30° (Target H=25°, tolerance ±10°); S=25% (Face S=95%, Background S=15%→Smax=95%, Smin=15%) V=85% (Face V=85%, Shadow V=25%→Vmax=85%, Vmin=25%).

[0084] The calculation process is as follows: ; ; .

[0085] S602, obtain the first dimension data correction coefficient corresponding to the visual characteristics and toner balance.

[0086] In this step, a relationship table can be constructed between visual characteristics, toner balance, and the first-dimensional data correction coefficient. Based on the visual characteristics and toner balance, the first-dimensional data correction coefficient is determined from the relationship table. The setting of the first-dimensional data correction coefficient in the relationship table can be based on numerical constraints. For example, when the visual characteristic is brightness contrast intensity, the value of brightness contrast intensity in the first-dimensional data correction coefficient is set higher, making it easier for the candidate color and the target color to be consistent in visual characteristics.

[0087] S603, based on the first dimension data and the first dimension data correction coefficient, determine the second dimension data, which includes data used to characterize color fidelity, contrast intensity, and color vividness.

[0088] This step involves multiplying the first-dimensional data K1x and the first-dimensional data correction coefficient Fx, and using the result as the second-dimensional data K2x. The color corresponding to the second-dimensional data is then used as the candidate color.

[0089] Alternatively, this step can involve multiplying the first-dimensional data K1x and the first-dimensional data correction coefficient Fx, and then performing other processing to obtain the second-dimensional data K2x. The color corresponding to the second-dimensional data can then be used as a candidate color.

[0090] K2x=K1x Fx; x represents color / con / sat.

[0091] In one implementation, when generating the second-dimensional data, a correction factor for the second-dimensional data corresponding to the user is considered. The correction factor for the second-dimensional data is determined based on the user's behavioral data and can also be called the user behavior correction factor.

[0092] For example, see Figure 8 Based on the first-dimensional data and its correction coefficients, the second-dimensional data is determined, including: S801, obtain the correction coefficient for the second dimension data corresponding to the user.

[0093] S802, determine the second dimension data based on the first dimension data, the first dimension data correction coefficient, and the second dimension data correction coefficient.

[0094] Based on the first-dimensional data K1x, the first-dimensional data correction coefficient Fx, and the second-dimensional data correction coefficient Wx, the second-dimensional data is determined as follows: K2x=K1x x Wx; x=color / con / sat.

[0095] S604 generates alternative colors based on the second-dimensional data.

[0096] When a certain visual characteristic is used as a numerical constraint in the optical color space, and at least one alternative color is generated for the image, the correction scheme is selected. For example, the correction scheme may include a default correction scheme, a color fidelity priority scheme, a brightness contrast intensity priority scheme, and a color vividness priority scheme.

[0097] The method in this embodiment ensures that the candidate color and the target color have consistent visual characteristics, thereby improving the image quality generated based on the candidate color.

[0098] The following examples illustrate the default correction scheme, the color fidelity priority scheme, the brightness contrast intensity priority scheme, and the color vividness priority scheme: Default correction: Reduce the color vibrancy (Fsat) of high-toner-consuming dimensions, retain the key color fidelity (Fcolor), and slightly increase the contrast intensity (Fcon) to compensate for color loss.

[0099] Sufficient toner: Supports high-fidelity printing, with corrections focused on minor optimizations to avoid excessive toner consumption.

[0100] Fcolor=1.05 (Slightly improves color accuracy to compensate for device errors); Fcon=1.0 (Maintain the contrast between light and dark areas, avoid over-enhancing); Fsat=0.95 (slightly reduces color vibrancy and toner consumption); Medium toner: Prioritize color reproduction, reduce color vibrancy to save toner, and maintain or slightly enhance contrast.

