A method, device, equipment and storage medium for intelligent color mapping based on feature saliency

Abstract

The present application discloses an intelligent color mapping method, apparatus, device, and storage medium based on feature saliency, relating to the field of scientific visualization technology. The method comprises the following steps: clustering pixels of a target style image to obtain a plurality of control points, determining a color order adjustment function for the control points based on perceptual uniform deviation and smoothing error, color mapping each control point using a color mapping table generated by the color order adjustment function to obtain a mapped image, obtaining a feature image for identifying a feature region to be highlighted, processing the mapped image using an MSRMNet network model to obtain a saliency image; processing the mapped image, the feature image, and the saliency image based on a feature saliency term, a color opposition term, and a feature sensitivity term to obtain a loss function; and determining a control point adjustment scheme based on a position adjustment result obtained by adjusting the position of each control point using an annealing algorithm and the loss function. This method can improve the efficiency of adjusting the color mapping control points.

Description

Technical Field

[0001] The present invention relates to the field of scientific visualization technology, and in particular to an intelligent color mapping method, device, equipment and storage medium based on feature significance. Background Art

[0002] Scientific visualization is a discipline and technical field that studies the theories, methods, and techniques for using computer graphics and image processing techniques to convert data generated by scientific computing and scientific measurements into graphics or images for on-screen display and interactive processing. Flow field visualization is a key research area in scientific visualization and an indispensable component of flow field scientific computing, specifically computational fluid dynamics (CFD). Currently, flow field visualization is playing an increasingly important role in analyzing and understanding complex flow mechanisms, gaining insight into flow field physics, and discovering scientific laws governing flow. For over two decades, flow field visualization has been one of the most fruitful areas of scientific visualization research in terms of both technical method research and application software tool development. Color mapping, a core tool in scientific visualization, helps researchers quickly identify and analyze key feature regions in data by mapping data values ​​to a color space. Therefore, the design of color mapping directly impacts data readability and analysis efficiency. However, the complex data types, diverse physical quantities, difficulty in extracting physical features, and high visualization requirements associated with flow field scientific computing have made the expression of feature regions through color mapping a research hotspot and a challenge in flow field visualization, and it continues to face new challenges.

[0003] In a broad sense, "feature regions" refer to areas of a dataset that researchers focus on, which are crucial for revealing key characteristics and patterns in the data. Researchers can identify these regions through feature extraction or interactive methods. In scientific visualization, color mapping typically consists of multiple color control points, each with two attributes: a color value and a position. By adjusting the position and color values ​​of these control points, a data-to-color mapping relationship can be achieved. A well-designed color mapping can highlight characteristic regions in the data, such as eddy currents, boundaries, or outliers.

[0004] However, current data-driven automated design methods have limitations when dealing with complex scientific simulation data: they typically treat all data points equally and apply a unified algorithm for feature representation and definition. However, this approach struggles to adapt to uneven data distribution and high noise levels, resulting in a lack of robustness in practical applications. It also requires extensive adjustments and can even fail when dealing with different data types. Furthermore, existing methods often overlook the need to accommodate the subjective preferences of diverse users and lack flexible customization options.

[0005] Therefore, in order to better observe the feature areas, existing tools construct color mapping relationships in a manual interactive manner, but interaction often means relying on experience and is time-consuming and tedious. In order to reduce interaction time and improve efficiency, many methods for automatically generating or adjusting color mapping tables have been proposed. The most commonly used is the one-dimensional color map. Although 2D (Two-Dimensional) color maps have been proposed for visualizing bivariate or multivariate data, such as ColorMapND (ColorMap n-Dimensional, multidimensional color mapping), they must be used with caution because they may be difficult to interpret, so the focus is on the one-dimensional color mapping table design technology:

[0006] An interpolation method that makes better use of the entire color space by increasing the distinguishing properties between similar values ​​and reducing the differences between different values.

[0007] 2. Based on the Knowledge-Augmented Vision (KAV) paradigm, a Support Vector Machine (SVM) model is trained using preference data collected from online user surveys to automatically predict optimized hue-preserving blending results, aiming to avoid false colors generated when using standard alpha compositing in visualizations.

[0008] 3. Identify prominent values ​​and ranges in the data through random sampling, and then adjust the color using histogram equalization;

[0009] 4. Consider background color and opacity variations of color scale when designing colormaps to match people’s inferred mappings;

[0010] 5. We formulate color mapping as a nonlinear constrained optimization problem and incorporate Kindlmann boundary models (a scientific visualization technique for generating perceptually uniform color maps) to reveal spatial variations. However, this approach works well for cases with distinct boundaries, but struggles to reveal features with subtle variations in data values.

[0011] 6. The perceptual recognizability of the color table is enhanced based on the segmented brightness parameter, and a color map that is adaptive to the data distribution characteristics is finally generated. However, segmented brightness may lead to violation of color consistency, resulting in the same color representing different values ​​and causing confusion.

[0012] As can be seen from the above, how to improve the efficiency of adjusting color mapping control points in the process of intelligent color mapping based on feature saliency is an urgent problem to be solved. Summary of the Invention

[0013] In view of this, the present invention aims to provide a method, apparatus, device, and storage medium for intelligent color mapping based on feature saliency, which can improve the efficiency of generating color mapping control point adjustment schemes during the intelligent color mapping process based on feature saliency, thereby improving the efficiency of adjusting color mapping control points. The specific scheme is as follows:

[0014] In a first aspect, the present application provides an intelligent color mapping method based on feature saliency, comprising:

[0015] Clustering the pixels corresponding to the target style image to obtain a number of control points, and determining a color order adjustment function corresponding to the control points based on the perceptual uniformity deviation and smoothing error, and then generating a color mapping table using the color order adjustment function; the perceptual uniformity deviation is the degree of deviation between the current perceptual distance of each adjacent control point in the perceptually uniform color space and a preset ideal perceptual distance; the smoothing error is the color change smoothness error determined by the angular change of the displacement vector corresponding to each control point;

[0016] Performing color mapping on each of the control points using the color mapping table to obtain a mapping image, obtaining a feature image for identifying a feature area to be highlighted, and processing the mapping image using the MSRMNet network model to obtain a saliency image;

[0017] The mapping image, the feature image, and the saliency image are processed based on a feature saliency term, a color opposition term, and a feature sensitivity term to obtain a loss function; the feature saliency term is the degree of overlap between the saliency image and the feature image; the color opposition term is the difference in average color modulus between a feature region and a non-feature region in the feature image; and the feature sensitivity term is the maximum distance between colors in the feature region in the color space;

[0018] The position of each of the control points is adjusted using an annealing algorithm and the loss function to obtain a position adjustment result, and a control point adjustment scheme corresponding to the target style image is determined based on the position adjustment result.

