CN108171658B - Method and system for detecting gamma correction - Google Patents
Method and system for detecting gamma correction Download PDFInfo
- Publication number
- CN108171658B CN108171658B CN201611112995.6A CN201611112995A CN108171658B CN 108171658 B CN108171658 B CN 108171658B CN 201611112995 A CN201611112995 A CN 201611112995A CN 108171658 B CN108171658 B CN 108171658B
- Authority
- CN
- China
- Prior art keywords
- calculating
- image
- value sequence
- gamma correction
- gray level
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- 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
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
- G06V10/507—Summing image-intensity values; Histogram projection analysis
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Picture Signal Circuits (AREA)
- Facsimile Image Signal Circuits (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a method for detecting gamma correction, which comprises the following steps: calculating to obtain a gray level histogram h (x) of the image I to be detected; calculating to obtain a wave peak value sequence P (x) according to the obtained gray level histogram h (x); calculating to obtain a trough value sequence G (x) according to the obtained gray level histogram h (x); calculating to obtain a one-dimensional discrimination feature F according to the obtained wave peak value sequence P (x) and the obtained wave trough value sequence G (x); calculating to obtain an optimal threshold value T; and detecting whether the image I is subjected to gamma correction or not according to the obtained distinguishing feature F and the optimal threshold value T. The invention also relates to a system for detecting gamma correction. The method calculates the one-dimensional discrimination characteristics based on all the wave crest and trough values, and the designed one-dimensional discrimination characteristics have low calculation complexity, easy realization and high detection accuracy.
Description
Technical Field
The invention relates to a method and a system for detecting gamma correction.
Background
In recent years, with the rapid development of IT industry, digital devices such as mobile phones and computers are popularized, and digital media are gradually recognized and accepted by the public as information carriers. Conventional film prints are eventually replaced under the impact of digital prints because they are not easy to store and edit. But at the same time, the digital image is easy to edit and convenient to distribute, and the common user has the capability of tampering the image. In a common saying, "the taste is not as good as one 'and" the ear is as weak as one' and the eye is as true ", which is a traditional information source, the source of pictures containing visual information, the authenticity and the like are easily ignored by people. In recent years, image security is highlighted, and application of image media to formal and serious occasions such as court and insurance industries is severely restricted.
Technically, all digital image editing operations that may occur should be detectable as a basis for a determination to identify whether an image is authentic. Gamma Correction (Gamma Correction), a typical operation for adjusting the brightness of a picture, is widely used in display devices and image processing software. If some regions of an image are detected as being gamma corrected and other regions are detected as not being gamma corrected, then the image is likely to be a mosaic of two different images. It can be seen that the detection of gamma correction is of practical significance in image tampering detection.
The existing method for estimating gamma correction parameters utilizes gamma correction to leave a series of peaks and valleys on an image gray histogram for detection, and although gamma correction can be detected, the existing method has the following disadvantages: (1) in order to control the calculation complexity not to be too large, only the pair of wave peak and wave valley values at the middle are used, and other wave peak and wave valley values are ignored, and the ignored wave peak and wave valley values often have important judgment information; (2) the method is designed aiming at parameter estimation, and is not concise and efficient for the detection problem of gamma correction, namely whether an image is subjected to gamma correction or not.
Disclosure of Invention
Accordingly, there is a need for a method and system for detecting gamma correction, which can overcome the disadvantages of the existing detection method and simply and efficiently detect whether an image is gamma-corrected.
The invention provides a method for detecting gamma correction, which comprises the following steps: calculating to obtain a gray level histogram h (x) of the image I to be detected; calculating to obtain a wave peak value sequence P (x) according to the obtained gray level histogram h (x); calculating to obtain a trough value sequence G (x) according to the obtained gray level histogram h (x); calculating to obtain a one-dimensional discrimination feature F according to the obtained wave peak value sequence P (x) and the obtained wave trough value sequence G (x); calculating to obtain an optimal threshold value T according to the discrimination characteristic values of the image which is not subjected to gamma correction and the image which is subjected to gamma correction; and detecting whether the image I is subjected to gamma correction or not according to the obtained distinguishing feature F and the optimal threshold value T.
Wherein, the step of calculating to obtain the gray level histogram h (x) of the image I to be detected specifically comprises the following steps:
and δ (x) is a dirichlet function, δ (x) is 1 when x is 0, δ (x) is 0 when x is other values, and I (I, j) represents the gray value of the image I to be detected in the ith row and j column.
