KR20180045164A - Reconstructing Method of Oil Painting Using Multi-Angle Photographing Image - Google Patents
Reconstructing Method of Oil Painting Using Multi-Angle Photographing Image Download PDFInfo
- Publication number
- KR20180045164A KR20180045164A KR1020160138983A KR20160138983A KR20180045164A KR 20180045164 A KR20180045164 A KR 20180045164A KR 1020160138983 A KR1020160138983 A KR 1020160138983A KR 20160138983 A KR20160138983 A KR 20160138983A KR 20180045164 A KR20180045164 A KR 20180045164A
- Authority
- KR
- South Korea
- Prior art keywords
- data
- height
- image data
- contrast
- mosaic
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/005—General purpose rendering architectures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/10—Constructive solid geometry [CSG] using solid primitives, e.g. cylinders, cubes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
- G06T7/507—Depth or shape recovery from shading
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
- G06T7/55—Depth or shape recovery from multiple images
- G06T7/557—Depth or shape recovery from multiple images from light fields, e.g. from plenoptic cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Computer Graphics (AREA)
- Software Systems (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to a method for restoring an oil painting using a multi-angle photographing image, and a method for restoring an oil painting using a multi-angle photographing image according to an embodiment of the present invention is a method for restoring an oil painting, Dividing into a plurality of zones of width; Performing image capturing at a plurality of different positions having different angles of each of the divided regions to generate image data; Generating mosaic contrast data by quantifying mosaic contrasts caused by differences in light and shade in the image data photographed at different angles for each zone; Analyzing a height of each of the zones by comparing the light and dark differences caused by the height of the brush-touch position of the image data and the data of the contrast data; Generating three-dimensional data having a height by mutually summing the positions of the image data to which the heights are applied; And restoring the three-dimensional data generated for each zone by arranging the three-dimensional data for each position to be one oil painting and using them as data for restoring oil painting.
Description
The present invention relates to a method of restoring an oil painting using a multi-angle photographing image, and more particularly, to a method of restoring an oil painting restoration method using a multi-angle photographing image, The present invention relates to a method for restoring an oil painting using a multi-angle photographing image that minimizes damage to a restoration target oil and reduces restoration costs by restoring only image data without using any restoration device.
Generally, emulsions are commonly recognized as two-dimensional images. However, from a more scrutiny point of view, the oil painting contains a large number of brush touches, each of which is distinct from the other brush touches. For example, each of the brushes has a unique height and color, creating a unique texture effect depending on the individual brushstick's oil paint thickness. Therefore, oil painting can be seen as a three-dimensional structure with various texture effects.
The oil painting uses oil painted with oil to express the painting on the canvas by the touch of a brush. The height of each brush touch is different between the brush touches, which is caused by the difference in thickness of the oil paint. This difference can be very fine.
Accordingly, the oil painting has a height by the brush touch, and when the two-dimensional image is analyzed and restored as in the conventional painting, the height can not be expressed by the brush touch, and accurate restoration is difficult.
Recently, in order to precisely express the texture effect due to the brush touch of the oil painting, a restoration method is used in which the texture of the brush touch of the oil painting is acquired as three-dimensional data using a laser scanner and the restoration is performed by the acquired data have.
In addition to requiring expensive laser scanner equipment, it is necessary to maintain the fixed state to scan the brush-touched surface while removing the frame when installing the scanning object in the scanning equipment for three-dimensional scanning. Therefore, .
Also, in order to express the texture effect when restoring the oil painting, there is a problem that the color of the oil is changed or the height is changed, so that the laser is likely to be altered.
Accordingly, there is a need for a technique capable of measuring the three-dimensional height data while using the photographing method used in the conventional two-dimensional restoration, thereby enabling the data of the texture of the oil painting to be saved while saving the cost.
SUMMARY OF THE INVENTION In order to solve the problems of the prior art described above, it is an object of the present invention to provide a method and apparatus for calculating a brightness difference of image data obtained by photographing restoration target oil in various angles, The present invention also provides a method of restoring an oil painting using a multi-angle photographing image that minimizes damage to the restoration target oil and restores the image data without using any restoration device.