[0019] Optionally, before determining the color order adjustment function corresponding to the control point based on the perceptual uniformity deviation and the smoothing error and then generating the color mapping table using the color order adjustment function, the method further includes:

[0020] determining a control point pair based on every two of the control points, obtaining a current perceived distance between each of the control point pairs, and then determining a distance average corresponding to each of the current perceived distances;

[0021] determining a distance difference between each of the perceived distances and the corresponding distance average, performing a square operation and summing the distance differences corresponding to each of the control point pairs to obtain a summation result, and then determining a calculation result based on the summation result and the number of all the control point pairs;

[0022] A perceptual uniformity deviation value is determined based on the calculation result and the distance average value; a numerical value of the perceptual uniformity deviation value is negatively correlated with a perceptual uniformity value corresponding to the control point.

[0023] Optionally, before determining the color order adjustment function corresponding to the control point based on the perceptual uniformity deviation and the smoothing error and then generating the color mapping table using the color order adjustment function, the method further includes:

[0024] Determine a first displacement vector between each of the control points and a previous control point and a second displacement vector between each of the control points and a subsequent control point;

[0025] performing normalization processing on the first displacement vector and the second displacement vector respectively to obtain corresponding first normalization results and second normalization results;

[0026] Determine a dot product result of a displacement vector corresponding to the first normalized result and the second normalized result, and determine a curvature metric corresponding to the control point based on the dot product result of the displacement vector;

[0027] Based on the curvature metrics of the control points, a corresponding curvature metric average is determined to obtain a smoothing error value; the numerical value of the smoothing error value is negatively correlated with the color change smoothness of the target style image.

[0028] Optionally, before the processing of the mapping image, the feature image, and the saliency image based on the feature saliency item, the color opposition item, and the feature sensitivity item to obtain the loss function, the method further includes:

[0029] Performing pixel-level alignment on the saliency image and the feature image to obtain an alignment result, and then multiplying pixel values ​​in the saliency image with corresponding pixel values ​​in the feature image to obtain a multiplication result;

[0030] The number of pixels marked as feature areas in the feature image is counted, and a coincidence index is determined based on the multiplication result of each pixel value and the number of pixels, and a feature saliency item is determined based on the coincidence index; the numerical value corresponding to the feature saliency item is negatively correlated with the presentation effect of the feature area in the saliency image.

[0031] Optionally, before the processing of the mapping image, the feature image, and the saliency image based on the feature saliency item, the color opposition item, and the feature sensitivity item to obtain the loss function, the method further includes:

[0032] extracting a first color value corresponding to a pixel point in each of the feature areas from the mapped image, and determining a corresponding first modulus average value based on each of the first color values;

[0033] Extracting a second color value corresponding to each pixel point in each non-feature area from the mapped image, and determining a corresponding second modulus average value based on each second color value;

[0034] An absolute difference result is determined based on the first modulus average value and the second modulus average value, and a color opposition term is determined based on the absolute difference result; the numerical value of the color opposition term is negatively correlated with the numerical value of the color distinction between the feature area and the non-feature area.

[0035] Optionally, before the processing of the mapping image, the feature image, and the saliency image based on the feature saliency item, the color opposition item, and the feature sensitivity item to obtain the loss function, the method further includes:

[0036] extracting each third color value in the feature area from the mapped image, and determining a perceptual distance between every two third color values ​​in the color space;

[0037] The perceptual distance with the largest value among the perceptual distances is set as the perceptual distance to be processed, and a feature sensitivity item is determined based on the perceptual distance to be processed; the numerical value of the feature sensitivity item is negatively correlated with the numerical value of the color change span corresponding to the feature area.

[0038] Optionally, the adjusting the position of each control point using an annealing algorithm and the loss function to obtain a position adjustment result, and determining a control point adjustment scheme corresponding to the target style image based on the position adjustment result includes:

[0039] Determine the initial temperature parameter and the cooling rate parameter, and then adjust the initial position direction of the control point using a preset position adjustment direction control rule at the current temperature to obtain a position direction to be processed;

[0040] Determining a function value change corresponding to a loss function value based on the initial position direction and the position direction to be processed using the loss function, and determining whether the function value change is greater than zero; if the function value change is not greater than zero, setting the position direction to be processed as a position adjustment result;

[0041] determining whether the current temperature is less than a preset temperature threshold; if the current temperature is less than the preset temperature threshold, determining whether the loss function value satisfies a preset stability condition; and if the loss function value satisfies the preset stability condition, determining a control point adjustment scheme corresponding to the target style image based on the corresponding position adjustment result;

[0042] If the function value change is greater than zero, the new current temperature is determined based on the initial temperature parameter and the cooling rate parameter, and the step of adjusting the initial position direction of the control point using the preset position adjustment direction control rule at the current temperature is triggered.