The step of calculating the wave peak value sequence P (x) according to the obtained gray level histogram h (x) specifically comprises the following steps: using formulas
Calculating to obtain a wave peak value sequence P (x) of the gray level histogram h (x).
The step of calculating a trough value sequence G (x) according to the obtained gray level histogram h (x) specifically comprises: using formulas
Calculating to obtain a trough value sequence G (x) of the gray level histogram h (x).
According to the obtained wave peak value sequence P (x) and the wave trough value sequence G (x), calculating to obtain a one-dimensional discrimination feature F, which specifically comprises the following steps:
the invention also provides a system for detecting gamma correction, which comprises a histogram calculation module, a wave crest value sequence calculation module, a trough value sequence calculation module, a discrimination feature calculation module, a threshold value calculation module and a judgment module, wherein: the histogram calculation module is used for calculating and obtaining a gray level histogram h (x) of the image I to be detected; the wave peak value sequence calculation module is used for calculating and obtaining a wave peak value sequence P (x) according to the obtained gray level histogram h (x); the wave trough value sequence calculating module is used for calculating to obtain a wave trough value sequence G (x) according to the obtained gray level histogram h (x); the discrimination feature calculation module is used for calculating to obtain a one-dimensional discrimination feature F according to the obtained wave peak value sequence P (x) and the obtained wave trough value sequence G (x); the threshold calculation module is used for calculating to obtain an optimal threshold T according to the discrimination characteristic values of the image which is not subjected to gamma correction and the image which is subjected to gamma correction. And the judging module is used for detecting whether the image is subjected to gamma correction or not according to the obtained distinguishing feature F and the optimal threshold value T.
The histogram calculation module is specifically configured to:
and δ (x) is a dirichlet function, δ (x) is 1 when x is 0, δ (x) is 0 when x is other values, and I (I, j) represents the gray value of the image I to be detected in the ith row and j column.
The wave peak sequence calculation module is specifically configured to: using formulas
Calculating to obtain a wave peak value sequence P (x) of the gray level histogram h (x).
The trough value sequence calculation module is specifically configured to: using formulas
Calculating to obtain a trough value sequence G (x) of the gray level histogram h (x).
The discriminant feature calculation module is specifically configured to:
the invention can overcome the defects of the existing detection method and simply and efficiently detect whether an image is subjected to gamma correction. The beneficial effects of the invention include: (1) all the wave peak values and the wave trough values are utilized to calculate the distinguishing characteristics, and not only the pair of wave peak and wave trough values at the middle are utilized, so that the distinguishing information is more fully utilized; (2) the invention is designed aiming at the gamma detection problem and is more suitable for the gamma detection problem. (3) The method calculates the one-dimensional discrimination characteristics without matching the wave crest and the wave trough templates, has lower calculation complexity and is easy to realize.
Drawings
FIG. 1 is a flow chart of a method of detecting gamma correction according to the present invention;
FIG. 2 is a diagram of the hardware architecture of the system for detecting gamma correction according to the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and specific embodiments.
Referring to FIG. 1, a flow chart of the preferred embodiment of the method for detecting gamma correction according to the present invention is shown.
And step S1, calculating to obtain a gray level histogram of the image to be detected. Specifically, the method comprises the following steps:
the number of rows is M and the number of columns is N for the image I to be detected. Calculating a gray level histogram h (x) of the image I to be detected, wherein x is more than or equal to 0 and less than or equal to 255, and the method comprises the following steps:
in the above formula, δ (x) is a dirichlet function, and δ (x) is 1 when x is 0, and δ (x) is 0 when x is other values. And I (I, j) represents the gray value of the image I to be detected in the ith row and j column.
In step S2, a peak value sequence is calculated from the obtained gradation histogram. The method specifically comprises the following steps:
calculating to obtain a wave peak value sequence P (x) of the gray level histogram h (x), which is as follows:
in this embodiment, the maximum and minimum values are calculated in the 3 neighborhoods { h (x-1), h (x +1) } of h (x). The specific meanings are as follows: when h (x) is the maximum value in { h (x-1), h (x +1) }, indicating that h (x) is a local peak value, at this time, P (x) is equal to the value obtained by subtracting the minimum value in { h (x-1), h (x +1) }fromh (x), and obtaining the difference value (a non-negative number) between the maximum value and the minimum value as the amplitude value of the peak; otherwise, let p (x) be 0. In order to define P (x) also when x is 0 and x is 255, P (0) is 0 and P (255) is 0.
