CN110084736A - A kind of method of detecting watermarks and system based on SURF and pyramid algorith - Google Patents
A kind of method of detecting watermarks and system based on SURF and pyramid algorith Download PDFInfo
- Publication number
- CN110084736A CN110084736A CN201910353277.5A CN201910353277A CN110084736A CN 110084736 A CN110084736 A CN 110084736A CN 201910353277 A CN201910353277 A CN 201910353277A CN 110084736 A CN110084736 A CN 110084736A
- Authority
- CN
- China
- Prior art keywords
- watermark
- roi
- image
- original image
- sample 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000006243 chemical reaction Methods 0.000 claims abstract description 10
- 238000001514 detection method Methods 0.000 claims description 36
- 230000008859 change Effects 0.000 description 13
- 230000009466 transformation Effects 0.000 description 8
- 239000011159 matrix material Substances 0.000 description 6
- 238000000605 extraction Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000005352 clarification Methods 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000011524 similarity measure Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000001131 transforming effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T1/00—General purpose image data processing
- G06T1/0021—Image watermarking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2201/00—General purpose image data processing
- G06T2201/005—Image watermarking
- G06T2201/0065—Extraction of an embedded watermark; Reliable detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20016—Hierarchical, coarse-to-fine, multiscale or multiresolution image processing; Pyramid transform
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Editing Of Facsimile Originals (AREA)
Abstract
The invention discloses a kind of method of detecting watermarks and system based on SURF and pyramid algorith, comprising steps of step S1, by original image scaling to size same as the second sample image；Step S2, second sample image is transformed to by scale space identical with original image by SURF algorithm；Step S3, by positioning ROI region in pyramid algorith the second sample image after the conversion；Step S4, watermark location is determined；Step S5, watermark is detected.The present invention has many advantages, such as that matching precision is high, matching speed is fast.
Description
Technical field
The present invention relates to the technical fields of computer vision and image procossing, and in particular to one kind is based on SURF and pyramid
The method of detecting watermarks and system of algorithm.
Background technique
Images match is by the corresponding relationship to presentation content, feature, structure, relationship, texture and gray scale etc., similitude
With the analysis of consistency, seek similar view target.Image matching technology all obtains in photogrammetric field and computer vision
To being extremely widely applied, such as target positioning, target following and three-dimensional reconstruction etc..For the performance image of these applications
Matched reliability and calculating speed have vital influence.Image matching algorithm can be divided into two parts, be base respectively
Images match in template and the images match based on feature.Images match based on template, mainly using piece image as
The process of the corresponding position of template and the method search pattern by comparing pixel-by-pixel on another piece image.
Image watermark detection is a branch of image object detection, therefore, current common image object detection algorithm
It is suitable for image watermark to detect.Especially since deep learning is fast-developing, the image object detection based on deep learning
Quickly, the image object detection algorithm based on deep learning can also be used to realize in image watermark detection to algorithm development.
The patent of invention of Publication No. CN109635844A discloses the method and device and watermark of a kind of trained classifier
Detection method and device, wherein the method for training classifier includes: to generate the corresponding watermark template of watermark to be detected；For multiple
Image pattern carries out template matching to image pattern using the watermark template, generates matching result, the matching result is institute
State in image pattern with the highest region of watermark template matching degree；Using the matching result and the matching result
In whether the information training classifier comprising watermark template.
But there is the deviation of displacement, scale and rotation, existing template matching in the image obtained for us from camera
Algorithm is difficult accurately to cause watermark depending on the relative position to the positioning of area-of-interest (region of interest, ROI)
The position inaccurate in region, to be unable to complete watermark detection.
Therefore in view of the drawbacks of the prior art, the watermark detection for how realizing that matching precision is high, matching speed is fast is this field
Urgent problem to be solved.
Summary of the invention
The purpose of the present invention is in view of the drawbacks of the prior art, provide a kind of watermark based on SURF and pyramid algorith
Detection method and system.It is mainly based upon SURF and pyramid algorith, improves the accuracy and efficiency of watermark detection.
