CN117853365A - Artistic result display method based on computer image processing - Google Patents
Artistic result display method based on computer image processing Download PDFInfo
- Publication number
- CN117853365A CN117853365A CN202410239072.5A CN202410239072A CN117853365A CN 117853365 A CN117853365 A CN 117853365A CN 202410239072 A CN202410239072 A CN 202410239072A CN 117853365 A CN117853365 A CN 117853365A
- Authority
- CN
- China
- Prior art keywords
- index
- artistic
- edge
- color
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000012545 processing Methods 0.000 title claims abstract description 25
- 239000007787 solid Substances 0.000 claims abstract description 28
- 238000009499 grossing Methods 0.000 claims abstract description 22
- 230000003044 adaptive effect Effects 0.000 claims abstract description 6
- 238000001914 filtration Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 abstract description 7
- 230000006870 function Effects 0.000 description 11
- 230000008859 change Effects 0.000 description 7
- 238000010422 painting Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000008439 repair process Effects 0.000 description 3
- 230000008451 emotion Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000001154 acute effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000004043 dyeing Methods 0.000 description 1
- 230000002996 emotional effect Effects 0.000 description 1
- IXSZQYVWNJNRAL-UHFFFAOYSA-N etoxazole Chemical compound CCOC1=CC(C(C)(C)C)=CC=C1C1N=C(C=2C(=CC=CC=2F)F)OC1 IXSZQYVWNJNRAL-UHFFFAOYSA-N 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 238000010428 oil painting Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 239000000049 pigment Substances 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
- 230000007480 spreading Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Image Processing (AREA)
Abstract
The invention relates to the technical field of image processing, in particular to an artistic achievement display method based on computer image processing, which comprises the following steps: acquiring an artistic result image and a gray artistic image; constructing a color channel difference index of the pixel point according to the pixel value of the pixel point; constructing an image color difference index of an artistic result image; further constructing color application vividness index of the artistic result image; according to the number of the pixel points and the Euclidean distance between each pixel point and the turning edge, constructing an edge straight index of each edge line; further constructing edge solid indexes of various color extension areas; constructing a shape solid index of each color extension area; constructing a texture style three-dimensional index of the artistic outcome image based on the texture style three-dimensional index; further constructing local style offset indexes and adaptive smoothing parameters of each block; and obtaining an optimized artistic image according to the self-adaptive smoothing parameters. The invention can improve the restoration effect of the artistic result image.
Description
Technical Field
The application relates to the technical field of image processing, in particular to an artistic achievement display method based on computer image processing.
Background
The art work display refers to a process of displaying an artwork to a viewer or audience in a public manner, allowing them to enjoy, experience and evaluate the artwork. The aim of the artistic achievement display is to enable audience to appreciate and understand the originality, skill and emotion expression of artists through the display of the artwork, the display of the artistic achievement can enable the audience to interact with the artwork, and inspire on aesthetics, culture, emotion and thought is obtained from the interaction, so that artistic communication, dialogue and thinking are promoted, and development and propagation of the art are promoted.
The artistic result image contains rich cultural, artistic, scientific and historical values, and has more or less damage or massive loss of part of the pictorial representations due to various reasons, thereby seriously affecting the activities of appreciation, cultural creative, cultural spreading and the like of the pictorial representations. Therefore, the method has extremely important practical significance in repairing old or damaged artistic result images so as to restore the original appearance and quality of the works.
The existing NLM non-local mean filtering algorithm can remove noise and maintain texture details by utilizing redundant information commonly existing in an artistic result image, and can repair the artistic result image, but the rules of style, color and the like implied by the artistic result image are not considered when smooth parameters are set, so that the repair effect on the artistic result image is not good enough.
Disclosure of Invention
In order to solve the technical problems, the invention provides an artistic achievement display method based on computer image processing to solve the existing problems.
The artistic achievement display method based on the computer image processing adopts the following technical scheme:
one embodiment of the present invention provides an artistic outcome presentation method based on computer image processing, the method comprising the steps of:
acquiring an artistic result image and a gray artistic image;
constructing color channel difference indexes of any two pixel points according to pixel values of each pixel point on three channels in an artistic result image; constructing an image color difference index of the artistic result image according to the gray values of the pixel points and the color channel difference indexes of any two pixel points in the artistic result image; constructing a color application vivid index of the artistic result image according to the gradient amplitude of the pixel points and the image color difference index of the artistic result image;
acquiring each growing area in the gray artistic image by using an area growing algorithm to serve as each color extending area; acquiring each edge line, each turning edge and each turning angle of each color extension area, and constructing an edge straight index of each edge line according to the number of pixel points on each edge line, each turning edge and the Euclidean distance between each pixel point on each edge line and the corresponding turning edge; constructing parallel line segments of all turning edges, and constructing edge solid indexes of all color extension areas according to edge straight indexes of all edge lines of all color extension areas and color channel difference indexes of two pixel points at corresponding positions on the turning edges and the parallel line segments; constructing a shape solid index of each color extension area according to the number of corner points on the edge of each color extension area, the length of each turning edge and the angle of each turning angle; constructing texture style three-dimensional indexes of an artistic result image according to the shape three-dimensional indexes and the edge three-dimensional indexes of various color extension areas in the gray artistic image;
dividing an artistic result image into a plurality of square blocks uniformly, and constructing local style offset indexes of the blocks according to the color application vivid indexes and texture style three-dimensional indexes of the blocks and the artistic result image; constructing self-adaptive smoothing parameters of each block according to the color application vividness index, texture style three-dimensional index and local style offset index of each block of the artistic result image; and obtaining an optimized artistic image by adopting an NLM non-local mean filtering algorithm according to the self-adaptive smoothing parameters of each block.
