Method for extracting high quality line structure based on cartoon film

Method for automatically evaluating synthetic quality of image based on image library

The invention discloses a method for automatically evaluating the synthetic quality of an image based on an image library. The method allows users to designate the image category of synthetic objects and synthetic location thereof from a classified image library which labels the objects of the images; labeled regions are processed to obtain the integrated region of synthetic objects; super image element in the integration region is partitioned; local self-defined synthetic energy of each partitioned region is calculated to obtain an enclosed minimum energy route, namely, the optimum syntheticroute; the total synthetic energy of each group of images to be synthesized is calculated and the synthetic quality of images to be synthesized is evaluated. Based on the image library, the method ensures optimal effect of synthetic images within the scope of selected images; the synthetic quality of two corresponding super image elements in the integration region is well evaluated by the local self-defined ...

Colorful optical grating image or video vectorization method

The present invention provides a vectorization method of color raster image or video, belonging to video image processing field, the invention includes following steps: a. firstly, the image or video is cut into four connecting regions according to the color information; b. subvoxel accuracy shared boundary of the cutting region is calculated; c. node of the boundary is determined, including shared boundary point of two or more regions and local curvature extremal point on the boundary; d. the sequences between nodes are processed fitting by spline curve and the straight line; e. the boundary of vectorization region is represented by the obtained curve and straight line; f. color of vectorization region is represented by the color mode; g. vectorization image or video is obtained. The vectorization method overcomes fault of the vectorization method of the traditional image or video, the vectorization result of the invention automatically makes the raster image or video acquire better vectorization ...

Method and device for processing image and video image frame

The invention discloses a method and a device for processing an image. The method comprises the following steps of: determining the H component value distribution of pixel points included by a reference image and determining a replacement H component value of each pixel point of an original image according to the H component value distribution, wherein the determined replacement H component value is closer to the H component value distribution than the H component value distribution of each pixel point of the original image; and generating a processed image according to the replacement H component value of each pixel point of the original image. The style of the processed image is closer to that of the reference image and processing efficiency is higher. The invention also discloses a video processing method and a video processing device. The video processing method comprises the following steps of: determining a replacement pixel value of a pixel point of an image frame according to the ...

Image synthesis method and apparatus based on mixed gradient field and mixed boundary condition

The present invention discloses an image synthesis method and apparatus based on mixed gradient field and mixed boundary condition, the method includes: acquiring a source image and a target image and a position of target image synthesized by object in the source image; acquiring outline of the object to be synthesized in the source image; getting a fusion area by expanding the outline; dividing the fusion area into two kinds according to differences of the source image and the target image in texture and color; choosing different gradient field and different boundary condition for the two kinds of areas, and obtaining a intermediate result by solving the poisson equation of the mixed boundary condition; proceeding transparency fusion to the intermediate result and the target image of one kind area, the other areas using the results solved by the poisson equation to synthetize final image. The invention can use accurate boundary of the synthesized object to reduce synthesis error, and can ...

Colorful optical grating image or video vectorization method

The present invention provides a vectorization method of color raster image or video, belonging to video image processing field, the invention includes following steps: a. firstly, the image or video is cut into four connecting regions according to the color information; b. subvoxel accuracy shared boundary of the cutting region is calculated; c. node of the boundary is determined, including shared boundary point of two or more regions and local curvature extremal point on the boundary; d. the sequences between nodes are processed fitting by spline curve and the straight line; e. the boundaryof vectorization region is represented by the obtained curve and straight line; f. color of vectorization region is represented by the color mode; g. vectorization image or video is obtained. The vectorization method overcomes fault of the vectorization method of the traditional image or video, the vectorization result of the invention automatically makes the raster image or video acquire better vectorization ...

Image synthesis method and apparatus based on mixed gradient field and mixed boundary condition

The present invention discloses an image synthesis method and apparatus based on mixed gradient field and mixed boundary condition, the method includes: acquiring a source image and a target image anda position of target image synthesized by object in the source image; acquiring outline of the object to be synthesized in the source image; getting a fusion area by expanding the outline; dividing the fusion area into two kinds according to differences of the source image and the target image in texture and color; choosing different gradient field and different boundary condition for the two kinds of areas, and obtaining a intermediate result by solving the poisson equation of the mixed boundary condition; proceeding transparency fusion to the intermediate result and the target image of onekind area, the other areas using the results solved by the poisson equation to synthetize final image. The invention can use accurate boundary of the synthesized object to reduce synthesis error, andcan ...

Stroke direction determining method and device

The invention discloses a stroke direction determining method, which is used for determining the stroke direction from a stroke starting point when an image with an oil painting style is generated according to the original image. The method comprises the following steps of: obtaining a pixel value of each pixel point of the original image and determining the gradient of each pixel point according to the pixel value; determining a neighborhood pixel point of each pixel point according to a set neighborhood range in the original image; modifying the gradient of a pixel point X to obtain a vector field of the pixel point X according to the vector field of a neighborhood pixel point of each pixel point X in the original image, wherein the original value of the vector field of the neighborhood pixel point is taken as the gradient of the neighborhood pixel point; and determining the vector field direction of the vector field of the pixel point corresponding to the stroke starting point as the ...