The object of the present invention is not limited to the above-mentioned objects, and other objects not mentioned can be clearly understood from the following description.
According to an aspect of the present invention, there is provided a method for restoring oil-repellency using multi-angle photographed images according to one aspect of the present invention includes dividing a plurality of areas having predetermined widths according to sizes of oil- step; Performing image capturing at a plurality of different positions having different angles of each of the divided regions to generate image data; Generating mosaic contrast data by quantifying mosaic contrasts caused by differences in light and shade in the image data photographed at different angles for each zone; Analyzing a height of each of the zones by comparing the light and dark differences caused by the height of the brush-touch position of the image data and the data of the contrast data; Generating three-dimensional data having a height by mutually summing the positions of the image data to which the heights are applied; And restoring the three-dimensional data generated for each zone by arranging the three-dimensional data for each position to be one oil painting and using them as data for restoring oil painting.
In analyzing the height, when the height is analyzed for each zone, a deviation occurs in which the height difference of the mosaic contrast data continuously changed along the brush touch of the image data is increased or decreased out of a preset range And generating the moon-tune data from the image data generated by photographing in the step of generating the image data again. When the height deviation is removed from the moon-tone data, the three-dimensional data is generated in the three- Can be generated.
BRIEF DESCRIPTION OF THE DRAWINGS The above and other objects, features and advantages of the present invention will be more apparent from the following detailed description taken in conjunction with the accompanying drawings, in which: FIG.
The present invention may, however, be embodied in many different forms and should not be construed as being limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art. It is provided to fully inform the owner of the scope of the invention.
According to one aspect of the present invention, there is provided a method for restoring an oil painting using a multi-angle photographing image according to an embodiment of the present invention, which comprises calculating a brightness difference of image data obtained by photographing a restoration subject oil painting in various angles, It is possible to minimize the damage of the restoration target oil and restore the image data without using any restoration device, thereby reducing the restoration cost.
Also, according to the embodiment of the present invention, the method of restoring the emulsion using the multi-angle photographing image is characterized in that the emulsion is photographed from various angles and the brightness and contrast of the emulsion are analyzed by converting the difference in brightness and contrast, Dimensional data for reconstruction and restoration can be performed. Therefore, the restoration process can be simplified, and the restoration cost can be reduced by using the image data photographed by the camera.
FIG. 1 is a process diagram illustrating an emulsion recovery method using a multi-view image according to an exemplary embodiment of the present invention.
FIG. 2 is a usage state diagram illustrating a state in which the multi-angle oil painting is photographed in the image data generation step among the oil painting restoration methods using the multi-angle photographing image of FIG.
FIG. 3 is a flow chart for executing an oil restoration method using the multi-view image of FIG.
While the present invention has been described in connection with certain exemplary embodiments, it is to be understood that the invention is not limited to the disclosed embodiments, but, on the contrary, is intended to cover various modifications and similarities. It should be understood, however, that the invention is not intended to be limited to the particular embodiments, but includes all modifications, equivalents, and alternatives falling within the spirit and scope of the invention.
DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, the present invention will be described in detail with reference to the accompanying drawings. In addition, numerals (e.g., first, second, etc.) used in the description of the present invention are merely an identifier for distinguishing one component from another.
Also, in this specification, when an element is referred to as being "connected" or "connected" with another element, the element may be directly connected or directly connected to the other element, It should be understood that, unless an opposite description is present, it may be connected or connected via another element in the middle.
Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
FIG. 1 is a process diagram illustrating an emulsion recovery method using a multi-view image according to an exemplary embodiment of the present invention.
Referring to FIG. 1, in an embodiment of the present invention, an oil painting restoration method using multi-angle photographing images is performed by using three-dimensional data in image data photographed by a camera for restoration of oiliness having a height by a texture effect using oil paints .
The method for reconstructing an emulsion using a multi-angle photographic image includes a segmentation step S10 for dividing the image into a plurality of regions for image analysis, an image data generation step S20, a mosaic contrast data generation step S30, S40), a three-dimensional data generation step (S50), and a restoration execution step (S60).