[0043] In a second aspect, the present application provides an intelligent color mapping device based on feature saliency, comprising:

[0044] A color mapping table determination module is configured to cluster the pixels corresponding to the target style image to obtain a plurality of control points, determine a color order adjustment function corresponding to the control points based on a perceptual uniformity deviation and a smoothing error, and then generate a color mapping table using the color order adjustment function; the perceptual uniformity deviation is the degree of deviation between the current perceptual distance of adjacent control points in a perceptually uniform color space and a preset ideal perceptual distance; and the smoothing error is a color change smoothness error determined by using an angular change in a displacement vector corresponding to each control point;

[0045] a mapping image acquisition module, configured to perform color mapping on each of the control points using the color mapping table to obtain a mapping image, obtain a feature image for identifying a feature area to be highlighted, and process the mapping image using the MSRMNet network model to obtain a saliency image;

[0046] a loss function determination module, configured to process the mapping image, the feature image, and the saliency image based on a feature saliency term, a color opposition term, and a feature sensitivity term to obtain a loss function; the feature saliency term being the degree of overlap between the saliency image and the feature image; the color opposition term being the difference in average color modulus between a feature region and a non-feature region in the feature image; and the feature sensitivity term being the maximum distance between colors in the feature region in the color space;

[0047] A control point adjustment scheme determination module is used to adjust the position of each of the control points using an annealing algorithm and the loss function to obtain a position adjustment result, and determine a control point adjustment scheme corresponding to the target style image based on the position adjustment result.

[0048] In a third aspect, the present application provides an electronic device, comprising:

[0049] Memory, used to store computer programs;

[0050] A processor is used to execute the computer program to implement the aforementioned intelligent color mapping method based on feature significance.

[0051] In a fourth aspect, the present application provides a computer-readable storage medium for storing a computer program, wherein the computer program, when executed by a processor, implements the aforementioned intelligent color mapping method based on feature significance.

[0052] As can be seen from the above, before performing intelligent color mapping based on feature saliency, the present application needs to cluster the pixel points corresponding to the target style image to obtain several control points, and determine the color order adjustment function corresponding to the control points based on the perceived uniformity deviation and smoothing error, and then use the color order adjustment function to generate a color mapping table; the perceived uniformity deviation is the degree of deviation between the perceived distance of each adjacent control point and the ideal uniform state; the smoothing error is the color change smoothness determined by the angular change of the displacement vector corresponding to each control point; the color mapping table is used to perform color mapping on each control point to obtain a mapping image, and a feature image for identifying the feature area to be highlighted is obtained. The mapping image is processed using the MSRMNet network model to obtain a saliency image; based on the feature saliency term, color opposition term and feature sensitivity term, the mapping image, feature image and saliency image are processed to obtain a loss function; the feature saliency term is the degree of overlap between the saliency image and the feature image; the color opposition term is the difference in the average color modulus between the feature area and the non-feature area in the feature image; the feature sensitivity term is the maximum distance between the colors in the feature area in the color space; the position of each control point is adjusted using the annealing algorithm and the loss function to obtain a position adjustment result, and based on the position adjustment result, a control point adjustment scheme corresponding to the target style image is determined.

[0053] As can be seen from this, the present application first needs to cluster the pixel points corresponding to the target style image to obtain a number of control points, and determine the color order adjustment function corresponding to the control points based on the perceptual uniform deviation and smoothing error, and then use the color order adjustment function to generate a color mapping table; then, use the color mapping table to perform color mapping on each control point to obtain a mapping image, and obtain a feature image for identifying the feature area to be highlighted, and use the MSRMNet network model to process the mapping image to obtain a saliency image; then, based on the feature saliency term, color opposition term, and feature sensitivity term, the mapping image, feature image, and saliency image are processed to obtain a loss function; finally, the position of each control point is adjusted using the annealing algorithm and the loss function to obtain a position adjustment result, and based on the position adjustment result, a control point adjustment scheme corresponding to the target style image is determined. In this way, the efficiency of generating the color mapping control point adjustment scheme is improved in the process of intelligent color mapping based on feature saliency, thereby improving the efficiency of adjusting the color mapping control points. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0055] Figure 1 This is a flow chart of an intelligent color mapping method based on feature significance disclosed in this application;

[0056] Figure 2 This is a flow chart of a specific intelligent color mapping method based on feature significance disclosed in this application;

[0057] Figure 3 This is a schematic diagram of the effects of different styles of images disclosed in this application; wherein, Figure 3 (a) is a schematic diagram of the style image effect corresponding to the first style. Figure 3 (b) is a schematic diagram of the style image effect corresponding to the second style. Figure 3 (c) is a schematic diagram of the style image effect corresponding to the third style;

[0058] Figure 4 This is a schematic diagram of a specific feature image obtained after feature extraction disclosed in this application;

[0059] Figure 5 This is a schematic diagram of the MSRMNet network architecture disclosed in this application;

[0060] Figure 6This is a schematic structural diagram of an intelligent color mapping device based on feature saliency disclosed in this application;

[0061] Figure 7 This is a structural diagram of an electronic device disclosed in this application. DETAILED DESCRIPTION

[0062] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0063] Current data-driven automated design methods also have limitations when processing complex scientific simulation data. They usually treat all data points equally and apply a unified algorithm for feature expression and definition. However, this approach is difficult to adapt to the unevenness and high noise of data distribution, resulting in a lack of robustness in practical applications, and requires a lot of adjustments or may even fail in the face of different data types. In addition, existing methods often ignore the need to meet the subjective preferences of different users and lack flexible customization options. To this end, the present application provides an intelligent color mapping method based on feature significance, which can improve the efficiency of generating color mapping control point adjustment schemes in the process of intelligent color mapping based on feature significance, thereby improving the efficiency of adjusting color mapping control points.

[0064] See also Figure 1 As shown, an embodiment of the present invention discloses an intelligent color mapping method based on feature saliency, comprising:

[0065] Step S11: cluster the pixel points corresponding to the target style image to obtain a number of control points, and determine the color order adjustment function corresponding to the control points based on the perceptual uniformity deviation and smoothing error, and then generate a color mapping table using the color order adjustment function; the perceptual uniformity deviation is the degree of deviation between the current perceptual distance of each adjacent control point in the perceptually uniform color space and the preset ideal perceptual distance; the smoothing error is the color change smoothness error determined by using the angular change of the displacement vector corresponding to each control point.