Method for automatically withdrawing draft-based network graphics primitives and system thereof

The invention discloses a method for automatically withdrawing draft-based network graphics primitives. The method consists of the following steps: firstly, receiving keywords and drafts of target-describing graphics primitives input by subscribers and then acquiring a set of corresponding pictures according to keywords; utilizing visual attention calculation to analyze the visual attention area of each picture; taking the visual attention area as the initial value and acquiring a set of initial graphics primitives by an image withdrawing method; finally ordering the acquired initial graphics primitives according to the matching degree of keywords and drafts and selecting a plurality of graphics primitives with high matching degree as the target graphics primitives. The invention also discloses a system for automatically withdrawing draft-based network graphics primitives. The invention can automatically acquire the graphics primitives expected by subscribers according to keywords and drafts ...

Stroke direction determining method and device

The invention discloses a stroke direction determining method, which is used for determining the stroke direction from a stroke starting point when an image with an oil painting style is generated according to the original image. The method comprises the following steps of: obtaining a pixel value of each pixel point of the original image and determining the gradient of each pixel point accordingto the pixel value; determining a neighborhood pixel point of each pixel point according to a set neighborhood range in the original image; modifying the gradient of a pixel point X to obtain a vector field of the pixel point X according to the vector field of a neighborhood pixel point of each pixel point X in the original image, wherein the original value of the vector field of the neighborhoodpixel point is taken as the gradient of the neighborhood pixel point; and determining the vector field direction of the vector field of the pixel point corresponding to the stroke starting point as the stroke ...

Method for vaporizing anti form liquid of pentaerythritol by using rising film evaporator with forced circulation

Method for automatically generating China ink and wash animations base on water stream structural diagram

The invention relates to an automatic generation method of Chinese ink-wash painting animations based on a water flow structural chart, which pertains to the video processing technical field. The method comprises the following steps: a. the ink-wash lines of the existing ink-wash painting animations are extracted; b. parameters of strokes of ink-wash water flow are counted; c. a library of various styles of templates of ink-wash lines is established; and step c' 'water flow structural chart based on true video is inputted' and then enters into the next step simultaneously; d. various styles of ink-wash strokes are drawn; e. the backgrounds are synthesized, the ink-wash lines of water flows and processed ink-wash styled backgrounds are merged into a whole, and the video results of ink-wash animations are outputted; f. the varying of angle of view of the original video is restored, and an ink-wash styled painting video that is the same with the angle of view of the original video is obtained ...

一种高温调剖剂及其制备方法和用途

... 本发明公开了一种高温调剖剂及其制备方法和用途，其由甲醛、苯酚、硅酸钠制备而成，其中甲醛与苯酚的摩尔比为2.5-3.5∶1，硅酸钠含量为5-15％(重量)。其制备步骤包括甲醛、苯酚搅拌反应及与硅酸钠水溶液反应而成。该高温调剖剂用于油井的高温化学堵水和注蒸汽井的高温调剖。 ...

High temp profile control agent and its preparation method as well as usage

A high-temp blocking regulator for oil well is prepared from formaldehyde, phenol and sodium silicate through stirring formaldehyde with phenol and reaction between resultant mixture and aqueous solution of sodium silicate.

System and method for automatic creating data gridding of stratum and fault

Method for automatically generating waterflow strictire chart of real waterflow video

The invention relates to an automatic generation method of the water flow structural chart of real water flow videos, which pertains to the field of video processing technology and computer visual method. The generation method comprises the following steps: a. an image containing water flow video is inputted; b. optic flows are preliminarily estimated; c. water flow areas and background areas are divided; d. the video is varied by removing the angle of view; e. whether the varying of angle of view and the water flow area is converged are judged, if not, step b is repeated; if so, step f is carried out; f. panoromic videos with fixed angle of view are generated; g. the optic flow is optimized by iteration-interpolation algorithm; h. the water flow structural lines are picked up and the water flow structural chart is finally acquired. The method of the invention overcomes the shortcomings of roughness and imprecision, and the generated water flow structural lines thereof can truly reflect ...

Method for automatically evaluating synthetic quality of image based on image library

The invention discloses a method for automatically evaluating the synthetic quality of an image based on an image library. The method allows users to designate the image category of synthetic objects and synthetic location thereof from a classified image library which labels the objects of the images; labeled regions are processed to obtain the integrated region of synthetic objects; super image element in the integration region is partitioned; local self-defined synthetic energy of each partitioned region is calculated to obtain an enclosed minimum energy route, namely, the optimum synthetic route; the total synthetic energy of each group of images to be synthesized is calculated and the synthetic quality of images to be synthesized is evaluated. Based on the image library, the method ensures optimal effect of synthetic images within the scope of selected images; the synthetic quality of two corresponding super image elements in the integration region is well evaluated by the local self-defined ...