The segmentation step S10 is a step of dividing into a plurality of regions having a preset width according to the size of the oil-based paint expressed by the brush texture with the oil-based paint.
In other words, the oil paint which expresses the texture effect of the oil paint on the brush touch has a large number of points bent by the brush touch, so that it is difficult to analyze the entire height of the oil paint. Divide the area.
The image data generation step S20 is a step of generating image data by photographing the divided regions at a plurality of different positions having different angles.
That is, considering the position of the light incident on each of the divided regions in a state where a plurality of regions are divided, when the height due to the brush touch is different due to the irradiation of light, a difference in brightness, which is shadow, is generated, In order to measure the exact contrast difference, a camera is used to capture images at different angles to generate image data.
FIG. 2 is a usage state diagram illustrating a state in which the multi-angle oil painting is photographed in the image data generation step among the oil painting restoration methods using the multi-angle photographing image of FIG.
Referring to FIG. 2, the
The moon-tune contrast data generation step S30 is a step of generating moon-tone contrast data by quantifying the moon-tone contrast caused by difference in light and shade in the image data photographed at different angles for each zone.
That is, in the image data photographed at different angles, the difference in brightness according to the height difference of the brush touch is calculated by using the numerical value of the contrast used in the computer program.
Here, the contrast data may be represented by data in the form of data obtained by digitizing the difference in color intensity according to each brightness and color saturation within a predetermined color range from a dark color to a light color in accordance with a difference in shadows in a typical computer program have.
In contrast, the contrast data of the myeonjo is darker as the height is higher in shadow form, and the difference of bright and dark as lower is generated in the images taken in various angles according to the height and the height generated by the brush touch. . That is, the contrast data for mosaic is generated by using numerical data of contrast difference, and since the height generated in the brush touch can be quantified, data capable of measuring the height can be specified only by the numerical value.
The height analysis step (S40) is a step of analyzing the height by contrasting the light and dark differences caused by the height of the brush-touch position of the image data and the contrast of the mosaic data.
That is, the height of the digitized mosaic data and the image data are compared with each other, and the height generated by the brush-touch in the image data is generated as a mosaic data, and the height is compared with the mosaic data according to the shape and height of the image data. do.
If a deviation occurs in which the difference in height of the mosaic contrast data continuously changing along with the brush touch of the image data is increased or decreased when the height is analyzed in the height analysis step S40, The height can be analyzed in a state in which height deviation is removed from the contrast data through the mosaic contrast generation step S30 from the image data generated by photographing in the generation step S20.
In other words, the brushstroke with the height represented by the shape of the image data in the oil painting is painted with the brush, so that the contrast data obtained by photographing at various angles according to the continuous height in one shape is not continuous, If a deviation of more than a predetermined value occurs, it means that distortion occurs at the time of photographing, and the photographing is performed again until the deviation is removed, so that the brightness contrast data can be regenerated to analyze the height.
The three-dimensional data generation step S50 is a step of generating three-dimensional data having a height by mutually summing the positions of the image data to which the analyzed heights are applied.
That is, the height is analyzed, and the height data is combined with the position of each shape to generate 3D data, which can be analyzed by a computer for restoration.
The restoration execution step S60 is a step of restoring the three-dimensional data generated for each zone by using the restoration data as restoration data for restoring the oil painting by arranging the three-dimensional data for each position to be one oil painting.
FIG. 3 is a flow chart for executing an oil restoration method using the multi-view image of FIG.
Referring to FIG. 3, the
The
The
The
If there is a deviation in the analyzed height at the position where the shape of the image data is consecutive at the
The
The
The foregoing description is merely illustrative of the technical idea of the present invention, and various changes and modifications may be made by those skilled in the art without departing from the essential characteristics of the present invention.
Therefore, the embodiments disclosed in the present invention are intended to illustrate rather than limit the scope of the present invention, and the scope of the technical idea of the present invention is not limited by these embodiments.
The scope of protection of the present invention should be construed according to the following claims, and all technical ideas within the scope of equivalents should be construed as falling within the scope of the present invention.