[0066] In this embodiment, the schematic diagram of performing intelligent color mapping based on feature significance is as follows Figure 2As shown: In the process of intelligent color mapping based on feature significance, the embodiment of the present application first needs to select a target style image according to user preferences and specific application scenarios. Subsequently, the K-Means clustering algorithm is used to cluster the pixels in the target style image to obtain a number of control points. It is worth mentioning that in order to meet the continuity requirements of the data values, the color distribution of the control points on the palette must be perceptually uniform. Therefore, the perceptual uniform deviation and smoothing error proposed in ColorMaker are cited in the embodiment of the present application to guide the color order of the control points, and the function expression is as follows:

[0067] ;

[0068] in, is the perceived uniform deviation, is the smoothing error.

[0069] It is worth mentioning that if all permutations are exhausted, the time complexity is , which results in a lot of time cost. Therefore, the embodiment of the present application needs to find the minimum value by branch and bound. Furthermore, the perceived color change due to a perceptually uniform palette is proportional to the amount by which the data value increases (or decreases), i.e., the perceptually uniform deviation Essentially, it is the deviation between the current state and the ideal state. Therefore, the specific expression of the perceived uniform deviation is as follows:

[0070] ;

[0071] in, is the standard deviation, is the average perceptual distance of all adjacent control points, To show the number of control points, For the control points.

[0072] Specifically, before determining the color order adjustment function corresponding to the control point based on the perceptual uniform deviation and the smoothing error and then generating a color mapping table using the color order adjustment function, it may also include: determining a control point pair based on every two control points in each control point, and obtaining the current perceptual distance between each control point pair, and then determining the distance average value corresponding to each current perceptual distance; determining the distance difference between each perceptual distance and the corresponding distance average value, and performing square operations and summing the distance differences corresponding to each control point pair to obtain a sum result, and then determining a calculation result based on the sum result and the number of all control point pairs; determining a perceptual uniform deviation value based on the calculation result and the distance average value; the numerical value of the perceptual uniform deviation value is negatively correlated with the perceptual uniformity size corresponding to the control point.

[0073] Furthermore, since a palette with high curvature will produce a steeper color transition, resulting in visual discontinuity, the embodiment of the present application needs to measure the angle between the displacement vectors at the control points. To approximate the curvature, and evaluate the palette smoothing error, where the smoothing error is determined as follows:

[0074] ;

[0075] in, , The first color in Lab color space The control point and The color vector corresponding to each control point.

[0076] It is worth mentioning that if is 0, indicating that all color vectors have the same direction. is 1, indicating that all color vectors are in opposite directions (i.e., the angle is 180°). Then, the sorted color list is constructed in a linear mapping manner to obtain a color mapping table. , to apply images of any style to visualization work, and the effect diagrams of different style images are as follows Figure 3 As shown: Figure 3 (a) Figure 3 (b) and Figure 3 (c) corresponds to different styles.

[0077] Specifically, before determining the color order adjustment function corresponding to the control point based on the perceptual uniform deviation and the smoothing error and then generating a color mapping table using the color order adjustment function, it may also include: determining a first displacement vector between each control point and the previous control point and a second displacement vector between each control point and the next control point; normalizing the first displacement vector and the second displacement vector respectively to obtain a corresponding first normalized result and a second normalized result; determining a dot product result of the displacement vector corresponding to the first normalized result and the second normalized result, and determining a curvature metric corresponding to the control point based on the dot product result of the displacement vector; determining a corresponding average value of the curvature metric based on the curvature metric of each control point to obtain a smoothing error value; the numerical value of the smoothing error value is negatively correlated with the smoothness of the color change of the target style image.

[0078] Step S12: performing color mapping on each of the control points using the color mapping table to obtain a mapping image, and obtaining a feature image for identifying the feature area to be highlighted, and processing the mapping image using the MSRMNet network model to obtain a saliency image.

[0079] In this embodiment, after obtaining the color mapping table, the embodiment of the present application needs to use Complete color mapping on the data to obtain a mapped image Then, the feature image obtained by user input through feature extraction criteria or interaction is obtained , and the feature image diagram obtained after feature extraction is as follows Figure 4 Then, the MSRMNet (Multi-scale skip residual and multi-mixed features network) network model is used to Perform saliency detection to output a saliency image Among them, the MSRMNet network architecture is as follows Figure 5 As shown, it is worth mentioning that the pink image in the legend corresponds to the pink image in the encoder and decoder, both representing 3×3 convolutional layers, the green image in the legend corresponds to the green image in the encoder, both representing batch normalization; the purple image in the legend corresponds to the purple image in the encoder, both representing ReLU activation functions, and the blue image in the legend corresponds to the blue image in the encoder and decoder, both representing upsampling.

[0080] Step S13: Based on the feature saliency item, the color opposition item and the feature sensitivity item, the mapping image, the feature image and the saliency image are processed to obtain a loss function; the feature saliency item is the degree of overlap between the saliency image and the feature image; the color opposition item is the difference in the average color modulus between the feature area and the non-feature area in the feature image; and the feature sensitivity item is the maximum distance between the colors in the feature area in the color space.

[0081] In this embodiment, , and Afterwards, the embodiment of this application needs to use , and Calculate the loss. It is worth mentioning that in the process of loss calculation, the embodiment of the present application formalizes the entire process into a nonlinear constrained optimization problem to balance the three key factors affecting R3: E1: feature saliency, E2: color opposition and E3: feature sensitivity. Among them, the feature saliency is intended to reduce With characteristic area map The color opposition term is used to prevent the color of the feature region from being too similar to that of other regions; and the feature sensitivity is used to prevent the numerical changes within the feature region from being ignored. In other words, the above three factors are the basis for ensuring that the color palette reveals the feature region and is thus understood by most users.

[0082] In one embodiment, the objective cost function is first minimized Determine a sequence of positions:

[0083] ;

[0084] In addition, since the control point color is fixed, so only the control point position This is one independent variable, then the expression of the target cost function is as follows:

[0085] ;

[0086] in, For evaluation Feature area in Significance, Used to describe Feature area in and non-feature areas The degree of color similarity, Used to maintain the consistency of color data and reveal the value changes within the feature area.