In order to achieve the goal above, the invention adopts the following technical scheme:
A kind of method of detecting watermarks based on SURF and pyramid algorith, comprising steps of
Step S1, by original image scaling to size same as the second sample image；
Step S2, second sample image is transformed to by scale space identical with original image by SURF algorithm；
Step S3, by positioning ROI region in pyramid algorith the second sample image after the conversion；
Step S4, watermark location is determined；
Step S5, watermark is detected.
Further, before the step S1 further include:
Step S1.1, the original image comprising watermark and ROI is obtained；
Step S1.2, the template area ROI is created based on the original image；And record the relative position of ROI and watermark；
Step S1.3, the second sample image comprising watermark and ROI is obtained.
Further, the step S4 are as follows:
Water is determined according to the relative position of the ROI region and pre-recorded ROI and watermark that position in the second sample image
Print position.
Further, the step S5 are as follows:
Watermark is detected using the method for gray level image blind Detecting digital watermarking.
Further, the original image and the second sample image are obtained using camera.
Correspondingly, also providing a kind of watermark detection system based on SURF and pyramid algorith, comprising:
Zoom module, for original image to be zoomed to size same as the second sample image；
Conversion module, it is empty for second sample image to be transformed to scale identical with original image by SURF algorithm
Between；
Locating module, for by positioning ROI region in the second sample image of pyramid algorith after the conversion；
Watermark location determining module, for determining watermark location；
Watermark detection module, for detecting watermark.
Further, the system also includes:
First obtains module, for obtaining the original image comprising watermark and ROI；
ROI template creation module, for creating the template area ROI based on the original image；And record ROI and watermark
Relative position；
Second obtains module, for obtaining the second sample image comprising watermark and ROI.
Further, according to the ROI region that is positioned in the second sample image and in advance in the watermark location determining module
The ROI of record and the relative position of watermark determine watermark location.
Further, the watermark detection module detects watermark using the method for gray level image blind Detecting digital watermarking.
Further, described first module and the second acquisition module are obtained using the camera acquisition original image and second
Sample image.
The present invention is based on the method for detecting watermarks and system of SURF and pyramid algorith, using SURF algorithm by described second
Sample image transforms to scale space identical with original image, and overcoming the second sample image of acquisition, there are positions with original image
The problem of shifting, rotation and change of scale.Improve the accuracy rate of watermark detection.Template matching is carried out using pyramid algorith, greatly
Matched efficiency is improved greatly.
Detailed description of the invention
Fig. 1 is the method for detecting watermarks flow chart based on SURF and pyramid algorith that embodiment one provides.
Fig. 2 is the watermark detection system structure chart based on SURF and pyramid algorith that embodiment two provides.
Fig. 3 is a kind of specific embodiment operating process figure.
Specific embodiment
Illustrate embodiments of the present invention below by way of specific specific example, those skilled in the art can be by this specification
Other advantages and efficacy of the present invention can be easily understood for disclosed content.The present invention can also pass through in addition different specific realities
The mode of applying is embodied or practiced, the various details in this specification can also based on different viewpoints and application, without departing from
Various modifications or alterations are carried out under spirit of the invention.It should be noted that in the absence of conflict, following embodiment and implementation
Feature in example can be combined with each other.
It should be noted that illustrating the basic structure that only the invention is illustrated in a schematic way provided in following embodiment
Think, only shown in schema then with related component in the present invention rather than component count, shape and size when according to actual implementation
Draw, when actual implementation kenel, quantity and the ratio of each component can arbitrarily change for one kind, and its assembly layout kenel
It is likely more complexity.
The present invention will be further explained below with reference to the attached drawings and specific examples, but not as the limitation of the invention.
Embodiment one
As shown in Figure 1, the present embodiment proposes a kind of method of detecting watermarks based on SURF and pyramid algorith, comprising:
Step S1, by original image scaling to size same as the second sample image；
Original image refers to the image for generating template, and the second sample image is the image for carrying out watermark detection.Cause
This, further comprises the steps of: before step S1
Step S1.1, the original image comprising watermark and ROI is obtained；
Specifically, the present invention obtains the original image comprising watermark and ROI using camera.In order to carry out accurate watermark inspection
It surveys, the original image of acquisition should be clear.
Step S1.2, the template area ROI is created based on the original image；And record the relative position of ROI and watermark；
Step S1.3, the second sample image comprising watermark and ROI is obtained；
Specifically, similar with original image is obtained, the figure including ROI region and watermark region is obtained again with mobile phone camera
As being used as the second sample image.But the second sample image obtained during this and original image exist and are displaced, rotation and
The problem of change of scale.For perspective transform, we should be avoided when obtaining the second sample image.