It is understood that, in another embodiment, the maximum value and the minimum value may also be calculated in the 5 neighborhoods { h (x-2), h (x-1), h (x), h (x +1), and h (x +2) } of h (x), and the value range of u in the above formula is changed accordingly.
It can be understood that, in other embodiments, the maximum value and the minimum value may also be calculated in the 7 neighborhoods { h (x-3), h (x-2), h (x-1), h (x), h (x +1), h (x +2), h (x +3) } of h (x), and the value range of u in the above formula may be changed accordingly.
And step S3, calculating to obtain a trough value sequence according to the obtained gray level histogram. Specifically, the method comprises the following steps:
calculating a valley value sequence G (x) of the gray level histogram h (x) as follows:
in this embodiment, the maximum and minimum values are calculated in the 3 neighborhoods { h (x-1), h (x +1) } of h (x). The specific meanings are as follows: when h (x) is the minimum value in { h (x-1), h (x +1) }, indicating that h (x) is a local valley value, at this time G (x) is equal to the difference (a non-positive number) between the minimum value and the maximum value obtained by subtracting the maximum value in { h (x-1), h (x +1) }fromh (x), and the difference is used as the amplitude of the valley; otherwise, let g (x) be 0. In order to define G (x) also when x is 0 and x is 255, G (0) is 0 and G (255) is 0.
It is understood that, in another embodiment, the maximum value and the minimum value may also be calculated in the 5 neighborhoods { h (x-2), h (x-1), h (x), h (x +1), and h (x +2) } of h (x), and the value range of u in the above formula is changed accordingly.
It can be understood that, in other embodiments, the maximum value and the minimum value may also be calculated in the 7 neighborhoods { h (x-3), h (x-2), h (x-1), h (x), h (x +1), h (x +2), h (x +3) } of h (x), and the value range of u in the above formula may be changed accordingly.
And step S4, calculating to obtain a one-dimensional discrimination feature F according to the obtained wave peak value sequence and the wave trough value sequence. Specifically, the method comprises the following steps:
the one-dimensional discriminant features F are calculated as follows:
since gamma correction causes the gray level histogram of the image to have significant peak values and valley values, F will take a larger value for the gamma-corrected image; for an image that has not been gamma corrected, F will take a smaller value. The denominator in the above formula plays a role of normalization, so that F characteristics of images with different resolutions also have similar value ranges.
In step S5, the optimal threshold T is calculated. Specifically, the method comprises the following steps:
some images that have not undergone gamma correction are collected and gamma-corrected for different parameters. Discrimination feature values of these non-gamma-corrected image and gamma-corrected image are calculated, respectively. For a threshold value t, the ratio of the image without gamma correction to all the images without gamma correction is R1(t) recording the ratio of the gamma-corrected images with the distinguishing characteristic value larger than t to all the gamma-corrected images as R2(t), then the decision accuracy can be calculated as: (R)1(t)+R2(t))/2. Adjusting T to maximize the judgment accuracy, and taking the threshold value obtained at the moment as an optimal threshold value T:
and step S6, detecting whether the image is subjected to gamma correction or not according to the obtained distinguishing feature F and the optimal threshold value T. Specifically, the method comprises the following steps:
comparing the discrimination feature F of the image to be detected with an optimal threshold value T: if F > T, determining that the image is gamma corrected; otherwise; it is determined that the image has not been gamma-corrected.
Referring to FIG. 2, a diagram of the hardware architecture of the system 10 for detecting gamma correction according to the present invention is shown. The system comprises a histogram calculation module 101, a wave crest value sequence calculation module 102, a trough value sequence calculation module 103, a discrimination feature calculation module 104, a threshold calculation module 105 and a judgment module 106.
The histogram calculation module 101 is configured to calculate a gray level histogram of the image to be detected. Specifically, the method comprises the following steps:
the number of rows is M and the number of columns is N for the image I to be detected. Calculating a gray level histogram h (x) of the image I to be detected, wherein x is more than or equal to 0 and less than or equal to 255, and the method comprises the following steps:
in the above formula, δ (x) is a dirichlet function, and δ (x) is 1 when x is 0, and δ (x) is 0 when x is other values. I (I, j) represents the gray scale value of the image I in the ith row and j column.