[0087] Furthermore, the embodiment of the present application needs to adjust the weight of the feature salient item. That is, in order to obtain a color palette that can truly simulate the human eye's perception of the prominent feature area, the embodiment of the present application needs to Starting from the feature area exist The significance of , and the process is as follows:

[0088] First, analyze the visual importance images of two single-channel images of the same size and The degree of overlap between them is used as an indicator to describe the saliency of the feature region. The formula for determining the feature saliency is as follows:

[0089] ;

[0090] ;

[0091] in, and They are and The width and height, and Respectively and exist The value at , express The number of pixels in the feature area.

[0092] Further, in In the embodiment of the present application, the product of the values ​​of the same position of the two images is accumulated as the consistency of the two images, and then the product of the two single-channel images is used to define In one embodiment, when hour, Both or , which shows that and Not overlapping at all, when hour, Both , which shows that and Total overlap.

[0093] Specifically, based on the feature saliency item, color opposition item and feature sensitivity item, the mapping image, feature image and saliency image are processed. Before obtaining the loss function, it can also include: pixel-level alignment of the saliency image and the feature image to obtain an alignment result, and then multiplying the pixel value in the saliency image with the corresponding pixel value in the feature image to obtain a multiplication result; counting the number of pixel points marked as feature areas in the feature image, and determining the overlap index based on the multiplication result of each pixel value and the number of pixels, and determining the feature saliency item based on the overlap index; the numerical value corresponding to the feature saliency item is negatively correlated with the presentation effect of the feature area in the saliency image.

[0094] Then, adjust the weights corresponding to the color opposition items, that is, to avoid and Since values ​​that are too close produce similar colors, which makes the feature outline unclear, the embodiment of the present application needs to add a color opposition term to the penalty function to increase and In a specific embodiment, the present application embodiment is based on and Two image pairs is defined, and the expression is as follows:

[0095] ;

[0096] ;

[0097] in, and They are and The number of pixels in the for middle The three-channel Lab color value at Represents color value It is worth mentioning that, The definition of is essentially the absolute value of the difference between the average color modulus of the feature area and the average color modulus of the non-feature area, because exist is 1, in is 0, so Only accumulate area, Only accumulate area.

[0098] Specifically, based on the feature saliency item, color opposition item and feature sensitivity item, the mapping image, feature image and saliency image are processed, and before the loss function is obtained, it can also include: extracting the first color value corresponding to the pixel point in each feature area from the mapping image, and determining the corresponding first modulus average value based on each first color value; extracting the second color value corresponding to each pixel point in each non-feature area from the mapping image, and determining the corresponding second modulus average value based on each second color value; determining the absolute difference result based on the first modulus average value and the second modulus average value, and determining the color opposition item based on the absolute difference result; the numerical value of the color opposition item is negatively correlated with the numerical value of the color distinction between the feature area and the non-feature area.

[0099] Finally, adjust the weight corresponding to the feature sensitivity, that is, if the embodiment of the present application only considers and The difference between the two, without limiting the internal area, may not reveal the value changes within the data. Therefore, the embodiment of the present application adds feature sensitivity to make the value changes within the feature have a wider span in color, and The expression is as follows:

[0100] ;

[0101] ;

[0102] in, For The color set that appears inside the feature area, and Represents the color value, express and Perceptual distance in Lab color space.

[0103] It is worth mentioning that since the Lab color space is considered to be perceptually uniform, according to The definition of As the value of increases, there will be a larger color interval for characterizing data changes. Therefore, the data changes within the feature area will also appear more sensitive in color, which is more conducive to analyzing the changing trend of the feature area data. In this way, the embodiment of the present application can formalize the scalar field color mapping problem into a nonlinear optimization problem by adopting the above-mentioned mathematical model. Specifically, based on the feature saliency term, the color opposition term and the feature sensitivity term, the mapping image, the feature image and the saliency image are processed. Before obtaining the loss function, it can also include: extracting each third color value in the feature area from the mapping image, and determining the perceptual distance between each two third color values ​​in the color space; setting the perceptual distance with the largest value among the perceptual distances as the perceptual distance to be processed, and determining the feature sensitivity term based on the perceptual distance to be processed; the numerical value of the feature sensitivity term is negatively correlated with the numerical value of the color change span corresponding to the feature area.

[0104] Step S14: adjusting the position of each of the control points using an annealing algorithm and the loss function to obtain a position adjustment result, and determining a control point adjustment scheme corresponding to the target style image based on the position adjustment result.

[0105] In this embodiment, the position of the color control point needs to be adjusted using an annealing algorithm, and the objective function is made to converge by continuously changing the mapping relationship from the data domain to the color domain. It is worth mentioning that in the process of adjusting the position of the color control point using the annealing algorithm, the embodiment of the present application first needs to start from a higher initial "temperature" and then gradually cool down. In each iteration, the algorithm will disturb the current solution by shifting a small amount of control points randomly selected to the left or right, and use the cost function to evaluate the palette. If the cost of the newly obtained solution is lower, the newly obtained solution is adopted. In order to prevent falling into a local optimum, when the new solution is worse, the following formula is used for probability determination to determine whether to adopt the above solution based on the obtained probability:

[0106] ;

[0107] in, Represents the difference between the current loss and the current optimal state, Indicates the current temperature.

[0108] Specifically, the position of each control point is adjusted using an annealing algorithm and a loss function to obtain a position adjustment result, and a control point adjustment scheme corresponding to the target style image is determined based on the position adjustment result. This may include: determining an initial temperature parameter and a cooling rate parameter, and then adjusting the initial position direction of the control point using a preset position adjustment direction control rule at the current temperature to obtain a position direction to be processed; using a loss function and determining a function value change corresponding to the loss function value based on the initial position direction and the position direction to be processed, and judging whether the function value change is greater than zero; if the function value change is not greater than zero, setting the position direction to be processed as the position adjustment result; judging whether the current temperature is less than a preset temperature threshold; if the current temperature is less than the preset temperature threshold, judging whether the loss function value satisfies a preset stability condition; if the loss function value satisfies the preset stability condition, determining a control point adjustment scheme corresponding to the target style image based on the corresponding position adjustment result; if the function value change is greater than zero, determining a new current temperature based on the initial temperature parameter and the cooling rate parameter, and triggering a step of adjusting the initial position direction of the control point using the preset position adjustment direction control rule at the current temperature.