Further, the constructing a color channel difference index of any two pixels according to the pixel values of each pixel on three channels in the artistic result image includes:
for any two pixel points in an artistic result image, calculating the absolute value of the difference value of the pixel values of the two pixel points on a red channel, marking the absolute value as a first difference value, calculating the absolute value of the difference value of the pixel values of the two pixel points on a green channel, marking the absolute value as a second difference value, calculating the absolute value of the difference value of the pixel values of the two pixel points on a blue channel, marking the absolute value as a third difference value, calculating the sum value of the first difference value and the second difference value, and taking the sum value of the sum value and the third difference value as the color channel difference index of the two pixel points.
Further, the constructing an image color difference index of the artistic result image according to the gray level value of the pixel point and the color channel difference index of any two pixel points in the artistic result image comprises:
and counting the maximum value and the minimum value of the gray values of all pixel points in the gray artistic image, calculating the absolute value of the difference value between the maximum value and the minimum value, calculating the average value of the color channel difference indexes of all any two pixel points in the artistic result image, and taking the product of the absolute value of the difference value and the average value as the image color difference index of the artistic result image.
Further, the constructing the color application vividness index of the artistic result image according to the gradient amplitude of the pixel points and the image color difference index of the artistic result image comprises the following steps:
calculating the sum value of gradient amplitude values of all pixel points in the gray artistic image, calculating the product of the sum value and the image color difference index of the artistic result image, and taking the product as the color application vividness index of the artistic result image.
Further, the obtaining each edge line, each turning edge and each turning angle of each color extension area, and constructing an edge straight index of each edge line according to each edge line, the number of pixel points on each turning edge and the euclidean distance between each pixel point on each edge line and the corresponding turning edge, includes:
detecting corner points of the edge of each color extension area, for any two adjacent corner points of the edge of the color extension area, forming an edge line by all edge pixel points between the two adjacent corner points, marking a connecting line between the two adjacent corner points as a turning edge of the edge line, and marking an included angle between the turning edge and the adjacent next turning edge as a turning angle of the turning edge;
counting the number of pixel points on the edge line, counting the number of pixel points on the turning edge of the edge line, counting the absolute value of the difference between the first number and the second number, counting the sum of Euclidean distances between all pixel points on the edge line and the corresponding turning edge, counting the product of the absolute value of the difference and the sum, taking the opposite number of the product as an index of an exponential function taking a natural constant as a base, and taking the calculation result of the exponential function as an edge straight index of the edge line.
Further, the constructing the edge solid index of each color extension area according to the edge straight index of each edge line of each color extension area and the color channel difference index of two pixel points at the corresponding positions on the turning edge and the parallel line segment includes:
for each turning edge in each color extension area, calculating color channel difference indexes of two pixel points at corresponding positions on a parallel line segment corresponding to the turning edge and the turning edge, calculating the average value of the color channel difference indexes of all the two pixel points at the corresponding positions of the turning edge, calculating the product of the average value and the edge straight index of an edge line corresponding to the turning edge, calculating the sum value of the product corresponding to all the turning edges in the color extension area, and taking the sum value as the edge solid index of the color extension area.
Further, the constructing the shape solid index of each color extension area according to the number of corner points on the edge of each color extension area, the length of each turning edge and the angle of each turning angle includes:
for each color extension area, calculating the ratio of the length of each turning edge in the color extension area to the degree of each corresponding turning angle, calculating the sum of the ratios of all turning edges, calculating the product of the sum and the number of corner points on the edge of the color extension area, and taking the product as the shape solid index of the color extension area.
Further, the construction of the texture style stereo index of the artistic outcome image according to the shape stereo index and the edge stereo index of each color extension area in the gray artistic image comprises the following steps:
calculating the product of the shape solid index and the edge solid index of each color extension area in the gray artistic image, calculating the sum value of the product of all the color extension areas, taking the opposite number of the sum value as the index of an exponential function taking a natural constant as a base, calculating the difference value between 1 and the calculation result of the exponential function, and taking the difference value as the texture solid index of the artistic result image.