Claims (2)
Performing image capturing at a plurality of different positions having different angles of each of the divided regions to generate image data;
Generating mosaic contrast data by quantifying mosaic contrasts caused by differences in light and shade in the image data photographed at different angles for each zone;
Analyzing a height of each of the zones by comparing the light and dark differences caused by the height of the brush-touch position of the image data and the data of the contrast data;
Generating three-dimensional data having a height by mutually summing the positions of the image data to which the heights are applied; And
And restoring the three-dimensional data generated by each zone by using the restored data for restoring the oil painting by arranging the three-
Reconstruction Method of Emulsion Using Multi - angle Photographed Images.
In the step of analyzing the height,
When the deviation of the height difference of the mosaic contrast data that continuously changes along the brush touch of the image data is increased or decreased due to the deviation of the height difference from the preset range when the height is analyzed for each zone, Generating three-dimensional data in the three-dimensional data generation step when the height contrast is removed from the mosaic contrast data through the step of generating the mosaic contrast data from the image data generated by photographing
Reconstruction Method of Emulsion Using Multi - angle Photographed Images.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020160138983A KR20180045164A (en) | 2016-10-25 | 2016-10-25 | Reconstructing Method of Oil Painting Using Multi-Angle Photographing Image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020160138983A KR20180045164A (en) | 2016-10-25 | 2016-10-25 | Reconstructing Method of Oil Painting Using Multi-Angle Photographing Image |
Publications (1)
Publication Number | Publication Date |
---|---|
KR20180045164A true KR20180045164A (en) | 2018-05-04 |
Family
ID=62199978
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
KR1020160138983A KR20180045164A (en) | 2016-10-25 | 2016-10-25 | Reconstructing Method of Oil Painting Using Multi-Angle Photographing Image |
Country Status (1)
Country | Link |
---|---|
KR (1) | KR20180045164A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2024040964A1 (en) * | 2022-08-22 | 2024-02-29 | 华为技术有限公司 | Recognition model training method and apparatus, and movable intelligent device |
-
2016
- 2016-10-25 KR KR1020160138983A patent/KR20180045164A/en unknown
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2024040964A1 (en) * | 2022-08-22 | 2024-02-29 | 华为技术有限公司 | Recognition model training method and apparatus, and movable intelligent device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9773302B2 (en) | Three-dimensional object model tagging | |
US20170308736A1 (en) | Three dimensional object recognition | |
DE102015005267B4 (en) | Information processing apparatus, method therefor and measuring apparatus | |
JP7253323B2 (en) | Three-dimensional measurement system and three-dimensional measurement method | |
JP5972498B2 (en) | Edge detection apparatus, edge detection method and program | |
JP6899189B2 (en) | Systems and methods for efficiently scoring probes in images with a vision system | |
KR101032446B1 (en) | Apparatus and method for detecting a vertex on the screen of a mobile terminal | |
JP6418884B2 (en) | Three-dimensional measuring apparatus, three-dimensional measuring method and program | |
CN110879131B (en) | Imaging quality testing method and imaging quality testing device for visual optical system, and electronic apparatus | |
JP2018128309A (en) | Crack detection method | |
TWI512284B (en) | Bubble inspection system for glass | |
JP2018128316A (en) | Crack detection method | |
JP2013002839A (en) | Crack detection method | |
WO2015115499A1 (en) | Tool inspection method and tool inspection device | |
JP6800676B2 (en) | Image processing equipment, image processing methods and programs | |
KR20180045164A (en) | Reconstructing Method of Oil Painting Using Multi-Angle Photographing Image | |
CN115184362B (en) | Rapid defect detection method based on structured light projection | |
JP2018128315A (en) | Crack detection method | |
US11127132B2 (en) | Method and device for multiple edge detection | |
JP5157575B2 (en) | Defect detection method | |
Li et al. | High-quality fringe pattern generation based on binary pattern optimization with projector defocusing | |
Lin | Resolution adjustable 3D scanner based on using stereo cameras | |
TWI510776B (en) | Bubble inspection processing method for glass | |
DE102015101079A1 (en) | SYSTEM AND METHOD FOR DETERMINING 3D SURFACE FEATURES AND IRREGULARITIES ON AN OBJECT | |
JP7289727B2 (en) | Image processing device, image processing method and program |