[0109] It can be seen that the embodiment of the present application first needs to cluster the pixel points corresponding to the target style image to obtain a number of control points, and determine the color order adjustment function corresponding to the control points based on the perceptual uniform deviation and smoothing error, and then use the color order adjustment function to generate a color mapping table; then, use the color mapping table to perform color mapping on each control point to obtain a mapping image, and obtain a feature image for identifying the feature area to be highlighted, and use the MSRMNet network model to process the mapping image to obtain a saliency image; then, based on the feature saliency item, color opposition item and feature sensitivity item, the mapping image, feature image and saliency image are processed to obtain a loss function; finally, the position of each control point is adjusted using the annealing algorithm and the loss function to obtain a position adjustment result, and based on the position adjustment result, a control point adjustment scheme corresponding to the target style image is determined. In this way, the efficiency of generating the color mapping control point adjustment scheme is improved in the process of intelligent color mapping based on feature saliency, thereby improving the efficiency of adjusting the color mapping control points.

[0110] Accordingly, see Figure 6 As shown, the present application also provides an intelligent color mapping device based on feature saliency, comprising:

[0111] A color mapping table determination module 11 is configured to cluster the pixels corresponding to the target style image to obtain a plurality of control points, determine a color order adjustment function corresponding to the control points based on a perceptual uniformity deviation and a smoothing error, and then generate a color mapping table using the color order adjustment function; the perceptual uniformity deviation is the degree of deviation between the current perceptual distance of adjacent control points in a perceptually uniform color space and a preset ideal perceptual distance; and the smoothing error is a color change smoothness error determined by an angular change in a displacement vector corresponding to each control point.

[0112] a mapping image acquisition module 12 for performing color mapping on each of the control points using the color mapping table to obtain a mapping image, obtaining a feature image for identifying a feature area to be highlighted, and processing the mapping image using the MSRMNet network model to obtain a saliency image;

[0113] a loss function determination module 13 configured to process the mapping image, the feature image, and the saliency image based on a feature saliency term, a color opposition term, and a feature sensitivity term to obtain a loss function; the feature saliency term being the degree of overlap between the saliency image and the feature image; the color opposition term being the difference in average color modulus between a feature region and a non-feature region in the feature image; and the feature sensitivity term being the maximum distance between colors in the feature region in the color space;

[0114] The control point adjustment scheme determining module 14 is configured to adjust the position of each of the control points using an annealing algorithm and the loss function to obtain a position adjustment result, and determine a control point adjustment scheme corresponding to the target style image based on the position adjustment result.

[0115] As can be seen from the above, before performing intelligent color mapping based on feature saliency, the embodiment of the present application first needs to cluster the pixel points corresponding to the target style image to obtain a number of control points, and determine the color order adjustment function corresponding to the control points based on the perceptual uniform deviation and smoothing error, and then use the color order adjustment function to generate a color mapping table; then, use the color mapping table to perform color mapping on each control point to obtain a mapping image, and obtain a feature image for identifying the feature area to be highlighted, and use the MSRMNet network model to process the mapping image to obtain a saliency image; then, based on the feature saliency term, color opposition term and feature sensitivity term, the mapping image, feature image and saliency image are processed to obtain a loss function; finally, the position of each control point is adjusted using the annealing algorithm and the loss function to obtain a position adjustment result, and based on the position adjustment result, a control point adjustment scheme corresponding to the target style image is determined. In this way, the efficiency of generating the color mapping control point adjustment scheme is improved in the process of intelligent color mapping based on feature saliency, thereby improving the efficiency of adjusting the color mapping control points.

[0116] In some specific implementations, the intelligent color mapping device based on feature significance may further include:

[0117] a distance average value determining unit, configured to determine a control point pair based on every two of the control points, obtain a current perceived distance between each of the control point pairs, and then determine a distance average value corresponding to each of the current perceived distances;

[0118] a calculation result determination unit, configured to determine a distance difference between each of the perceived distances and the corresponding distance average, perform a square operation and sum the distance differences corresponding to each of the control point pairs to obtain a summation result, and then determine a calculation result based on the summation result and the number of all the control point pairs;

[0119] The perceptual uniformity deviation value determining unit is configured to determine a perceptual uniformity deviation value based on the calculation result and the distance average value; the numerical value of the perceptual uniformity deviation value is negatively correlated with the perceptual uniformity value corresponding to the control point.

[0120] In some specific implementations, the intelligent color mapping device based on feature significance may further include:

[0121] a displacement vector determining unit, configured to determine a first displacement vector between each of the control points and a previous control point and a second displacement vector between each of the control points and a subsequent control point;

[0122] a normalization result determining unit, configured to perform normalization processing on the first displacement vector and the second displacement vector respectively to obtain a corresponding first normalization result and a second normalization result;

[0123] a curvature metric determining unit, configured to determine a dot product result of a displacement vector corresponding to the first normalized result and the second normalized result, and determine a curvature metric corresponding to the control point based on the dot product result of the displacement vector;

[0124] A smoothing error value determining unit is configured to determine a corresponding curvature metric average value based on the curvature metric of each control point to obtain a smoothing error value; the numerical value of the smoothing error value is negatively correlated with the color change smoothness of the target style image.

[0125] In some specific implementations, the intelligent color mapping device based on feature significance may further include:

[0126] a multiplication result determining unit, configured to perform pixel-level alignment on the saliency image and the feature image to obtain an alignment result, and then multiply pixel values ​​in the saliency image with corresponding pixel values ​​in the feature image to obtain a multiplication result;

[0127] A feature saliency item determination unit is used to count the number of pixel points marked as feature areas in the feature image, determine a coincidence index based on the multiplication result of each pixel value and the number of pixel points, and determine a feature saliency item based on the coincidence index; the numerical value corresponding to the feature saliency item is negatively correlated with the presentation effect of the feature area in the saliency image.