[0101] Fcolor=0.9 (Slightly reduce the priority of color fidelity); Fcon=1.1 (Increases the contrast between light and dark areas to compensate for color loss); Fsat=0.7 (significantly reduces color vibrancy and toner consumption); Toner shortage: Only color reproduction is preserved, while the intensity of contrast and the vibrancy of colors are greatly reduced; Fcolor=0.7 (reduces the priority of color fidelity to preserve key color areas); Fcon=0.8 (reduces the intensity of light and dark contrast to avoid areas with high toner consumption); Fsat=0.3 (only retain the vibrancy of key colors, gray out other areas); Example explanation: Assuming the original first-dimensional data is [0.8, 0.7, 0.6] and the toner balance is moderate, the corrected data is shown in the table below:

[0102] Color fidelity priority scheme: Prioritizes preserving the color fidelity of the image, allowing for a moderate reduction in contrast and saturation; Correction logic: When toner is plentiful: keep Kcolor close to 1.0, slightly reduce Ksat, and keep Kcon natural; When toner is insufficient: prioritize ensuring Kcolor is not lower than 0.6, significantly reduce Ksat, and slightly reduce Kcon; The specific parameters are shown in the table below:

[0103] Prioritize contrast intensity: Enhance the sense of depth and visual impact of the image, while allowing for a moderate reduction in color fidelity and saturation.

[0104] Correction logic: When there is enough toner: increase Kcon to 1.1 to enhance the sense of layering, slightly reduce Ksat, and keep Kcolor natural; When toner is insufficient: prioritize ensuring Kcon is not lower than 0.8, significantly reduce Ksat, and slightly reduce Kcolor to avoid color distortion.

[0105] The specific parameters are shown in the table below:

[0106] Color Vividness Priority Option: Enhances the vibrancy of colors in the image, allowing for a moderate reduction in color and contrast to conserve toner; Correction logic: When there is sufficient toner: increase Ksat to 1.1 to enhance vibrancy, slightly decrease Kcon (to avoid overexposure), and keep Kcolor natural; When toner is insufficient: prioritize ensuring Ksat is not lower than 0.5, significantly reduce Kcon, and slightly reduce Kcolor to avoid color distortion; The specific parameters are shown in the table below:

[0107] In one embodiment, see Figure 9 The steps to generate the default fix include: S901, obtain the remaining toner.

[0108] S902, obtain the toner balance correction mapping table.

[0109] The toner balance correction mapping table includes the correction coefficient corresponding to the toner balance, and the toner balance correction mapping table used by the default correction scheme under no additional requirements.

[0110] S903, obtain the correction factor.

[0111] S904 generates a color scheme.

[0112] In one embodiment, see Figure 10 The alternative schemes include a color fidelity priority scheme, a brightness contrast intensity priority scheme, and a color vibrancy priority scheme. The color fidelity priority scheme, brightness contrast intensity priority scheme, and color vibrancy priority scheme are based on the color scheme generated by the default correction scheme, and respectively, they enhance color (strengthen Kcolor), enhance contrast (strengthen Kcon), and enhance saturation (i.e., strengthen Ksat). Therefore, S1001, adding Fcolor; S1002, adding Fcon; and S1003, adding Fsat can be executed respectively to generate alternative schemes by adding Fcolor, adding Fcon, and adding Fsat to the color scheme generated by the default correction scheme.

[0113] In one implementation, obtaining the second-dimensional data correction coefficient corresponding to the user includes: Using a neural network model, second-dimensional data correction coefficients are generated based on the user behavior profile tensor. The user behavior profile tensor includes adjustment time, association scheme, adjustment dimension, and adjustment value. The neural network model is trained based on sample data, which includes historical user behavior profile tensors and their dimensional data correction coefficient labels.

[0114] Adjustment time: The timestamp of each adjustment, used to analyze the time distribution of user usage habits.

[0115] Related scheme: The type of scheme selected by the user when making adjustments, such as when the user adjusts Ksat under the color reproduction priority scheme; Adjustment Dimension: Is the user adjusting Kcolor, Kcon, or Ksat? Adjustment value: The specific value after adjustment, such as when the user adjusts Kcolor from 0.8 to 0.9; Record user adjustment behavior and extract user behavior data, which includes information such as adjustment time, associated scheme, adjustment dimension and adjustment value. Record this user behavior data and use a neural network model to analyze the long-term preferences of the user behavior profile tensor corresponding to the user behavior data, so as to generate the second dimension data correction coefficient, that is, the user correction coefficient.

[0116] Neural network models can employ artificial intelligence (AI) models. Specifically, they can use the Long Short-Term Memory (LSTM) model, which excels at processing time-series data and capturing users' long-term and short-term preferences. The model learns users' preference patterns by analyzing the time-behavior-scenario correlations in historical data and outputs a user-specific second-dimensional data correction coefficient Wx[0, 1.0].

