CN108985272B - High-reliability painting and calligraphy filing and authenticating method based on fusion of reflection and perspective images - Google Patents
High-reliability painting and calligraphy filing and authenticating method based on fusion of reflection and perspective images Download PDFInfo
- Publication number
- CN108985272B CN108985272B CN201810939647.9A CN201810939647A CN108985272B CN 108985272 B CN108985272 B CN 108985272B CN 201810939647 A CN201810939647 A CN 201810939647A CN 108985272 B CN108985272 B CN 108985272B
- Authority
- CN
- China
- Prior art keywords
- image
- matching
- painting
- calligraphy
- characteristic
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/80—Recognising image objects characterised by unique random patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
Abstract
The invention discloses a high-reliability painting and calligraphy filing and authenticating method based on reflection and perspective image fusion.A device used in the method comprises a work box with black inner wall, an upper layer flat light source, a lower layer flat light source, a wide-view camera and a micro camera; the computer can shoot the reflection texture image and the perspective texture image by controlling the time-sharing illumination of the upper and lower layers of flat light sources, and the reliability of identity verification is improved by fusing different images. The method comprises a filing stage and an authentication stage. The invention integrates two texture images of reflection and perspective and finally adopts surface characteristics for matching, thereby not only improving the reliability of the painting and calligraphy authentication, but also reducing the requirements of the painting and calligraphy authentication on the use environment.
Description
Technical Field
The invention relates to a painting and calligraphy filing and authenticating method, in particular to a high-reliability painting and calligraphy filing and authenticating method based on fusion of reflection and perspective images.
Background
The current painting and calligraphy filing and authenticating method usually carries out matching by shooting fine textures on the surface of the painting and calligraphy works, extracting characteristic points (such as SIFT) of texture images of the painting and calligraphy works, and determining whether the matching is successful or not according to the matching consistency degree of the characteristic points. However, such methods have the following disadvantages:
(1) the punctate feature of the texture image similar to SIFT may be affected by external conditions and the like to be unstable, and the matching is adversely affected;
(2) only the texture characteristics of the surface of the paper are utilized, and the fiber distribution characteristics in the paper are not fully utilized, so that the authentication reliability is influenced.
Disclosure of Invention
In order to solve the defects of the technology, the invention provides a high-reliability painting and calligraphy filing and authenticating method based on the fusion of reflection and perspective images.
In order to solve the technical problems, the invention adopts the technical scheme that: a high-reliability painting and calligraphy filing and authenticating method based on fusion of reflection and perspective images uses equipment comprising a working box with black inner wall; the lower end of the working box is provided with a working table, and the upper end of the working table is provided with a lower flat light source; a transparent glass plate is arranged above the lower flat light source, and the painting and calligraphy works are flatly laid on the transparent glass plate; the upper end of the working box is provided with an upper flat light source; a wide-view camera is arranged in the middle of the lower end of the upper flat light source; a movable bracket is arranged on the inner side wall of the working box, and a microscopic camera is fixedly arranged on the movable bracket; the computer is used for controlling the movement and the matching of the microscopic images, and can shoot the reflection texture images and the perspective texture images by controlling the time-sharing illumination of the upper and lower layers of flat light sources and improve the reliability of identity verification through different image fusion;
the method comprises the following overall steps:
firstly, a filing stage:
a. only turning on the upper flat light source for illumination, and shooting the whole reflection image of the painting and calligraphy works by using a wide-field camera to obtain painting and calligraphy samples; the shot breadth is required to cover most of the area of the painting and calligraphy works;
b. extracting feature points in the graph and obtaining respective feature attribute description of the feature points;
c. screening the characteristic points, and selecting a plurality of stable characteristic points more uniformly;
d. moving the microscopic camera to a selected characteristic point to shoot and enlarge an image, extracting the characteristic point of the image again according to the method and storing the characteristic point and description of the image;
e. selecting a block area with rich small blocks of textures as matching candidate positions in a blank area of the painting and calligraphy sample, storing the characteristic image and the original texture image after characteristic transformation, and marking offset positions and sizes of the small blocks;