[0128] In some specific implementations, the intelligent color mapping device based on feature significance may further include:

[0129] a first modulus average value determining unit, configured to extract a first color value corresponding to a pixel point in each of the feature areas from the mapped image, and determine a corresponding first modulus average value based on each of the first color values;

[0130] a second modulus average value determining unit, configured to extract a second color value corresponding to each pixel point in each non-feature area from the mapped image, and determine a corresponding second modulus average value based on each second color value;

[0131] A color opposition item determination unit is used to determine an absolute difference result based on the first modulus average value and the second modulus average value, and determine a color opposition item based on the absolute difference result; the numerical value of the color opposition item is negatively correlated with the numerical value of the color distinction between the feature area and the non-feature area.

[0132] In some specific implementations, the intelligent color mapping device based on feature significance may further include:

[0133] a perceptual distance determining unit, configured to extract each third color value in the feature area from the mapped image, and determine a perceptual distance between every two third color values ​​in the color space;

[0134] A feature sensitivity item determination unit is used to set the perception distance with the largest value among the perception distances as the perception distance to be processed, and determine the feature sensitivity item based on the perception distance to be processed; the numerical value of the feature sensitivity item is negatively correlated with the numerical value of the color change span corresponding to the feature area.

[0135] In some specific implementations, the control point adjustment solution determination module 14 may specifically include:

[0136] a position and direction adjustment unit, configured to determine an initial temperature parameter and a cooling rate parameter, and then adjust the initial position and direction of the control point at the current temperature using a preset position adjustment direction control rule to obtain a position and direction to be processed;

[0137] a position adjustment result determining unit, configured to determine, using the loss function and based on the initial position direction and the position direction to be processed, a function value change corresponding to the loss function value, and determine whether the function value change is greater than zero; if the function value change is not greater than zero, setting the position direction to be processed as the position adjustment result;

[0138] a control point adjustment scheme subunit, configured to determine whether the current temperature is less than a preset temperature threshold; if so, determine whether the loss function value satisfies a preset stability condition; and if so, determine a control point adjustment scheme corresponding to the target style image based on the corresponding position adjustment result;

[0139] A current temperature determination unit is used to determine a new current temperature based on the initial temperature parameter and the cooling rate parameter if the change in the function value is greater than zero, and trigger the step of adjusting the initial position direction of the control point using a preset position adjustment direction control rule at the current temperature.

[0140] Furthermore, the embodiment of the present application also discloses an electronic device, Figure 7This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content in the diagram should not be considered as any limitation on the scope of use of this application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the intelligent color mapping method based on feature significance disclosed in any of the aforementioned embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0141] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and the external device. The communication protocol it follows is any communication protocol that can be applied to the technical solution of this application and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world. Its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0142] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk or CD, etc. The resources stored thereon can include an operating system 221, a computer program 222, etc., and the storage method can be temporary storage or permanent storage.

[0143] The operating system 221 is used to manage and control the hardware devices and computer program 222 on the electronic device 20, and can be Windows Server, Netware, Unix, Linux, etc. In addition to including a computer program capable of implementing the feature saliency-based intelligent color mapping method performed by the electronic device 20 as disclosed in any of the aforementioned embodiments, the computer program 222 may further include a computer program capable of implementing other specific tasks.

[0144] Furthermore, this application discloses a computer-readable storage medium for storing a computer program; wherein, when executed by a processor, the computer program implements the aforementioned intelligent color mapping method based on feature saliency. The specific steps of this method can be found in the corresponding contents disclosed in the aforementioned embodiments and will not be repeated here.

[0145] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from the other embodiments. Reference can be made to the descriptions of the identical or similar parts between the various embodiments. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple, and the relevant parts can be referred to the descriptions of the methods.

[0146] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the components and steps of each example according to their functions. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0147] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0148] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or device comprising the element.

[0149] The above is a detailed introduction to the technical solution provided by the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for those skilled in the art, according to the ideas of the present application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. An intelligent color mapping method based on feature saliency, characterized in that: include: Clustering the pixels corresponding to the target style image to obtain a number of control points, and determining a color order adjustment function corresponding to the control points based on the perceptual uniformity deviation and smoothing error, and then generating a color mapping table using the color order adjustment function; the perceptual uniformity deviation is the degree of deviation between the current perceptual distance of each adjacent control point in the perceptually uniform color space and a preset ideal perceptual distance; the smoothing error is the color change smoothness error determined by the angular change of the displacement vector corresponding to each control point; Performing color mapping on each of the control points using the color mapping table to obtain a mapping image, obtaining a feature image for identifying a feature area to be highlighted, and processing the mapping image using the MSRMNet network model to obtain a saliency image; The mapping image, the feature image, and the saliency image are processed based on a feature saliency term, a color opposition term, and a feature sensitivity term to obtain a loss function; the feature saliency term is the degree of overlap between the saliency image and the feature image; the color opposition term is the difference in average color modulus between a feature region and a non-feature region in the feature image; and the feature sensitivity term is the maximum distance between colors in the feature region in the color space; The position of each of the control points is adjusted using an annealing algorithm and the loss function to obtain a position adjustment result, and a control point adjustment scheme corresponding to the target style image is determined based on the position adjustment result.

2. The intelligent color mapping method based on feature saliency according to claim 1, characterized in that: Before determining the color order adjustment function corresponding to the control point based on the perceptual uniform deviation and the smoothing error and then generating a color mapping table using the color order adjustment function, the method further includes: determining a control point pair based on every two of the control points, obtaining a current perceived distance between each of the control point pairs, and then determining a distance average corresponding to each of the current perceived distances; determining a distance difference between each of the perceived distances and the corresponding distance average, performing a square operation and summing the distance differences corresponding to each of the control point pairs to obtain a summation result, and then determining a calculation result based on the summation result and the number of all the control point pairs; A perceptual uniformity deviation value is determined based on the calculation result and the distance average value; a numerical value of the perceptual uniformity deviation value is negatively correlated with a perceptual uniformity value corresponding to the control point.