[0117] Wx indicates the user's preference for adjusting this dimension: Wx>1.0: The user wants to increase this dimension parameter (e.g., Wcolor=1.1 means the user wants more accurate color reproduction). Wx=1.0: No adjustment needed; Wx < 1.0: The user wants to reduce this dimension parameter (e.g., Wast = 0.9, which means the user wants the color to be softer). The specific processing steps are: model language conversion, model data input, and result output.

[0118] 1. Model language conversion 1.1. Temporal characteristics: Time difference: Calculate the minute difference between the adjustment time and the current time (e.g., mark the difference as 5 for the last 5 minutes); 1.2 Dimensions and Scheme Characteristics: Adjustable dimensions: The user adjusts dimensions by encoding them, for example, the color dimension corresponds to [1, 0, 0]; Association scheme: Represent the user's intent to adjust the scene through embedding encoding; 1.3. Characteristics of the adjustment value: The adjustment value is normalized to the range of [0, 1] to reflect the user's adjustment intensity for this dimension.

[0119] 2. Model data input A user behavior profile tensor is constructed, and the processed features are combined into a 3D tensor as model input. Each element of the tensor represents a "time-behavior" sample, containing the following features:

[0120] 3. Model Output By inputting data, the model can infer information such as attention weights and context vectors. Through multi-branch fusion technology, the second-dimensional data correction coefficient Wx(color / con / sat) can be calculated.

[0121] In one implementation, see Figure 11 Before determining the print color scheme of the image based on the alternative colors selected by the user, the method also includes: S1101, Display at least one alternative color in the user interface for the user to select; S1102, retrieve the alternative colors selected by the user.

[0122] Users can select the desired alternative colors in the user interface. The system can determine the printing color scheme of the image based on the alternative colors selected by the user and perform printing using the printing color scheme. One printing color scheme is one color scheme.

[0123] See Figure 12 The printer driver or accompanying software displays the generated alternative colors in an intuitive way. Users can preview the printing effect under different schemes through Figure 1201 and choose the scheme that best meets their expectations. Each label represents a color scheme, allowing users to directly select the desired scheme based on the effect without needing to pay too much attention to color details.

[0124] In one implementation, see Figure 13 Before determining the print color scheme of the image based on the alternative colors selected by the user, the method also includes: S1301, Display at least one alternative color in the user interface for the user to adjust; S1302 adjusts the alternative colors according to the user's adjustment operation.

[0125] See Figure 12 , Figure 14 and Figure 15It provides preview and editing functions. The editing function allows users to fine-tune the recommended color schemes according to their personal preferences. When users are not satisfied with all the recommended schemes, they can select the label corresponding to the closest preview image 1201, click the edit button 1401 to enter the editing page, adjust the parameters of different dimensions by adjusting the coefficients of different dimensions such as color, contrast, and saturation by adjusting the adjustment button 1501, and then click the save button 1502 to confirm the color scheme.

[0126] For example, see Figure 16 The user interaction process includes: S1601, select the image to print in the user interface.

[0127] Selecting a printable image in the user interface triggers the generation of a color scheme.

[0128] S1602, Generate color scheme.

[0129] S1603, the user interface displays a set of color scheme candidates.

[0130] S1604 allows users to select a satisfactory color scheme and fine-tune it.

[0131] S1605, Confirm Printing.

[0132] See Figure 17 This application also provides a color matching device, including: The generation module 1701 is used to generate at least one alternative color of the image when it is detected that the toner of the image forming apparatus cannot present the target color of the image, based on the numerical constraint of at least one visual characteristic in the optical color space, so that the alternative color is consistent with the target color in visual characteristics. The determination module 1702 is used to determine the print color scheme of an image based on the alternative colors selected by the user. In this embodiment, the color matching device can be an image forming apparatus. It can also be a module device within the image forming apparatus or a device connected to the image forming apparatus.

[0133] In one embodiment, the color matching device further includes: The preference determination module determines the user's visual preference based on the alternative colors selected by the user. The visual preference is used to characterize the degree of attention the user pays to visual characteristics. The secondary color generation module is used to generate at least one secondary color for an image based on visual preferences, so that the secondary color conforms to visual preferences.

[0134] In one embodiment, the color matching device further includes: The preference determination module determines the user's visual preference based on the alternative colors selected by the user. The visual preference is used to characterize the degree of attention the user pays to visual characteristics. The building module is used to construct color profile files or color gamut maps based on visual preferences. These files or maps are used to generate alternative colors that match the visual preferences.