The wave peak value sequence calculating module 102 is configured to calculate a wave peak value sequence according to the obtained gray level histogram. The method specifically comprises the following steps:
calculating to obtain a wave peak value sequence P (x) of the gray level histogram h (x), which is as follows:
in this embodiment, the maximum and minimum values are calculated in the 3 neighborhoods { h (x-1), h (x +1) } of h (x). The specific meanings are as follows: when h (x) is the maximum value in { h (x-1), h (x +1) }, indicating that h (x) is a local peak value, at this time, P (x) is equal to the value obtained by subtracting the minimum value in { h (x-1), h (x +1) }fromh (x), and obtaining the difference value (a non-negative number) between the maximum value and the minimum value as the amplitude value of the peak; otherwise, let p (x) be 0. In order to define P (x) also when x is 0 and x is 255, P (0) is 0 and P (255) is 0.
It is understood that, in another embodiment, the maximum value and the minimum value may also be calculated in the 5 neighborhoods { h (x-2), h (x-1), h (x), h (x +1), and h (x +2) } of h (x), and the value range of u in the above formula is changed accordingly.
It can be understood that, in other embodiments, the maximum value and the minimum value may also be calculated in the 7 neighborhoods { h (x-3), h (x-2), h (x-1), h (x), h (x +1), h (x +2), h (x +3) } of h (x), and the value range of u in the above formula may be changed accordingly.
And the trough value sequence calculating module 103 is configured to calculate a trough value sequence according to the obtained gray level histogram. Specifically, the method comprises the following steps:
calculating a valley value sequence G (x) of the gray level histogram h (x) as follows:
in this embodiment, the maximum and minimum values are calculated in the 3 neighborhoods { h (x-1), h (x +1) } of h (x). The specific meanings are as follows: when h (x) is the minimum value in { h (x-1), h (x +1) }, indicating that h (x) is a local valley value, at this time G (x) is equal to the difference (a non-positive number) between the minimum value and the maximum value obtained by subtracting the maximum value in { h (x-1), h (x +1) }fromh (x), and the difference is used as the amplitude of the valley; otherwise, let g (x) be 0. In order to define G (x) also when x is 0 and x is 255, G (0) is 0 and G (255) is 0.
It is understood that, in another embodiment, the maximum value and the minimum value may also be calculated in the 5 neighborhoods { h (x-2), h (x-1), h (x), h (x +1), and h (x +2) } of h (x), and the value range of u in the above formula is changed accordingly.
It can be understood that, in other embodiments, the maximum value and the minimum value may also be calculated in the 7 neighborhoods { h (x-3), h (x-2), h (x-1), h (x), h (x +1), h (x +2), h (x +3) } of h (x), and the value range of u in the above formula may be changed accordingly.
The discrimination feature calculation module 104 is configured to calculate a one-dimensional discrimination feature F according to the obtained wave peak value sequence and the wave trough value sequence. Specifically, the method comprises the following steps:
the one-dimensional discriminant features F are calculated as follows:
since gamma correction causes the gray level histogram of the image to have significant peak values and valley values, F will take a larger value for the gamma-corrected image; for an image that has not been gamma corrected, F will take a smaller value. The denominator in the above formula plays a role of normalization, so that F characteristics of images with different resolutions also have similar value ranges.
The threshold calculation module 105 is configured to calculate an optimal threshold T. Specifically, the method comprises the following steps:
some images that have not undergone gamma correction are collected and gamma-corrected for different parameters. Discrimination feature values of these non-gamma-corrected image and gamma-corrected image are calculated, respectively. For a threshold value t, the ratio of the image without gamma correction to all the images without gamma correction is R1(t) recording the ratio of the gamma-corrected images with the distinguishing characteristic value larger than t to all the gamma-corrected images as R2(t), then the decision accuracy can be calculated as: (R)1(t)+R2(t))/2. Adjusting T to maximize the judgment accuracy, and taking the threshold value obtained at the moment as an optimal threshold value T:
the determining module 106 is configured to detect whether the image is subjected to gamma correction according to the obtained distinguishing feature F and the optimal threshold T. Specifically, the method comprises the following steps:
comparing the discrimination feature F of the image to be detected with an optimal threshold value T: if F > T, determining that the image is gamma corrected; otherwise; it is determined that the image has not been gamma-corrected.
Although the present invention has been described with reference to the presently preferred embodiments, it will be understood by those skilled in the art that the foregoing description is illustrative only and is not intended to limit the scope of the invention, as claimed.