Further, the constructing a local style shift index of each block according to the color application vividness index and the texture style stereo index of each block and the artistic outcome image comprises:
for each block, calculating the absolute value of the difference between the color application vividness index of the block and the color application vividness index of the artistic result image, recording the absolute value as a first absolute value of the difference, calculating the absolute value of the difference between the texture style three-dimensional index of the block and the texture style three-dimensional index of the artistic result image, recording the absolute value as a second absolute value of the difference, calculating the sum of the absolute value of the first difference and the absolute value of the second difference, and taking the sum as the local style offset index of the block.
Further, the constructing the adaptive smoothing parameters of each block according to the color application vividness index, the texture style stereo index and the local style offset index of each block of the artistic result image comprises:
for each block, calculating the product of the color application vivid index and the texture style three-dimensional index of the artistic result image, taking the opposite number of the product as the index of an exponential function based on a natural constant, calculating the difference value between 1 and the calculation result of the exponential function, and taking the product of the difference value and the local style deviation index of the block as the self-adaptive smoothing parameter of the block.
The invention has at least the following beneficial effects:
comprehensively considering the brightness change and the color change characteristics of the artistic result image, and acquiring a color channel difference index between pixel points and a color application vividness index of the artistic result image according to the artistic result image and the gray artistic image to evaluate the color contrast degree of the artistic result image, thereby improving the accuracy of evaluating the color application vividness degree of the artistic result image; dividing a color extension area according to color channel difference indexes among pixel points, comprehensively considering the straightness degree of edge lines of the color extension area and the difference of two sides of the edge lines, and acquiring an edge three-dimensional index of the color extension area according to the color channel difference indexes among the pixel points on a parallel line segment and a turning edge and the edge straightness index of the color extension area, so as to evaluate the three-dimensional characteristics of lines of the color extension area and improve the accuracy of evaluating the three-dimensional characteristics of lines of an image of an artistic result; comprehensively analyzing the shape characteristics and the line characteristics in the artistic result image, and acquiring the texture style three-dimensional index of the artistic result image according to the degrees of all turning angles and the lengths of turning edges on each color extension area and combining the edge three-dimensional index to evaluate the artistic style of the artistic result image, thereby improving the reliability of the artistic style evaluation of the artistic result image; according to the texture style three-dimensional index and the color application vivid index of each block and the artistic result image, the self-adaptive smoothing parameters of each block are obtained, each block in the gray artistic image is respectively processed by using an NLM non-local mean filtering algorithm, so that an optimized artistic image is constructed, and the restoration effect of the artistic result image is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart showing steps of an artistic achievement display method based on computer image processing;
FIG. 2 is a schematic view of a turning edge and a turning angle;
FIG. 3 is a schematic diagram of parallel line segments;
fig. 4 is a schematic diagram of an adaptive smoothing parameter acquisition flow.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description is given below of the specific implementation, structure, characteristics and effects of the method for displaying the artistic achievement based on the computer image processing according to the invention with reference to the attached drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of the method for displaying the artistic result based on the computer image processing provided by the invention with reference to the accompanying drawings.
The present invention provides an artistic achievement display method based on computer image processing, and in particular provides an artistic achievement display method based on computer image processing, referring to fig. 1, the method comprises the following steps:
and S001, obtaining an artistic result image and a gray artistic image.
The painting is placed right in front of a CCD camera lens, a picture is kept vertical to the camera, the picture is filled up as much as possible, so that the details and definition of the picture are ensured, the painting is shot, an artistic result image is obtained, and due to the fact that the painting possibly has insufficient brightness and contrast, the artistic result image is adjusted by using a histogram equalization algorithm, and gray-scale treatment is carried out on the artistic result image, so that a gray-scale artistic image is obtained. The histogram equalization algorithm is a well-known technique, and this embodiment will not be described in detail.
Step S002, according to the artistic result image and the gray artistic image, obtaining a color channel difference index, dividing a color extension area, calculating an edge straight index, obtaining an edge three-dimensional index, dividing the artistic result image into blocks, and constructing a color application vividness index and a texture style three-dimensional index of each block of the artistic result image.
The pen touch, also known as texture, is often referred to as the trace of the pen in oil painting and gouache. The painting brush can show the object texture, the volume sense and the drawing capability of the shadow deficiency and excess by means of the thickness contrast of the pigment, the shade change of the blending agent, the light and heavy force of the pen, the fast and slow rhythm of the painting brush and the feeling of the point dyeing, different strokes feel different expression characteristics, become natural exposure of painters' characters and artistic inheritance, and represent the artistic style and personality characteristics of the painters. Therefore, the whole artistic style of the artistic outcome image needs to be analyzed before the artistic outcome image is restored.
Different artistic styles have obvious differences in color application. For example, baroque art emphasizes contrast sharp shades, creating dramatic effects; modern art is more focused on the pure nature and emotional expression of colors.