Perspective transform (Perspective Transformation), which refers to, utilizes the centre of perspectivity, picture point, 3 points of target point
Conllinear condition makes image-bearing surface (perspective plane) rotate a certain angle around trace (axis of homology), destroys original by chasles theorem
Projected light harness, be still able to maintain on image-bearing surface and project the constant transformation of geometric figure.
Step S2, second sample image is transformed to by scale space identical with original image by SURF algorithm；
SURF (Speeded Up Robust Features) is that a kind of characteristic point detection and description similar to SIFT is sub
Algorithm.It determines the position of characteristic point by Hessian matrix, and the Haar small echo response further according to feature vertex neighborhood point comes really
Fixed description.The advantages of Sift algorithm be feature stablize, maintain the invariance to rotation, change of scale, brightness, to view transformation,
Noise also has a degree of stability；The disadvantage is that real-time is not high, and energy is extracted for the smooth of the edge clarification of objective point
Power is weaker.Surf improves extraction and the describing mode of feature, completes the extraction of feature with a kind of highly efficient mode and retouches
It states.
Surf obtains the characteristic point of two images and carries out the matching of characteristic point, and passes through the side such as given threshold, RANSAC
Method eliminates Mismatching point.Corresponding transformation matrix is found according to the characteristic point of two images, the second sample image is passed through into change
Change matrixing to original image identical scale space.Therefore, the present invention utilizes SURF algorithm by second sample graph
As transforming to scale space identical with original image, the second sample image and original image for overcoming acquisition, which exist, to be displaced, rotation
Turn and the problem of change of scale.Improve the accuracy rate of watermark detection.
Step S3, by positioning ROI region in pyramid algorith the second sample image after the conversion；
The present invention positions ROI region using template matching.By the way that the second sample image is created with based on the original image
The template area ROI built is matched, to position ROI region in the second sample image.
During target detection, common method is exactly that a template is arranged, and whole picture is traversed in the form of sliding window
Source images (image to be detected)；Sliding can all generate the ROI image of the sizes such as one and template every time, be based on certain measurement side
Formula, the similarity measure values of calculation template and current ROI image.It just will form an image after having traversed entire image in this way,
The corresponding position of maximum value is found out, it is exactly the position of target.
However, it is very time-consuming to have traversed entire image when source images are very big, therefore, the application is based on pyramid and carries out template
Matching, pyramid method is to divide the image into different sizes, and the pyramid of piece image is a series of to be arranged with Pyramid
The resolution ratio of column gradually reduces, and derives from the image collection of same original graph.Pyramidal level is higher, and image is smaller,
Resolution ratio is lower.The template area ROI is searched in this way since highest tomographic image, can significantly improve matching speed.It is searching for
In the process, it can be mapped down from level to level in the top template result searched, obtain the template result of the bottom.
Therefore, the present invention carries out template matching using pyramid algorith, substantially increases matched efficiency.
Step S4, watermark location is determined；
Specifically, according to the relative position of the ROI region and previously known ROI and watermark that are positioned in the second sample image
Determine watermark location.
Step S5, watermark is detected.
The present invention is not defined the specific method of watermark detection.For example, can use redundant discrete small echo
(RDWT) method of the gray level image blind Detecting digital watermarking combined is decomposed with matrix Schur to detect watermark.
Embodiment two
As shown in Fig. 2, the present embodiment proposes a kind of watermark detection system based on SURF and pyramid algorith, comprising:
Zoom module, for original image to be zoomed to size same as the second sample image；
Original image refers to the image for generating template, and the second sample image is the image for carrying out watermark detection.Cause
This, before Zoom module processing further include:
First obtains module, for obtaining the original image comprising watermark and ROI；
Specifically, the present invention obtains the original image comprising watermark and ROI using camera.In order to carry out accurate watermark inspection
It surveys, the original image of acquisition should be clear.