f. closing the upper flat light source and opening the lower flat light source, shooting a perspective image, selecting a small block area with rich texture as a matching candidate position in a blank area of the painting and calligraphy sample, and storing the characteristic image and the original texture image after characteristic transformation;
g. repeating the process from e to f, and selecting a plurality of different microscopic feature matching candidate point positions;
h. storing the feature points and the attribute description, all the images, the feature image blocks and the offset positions and sizes of the feature images and the original texture images into a set file directory, and recording the file directories as template image data;
II, authentication stage:
a. only turning on the upper flat light source for illumination, and shooting an integral reflection image of a painting and calligraphy sample to be authenticated by using a wide-field camera; the shot breadth covers most of the area of the painting and calligraphy image;
b. extracting feature points on the graph and obtaining respective feature attribute description of the feature points;
c. matching the characteristic points with the characteristic points in the painting and calligraphy samples, and if the number of successfully matched points is less than a set proportion, considering that the matching fails and quitting the authentication; otherwise, considering the matching to be successful, calculating the position, angle and scale deviation of the authentication image and the sample image, and continuing the next step;
d. moving the micro camera to a matching successful position, extracting image feature points of the position again, then matching the image feature points with the feature points in the template, and if the matching is successful, calculating the position, angle and scale deviation of the current sample image and the template; if the matching fails, the point is changed again and the operation is repeated;
e. closing the upper flat light source and opening the lower flat light source, and shooting a transmission image; correcting the current sample image and the position, angle and scale deviation of the current sample image and the template according to the matching result of the images to obtain a matching candidate image or a characteristic image block corresponding to the matching candidate position of the template; the characteristic image blocks are divided into reflection characteristic image blocks and transmission characteristic image blocks;
f. respectively moving the reflection characteristic image block and the transmission characteristic image block left and right to match with the characteristic image blocks corresponding to the template, and observing whether the matching degree exceeds a set threshold value; if yes, matching is successful; otherwise, the matching fails;
g. and selecting the matching points according to the reliability requirement, if the matching points are larger than the set proportion, considering that the consistency check is successful, and otherwise, considering that the consistency check is failed.
Further, the feature points include SIFT points, Surf points, and corner points.
The invention integrates two texture images of reflection and perspective and finally adopts surface characteristics for matching, thereby not only improving the reliability of the painting and calligraphy authentication, but also reducing the requirements of the painting and calligraphy authentication on the use environment.
Drawings
FIG. 1 is a schematic diagram of the structure of the apparatus used in the present invention.
FIG. 2 is a reflection texture image of a painting and calligraphy work.
FIG. 3 is a perspective texture image of the same location of the painting and calligraphy work of FIG. 2.
In the figure: 1. an upper flat light source; 2. a wide field of view camera; 3. moving the support; 4. a microscopic camera; 5. a transparent glass plate; 6. a lower flat light source; 7. a work table; 8. a work box.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and specific embodiments.
A high-reliability painting and calligraphy filing and authenticating method based on fusion of reflection and perspective images uses equipment as shown in figure 1, and comprises a work box with black inner wall; the lower end of the working box is provided with a working table, and the upper end of the working table is provided with a lower flat light source; a transparent glass plate is arranged above the lower flat light source, and the painting and calligraphy works are flatly laid on the transparent glass plate; the upper end of the working box is provided with an upper flat light source; a wide-view camera is arranged in the middle of the lower end of the upper flat light source; a movable bracket is arranged on the inner side wall of the working box, and a microscopic camera is fixedly arranged on the movable bracket; the computer is used for controlling the movement and the micro image matching, the computer can shoot a reflection texture image (shown in figure 2) and a perspective texture image (shown in figure 3) by controlling the time-sharing illumination of the upper and lower layers of flat light sources, and the reliability of identity verification is improved by fusing different images; the upper and lower flat light sources can be replaced by other distributed illumination light sources equally, so as to eliminate the influence of shadow.