In order to analyze the color style of the whole gray art image, the Sobel operator is used to obtain the gradient amplitude values of all the pixels in the gray art image, and the color application vividness index of the gray art image is expressed as follows according to the pixel values of all the pixels in the artistic result image on three channels and the gradient amplitude values of all the pixels in the gray art image:
wherein,applying vividness index to color of artistic result image, < ->Image color for artistic result imageColor difference index (DOI)>Is the first part of the artistic result image>Pixel dot and +.>Color channel difference index of each pixel, < ->Representing +.>The number of the combination of every two pixel points, < >>For the maximum value of gray values of all pixel points in the gray artistic image, < >>Is the minimum value of the gray values of all pixel points in the gray art image,is the number of pixels in the artistic result image, < >>Is the>Gradient magnitude of individual pixels.
、/>Respectively is the +.>Each pixel point,First->Pixel value of each pixel point on red channel, ">、/>Respectively is the +.>Individual pixel, th->Pixel value of each pixel point on the green channel,>、/>respectively is the +.>Individual pixel, th->Pixel values for each pixel point on the blue channel.
When the pixel value difference of the two pixel points on the same color channel is larger, the color difference of the two pixel points is larger, and the color channel difference index value is larger; when the difference between the gray maximum value and the gray minimum value of all the pixel points in the artistic result image is larger, and the color channel difference index between the pixel points is larger, the color change span in the artistic result image is larger, and the image color difference index value is larger; when the image color difference index of the pixel point is larger, and the gradient amplitude of each pixel point in the artistic result image is larger, the color change in the artistic result image is more obvious, and the color application vivid index value is larger.
Different artistic styles may also differ significantly in shape and line. For example, stereoscopically emphasizes geometric and multi-angle displays, lines and shapes with distinct edges and corners often appear in the work; the impression style works pay more attention to the change and fluidity of the expressed light, and the lines are softer and more fuzzy.
In order to analyze the overall line and shape style of the artistic image, a random function is used to randomly select the gray artistic imageThe pixel points are used as seed points of an area growth algorithm, the color channel difference index between the two pixel points is used as a growth criterion, and the area growth algorithm is used for obtaining +_ in the gray artistic image>Growth region, will->The growth region is taken as->Color extension area->The value implementation can be selected by the user, in this embodiment +.>10.
Detecting the corner points of the edges of each color extension area by adopting a Harris corner detection algorithm, randomly selecting one corner point of the edges of each color extension area by using a random function as a starting corner point, numbering all the corner points of the edges of each color extension area from the starting corner point along the clockwise direction of the edge line of the color extension area, forming an edge line for any two adjacent corner points of the edges of the color extension area, marking the connection line between the two adjacent corner points as a turning edge of the edge line, marking the included angle between the turning edge and the adjacent following turning edge as the turning angle of the turning edge, and the turning angle schematic diagram is shown in figure 2.
According to the Euclidean distance from all the pixel points on each edge line to the turning edge and the difference between the number of the pixel points on the turning edge and the number of the pixel points on the edge line, the edge straight index of each edge line is expressed as follows:
wherein,is->Edge straight index of edge line corresponding to the mth turning edge of the color extension area, +.>Is an exponential function based on natural constants, < ->Is->The number of pixel points on the edge line corresponding to the m-th turning edge of the color extension area, +.>Is->The +.>The number of pixel points on the turning edge of the strip, < >>Is->The m-th turning edge of the color extension areaCorresponding edge line +.>The number of pixels in a pixel is one,is->M-th turning edge of color extension area, < >>Representing the euclidean distance from the point to the line.
When the distance from each pixel point on the edge line to the turning edge is smaller and the difference between the number of the pixel points on the turning edge and the number of the pixel points on the edge is smaller, the edge line between two corner points is more likely to be a straight line, the edge straight index value is larger, and the whole style of the artistic result image is more likely to be biased towards stereology.
Stereoscopy pursues the presentation of objects in geometric and multi-angle viewing angles, emphasizing the stereoscopic and spatial perception of the depicted objects. In stereotactic painting, the line looks more stereoscopic by applying the change of shadows and light on both sides of the line, while also being able to highlight the shape of the object.
In order to analyze the three-dimensional characteristics of two sides of a line in an artistic result image, the distance between the line and the turning edge is as followsIs marked as double-sided parallel lines, and the double-sided parallel lines far from the center point of the smallest circumscribed rectangle of the color extension area are marked as parallel edges +.>Can be selected by the user, in this embodiment +.>For color extension area minimum bounding rectangle width +.>For two corner points on the turning edge, each corner point is taken as an auxiliary corner point, a perpendicular line of the parallel edge is made by passing through the auxiliary corner point, the perpendicular foot is taken as a parallel cutting point, a line segment between two parallel cutting points on the same parallel edge is marked as a parallel line segment, the length of the parallel line segment is the same as that of the turning edge, and a schematic diagram of the parallel line segment is shown in fig. 3.