ROI template creation module, for creating the template area ROI based on the original image；And record ROI and watermark
Relative position；
Second obtains module, for obtaining the second sample image comprising watermark and ROI；
Specifically, similar with original image is obtained, the figure including ROI region and watermark region is obtained again with mobile phone camera
As being used as the second sample image.But the second sample image obtained during this and original image exist and are displaced, rotation and
The problem of change of scale.For perspective transform, we should be avoided when obtaining the second sample image.
Perspective transform (Perspective Transformation), which refers to, utilizes the centre of perspectivity, picture point, 3 points of target point
Conllinear condition makes image-bearing surface (perspective plane) rotate a certain angle around trace (axis of homology), destroys original by chasles theorem
Projected light harness, be still able to maintain on image-bearing surface and project the constant transformation of geometric figure.
Conversion module, it is empty for second sample image to be transformed to scale identical with original image by SURF algorithm
Between；
SURF (Speeded Up Robust Features) is that a kind of characteristic point detection and description similar to SIFT is sub
Algorithm.It determines the position of characteristic point by Hessian matrix, and the Haar small echo response further according to feature vertex neighborhood point comes really
Fixed description.The advantages of Sift algorithm be feature stablize, maintain the invariance to rotation, change of scale, brightness, to view transformation,
Noise also has a degree of stability；The disadvantage is that real-time is not high, and energy is extracted for the smooth of the edge clarification of objective point
Power is weaker.Surf improves extraction and the describing mode of feature, completes the extraction of feature with a kind of highly efficient mode and retouches
It states.
Surf obtains the characteristic point of two images and carries out the matching of characteristic point, and passes through the side such as given threshold, RANSAC
Method eliminates Mismatching point.Corresponding transformation matrix is found according to the characteristic point of two images, the second sample image is passed through into change
Change matrixing to original image identical scale space.Therefore, the present invention utilizes SURF algorithm by second sample graph
As transforming to scale space identical with original image, the second sample image and original image for overcoming acquisition, which exist, to be displaced, rotation
Turn and the problem of change of scale.Improve the accuracy rate of watermark detection.
Locating module, for by positioning ROI region in the second sample image of pyramid algorith after the conversion；
The present invention positions ROI region using template matching.By the way that the second sample image is created with based on the original image
The template area ROI built is matched, to position ROI region in the second sample image.
During target detection, common method is exactly that a template is arranged, and whole picture is traversed in the form of sliding window
Source images (image to be detected)；Sliding can all generate the ROI image of the sizes such as one and template every time, be based on certain measurement side
Formula, the similarity measure values of calculation template and current ROI image.It just will form an image after having traversed entire image in this way,
The corresponding position of maximum value is found out, it is exactly the position of target.
However, it is very time-consuming to have traversed entire image when source images are very big, therefore, the application is based on pyramid and carries out template
Matching, pyramid method is to divide the image into different sizes, and the pyramid of piece image is a series of to be arranged with Pyramid
The resolution ratio of column gradually reduces, and derives from the image collection of same original graph.Pyramidal level is higher, and image is smaller,
Resolution ratio is lower.The template area ROI is searched in this way since highest tomographic image, can significantly improve matching speed.It is searching for
In the process, it can be mapped down from level to level in the top template result searched, obtain the template result of the bottom.
Therefore, the present invention carries out template matching using pyramid algorith, substantially increases matched efficiency.
Watermark location determining module, for determining watermark location；
Specifically, according to the relative position of the ROI region and previously known ROI and watermark that are positioned in the second sample image
Determine watermark location.
Watermark detection module, for detecting watermark.
The present invention is not defined the specific method of watermark detection.For example, can use redundant discrete small echo
(RDWT) method of the gray level image blind Detecting digital watermarking combined is decomposed with matrix Schur to detect watermark.
It follows that utilizing SURF algorithm the present invention is based on the method for detecting watermarks and system of SURF and pyramid algorith
Second sample image is transformed into scale space identical with original image, overcome the second sample image of acquisition with it is original
There is the problem of displacement, rotation and change of scale in image.Improve the accuracy rate of watermark detection.Mould is carried out using pyramid algorith
Plate matching, substantially increases matched efficiency.
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (10)
1. a kind of method of detecting watermarks based on SURF and pyramid algorith, which is characterized in that comprising steps of
Step S1, by original image scaling to size same as the second sample image；
Step S2, second sample image is transformed to by scale space identical with original image by SURF algorithm；
Step S3, by positioning ROI region in pyramid algorith the second sample image after the conversion；
Step S4, watermark location is determined；
Step S5, watermark is detected.