3. The intelligent color mapping method based on feature saliency according to claim 1, wherein: Before determining the color order adjustment function corresponding to the control point based on the perceptual uniform deviation and the smoothing error and then generating a color mapping table using the color order adjustment function, the method further includes: Determine a first displacement vector between each of the control points and a previous control point and a second displacement vector between each of the control points and a subsequent control point; performing normalization processing on the first displacement vector and the second displacement vector respectively to obtain corresponding first normalization results and second normalization results; Determine a dot product result of a displacement vector corresponding to the first normalized result and the second normalized result, and determine a curvature metric corresponding to the control point based on the dot product result of the displacement vector; Based on the curvature metrics of the control points, a corresponding curvature metric average is determined to obtain a smoothing error value; the numerical value of the smoothing error value is negatively correlated with the color change smoothness of the target style image.

4. The intelligent color mapping method based on feature saliency according to claim 1, wherein: Before the mapping image, the feature image and the saliency image are processed based on the feature saliency item, the color opposition item and the feature sensitivity item to obtain the loss function, the method further includes: Performing pixel-level alignment on the saliency image and the feature image to obtain an alignment result, and then multiplying pixel values ​​in the saliency image with corresponding pixel values ​​in the feature image to obtain a multiplication result; The number of pixels marked as feature areas in the feature image is counted, and a coincidence index is determined based on the multiplication result of each pixel value and the number of pixels, and a feature saliency item is determined based on the coincidence index; the numerical value corresponding to the feature saliency item is negatively correlated with the presentation effect of the feature area in the saliency image.

5. The intelligent color mapping method based on feature saliency according to claim 1, wherein: Before the mapping image, the feature image and the saliency image are processed based on the feature saliency item, the color opposition item and the feature sensitivity item to obtain the loss function, the method further includes: extracting a first color value corresponding to a pixel point in each of the feature areas from the mapped image, and determining a corresponding first modulus average value based on each of the first color values; Extracting a second color value corresponding to each pixel point in each non-feature area from the mapped image, and determining a corresponding second modulus average value based on each second color value; An absolute difference result is determined based on the first modulus average value and the second modulus average value, and a color opposition term is determined based on the absolute difference result; the numerical value of the color opposition term is negatively correlated with the numerical value of the color distinction between the feature area and the non-feature area.

6. The intelligent color mapping method based on feature saliency according to claim 1, wherein: Before the mapping image, the feature image and the saliency image are processed based on the feature saliency item, the color opposition item and the feature sensitivity item to obtain the loss function, the method further includes: extracting each third color value in the feature area from the mapped image, and determining a perceptual distance between every two third color values ​​in the color space; The perceptual distance with the largest value among the perceptual distances is set as the perceptual distance to be processed, and a feature sensitivity item is determined based on the perceptual distance to be processed; the numerical value of the feature sensitivity item is negatively correlated with the numerical value of the color change span corresponding to the feature area.

7. The intelligent color mapping method based on feature saliency according to any one of claims 1 to 6, characterized in that: The adjusting the position of each of the control points using the annealing algorithm and the loss function to obtain a position adjustment result, and determining a control point adjustment scheme corresponding to the target style image based on the position adjustment result, includes: Determine the initial temperature parameter and the cooling rate parameter, and then adjust the initial position direction of the control point using a preset position adjustment direction control rule at the current temperature to obtain a position direction to be processed; Determining a function value change corresponding to a loss function value based on the initial position direction and the position direction to be processed using the loss function, and determining whether the function value change is greater than zero; if the function value change is not greater than zero, setting the position direction to be processed as a position adjustment result; determining whether the current temperature is less than a preset temperature threshold; if the current temperature is less than the preset temperature threshold, determining whether the loss function value satisfies a preset stability condition; and if the loss function value satisfies the preset stability condition, determining a control point adjustment scheme corresponding to the target style image based on the corresponding position adjustment result; If the function value change is greater than zero, the new current temperature is determined based on the initial temperature parameter and the cooling rate parameter, and the step of adjusting the initial position direction of the control point using the preset position adjustment direction control rule at the current temperature is triggered.

8. An intelligent color mapping device based on feature saliency, characterized in that: include: A color mapping table determination module is configured to cluster the pixels corresponding to the target style image to obtain a plurality of control points, determine a color order adjustment function corresponding to the control points based on a perceptual uniformity deviation and a smoothing error, and then generate a color mapping table using the color order adjustment function; the perceptual uniformity deviation is the degree of deviation between the current perceptual distance of adjacent control points in a perceptually uniform color space and a preset ideal perceptual distance; and the smoothing error is a color change smoothness error determined by using an angular change in a displacement vector corresponding to each control point; a mapping image acquisition module, configured to perform color mapping on each of the control points using the color mapping table to obtain a mapping image, obtain a feature image for identifying a feature area to be highlighted, and process the mapping image using the MSRMNet network model to obtain a saliency image; a loss function determination module, configured to process the mapping image, the feature image, and the saliency image based on a feature saliency term, a color opposition term, and a feature sensitivity term to obtain a loss function; the feature saliency term being the degree of overlap between the saliency image and the feature image; the color opposition term being the difference in average color modulus between a feature region and a non-feature region in the feature image; and the feature sensitivity term being the maximum distance between colors in the feature region in the color space; A control point adjustment scheme determination module is used to adjust the position of each of the control points using an annealing algorithm and the loss function to obtain a position adjustment result, and determine a control point adjustment scheme corresponding to the target style image based on the position adjustment result.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the intelligent color mapping method based on feature significance as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that Used to store a computer program, wherein when the computer program is executed by a processor, the intelligent color mapping method based on feature significance according to any one of claims 1 to 7 is implemented.

Images