Comprehensively considering the straightness degree of the edge line of the color extension area and the difference of two sides of the edge line, and according to the color channel difference index between the parallel line segments and the pixel points on the turning edge, combining the edge straightness index of the color extension area, and expressing the edge solid index of the color extension area as follows:
wherein,is->Edge solid index of individual color extension regions +.>Is->The number of corner points on the edge of the color extension area, < >>Is->Edge straight index of edge line corresponding to the mth turning edge of the color extension area, +.>Color channel difference index representing two pixel points>Is->The +.>The +.>Pixels>Is->The +.>The first line segment on the parallel line segment corresponding to the turning edge of the strip>Pixels>Is->The +.>The number of pixels on the edge of the bar break.
When the edge straight index of each edge line of the color extension area is higher, and the color channel difference index of the pixel points on the turning edge and the parallel line segments is larger, the color extension area is more likely to be a geometrical shape which is obviously compared with other areas, and the line of the artistic outcome image is more biased to the stereoscopic sense style.
The lines in the stereotactic image are typically straight or acute lines to delineate the edges and contours of the object. These lines will form sharp vertices at the junction, protruding the angle and edges of the object. In order to analyze the shape characteristics and the line characteristics in the artistic result image, the texture style solid index of the artistic result image is expressed as follows according to the degrees of all turning angles and the lengths of turning edges on each color extension area in combination with the edge solid index:
wherein,is the texture style three-dimensional index of the artistic outcome image, < >>Is an exponential function based on natural constants, < ->Is->Shape solid index of individual color extension regions +.>Is->Edge solid index of individual color extension regions +.>Is->The number of corner points on the edge of the color extension area, < >>Is->The +.>Length of strip turning edge +.>Is->The +.>The degree of the turning angle of the strip turning edge,the number of color extension areas in the artistic result image.
When the number of corner points on the edge of the color extension area is larger, the turning edge at each corner point is longer, and the degree of the turning angle is smaller, the sharper the vertex angle of the color extension area is, the more likely the corner angle is in a clear shape, and the larger the three-dimensional index value of the shape of the color extension area is; when the shape solid index and the edge solid index of the color extension area are larger, the color difference at two sides of the turning edge is larger, the color extension area is more likely to be a geometrical shape with clear edges and corners, and the whole style of the artistic result image is more favored to be stereoscopic.
In order to remove noise and enhance the artistic result image to different degrees according to the characteristics of different areas in the artistic result image, the gray artistic image is divided into the following partsIndividual blocks->Can be selected by the user, in this embodiment10, according to the color application vivid index and texture style solid index of the artistic result imageThe calculating method is used for obtaining the color application vivid index and the texture style three-dimensional index of each block.
Step S003, according to the texture style three-dimensional index and the color application vividness index of each block and the artistic result image, obtaining the self-adaptive smoothing parameters of each block, and processing each block in the artistic result image by using an NLM non-local mean filtering algorithm to construct an optimized artistic image.
According to the texture style three-dimensional index and the color application vivid index of each block and the artistic result image, the self-adaptive smoothing parameters of each block are expressed as follows:
wherein,is->Adaptive smoothing parameters for individual blocks, +.>Is an exponential function based on natural constants, < ->Applying vividness index to color of artistic result image, < ->Is the texture style three-dimensional index of the artistic result image,is->Local style offset index of individual tiles, +.>Is->The color of each segment uses a vivid index,is->Texture style stereo index of each block.
When the local style deviation index is larger, and the whole style of the artistic result image is more biased to the stereosense of strong color contrast and clear edges and corners, the damage degree on the artistic result image is probably higher, the whole contrast of the image is obvious, and in order to better repair a damaged area, a larger smoothing parameter is set, and the self-adaptive smoothing parameter value is larger; when the local style deviation index is smaller and the whole style of the artistic outcome image is more biased to the impression of weaker color pairs, the damage degree on the artistic outcome image is probably lower, the texture details of the whole image are more, smaller smoothing parameters are set for better retaining the detail information in the artistic outcome image, and the self-adaptive smoothing parameter values are smaller. A schematic diagram of the adaptive smoothing parameter acquisition process is shown in fig. 4.
And using the self-adaptive smoothing parameter of each block as the smoothing parameter of the NLM non-local mean filtering algorithm, processing each block in the gray artistic image by using the NLM non-local mean filtering algorithm to obtain a block optimized image, and combining the block optimized image into an optimized artistic image according to the arrangement mode in the artistic result image.
In this specification, each embodiment is described in a progressive manner, and the same or similar parts of each embodiment are referred to each other, and each embodiment mainly describes differences from other embodiments.