The method comprises the following overall steps:
firstly, a filing stage:
a. only turning on the upper flat light source for illumination, and shooting the whole reflection image of the painting and calligraphy works by using a wide-field camera to obtain painting and calligraphy samples; the shot breadth is required to cover most of the area of the painting and calligraphy works;
b. extracting feature points in the image, such as SIFT points, Surf points, corner points and the like, and obtaining respective feature attribute description;
c. screening the characteristic points, and selecting a plurality of stable characteristic points more uniformly;
d. moving the microscopic camera to a selected characteristic point to shoot and enlarge an image, extracting the characteristic point of the image again according to the method and storing the characteristic point and description of the image;
e. selecting a block area with rich small blocks of textures as matching candidate positions in a blank area of the painting and calligraphy sample, storing the characteristic image and the original texture image after characteristic transformation such as gradient transformation, and marking the offset positions and sizes of the small blocks;
f. closing the upper flat light source and opening the lower flat light source, shooting a perspective image, selecting a small block area with rich texture as a matching candidate position in a blank area of the painting and calligraphy sample, and storing the characteristic image and the original texture image after characteristic transformation;
in the step, after the point characteristics and the block characteristics of the reflection image are completely shot and stored, the upper flat light source is closed, the lower flat light source is opened, the perspective image is shot, and the point characteristics and the surface characteristics are extracted again and stored;
g. repeating the process from e to f, and selecting a plurality of different microscopic feature matching candidate point positions;
h. storing the feature points and the attribute description, all the images, the feature image blocks and the offset positions and sizes of the feature images and the original texture images into a set file directory, and recording the file directories as template image data;
II, authentication stage:
a. only turning on the upper flat light source for illumination, and shooting an integral reflection image of a painting and calligraphy sample to be authenticated by using a wide-field camera; the shot breadth covers most of the area of the painting and calligraphy image;
b. extracting feature points on the graph and obtaining respective feature attribute description of the feature points;
c. matching the characteristic points with the characteristic points in the painting and calligraphy samples, and if the number of successfully matched points is less than a set proportion, considering that the matching fails and quitting the authentication; otherwise, considering the matching to be successful, calculating the position, angle and scale deviation of the authentication image and the sample image, and continuing the next step;
d. moving the micro camera to a matching successful position, extracting image feature points of the position again, then matching the image feature points with the feature points in the template, and if the matching is successful, calculating the position, angle and scale deviation of the current sample image and the template; if the matching fails, the point is changed again and the operation is repeated;
e. closing the upper flat light source and opening the lower flat light source, and shooting a transmission image; correcting the current sample image and the position, angle and scale deviation of the current sample image and the template according to the matching result of the images to obtain a matching candidate image or a characteristic image block corresponding to the matching candidate position of the template; the characteristic image blocks are divided into reflection characteristic image blocks and transmission characteristic image blocks;
f. respectively moving the reflection characteristic image block and the transmission characteristic image block left and right to match with the characteristic image blocks corresponding to the template, and observing whether the matching degree exceeds a set threshold value; if yes, matching is successful; otherwise, the matching fails;
g. and selecting the matching points according to the reliability requirement, if the matching points are larger than the set proportion, considering that the consistency check is successful, and otherwise, considering that the consistency check is failed.
The image block matching is used for calculating the correlation coefficient between the images or the characteristic images, and has the characteristics of insensitivity to environmental changes such as illumination and the like and good stability when being used in the painting and calligraphy filing authentication, and a small amount of image disturbance can not influence the authentication result, so that the consistency and the stability are better unified.
According to the invention, the reflection texture image and the perspective texture image can be shot in a time-sharing illumination mode of the upper layer light source and the lower layer light source, and the reliability of identity verification can be obviously improved through different image fusion.
Although the method is based on the painting and calligraphy filing and authentication method by fusing reflection images and transmission images, the painting and calligraphy filing and authentication can be independently carried out based on the two images.
The above embodiments are not intended to limit the present invention, and the present invention is not limited to the above examples, and those skilled in the art may make variations, modifications, additions or substitutions within the technical scope of the present invention.