[0135] In one embodiment, the color matching device further includes: The feature acquisition module is used to acquire at least one visual feature, which includes at least one of color fidelity, brightness contrast intensity, and color vividness.

[0136] In one embodiment, the color matching device further includes: The toner balance acquisition module acquires the toner balance of the image forming apparatus. Based on the remaining amount of toner, determine whether the toner can reproduce the target color of the image.

[0137] In one implementation, when generating at least one candidate color for an image, using at least one visual characteristic as a numerical constraint in the optical color space, the generation module is specifically used for: Based on the color gamut features of the image, the first dimension data is generated, which includes data used to characterize color fidelity, contrast intensity, and color vividness. Obtain the first-dimensional data correction coefficients corresponding to visual characteristics and toner balance; Based on the first dimension data and the first dimension data correction coefficient, the second dimension data that meets the numerical constraints is determined. The second dimension data includes data used to characterize color fidelity, contrast intensity, and color vividness. Based on the second dimension of data, alternative colors are generated.

[0138] In one implementation, when the generation module determines the second dimension data based on the first dimension data and the first dimension data correction coefficient, it is specifically used for: Obtain the correction coefficient for the second dimension data corresponding to the user; The second dimension data is determined based on the first dimension data, the first dimension data correction coefficient, and the second dimension data correction coefficient.

[0139] In one implementation, when the generation module obtains the second-dimensional data correction coefficient corresponding to the user, it is specifically used for: Using a neural network model, second-dimensional data correction coefficients are generated based on the user behavior profile tensor. The user behavior profile tensor includes adjustment time, association scheme, adjustment dimension, and adjustment value. The neural network model is trained based on sample data, which includes historical user behavior profile tensors and their dimensional data correction coefficient labels.

[0140] In one embodiment, the color matching device further includes: The first display module is used to display at least one alternative color on the user interface for the user to select. The color acquisition module is used to acquire the alternative colors selected by the user.

[0141] In one embodiment, the color matching device further includes: The second display module displays at least one alternative color on the user interface for the user to adjust. The adjustment module is used to adjust the alternative colors according to the user's adjustment operations.

[0142] refer to Figure 18 An exemplary embodiment of this application also provides a computer program product 1800, including a computer program 1801, wherein the computer program, when executed by a computer's processor, is used to cause the computer to perform a method according to an embodiment of this application.

[0143] refer to Figure 19 The present invention describes a structural block diagram of an electronic device 1900 that can serve as a server or client of this application, which is an example of a hardware device that can be applied to various aspects of this application. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the application described and / or claimed herein.

[0144] Electronic device 1900 includes a computing unit 1901, which can perform various appropriate actions and processes according to a computer program stored in read-only memory (ROM) 1902 or a computer program loaded into random access memory (RAM) 1903 from storage unit 1908. The RAM 1903 may also store various programs and data required for device operation. The computing unit 1901, ROM 1902, and RAM 1903 are interconnected via bus 1904. An input / output (I / O) interface 1905 is also connected to bus 1904.

[0145] Multiple components in electronic device 1900 are connected to I / O interface 1905, including: input unit 1906, output unit 1907, storage unit 1908, and communication unit 1909. Input unit 1906 can be any type of device capable of inputting information to electronic device 1900. Input unit 1906 can receive input digital or character information and generate key signal inputs related to user settings and / or function control of electronic device. Output unit 1907 can be any type of device capable of presenting information and may include, but is not limited to, a display, speaker, video / audio output terminal, vibrator, and / or printer. Storage unit 1908 may include, but is not limited to, disk and optical disk. Communication unit 1909 allows electronic device 1900 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers, and / or chipsets, such as Bluetooth™ devices, WiFi devices, WiMax devices, cellular communication devices, and / or the like.

[0146] The computing unit 1901 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1901 performs the various methods and processes described above. For example, in some embodiments, the methods of the embodiments of this application can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as storage unit 1908. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 1900 via ROM 1902 and / or communication unit 1909. In some embodiments, the computing unit 1901 can be configured to perform the methods of the embodiments of this application by any other suitable means (e.g., by means of firmware).