The above embodiments are only for illustrating the technical solution of the present application, and are not limiting; the technical solutions described in the foregoing embodiments are modified or some of the technical features are replaced equivalently, so that the essence of the corresponding technical solutions does not deviate from the scope of the technical solutions of the embodiments of the present application, and all the technical solutions are included in the protection scope of the present application.
Claims (10)
1. The artistic achievement display method based on computer image processing is characterized by comprising the following steps:
acquiring an artistic result image and a gray artistic image;
constructing color channel difference indexes of any two pixel points according to pixel values of each pixel point on three channels in an artistic result image; constructing an image color difference index of the artistic result image according to the gray values of the pixel points and the color channel difference indexes of any two pixel points in the artistic result image; constructing a color application vivid index of the artistic result image according to the gradient amplitude of the pixel points and the image color difference index of the artistic result image;
acquiring each growing area in the gray artistic image by using an area growing algorithm to serve as each color extending area; acquiring each edge line, each turning edge and each turning angle of each color extension area, and constructing an edge straight index of each edge line according to the number of pixel points on each edge line, each turning edge and the Euclidean distance between each pixel point on each edge line and the corresponding turning edge; constructing parallel line segments of all turning edges, and constructing edge solid indexes of all color extension areas according to edge straight indexes of all edge lines of all color extension areas and color channel difference indexes of two pixel points at corresponding positions on the turning edges and the parallel line segments; constructing a shape solid index of each color extension area according to the number of corner points on the edge of each color extension area, the length of each turning edge and the angle of each turning angle; constructing texture style three-dimensional indexes of an artistic result image according to the shape three-dimensional indexes and the edge three-dimensional indexes of various color extension areas in the gray artistic image;
dividing an artistic result image into a plurality of square blocks uniformly, and constructing local style offset indexes of the blocks according to the color application vivid indexes and texture style three-dimensional indexes of the blocks and the artistic result image; constructing self-adaptive smoothing parameters of each block according to the color application vividness index, texture style three-dimensional index and local style offset index of each block of the artistic result image; and obtaining an optimized artistic image by adopting an NLM non-local mean filtering algorithm according to the self-adaptive smoothing parameters of each block.
2. The computer image processing-based artistic outcome presentation method of claim 1, wherein said constructing a color channel difference index of any two pixels according to pixel values of each pixel on three channels in an artistic outcome image comprises:
for any two pixel points in an artistic result image, calculating the absolute value of the difference value of the pixel values of the two pixel points on a red channel, marking the absolute value as a first difference value, calculating the absolute value of the difference value of the pixel values of the two pixel points on a green channel, marking the absolute value as a second difference value, calculating the absolute value of the difference value of the pixel values of the two pixel points on a blue channel, marking the absolute value as a third difference value, calculating the sum value of the first difference value and the second difference value, and taking the sum value of the sum value and the third difference value as the color channel difference index of the two pixel points.
3. The computer image processing-based artistic effort presentation method of claim 2, wherein said constructing an image color difference index of an artistic effort image based on gray values of pixels and color channel difference indexes of any two pixels in the artistic effort image comprises:
and counting the maximum value and the minimum value of the gray values of all pixel points in the gray artistic image, calculating the absolute value of the difference value between the maximum value and the minimum value, calculating the average value of the color channel difference indexes of all any two pixel points in the artistic result image, and taking the product of the absolute value of the difference value and the average value as the image color difference index of the artistic result image.
4. The computer image processing based artistic effort presentation method of claim 1, wherein said constructing a color operational vividness index of an artistic effort image based on gradient magnitudes of pixels and an image color difference index of the artistic effort image comprises:
calculating the sum value of gradient amplitude values of all pixel points in the gray artistic image, calculating the product of the sum value and the image color difference index of the artistic result image, and taking the product as the color application vividness index of the artistic result image.
5. The method of claim 1, wherein the step of obtaining the edge lines, the turning edges and the turning angles of the color extension areas, and constructing the edge straight index of each edge line according to the number of the pixel points on each edge line, the number of the pixel points on each turning edge and the euclidean distance between each pixel point on each edge line and the corresponding turning edge, comprises:
detecting corner points of the edge of each color extension area, for any two adjacent corner points of the edge of the color extension area, forming an edge line by all edge pixel points between the two adjacent corner points, marking a connecting line between the two adjacent corner points as a turning edge of the edge line, and marking an included angle between the turning edge and the adjacent next turning edge as a turning angle of the turning edge;
counting the number of pixel points on the edge line, counting the number of pixel points on the turning edge of the edge line, counting the absolute value of the difference between the first number and the second number, counting the sum of Euclidean distances between all pixel points on the edge line and the corresponding turning edge, counting the product of the absolute value of the difference and the sum, taking the opposite number of the product as an index of an exponential function taking a natural constant as a base, and taking the calculation result of the exponential function as an edge straight index of the edge line.