2. method of detecting watermarks according to claim 1, which is characterized in that before the step S1 further include:
Step S1.1, the original image comprising watermark and ROI is obtained；
Step S1.2, the template area ROI is created based on the original image；And record the relative position of ROI and watermark；
Step S1.3, the second sample image comprising watermark and ROI is obtained.
3. method of detecting watermarks according to claim 1, which is characterized in that the step S4 are as follows:
Watermark bit is determined according to the relative position of the ROI region and pre-recorded ROI and watermark that position in the second sample image
It sets.
4. method of detecting watermarks according to claim 1, which is characterized in that the step S5 are as follows:
Watermark is detected using the method for gray level image blind Detecting digital watermarking.
5. method of detecting watermarks according to claim 2, which is characterized in that obtain the original image and the using camera
Two sample images.
6. a kind of watermark detection system based on SURF and pyramid algorith characterized by comprising
Zoom module, for original image to be zoomed to size same as the second sample image；
Conversion module, for second sample image to be transformed to scale space identical with original image by SURF algorithm；
Locating module, for by positioning ROI region in the second sample image of pyramid algorith after the conversion；Watermark location is true
Cover half block, for determining watermark location；
Watermark detection module, for detecting watermark.
7. watermark detection system according to claim 6, which is characterized in that the system also includes:
First obtains module, for obtaining the original image comprising watermark and ROI；
ROI template creation module, for creating the template area ROI based on the original image；And record the opposite of ROI and watermark
Position；
Second obtains module, for obtaining the second sample image comprising watermark and ROI.
8. watermark detection system according to claim 6, which is characterized in that in the watermark location determining module according to
The relative position of the ROI region and pre-recorded ROI and watermark that position in two sample images determines watermark location.
9. watermark detection system according to claim 6, which is characterized in that the watermark detection module utilizes gray level image
The method of blind Detecting digital watermarking detects watermark.
10. watermark detection system according to claim 7, which is characterized in that described first obtains module obtains with second
Module obtains the original image and the second sample image using camera.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910353277.5A CN110084736A (en) | 2019-04-29 | 2019-04-29 | A kind of method of detecting watermarks and system based on SURF and pyramid algorith |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910353277.5A CN110084736A (en) | 2019-04-29 | 2019-04-29 | A kind of method of detecting watermarks and system based on SURF and pyramid algorith |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110084736A true CN110084736A (en) | 2019-08-02 |
Family
ID=67417611
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910353277.5A Pending CN110084736A (en) | 2019-04-29 | 2019-04-29 | A kind of method of detecting watermarks and system based on SURF and pyramid algorith |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110084736A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110827189A (en) * | 2019-11-01 | 2020-02-21 | 山东浪潮人工智能研究院有限公司 | Method and system for removing watermark of digital image or video |
| CN111260625A (en) * | 2020-01-15 | 2020-06-09 | 征图新视(江苏)科技股份有限公司 | Automatic extraction method for offset printing large image detection area |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101147159A (en) * | 2005-02-21 | 2008-03-19 | 三菱电机株式会社 | Fast method of object detection by statistical template matching |
| CN102044055A (en) * | 2010-09-09 | 2011-05-04 | 中国矿业大学 | High-capacity digital watermarking method combining multi-scale characteristics and Chinese remainder theorem |
| CN104091302A (en) * | 2014-07-10 | 2014-10-08 | 北京工业大学 | Robust watermark embedding and extracting method based on multi-scale space |
| CN104700347A (en) * | 2015-03-01 | 2015-06-10 | 江西科技学院 | Image feature-based color image digital watermark algorithm |
| CN108319961A (en) * | 2018-01-23 | 2018-07-24 | 西南科技大学 | A kind of image ROI rapid detection methods based on local feature region |