Claims (2)
1. A high-reliability painting and calligraphy filing and authenticating method based on reflection and perspective image fusion is characterized in that: the equipment used by the authentication method comprises a working box with black inner wall; the lower end of the working box is provided with a working table, and the upper end of the working table is provided with a lower flat light source; a transparent glass plate is arranged above the lower flat light source, and the painting and calligraphy works are flatly laid on the transparent glass plate; an upper flat light source is arranged at the upper end of the working box; a wide-view camera is arranged in the middle of the lower end of the upper flat light source; a movable bracket is arranged on the inner side wall of the working box, and a microscopic camera is fixedly arranged on the movable bracket; the computer is used for controlling the movement and the micro image matching, the computer can shoot the reflection texture image and the perspective texture image by controlling the upper and lower layers of flat light sources to illuminate in a time-sharing manner, and the reliability of identity verification is improved by fusing different images;
the authentication method comprises the following overall steps:
firstly, a filing stage:
a. only turning on the upper flat light source for illumination, and shooting the whole reflection image of the painting and calligraphy works by using a wide-field camera to obtain painting and calligraphy samples; the shot breadth is required to cover most of the area of the painting and calligraphy works;
b. extracting feature points in the graph and obtaining respective feature attribute description of the feature points;
c. screening the characteristic points, and selecting a plurality of stable characteristic points more uniformly;
d. moving the microscopic camera to a selected characteristic point to shoot and enlarge an image, extracting the characteristic point of the image again according to the method and storing the characteristic point and description of the image;
e. selecting a block area with rich small blocks of textures as matching candidate positions in a blank area of the painting and calligraphy sample, storing the characteristic image and the original texture image after characteristic transformation, and marking offset positions and sizes of the small blocks;
f. closing the upper flat light source and opening the lower flat light source, shooting a perspective image, selecting a small block area with rich texture as a matching candidate position in a blank area of the painting and calligraphy sample, and storing the characteristic image and the original texture image after characteristic transformation;
g. repeating the process from e to f, and selecting a plurality of different microscopic feature matching candidate point positions;
h. storing the feature points and the attribute description, all the images, the feature image blocks and the offset positions and sizes of the feature images and the original texture images into a set file directory, and recording the file directories as template image data;
II, authentication stage:
a. only turning on the upper flat light source for illumination, and shooting an integral reflection image of a painting and calligraphy sample to be authenticated by using a wide-field camera; the shot breadth covers most of the area of the painting and calligraphy image;
b. extracting feature points on the graph and obtaining respective feature attribute description of the feature points;
c. matching the characteristic points with the characteristic points in the painting and calligraphy samples, and if the number of successfully matched points is less than a set proportion, considering that the matching fails and quitting the authentication; otherwise, considering the matching to be successful, calculating the position, angle and scale deviation of the authentication image and the sample image, and continuing the next step;
d. moving the micro camera to a matching successful position, extracting image feature points of the position again, then matching the image feature points with the feature points in the template, and if the matching is successful, calculating the position, angle and scale deviation of the current sample image and the template; if the matching fails, the point is changed again and the operation is repeated;
e. closing the upper flat light source and opening the lower flat light source, and shooting a transmission image; correcting the current sample image and the position, angle and scale deviation of the current sample image and the template according to the matching result of the images to obtain a matching candidate image or a characteristic image block corresponding to the matching candidate position of the template; the characteristic image blocks are divided into reflection characteristic image blocks and transmission characteristic image blocks;
f. respectively moving the reflection characteristic image block and the transmission characteristic image block left and right to match with the characteristic image blocks corresponding to the template, and observing whether the matching degree exceeds a set threshold value; if yes, matching is successful; otherwise, the matching fails;
g. and selecting the matching points according to the reliability requirement, if the matching points are larger than the set proportion, considering that the consistency check is successful, and otherwise, considering that the consistency check is failed.