6. The computer image processing-based artistic outcome presentation method of claim 1, wherein said constructing the edge three-dimensional index of each color extension area according to the edge straight index of each edge line of each color extension area and the color channel difference index of two pixel points at the corresponding positions on the turning edge and the parallel line segment comprises:
for each turning edge in each color extension area, calculating color channel difference indexes of two pixel points at corresponding positions on a parallel line segment corresponding to the turning edge and the turning edge, calculating the average value of the color channel difference indexes of all the two pixel points at the corresponding positions of the turning edge, calculating the product of the average value and the edge straight index of an edge line corresponding to the turning edge, calculating the sum value of the product corresponding to all the turning edges in the color extension area, and taking the sum value as the edge solid index of the color extension area.
7. The computer image processing based artistic outcome presentation method according to claim 1, wherein said constructing the shape solid index of each color extension area according to the number of corner points on the edge of each color extension area, the length of each turning edge, and the angle of each turning angle comprises:
for each color extension area, calculating the ratio of the length of each turning edge in the color extension area to the degree of each corresponding turning angle, calculating the sum of the ratios of all turning edges, calculating the product of the sum and the number of corner points on the edge of the color extension area, and taking the product as the shape solid index of the color extension area.
8. The method for displaying artistic effort based on computer image processing according to claim 1, wherein said constructing the texture style stereoscopic index of the artistic effort image according to the shape stereoscopic index and the edge stereoscopic index of each color extension area in the gray artistic image comprises:
calculating the product of the shape solid index and the edge solid index of each color extension area in the gray artistic image, calculating the sum value of the product of all the color extension areas, taking the opposite number of the sum value as the index of an exponential function taking a natural constant as a base, calculating the difference value between 1 and the calculation result of the exponential function, and taking the difference value as the texture solid index of the artistic result image.
9. The computer image processing based artistic effort presentation method of claim 1, wherein said constructing a local style shift index for each tile based on a color application vividness index and a texture style stereo index for each tile and an artistic effort image comprises:
for each block, calculating the absolute value of the difference between the color application vividness index of the block and the color application vividness index of the artistic result image, recording the absolute value as a first absolute value of the difference, calculating the absolute value of the difference between the texture style three-dimensional index of the block and the texture style three-dimensional index of the artistic result image, recording the absolute value as a second absolute value of the difference, calculating the sum of the absolute value of the first difference and the absolute value of the second difference, and taking the sum as the local style offset index of the block.
10. The computer image processing-based artistic effort presentation method of claim 1, wherein said constructing adaptive smoothing parameters for each tile based on color application vividness index, texture style stereo index, and local style shift index of each tile of an artistic effort image comprises:
for each block, calculating the product of the color application vivid index and the texture style three-dimensional index of the artistic result image, taking the opposite number of the product as the index of an exponential function based on a natural constant, calculating the difference value between 1 and the calculation result of the exponential function, and taking the product of the difference value and the local style deviation index of the block as the self-adaptive smoothing parameter of the block.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410239072.5A CN117853365B (en) | 2024-03-04 | 2024-03-04 | Artistic result display method based on computer image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410239072.5A CN117853365B (en) | 2024-03-04 | 2024-03-04 | Artistic result display method based on computer image processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117853365A true CN117853365A (en) | 2024-04-09 |
| CN117853365B CN117853365B (en) | 2024-05-17 |
Family
ID=90530517
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410239072.5A Active CN117853365B (en) | 2024-03-04 | 2024-03-04 | Artistic result display method based on computer image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117853365B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5093717A (en) * | 1987-08-03 | 1992-03-03 | American Film Technologies, Inc. | System and method for digitally coloring images |