Claims

1. A color matching method, characterized in that, include: When it is detected that the toner of the image forming apparatus cannot reproduce the target color of the image, at least one visual characteristic is used as a numerical constraint condition in the optical color space to generate at least one alternative color of the image, such that the alternative color is consistent with the target color in the visual characteristic. The printing color scheme of the image is determined based on the alternative colors selected by the user. The step of generating at least one candidate color for the image by using at least one visual characteristic as a numerical constraint condition in the optical color space includes: Based on the color gamut features of the image, a first dimension data is generated, which includes data for characterizing color fidelity, contrast intensity, and color vividness. Obtain the first dimension data correction coefficient corresponding to the visual characteristics and toner balance; Obtain the second-dimensional data correction coefficient corresponding to the user; Based on the first dimension data, the first dimension data correction coefficient, and the second dimension data correction coefficient, the second dimension data that satisfies the numerical constraints is determined. The second dimension data includes data used to characterize color fidelity, brightness contrast intensity, and color vividness. The candidate colors are generated based on the second dimension data.

2. The method according to claim 1, characterized in that, The method further includes: Based on the alternative colors selected by the user, the user's visual preference is determined, which is used to characterize the degree of attention the user pays to the visual characteristics. Based on the visual preference, at least one secondary color of the image is generated, such that the secondary color conforms to the visual preference.

3. The method according to claim 1, characterized in that, The method further includes: Based on the alternative colors selected by the user, the user's visual preference is determined, which is used to characterize the degree of attention the user pays to the visual characteristics. Based on the visual preference, a color characteristic file or color gamut mapping table is constructed, which is used to generate alternative colors that conform to the visual preference.

4. The method according to claim 1, characterized in that, Before using at least one visual characteristic as a numerical constraint condition for the optical color space, the method includes: The at least one visual characteristic is obtained, wherein the at least one visual characteristic includes at least one of color fidelity, light and dark contrast intensity, and color vividness.

5. The method according to claim 1, characterized in that, Before the detection that the toner of the image forming apparatus cannot reproduce the target color of the image, the method includes: Obtain the remaining toner level in the image forming apparatus; Based on the remaining amount of toner, determine whether the toner is sufficient to reproduce the target color of the image.

6. The method according to claim 1, characterized in that, The step of obtaining the second-dimensional data correction coefficient corresponding to the user includes: Using a neural network model, the second dimension data correction coefficient is generated based on the user behavior profile tensor. The user behavior profile tensor includes adjustment time, association scheme, adjustment dimension, and adjustment value. The neural network model is trained based on sample data, which includes historical user behavior profile tensors and their dimension data correction coefficient labels.

7. The method according to claim 1, characterized in that, Before determining the print color scheme of the image based on the alternative colors selected by the user, the method further includes: At least one of the alternative colors is displayed in the user interface for the user to select; Get the alternative color selected by the user.

8. The method according to claim 1, characterized in that, Before determining the print color scheme of the image based on the alternative colors selected by the user, the method further includes: At least one of the alternative colors is displayed in the user interface for the user to adjust; The alternative colors are adjusted according to the user's settings.

9. A color matching device, characterized in that, include: A generation module is used to generate at least one alternative color for an image when it is detected that the toner of the image forming apparatus cannot reproduce the target color of the image, using at least one visual characteristic as a numerical constraint condition in the optical color space, so that the alternative color is consistent with the target color in the visual characteristic. A determining module is used to determine the printing color scheme of the image based on the alternative colors selected by the user; The generation module, used to generate at least one alternative color for the image by using at least one visual characteristic as a numerical constraint in the optical color space, specifically includes: Based on the color gamut features of the image, a first dimension data is generated, which includes data for characterizing color fidelity, contrast intensity, and color vividness. Obtain the first dimension data correction coefficient corresponding to the visual characteristics and toner balance; Obtain the second-dimensional data correction coefficient corresponding to the user; Based on the first dimension data, the first dimension data correction coefficient, and the second dimension data correction coefficient, the second dimension data that satisfies the numerical constraints is determined. The second dimension data includes data used to characterize color fidelity, brightness contrast intensity, and color vividness. The candidate colors are generated based on the second dimension data.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 8.

11. A computer-readable storage medium having a computer program / instructions stored thereon, characterized in that, When the computer program / instruction is executed by the processor, it implements the steps of the method according to any one of claims 1 to 8.

12. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instruction is executed by the processor, it implements the steps of the method according to any one of claims 1 to 8.

Images