Claims (8)
1. A method of detecting gamma correction, the method comprising the steps of:
calculating to obtain a gray level histogram h (x) of the image I to be detected;
calculating to obtain a wave peak value sequence P (x) according to the obtained gray level histogram h (x);
calculating to obtain a trough value sequence G (x) according to the obtained gray level histogram h (x);
according to the obtained wave crest value sequence P (x) and the wave trough value sequence G (x), calculating to obtain a one-dimensional discrimination feature F,
calculating to obtain an optimal threshold value T according to the discrimination characteristic values of the image which is not subjected to gamma correction and the image which is subjected to gamma correction:
separately calculating the discriminating characteristic values of the non-gamma-corrected image and the gamma-corrected image for a threshold t, R1(t) is a ratio of the image without gamma correction to all the images without gamma correction, R2(t) judging the proportion of the images with characteristic values larger than t and subjected to gamma correction in all the images subjected to gamma correction, wherein the judgment accuracy is as follows: (R)1(t)+R2(T))/2, adjusting T, and taking the threshold obtained when the judgment accuracy is maximum as an optimal threshold T:
and detecting whether the image I is subjected to gamma correction or not according to the obtained distinguishing feature F and the optimal threshold value T.
2. The method according to claim 1, wherein said step of calculating a gray level histogram h (x) of the image I to be detected comprises:
and δ (x) is a dirichlet function, δ (x) is 1 when x is 0, δ (x) is 0 when x is other values, and I (I, j) represents the gray value of the image I to be detected in the ith row and j column.
3. The method according to claim 2, wherein the step of calculating the peak value sequence p (x) according to the obtained gray level histogram h (x) comprises:
using formulas
Calculating to obtain a wave peak value sequence P (x) of the gray level histogram h (x).
4. The method according to claim 2, wherein the step of calculating the valley value sequence g (x) according to the obtained gray level histogram h (x) comprises:
using formulas
Calculating to obtain a trough value sequence G (x) of the gray level histogram h (x).
5. A system for detecting gamma correction is characterized by comprising a histogram calculation module, a wave peak value sequence calculation module, a trough value sequence calculation module, a distinguishing characteristic calculation module, a threshold value calculation module and a judgment module, wherein:
the histogram calculation module is used for calculating and obtaining a gray level histogram h (x) of the image I to be detected;
the wave peak value sequence calculation module is used for calculating and obtaining a wave peak value sequence P (x) according to the obtained gray level histogram h (x);
the wave trough value sequence calculating module is used for calculating to obtain a wave trough value sequence G (x) according to the obtained gray level histogram h (x);
the discrimination feature calculation module is used for calculating to obtain a one-dimensional discrimination feature F according to the obtained wave peak value sequence P (x) and the wave trough value sequence G (x),
the threshold calculation module is used for calculating to obtain an optimal threshold T according to the discrimination characteristic values of the image which is not subjected to gamma correction and the image which is subjected to gamma correction:
separately calculating the discriminating characteristic values of the non-gamma-corrected image and the gamma-corrected image for a threshold t, R1(t) is a ratio of the image without gamma correction to all the images without gamma correction, R2(t) judging the proportion of the images with characteristic values larger than t and subjected to gamma correction in all the images subjected to gamma correction, wherein the judgment accuracy is as follows: (R)1(t)+R2(T))/2, adjusting T, and taking the threshold obtained when the judgment accuracy is maximum as an optimal threshold T:
and the judging module is used for detecting whether the image is subjected to gamma correction or not according to the obtained distinguishing feature F and the optimal threshold value T.
6. The system of claim 5, wherein the histogram calculation module is specifically configured to:
and δ (x) is a dirichlet function, δ (x) is 1 when x is 0, δ (x) is 0 when x is other values, and I (I, j) represents the gray value of the image I to be detected in the ith row and j column.
7. The system of claim 6, wherein the crest value sequence calculation module is specifically configured to:
using formulas
Calculating to obtain a wave peak value sequence P (x) of the gray level histogram h (x).