2. The high-reliability painting and calligraphy filing and authenticating method based on the fusion of the reflection image and the perspective image as claimed in claim 1, wherein: the feature points comprise SIFT points, Surf points and corner points.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810939647.9A CN108985272B (en) | 2018-08-17 | 2018-08-17 | High-reliability painting and calligraphy filing and authenticating method based on fusion of reflection and perspective images |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810939647.9A CN108985272B (en) | 2018-08-17 | 2018-08-17 | High-reliability painting and calligraphy filing and authenticating method based on fusion of reflection and perspective images |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108985272A CN108985272A (en) | 2018-12-11 |
| CN108985272B true CN108985272B (en) | 2021-11-23 |
Family
ID=64553976
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810939647.9A Active CN108985272B (en) | 2018-08-17 | 2018-08-17 | High-reliability painting and calligraphy filing and authenticating method based on fusion of reflection and perspective images |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108985272B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114125295A (en) * | 2021-11-25 | 2022-03-01 | 大势大非(北京)文化有限公司 | Private data painting and calligraphy right confirming method and device |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1204078B1 (en) * | 2000-11-02 | 2003-12-03 | Orell Füssli Security Documents AG | A method for verifying the authenticity of articles |
| JP4697480B2 (en) * | 2008-01-11 | 2011-06-08 | 日本電気株式会社 | Lane recognition device, lane recognition method, and lane recognition program |
| JP5293815B2 (en) * | 2009-06-02 | 2013-09-18 | 日本電気株式会社 | Image processing apparatus, image processing method, and image processing program |
| JP2011158788A (en) * | 2010-02-02 | 2011-08-18 | Sony Corp | Hologram-including medium, apparatus for producing hologram-including medium, and information authentication method |
| CN103116755B (en) * | 2013-01-27 | 2016-01-06 | 深圳市书圣艺术品防伪鉴定有限公司 | Painting and calligraphy authenticity degree automatic checkout system and method thereof |
| CN105323208A (en) * | 2014-06-07 | 2016-02-10 | 李季 | Method for tracing calligraphy and painting identity tag |
| CN105654216A (en) * | 2014-11-15 | 2016-06-08 | 北京翰易得科技有限公司 | Calligraphy and painting management and selling system based on intelligent handset platform |
| CN106131389A (en) * | 2016-08-24 | 2016-11-16 | 北京雅昌艺术印刷有限公司 | Apparatus and method for painting and calligraphy pieces put on record and identify |
| CN106529506A (en) * | 2016-12-05 | 2017-03-22 | 沈阳毓沣恒装饰材料有限公司 | A calligraphy and painting record authentication device based on multistage magnification times |
-
2018
- 2018-08-17 CN CN201810939647.9A patent/CN108985272B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN108985272A (en) | 2018-12-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111126125A (en) | Method, device and equipment for extracting target text in certificate and readable storage medium | |
| CN108288088A (en) | A kind of scene text detection method based on end-to-end full convolutional neural networks | |
| KR102521386B1 (en) | Dimension measuring device, dimension measuring method, and semiconductor manufacturing system | |
| CN102542275B (en) | Automatic identification method for identification photo background and system thereof | |
| JP2016517559A (en) | Hall slide image registration and inter-image annotation device, system, and method | |
| Oliveira Santos et al. | Automatic mapping of cracking patterns on concrete surfaces with biological stains using hyper‐spectral images processing | |
| CN108985272B (en) | High-reliability painting and calligraphy filing and authenticating method based on fusion of reflection and perspective images | |
| CN108428249A (en) | A kind of initial position and orientation estimation method based on optical flow tracking and double geometrical models | |
| CN110717492B (en) | Method for correcting direction of character string in drawing based on joint features | |
| CN108364037A (en) | Method, system and the equipment of Handwritten Chinese Character Recognition | |
| CN105513083A (en) | PTAM camera tracking method and device | |
| CN112489002A (en) | Defect detection method, device, equipment and storage medium | |
| CN110910445A (en) | Object size detection method and device, detection equipment and storage medium | |
| CN109325434A (en) | A kind of image scene classification method of the probability topic model of multiple features | |
| CN108898597B (en) | Method for identifying painting and calligraphy based on smart phone | |
| CN112166456A (en) | Image processing method and image processing apparatus | |
| CN104881434A (en) | Image feature based intelligent wild lithology identification method | |
| CN110163910B (en) | Object positioning method, device, computer equipment and storage medium | |
| CN112541966A (en) | Face replacement method based on reconstruction and network generation | |
| CN107948220A (en) | The synchronous method and device of address list cloud service | |
| CN109753958A (en) | Image character recognition methods | |
| CN110503087A (en) | A kind of searching method, device, terminal and the storage medium of frame topic of taking pictures | |
| CN111145307A (en) | Method for automatically making electronic signature | |
| CN110826551A (en) | Intelligent discrimination method for VIN code rubbing die image of motor vehicle | |
| CN105590111B (en) | The method of reserved area in electronic document for identification |
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 |