Method for extracting high quality line structure based on cartoon film

A high-quality line structure extraction method based on cartoons belongs to the image processing technology field. The method comprises steps of, a, image pre-processing: removing image noise by a bilinear filtering method; b, reinforcing the line structure by a second-order Gauss template convolution method; c, obtaining isolated line points by restraining non-maximal values on the reinforced image; d, line structure acquiring: selecting a biggest-response point as an initial enlarging point by a best and prepreference manner, enlarging the point to the two sides so as to obtain the line structure with line strips; e, repairing the result based on semantic information. According to the method, vector elements with more semantic information can be obtained, and inter-frame continuity and inter-frame association quality can be increased during the vectorization process of the cartoons.

Method for automatically withdrawing draft-based network graphics primitives and system thereof

The invention discloses a method for automatically withdrawing draft-based network graphics primitives. The method consists of the following steps: firstly, receiving keywords and drafts of target-describing graphics primitives input by subscribers and then acquiring a set of corresponding pictures according to keywords; utilizing visual attention calculation to analyze the visual attention area of each picture; taking the visual attention area as the initial value and acquiring a set of initial graphics primitives by an image withdrawing method; finally ordering the acquired initial graphicsprimitives according to the matching degree of keywords and drafts and selecting a plurality of graphics primitives with high matching degree as the target graphics primitives. The invention also discloses a system for automatically withdrawing draft-based network graphics primitives. The invention can automatically acquire the graphics primitives expected by subscribers according to keywords anddrafts ...

Process for the separating prospect background of 2D cartoon animation

A foreground and background separating method for a 2D cartoon, belonging to the image processing technology field, comprises steps of: a, dividing frames of images based on colors into a plurality of areas; b, performing video alignment on each frame of images; c, video visual angle transformation removing and generating of a panoramic video: removing the visual angle transformation of a video, and obtaining a panoramic video with a fixed visual angle; d, constructing initial background images; e, calculating background probabilities of all areas; f, descending-ordering the areas based on the background probabilities to create an area queue; g, judging whether the background probability of a first area in the area queue is larger than or equal to a threshold value, if it is, entering h orderly, and if not, exiting from the circulation and entering i; h, extracting the first area from the area queue to optimize the background image; i, judging the areas remaining in the queue as foreground ...

Method for automatically generating waterflow strictire chart of real waterflow video

The invention relates to an automatic generation method of the water flow structural chart of real water flow videos, which pertains to the field of video processing technology and computer visual method. The generation method comprises the following steps: a. an image containing water flow video is inputted; b. optic flows are preliminarily estimated; c. water flow areas and background areas aredivided; d. the video is varied by removing the angle of view; e. whether the varying of angle of view and the water flow area is converged are judged, if not, step b is repeated; if so, step f is carried out; f. panoromic videos with fixed angle of view are generated; g. the optic flow is optimized by iteration-interpolation algorithm; h. the water flow structural lines are picked up and the water flow structural chart is finally acquired. The method of the invention overcomes the shortcomings of roughness and imprecision, and the generated water flow structural lines thereof can truly reflect ...

Grounder dividing algorithm based on Mark

The invention discloses a rolling ball segmentation algorithm based on Mask and belongs to the video image processing technical field. The method is operated according to the following steps that: Mask of a selected image is extracted; a ball with enough large initial radius is preset; rolling is made in a region that Mask surrounds; the region is grown according to a color model; the size of the radius of the ball is reduced; the reduction is made until the radius of the ball is reduced to the size of a pixel; thus all unknown regions can be rolled by the ball, thereby obtaining the segmentation of the whole image. With the rolling ball model, the problem of the unclosed boundary of the Canny algorithm is solved. With the growth algorithm, the segmentation of the complex color model can be realized. The rolling ball model and the growth algorithm of the method can both be efficiently realized, so the algorithm has quick speed, and only spends not more than one second when a cartoon picture ...

Method and device for processing image and video image frame

The invention discloses a method and a device for processing an image. The method comprises the following steps of: determining the H component value distribution of pixel points included by a reference image and determining a replacement H component value of each pixel point of an original image according to the H component value distribution, wherein the determined replacement H component valueis closer to the H component value distribution than the H component value distribution of each pixel point of the original image; and generating a processed image according to the replacement H component value of each pixel point of the original image. The style of the processed image is closer to that of the reference image and processing efficiency is higher. The invention also discloses a video processing method and a video processing device. The video processing method comprises the following steps of: determining a replacement pixel value of a pixel point of an image frame according to the ...

Virtual oil-layer natural simulation system and method