| CN109635844A (en) * | 2018-11-14 | 2019-04-16 | 网易传媒科技（北京）有限公司 | The method and device and method of detecting watermarks and device of training classifier |
-
2019
- 2019-04-29 CN CN201910353277.5A patent/CN110084736A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101147159A (en) * | 2005-02-21 | 2008-03-19 | 三菱电机株式会社 | Fast method of object detection by statistical template matching |
| CN102044055A (en) * | 2010-09-09 | 2011-05-04 | 中国矿业大学 | High-capacity digital watermarking method combining multi-scale characteristics and Chinese remainder theorem |
| CN104091302A (en) * | 2014-07-10 | 2014-10-08 | 北京工业大学 | Robust watermark embedding and extracting method based on multi-scale space |
| CN104700347A (en) * | 2015-03-01 | 2015-06-10 | 江西科技学院 | Image feature-based color image digital watermark algorithm |
| CN108319961A (en) * | 2018-01-23 | 2018-07-24 | 西南科技大学 | A kind of image ROI rapid detection methods based on local feature region |
| CN109635844A (en) * | 2018-11-14 | 2019-04-16 | 网易传媒科技（北京）有限公司 | The method and device and method of detecting watermarks and device of training classifier |
Non-Patent Citations (4)
| Title |
|---|
| 刘国华: "《HALCON数字图像处理》", 西安电子科技大学出版社, pages: 218 - 219 * |
| 赵春晖 等: "一种基于词袋模型的图像优化分类方法", 《电子与信息学报》, 30 September 2012 (2012-09-30), pages 2064 - 2070 * |
| 郭鹏飞 等: "新式灰度图像盲检测数字水印算法", 《计算机工程与科学》 * |
| 郭鹏飞 等: "新式灰度图像盲检测数字水印算法", 《计算机工程与科学》, 31 January 2019 (2019-01-31), pages 104 - 112 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110827189A (en) * | 2019-11-01 | 2020-02-21 | 山东浪潮人工智能研究院有限公司 | Method and system for removing watermark of digital image or video |
| CN110827189B (en) * | 2019-11-01 | 2023-12-05 | 山东浪潮科学研究院有限公司 | Watermark removing method and system for digital image or video |
| CN111260625A (en) * | 2020-01-15 | 2020-06-09 | 征图新视(江苏)科技股份有限公司 | Automatic extraction method for offset printing large image detection area |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110866953B (en) | Map construction method and device, and positioning method and device | |
| Meher et al. | A survey on region based image fusion methods | |
| Ye et al. | Fast and robust matching for multimodal remote sensing image registration | |
| Yin et al. | Hot region selection based on selective search and modified fuzzy C-means in remote sensing images | |
| Chen et al. | Automatically conflating road vector data with orthoimagery | |
| Blostein et al. | Shape from texture: Integrating texture-element extraction and surface estimation | |
| US5613013A (en) | Glass patterns in image alignment and analysis | |
| CN109191424B (en) | Breast mass detection and classification system and computer-readable storage medium | |
| CN101147159A (en) | Fast method of object detection by statistical template matching | |
| Lee et al. | Skewed rotation symmetry group detection | |
| JP2013025799A (en) | Image search method, system, and program | |
| Bigün | Pattern recognition in images by symmetries and coordinate transformations | |
| CN106296587B (en) | Splicing method of tire mold images | |
| Yu et al. | Traffic sign detection based on visual co-saliency in complex scenes | |
| CN115311618A (en) | Assembly quality inspection method based on deep learning and object matching | |
| CN110084736A (en) | A kind of method of detecting watermarks and system based on SURF and pyramid algorith | |
| JP4003465B2 (en) | Specific pattern recognition method, specific pattern recognition program, specific pattern recognition program recording medium, and specific pattern recognition apparatus | |
| CN116958434A (en) | Multi-view three-dimensional reconstruction method, measurement method and system | |
| CN115994899A (en) | Bolt loosening detection method, device and detection equipment | |
| Huang et al. | Multimodal image matching using self similarity | |
| CN112233104B (en) | Real-time displacement field and strain field detection method, system, device and storage medium | |
| CN113689397A (en) | Workpiece circular hole feature detection method and workpiece circular hole feature detection device | |
| Frisky et al. | Acquisition Evaluation on Outdoor Scanning for Archaeological Artifact Digitalization. | |
| CN114663917A (en) | Multi-view-angle-based multi-person three-dimensional human body pose estimation method and device | |
| Lu | New efficient vanishing point detection from a single road image based on intrinsic line orientation and color texture properties |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190802 |