8. The system of claim 7, wherein the trough value sequence calculation module is specifically configured to:
using formulas
Calculating to obtain a trough value sequence G (x) of the gray level histogram h (x).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611112995.6A CN108171658B (en) | 2016-12-07 | 2016-12-07 | Method and system for detecting gamma correction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611112995.6A CN108171658B (en) | 2016-12-07 | 2016-12-07 | Method and system for detecting gamma correction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108171658A CN108171658A (en) | 2018-06-15 |
| CN108171658B true CN108171658B (en) | 2021-07-20 |
Family
ID=62526065
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611112995.6A Active CN108171658B (en) | 2016-12-07 | 2016-12-07 | Method and system for detecting gamma correction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108171658B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101377919A (en) * | 2007-08-28 | 2009-03-04 | 晨星半导体股份有限公司 | Gamma correction device |
| CN101646091A (en) * | 2009-08-25 | 2010-02-10 | 浙江大学 | Gamma correction method and gamma correction device based on edge detection error diffusion |
| CN106342330B (en) * | 2009-08-12 | 2013-04-17 | 中国航空工业集团公司洛阳电光设备研究所 | A kind of image enchancing method of the gamma correction based on infrared image |
| CN104574337A (en) * | 2015-01-21 | 2015-04-29 | 山东科技大学 | Image enhancement method based on bilateral gamma correction and multi-scale image fusion |
| CN105590587A (en) * | 2016-03-24 | 2016-05-18 | 京东方科技集团股份有限公司 | Gamma correcting method and device for display modules |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5754929B2 (en) * | 2010-11-30 | 2015-07-29 | キヤノン株式会社 | Image processing apparatus and image processing method |
-
2016
- 2016-12-07 CN CN201611112995.6A patent/CN108171658B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101377919A (en) * | 2007-08-28 | 2009-03-04 | 晨星半导体股份有限公司 | Gamma correction device |
| CN106342330B (en) * | 2009-08-12 | 2013-04-17 | 中国航空工业集团公司洛阳电光设备研究所 | A kind of image enchancing method of the gamma correction based on infrared image |
| CN101646091A (en) * | 2009-08-25 | 2010-02-10 | 浙江大学 | Gamma correction method and gamma correction device based on edge detection error diffusion |
| CN104574337A (en) * | 2015-01-21 | 2015-04-29 | 山东科技大学 | Image enhancement method based on bilateral gamma correction and multi-scale image fusion |
| CN105590587A (en) * | 2016-03-24 | 2016-05-18 | 京东方科技集团股份有限公司 | Gamma correcting method and device for display modules |
Non-Patent Citations (3)
| Title |
|---|
| Analyzing the Effect of JPEG Compression on Local Variance of Image Intensity;Jianquan Yang;<IEEE Transactions on Image Processing>;20160630;第2647-2656页 * |
| 利用取证特征检测数字图像的篡改;张尚凡;《中国优秀硕士学位论文全文数据库 信息科技辑》;20140115;第1-53页 * |
| 抗几何失真的视频 Hashing 算法研究;项世军等;《中国科学: 信息科学》;20121231;第42卷(第5期);第578-587页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108171658A (en) | 2018-06-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20230215197A1 (en) | Systems and Methods for Detection and Localization of Image and Document Forgery | |
| US8867828B2 (en) | Text region detection system and method | |
| US8774514B2 (en) | Method of and apparatus for classifying image using histogram analysis, and method of and apparatus for recognizing text image using the histogram analysis | |
| CN103763515B (en) | A kind of video abnormality detection method based on machine learning | |
| CN104933721B (en) | Stitching image altering detecting method based on color filter array characteristic | |
| US8306262B2 (en) | Face tracking method for electronic camera device | |
| US8587685B2 (en) | Method and apparatus for retrieving label | |
| CN100550037C (en) | Utilize and improve Hausdorff apart from the method for extracting the identification human ear characteristic | |
| US7720288B2 (en) | Detecting compositing in a previously compressed image | |
| EP2149098A1 (en) | Deriving video signatures that are insensitive to picture modification and frame-rate conversion | |
| US8254690B2 (en) | Information processing apparatus, information processing method, and program | |
| US8655060B2 (en) | Night-scene light source detecting device and night-scene light source detecting method | |
| US20130170756A1 (en) | Edge detection apparatus, program and method for edge detection | |
| US10657628B2 (en) | Method of providing a sharpness measure for an image | |
| Kwok et al. | Alternative anti-forensics method for contrast enhancement | |
| CN103093458A (en) | Detecting method and detecting device for key frame | |
| CN107729794A (en) | Flame detecting method, flame detecting device and electronic equipment | |
| CN102301697B (en) | Video identifier creation device | |
| CN106709915B (en) | Image resampling operation detection method | |
| CN108171658B (en) | Method and system for detecting gamma correction | |
| CN110782392B (en) | Image processing method, device, electronic equipment and storage medium | |
| US20070086059A1 (en) | Image sharpness device and method | |
| CN106845540B (en) | Image resampling operation interpolation type identification method | |
| Zhu et al. | Recaptured image detection through enhanced residual-based correlation coefficients | |
| CN111223050A (en) | Real-time image edge detection algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 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 |