| JP2007133347A (en) * | 2005-10-13 | 2007-05-31 | Seiko Epson Corp | Image display device, electronic apparatus and pixel location design method |
| CN102663806A (en) * | 2012-03-02 | 2012-09-12 | 西安交通大学 | Artistic-vision-based cartoon stylized rendering method of image |
| WO2020118902A1 (en) * | 2018-12-14 | 2020-06-18 | 深圳市华星光电半导体显示技术有限公司 | Image processing method and image processing system |
| CN111915507A (en) * | 2020-06-19 | 2020-11-10 | 西安理工大学 | Repair method for falling-off of mural |
| WO2020238970A1 (en) * | 2019-05-31 | 2020-12-03 | 杭州海康威视数字技术股份有限公司 | Image denoising device and image denoising method |
| CN114863492A (en) * | 2022-07-06 | 2022-08-05 | 北京圣点云信息技术有限公司 | Method and device for repairing low-quality fingerprint image |
| CN114863493A (en) * | 2022-07-06 | 2022-08-05 | 北京圣点云信息技术有限公司 | Detection method and detection device for low-quality fingerprint image and non-fingerprint image |
| WO2022199583A1 (en) * | 2021-03-26 | 2022-09-29 | 影石创新科技股份有限公司 | Image processing method and apparatus, computer device, and storage medium |
| CN116721106A (en) * | 2023-08-11 | 2023-09-08 | 山东明达圣昌铝业集团有限公司 | Profile flaw visual detection method based on image processing |
-
2024
- 2024-03-04 CN CN202410239072.5A patent/CN117853365B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5093717A (en) * | 1987-08-03 | 1992-03-03 | American Film Technologies, Inc. | System and method for digitally coloring images |
| JP2007133347A (en) * | 2005-10-13 | 2007-05-31 | Seiko Epson Corp | Image display device, electronic apparatus and pixel location design method |
| CN102663806A (en) * | 2012-03-02 | 2012-09-12 | 西安交通大学 | Artistic-vision-based cartoon stylized rendering method of image |
| WO2020118902A1 (en) * | 2018-12-14 | 2020-06-18 | 深圳市华星光电半导体显示技术有限公司 | Image processing method and image processing system |
| WO2020238970A1 (en) * | 2019-05-31 | 2020-12-03 | 杭州海康威视数字技术股份有限公司 | Image denoising device and image denoising method |
| CN111915507A (en) * | 2020-06-19 | 2020-11-10 | 西安理工大学 | Repair method for falling-off of mural |
| WO2022199583A1 (en) * | 2021-03-26 | 2022-09-29 | 影石创新科技股份有限公司 | Image processing method and apparatus, computer device, and storage medium |
| CN114863492A (en) * | 2022-07-06 | 2022-08-05 | 北京圣点云信息技术有限公司 | Method and device for repairing low-quality fingerprint image |
| CN114863493A (en) * | 2022-07-06 | 2022-08-05 | 北京圣点云信息技术有限公司 | Detection method and detection device for low-quality fingerprint image and non-fingerprint image |
| CN116721106A (en) * | 2023-08-11 | 2023-09-08 | 山东明达圣昌铝业集团有限公司 | Profile flaw visual detection method based on image processing |
Non-Patent Citations (4)
| Title |
|---|
| MUHAMMAD SHARIF: "A framework of human detection and action recognition based on uniform segmentation and combination of Euclidean distance and joint entropy-based features selection", 《SHARIF ET AL. EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING (2017)》, 19 September 2017 (2017-09-19) * |
| 张茗;: "论Photoshop在青铜文物修复做色过程中的运用", 上海工艺美术, no. 02, 15 June 2020 (2020-06-15) * |
| 李春生;袁玉珍;: "油画创作中计算机图像处理技术的应用", 电子测试, no. 11, 5 June 2013 (2013-06-05) * |
| 黄鹤;李昕芮;宋京;王会峰;茹锋;盛广峰;: "多尺度窗口的自适应透射率修复交通图像去雾方法", 中国光学, no. 06, 15 December 2019 (2019-12-15) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117853365B (en) | 2024-05-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107749077B (en) | Card ventilation grid shadow rendering method, device, equipment and medium | |
| Decaudin | Cartoon-looking rendering of 3D-scenes | |
| US7538779B2 (en) | Method of rendering pixel images from abstract datasets | |
| CN102098528B (en) | Method and device for converting planar image into stereoscopic image | |
| WO2017004882A1 (en) | Video 3d rendering method for flat display apparatuses | |
| CN103413340B (en) | The image stick figure generation method that the degree of depth strengthens | |
| CN103020917A (en) | Method for restoring ancient Chinese calligraphy and painting images on basis of conspicuousness detection | |
| CN104952102A (en) | Deferred shading-orientated uniform anti-aliasing method | |
| CN105787995B (en) | A kind of graphical image plane processing method | |
| CN117853365B (en) | Artistic result display method based on computer image processing | |
| WO2002056253A1 (en) | Method for representing color paper mosaic using computer | |
| KR100454070B1 (en) | Method for Real-time Toon Rendering with Shadow using computer | |
| Arpa et al. | Perceptual 3D rendering based on principles of analytical cubism | |
| CN113936080A (en) | Rendering method and device of virtual model, storage medium and electronic equipment | |
| Kim et al. | Automated hedcut illustration using isophotes | |
| Kennelly et al. | Non-photorealistic rendering and terrain representation | |
| Lien et al. | On preserving structure in stereo seam carving | |
| CN107481184B (en) | Low polygon style diagram generation interactive system | |
| CN110264564A (en) | A kind of video display style emulation mode based on colour atla mapping and Histogram Mapping | |
| Feldman et al. | Interactive 2D to 3D stereoscopic image synthesis | |
| Döllner et al. | Expressive virtual 3D city models | |
| Huang et al. | Generation of stereo oil paintings from RGBD images | |
| Chamaret et al. | Harmony-guided image editing | |
| Houit et al. | Video stippling | |
| CN108154485A (en) | A kind of ancient painting restorative procedure based on layering and stroke direction parsing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |