CN112669222A - Digital image defogging method based on wavelet domain histogram equalization - Google Patents
Digital image defogging method based on wavelet domain histogram equalization Download PDFInfo
- Publication number
- CN112669222A CN112669222A CN201910976371.6A CN201910976371A CN112669222A CN 112669222 A CN112669222 A CN 112669222A CN 201910976371 A CN201910976371 A CN 201910976371A CN 112669222 A CN112669222 A CN 112669222A
- Authority
- CN
- China
- Prior art keywords
- wavelet
- frequency
- coefficient
- integer
- low
- 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
Images
Landscapes
- Image Processing (AREA)
Abstract
The invention relates to the technical field of image processing, and discloses a digital image defogging method based on wavelet domain histogram equalization. Wherein, the method comprises the following steps: performing integer wavelet transformation on an image to be processed, and extracting a wavelet low-frequency integer coefficient, a wavelet intermediate-frequency integer coefficient and a wavelet high-frequency integer coefficient; drawing a wavelet domain histogram based on the wavelet low-frequency integer coefficient and the frequency of occurrence of each numerical value in the wavelet low-frequency integer coefficient; carrying out equalization processing on the drawn histogram to obtain an equalized wavelet low-frequency integer coefficient; and carrying out integer wavelet inverse transformation on the wavelet intermediate frequency integer coefficient, the wavelet high frequency integer coefficient and the equalized wavelet low frequency integer coefficient to obtain a new image after defogging. Therefore, the low-distortion digital image defogging method based on wavelet domain histogram equalization is realized, the detail information such as the contour line of the image can be effectively protected, the damage to the detail information in the defogging process can be avoided, and the image distortion degree can be reduced.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a digital image defogging method based on wavelet domain histogram equalization.
Background
Fog, as a particle that diffuses into the atmosphere, can cause adverse effects such as reduced definition and reduced contrast on digital images when its concentration is high, and may further affect the accuracy of digital image recognition systems. However, due to the fact that digital images are high in instantaneity, a method for obtaining clear images at another time is not feasible, and therefore if clear images are obtained, the method for enhancing the current foggy images by means of a digital signal processing technology is an effective way. The key point is to furthest protect other information in the picture from being influenced on the premise of removing the influence of the fog on the picture quality as much as possible, namely to reduce the distortion to the minimum.
One of the currently common digital image defogging methods is to perform equalization adjustment on a pixel value histogram of an image in a spatial domain. By the method, the equalization of the original image pixel distribution histogram can be realized, and the defogging effect is achieved. The method has the advantages that the contrast of the image can be obviously improved, the defogging effect is achieved to a certain degree, and the influence of the defogging effect on the image quality is reduced to a great extent. However, this method has a problem in that the contour information that should be retained in the image is lost during the "defogging" process, which causes different degrees of distortion for different images.
Disclosure of Invention
The invention provides a digital image defogging method based on wavelet domain histogram equalization, which can solve the problem of distortion caused by loss of contour information to be reserved in an image in the prior art.
The invention provides a digital image defogging method based on wavelet domain histogram equalization, wherein the method comprises the following steps:
performing integer wavelet transformation on an image to be processed, and extracting a wavelet low-frequency integer coefficient, a wavelet intermediate-frequency integer coefficient and a wavelet high-frequency integer coefficient;
drawing a wavelet domain histogram based on the wavelet low-frequency integer coefficient and the frequency of occurrence of each numerical value in the wavelet low-frequency integer coefficient;
carrying out equalization processing on the drawn histogram to obtain an equalized wavelet low-frequency integer coefficient;
and carrying out integer wavelet inverse transformation on the wavelet intermediate frequency integer coefficient, the wavelet high frequency integer coefficient and the equalized wavelet low frequency integer coefficient to obtain a new image after defogging.
Preferably, the integer wavelet transform of the image to be processed, and extracting the wavelet low-frequency integer coefficient, the wavelet intermediate-frequency integer coefficient, and the wavelet high-frequency integer coefficient comprises:
for each row of pixels of the matrix, sequentially selecting two adjacent pixels, calculating the average value of the sum of the two pixels and the average value of the difference of the two pixels, and storing the average value of the sum of the two pixels and the average value of the difference of the two pixels in the original positions of the two adjacent pixels to obtain a new matrix;
for each column of pixels of the new matrix, sequentially selecting two adjacent pixels, calculating the average value of the sum of the two pixels and the average value of the difference of the two pixels, and storing the average value of the sum of the two pixels and the average value of the difference of the two pixels in the original positions of the two adjacent pixels to obtain a wavelet low-frequency coefficient, a wavelet intermediate-frequency coefficient and a wavelet high-frequency coefficient;
and performing rounding on the wavelet low-frequency coefficient, the wavelet intermediate-frequency coefficient and the wavelet high-frequency coefficient to obtain a wavelet low-frequency integer coefficient, a wavelet intermediate-frequency integer coefficient and a wavelet high-frequency integer coefficient.
Preferably, the step of drawing a wavelet domain histogram based on the wavelet low-frequency integer coefficients and the frequency numbers of occurrence of the respective numerical values in the wavelet low-frequency integer coefficients comprises:
normalizing frequency numbers of occurrence of each numerical value in the wavelet low-frequency integer coefficient;
and drawing a wavelet domain histogram by taking the wavelet low-frequency integer coefficient as an abscissa and the normalized frequency number as an ordinate.
Preferably, the equalizing the drawn histogram to obtain equalized wavelet low-frequency integer coefficients includes:
transforming the drawn histogram by using a cumulative distribution function to obtain new frequency numbers corresponding to all numerical values in the wavelet low-frequency integer coefficient;
carrying out approximation processing on the new frequency count, and updating the frequency count of each numerical value;
and merging the frequency counts which are equal or close to each other in the updated frequency counts of the numerical values to obtain the equalized wavelet low-frequency integer coefficient.
Preferably, the basis functions of the integer wavelet transform are haar-basis functions.
By the technical scheme, integer wavelet change can be performed on an image to be processed (namely, the image to be processed containing fog) to obtain a wavelet low-frequency integer coefficient, a wavelet intermediate-frequency integer coefficient and a wavelet high-frequency integer coefficient, then a wavelet domain histogram can be drawn based on frequency of occurrence of each numerical value in the wavelet low-frequency integer coefficient and the wavelet low-frequency integer coefficient, an equalized wavelet low-frequency integer coefficient can be obtained by performing equalization processing on the drawn histogram, and finally integer wavelet inverse transformation is performed on the wavelet intermediate-frequency integer coefficient, the wavelet high-frequency integer coefficient and the equalized wavelet low-frequency integer coefficient to obtain a new image after fog removal. Therefore, the low-distortion digital image defogging method based on wavelet domain histogram equalization is realized, the detail information such as the contour line of the image can be effectively protected, the damage to the detail information in the defogging process can be avoided, and the image distortion degree can be reduced.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention. It is obvious that the drawings in the following description are only some embodiments of the invention, and that for a person skilled in the art, other drawings can be derived from them without inventive effort.
Fig. 1 shows a flow chart of a digital image defogging method based on wavelet domain histogram equalization according to an embodiment of the invention.
Detailed Description
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The relative arrangement of the components and steps, the numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise. Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description. Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate. In all examples shown and discussed herein, any particular value should be construed as merely illustrative, and not limiting. Thus, other examples of the exemplary embodiments may have different values. It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.
Fig. 1 shows a flow chart of a digital image defogging method based on wavelet domain histogram equalization according to an embodiment of the invention.
As shown in fig. 1, an embodiment of the present invention provides a digital image defogging method based on wavelet domain histogram equalization, wherein the method includes:
s100, performing integer wavelet transformation on an image to be processed, and extracting a wavelet low-frequency integer coefficient, a wavelet intermediate-frequency integer coefficient and a wavelet high-frequency integer coefficient;
the wavelet low-frequency integer coefficient can represent non-contour information and comprises a main defogging object; the wavelet intermediate frequency integer coefficient and the wavelet high frequency integer coefficient can represent detail information such as a contour.
Integer wavelet coefficients are derived by integer wavelet transform such that the digital image processing tool can render discrete integer wavelet coefficients into a histogram.
S102, drawing a wavelet domain histogram based on the wavelet low-frequency integer coefficient and frequency of occurrence of each numerical value in the wavelet low-frequency integer coefficient;
s104, carrying out equalization processing on the drawn histogram to obtain an equalized wavelet low-frequency integer coefficient;
s106, performing integer wavelet inverse transformation on the wavelet intermediate frequency integer coefficient, the wavelet high frequency integer coefficient and the equalized wavelet low frequency integer coefficient to obtain a new image after defogging.
Namely, fusion is carried out on the unprocessed wavelet intermediate frequency integer coefficient and the wavelet high frequency integer coefficient and the equalized wavelet low frequency integer coefficient to restore into a new image after defogging.
By the technical scheme, integer wavelet change can be performed on an image to be processed (namely, the image to be processed containing fog) to obtain a wavelet low-frequency integer coefficient, a wavelet intermediate-frequency integer coefficient and a wavelet high-frequency integer coefficient, then a wavelet domain histogram can be drawn based on frequency of occurrence of each numerical value in the wavelet low-frequency integer coefficient and the wavelet low-frequency integer coefficient, equalized wavelet low-frequency integer coefficients can be obtained by performing equalization processing on the drawn histogram, and finally integer wavelet inverse transformation is performed on the wavelet intermediate-frequency integer coefficient, the wavelet high-frequency integer coefficient and the equalized wavelet low-frequency integer coefficient to obtain a new image after defogging (namely, influence of substances such as water fog, smog or haze on picture quality can be removed). Therefore, the low-distortion digital image defogging method based on wavelet domain histogram equalization is realized, the detail information such as the contour line of the image can be effectively protected, the damage to the detail information in the defogging process can be avoided, and the image distortion degree can be reduced.
Furthermore, because the image processed by the method has high quality, if the image processed by the method is used as a material of the image recognition algorithm, the influence of objective factors on the accuracy of the algorithm is reduced, the performance of the algorithm is fully exerted, and the reliability of the algorithm result is improved.
According to an embodiment of the present invention, performing integer wavelet transform on an image to be processed, and extracting a wavelet low-frequency integer coefficient, a wavelet intermediate-frequency integer coefficient, and a wavelet high-frequency integer coefficient includes:
for each row of pixels of the matrix, sequentially selecting two adjacent pixels, calculating the average value of the sum of the two pixels and the average value of the difference of the two pixels, and storing the average value of the sum of the two pixels and the average value of the difference of the two pixels in the original positions of the two adjacent pixels to obtain a new matrix;
for example, taking two adjacent pixel values a and b as an example, the average value of the sum of the two values is (a + b)/2, and the value is stored at the original position of a; the average value of the difference is (a-b)/2, and the value is stored at the original position b.
For each column of pixels of the new matrix, sequentially selecting two adjacent pixels, calculating the average value of the sum of the two pixels and the average value of the difference of the two pixels, and storing the average value of the sum of the two pixels and the average value of the difference of the two pixels in the original positions of the two adjacent pixels to obtain a wavelet low-frequency coefficient, a wavelet intermediate-frequency coefficient and a wavelet high-frequency coefficient;
and performing rounding on the wavelet low-frequency coefficient, the wavelet intermediate-frequency coefficient and the wavelet high-frequency coefficient to obtain a wavelet low-frequency integer coefficient, a wavelet intermediate-frequency integer coefficient and a wavelet high-frequency integer coefficient.
Therefore, the wavelet low-frequency coefficient, the wavelet intermediate-frequency coefficient and the wavelet high-frequency coefficient can be obtained through integer wavelet transformation
Alternatively, under the condition that the format of the picture is represented by integer variables, the obtained wavelet low-frequency coefficient, wavelet intermediate-frequency coefficient and wavelet high-frequency coefficient are the wavelet low-frequency integer coefficient, the wavelet intermediate-frequency integer coefficient and the wavelet high-frequency integer coefficient without rounding operation.
According to an embodiment of the present invention, the rendering a wavelet domain histogram based on the wavelet low-frequency integer coefficient and the frequency of occurrence of each value in the wavelet low-frequency integer coefficient comprises:
normalizing frequency numbers of occurrence of each numerical value in the wavelet low-frequency integer coefficient;
and drawing a wavelet domain histogram by taking the wavelet low-frequency integer coefficient as an abscissa and the normalized frequency number as an ordinate.
That is, a histogram may be drawn based on the individual values themselves and the frequency of occurrence of the individual values of the wavelet low frequency integer coefficients.
According to an embodiment of the present invention, equalizing the drawn histogram to obtain an equalized wavelet low-frequency integer coefficient includes:
transforming the drawn histogram by using a cumulative distribution function to obtain new frequency numbers corresponding to all numerical values in the wavelet low-frequency integer coefficient;
carrying out approximation processing on the new frequency count, and updating the frequency count of each numerical value;
and merging the frequency counts which are equal or close to each other in the updated frequency counts of the numerical values to obtain the equalized wavelet low-frequency integer coefficient.
Histogram equalization is a method for adjusting the contrast of an image using histogram transformation in the field of image processing. The histogram of the original image is transformed into a form of approximate uniform distribution, and the dynamic change range of the pixel gray value is increased, so that the adjustment of the integral contrast of the image is realized, and the image quality is enhanced.
That is, the wavelet low-frequency integer coefficient distribution is made to tend to be equalized by performing equalization processing on the histogram.
The cumulative distribution function has the advantages of convenience and suitability for batch processing.
Alternatively, instead of using the cumulative distribution function to perform histogram transformation, the corresponding function may be set according to the proportional relationship of the histogram for adjustment.
The self-set function is flexible, the position of the current histogram distribution unbalance can be accurately selected, and the histogram distribution unbalance is uniformly extended to a required range by means of a proportional relation.
In addition, in practical applications, a self-setting function may be considered for the optimization of the result of the cumulative distribution function.
According to one embodiment of the invention, the basis functions of the integer wavelet transform are haar-basis functions.
Based on this, what is done with the image to be processed is a haar wavelet integer transform.
Similarly, the inverse integer wavelet transform corresponds to the inverse haar wavelet transform.
Since integer wavelet transforms are fully invertible, the method described in the present invention supports decomposition and reconstruction of graphs using any wavelet. In other words, any wavelet can be selected to perform defogging processing on any image, and the defogging effect is more obvious for color and photos with scenes and low distortion.
It should be understood by those skilled in the art that although the above embodiments describe the haar-basis function as the basis function of the integer wavelet transform, it is only exemplary and not intended to limit the present invention.
It can be seen from the above embodiments that the key point of the present invention is that the low-frequency coefficient of the integer wavelet transform represents the non-contour information (i.e. the main part affected by the "fog") of the image to be processed, and the "defogging" process is performed on the non-contour information, so that the damage of the existing method to details such as the image contour line is avoided, and the distortion degree is reduced. In addition, the method has the advantage of low distortion, so that the method has very important application value in the fields of image enhancement, image classification, image recognition algorithm development and the like.
In the description of the present invention, it is to be understood that the orientation or positional relationship indicated by the orientation words such as "front, rear, upper, lower, left, right", "lateral, vertical, horizontal" and "top, bottom", etc. are usually based on the orientation or positional relationship shown in the drawings, and are only for convenience of description and simplicity of description, and in the case of not making a reverse description, these orientation words do not indicate and imply that the device or element being referred to must have a specific orientation or be constructed and operated in a specific orientation, and therefore, should not be considered as limiting the scope of the present invention; the terms "inner and outer" refer to the inner and outer relative to the profile of the respective component itself.
Spatially relative terms, such as "above … …," "above … …," "above … …," "above," and the like, may be used herein for ease of description to describe one device or feature's spatial relationship to another device or feature as illustrated in the figures. It will be understood that the spatially relative terms are intended to encompass different orientations of the device in use or operation in addition to the orientation depicted in the figures. For example, if a device in the figures is turned over, devices described as "above" or "on" other devices or configurations would then be oriented "below" or "under" the other devices or configurations. Thus, the exemplary term "above … …" can include both an orientation of "above … …" and "below … …". The device may be otherwise variously oriented (rotated 90 degrees or at other orientations) and the spatially relative descriptors used herein interpreted accordingly.
It should be noted that the terms "first", "second", and the like are used to define the components, and are only used for convenience of distinguishing the corresponding components, and the terms have no special meanings unless otherwise stated, and therefore, the scope of the present invention should not be construed as being limited.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (5)
1. A digital image defogging method based on wavelet domain histogram equalization is characterized by comprising the following steps:
performing integer wavelet transformation on an image to be processed, and extracting a wavelet low-frequency integer coefficient, a wavelet intermediate-frequency integer coefficient and a wavelet high-frequency integer coefficient;
drawing a wavelet domain histogram based on the wavelet low-frequency integer coefficient and the frequency of occurrence of each numerical value in the wavelet low-frequency integer coefficient;
carrying out equalization processing on the drawn histogram to obtain an equalized wavelet low-frequency integer coefficient;
and carrying out integer wavelet inverse transformation on the wavelet intermediate frequency integer coefficient, the wavelet high frequency integer coefficient and the equalized wavelet low frequency integer coefficient to obtain a new image after defogging.
2. The method of claim 1, wherein performing an integer wavelet transform on the image to be processed and extracting wavelet low frequency integer coefficients, wavelet intermediate frequency integer coefficients, and wavelet high frequency integer coefficients comprises:
for each row of pixels of the matrix, sequentially selecting two adjacent pixels, calculating the average value of the sum of the two pixels and the average value of the difference of the two pixels, and storing the average value of the sum of the two pixels and the average value of the difference of the two pixels in the original positions of the two adjacent pixels to obtain a new matrix;
for each column of pixels of the new matrix, sequentially selecting two adjacent pixels, calculating the average value of the sum of the two pixels and the average value of the difference of the two pixels, and storing the average value of the sum of the two pixels and the average value of the difference of the two pixels in the original positions of the two adjacent pixels to obtain a wavelet low-frequency coefficient, a wavelet intermediate-frequency coefficient and a wavelet high-frequency coefficient;
and performing rounding on the wavelet low-frequency coefficient, the wavelet intermediate-frequency coefficient and the wavelet high-frequency coefficient to obtain a wavelet low-frequency integer coefficient, a wavelet intermediate-frequency integer coefficient and a wavelet high-frequency integer coefficient.
3. The method of claim 2, wherein rendering a wavelet domain histogram based on the wavelet low frequency integer coefficients and the frequency of occurrence of the respective values in the wavelet low frequency integer coefficients comprises:
normalizing frequency numbers of occurrence of each numerical value in the wavelet low-frequency integer coefficient;
and drawing a wavelet domain histogram by taking the wavelet low-frequency integer coefficient as an abscissa and the normalized frequency number as an ordinate.
4. The method of claim 3, wherein the equalizing the rendered histogram to obtain equalized wavelet low frequency integer coefficients comprises:
transforming the drawn histogram by using a cumulative distribution function to obtain new frequency numbers corresponding to all numerical values in the wavelet low-frequency integer coefficient;
carrying out approximation processing on the new frequency count, and updating the frequency count of each numerical value;
and merging the frequency counts which are equal or close to each other in the updated frequency counts of the numerical values to obtain the equalized wavelet low-frequency integer coefficient.
5. The method according to any one of claims 1-4, wherein the basis functions of the integer wavelet transform are Hardgy-functions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910976371.6A CN112669222A (en) | 2019-10-15 | 2019-10-15 | Digital image defogging method based on wavelet domain histogram equalization |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910976371.6A CN112669222A (en) | 2019-10-15 | 2019-10-15 | Digital image defogging method based on wavelet domain histogram equalization |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112669222A true CN112669222A (en) | 2021-04-16 |
Family
ID=75399870
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910976371.6A Pending CN112669222A (en) | 2019-10-15 | 2019-10-15 | Digital image defogging method based on wavelet domain histogram equalization |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112669222A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114332081A (en) * | 2022-03-07 | 2022-04-12 | 泗水县亿佳纺织厂 | Textile surface abnormity determination method based on image processing |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008283724A (en) * | 1999-08-17 | 2008-11-20 | Fujifilm Corp | Method, apparatus and program for image processing |
| CN105931201A (en) * | 2016-04-20 | 2016-09-07 | 北京航空航天大学 | Image subjective visual effect enhancing method based on wavelet transformation |
| CN106056525A (en) * | 2016-05-25 | 2016-10-26 | 金陵科技学院 | Multispectral remote sensing image authentication method and multispectral remote sensing image authentication system based on band perceptual feature fusion |
| CN106709891A (en) * | 2016-11-15 | 2017-05-24 | 哈尔滨理工大学 | Image processing method based on combination of wavelet transform and self-adaptive transform |
| CN108876741A (en) * | 2018-06-22 | 2018-11-23 | 中国矿业大学(北京) | A kind of image enchancing method under the conditions of complex illumination |
-
2019
- 2019-10-15 CN CN201910976371.6A patent/CN112669222A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008283724A (en) * | 1999-08-17 | 2008-11-20 | Fujifilm Corp | Method, apparatus and program for image processing |
| CN105931201A (en) * | 2016-04-20 | 2016-09-07 | 北京航空航天大学 | Image subjective visual effect enhancing method based on wavelet transformation |
| CN106056525A (en) * | 2016-05-25 | 2016-10-26 | 金陵科技学院 | Multispectral remote sensing image authentication method and multispectral remote sensing image authentication system based on band perceptual feature fusion |
| CN106709891A (en) * | 2016-11-15 | 2017-05-24 | 哈尔滨理工大学 | Image processing method based on combination of wavelet transform and self-adaptive transform |
| CN108876741A (en) * | 2018-06-22 | 2018-11-23 | 中国矿业大学(北京) | A kind of image enchancing method under the conditions of complex illumination |
Non-Patent Citations (4)
| Title |
|---|
| 张晶 著: "《数字图像处理应用研究》[M]", vol. 978, 长春：吉林大学出版社, pages: 165 - 169 * |
| 翁天阳 等: "基于改进的多层小波分解压缩感知图像处理", 山西电子技术, no. 06, pages 5 - 6 * |
| 陈大海 等: "指纹图像预处理效果分析", 计算机应用, vol. 26, no. 6, pages 1370 - 1373 * |
| 高岩 等: "一种基于改进直方图均衡的图像增强方法", 计算机仿真, no. 04, pages 198 - 201 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114332081A (en) * | 2022-03-07 | 2022-04-12 | 泗水县亿佳纺织厂 | Textile surface abnormity determination method based on image processing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhang et al. | Single image defogging based on multi-channel convolutional MSRCR | |
| Vijayalakshmi et al. | A comprehensive survey on image contrast enhancement techniques in spatial domain | |
| CN104063848B (en) | A kind of enhancement method of low-illumination image and device | |
| Maggioni et al. | Video denoising, deblocking, and enhancement through separable 4-D nonlocal spatiotemporal transforms | |
| KR102104403B1 (en) | Method and Apparatus for removing haze in a single image | |
| CN111275626A (en) | Video deblurring method, device and equipment based on ambiguity | |
| JP4456819B2 (en) | Digital image sharpening device | |
| WO2022257759A1 (en) | Image banding artifact removal method and apparatus, and device and medium | |
| CN108038833B (en) | Image self-adaptive sharpening method for gradient correlation detection and storage medium | |
| CN109743473A (en) | Video image 3 D noise-reduction method, computer installation and computer readable storage medium | |
| CN110782407B (en) | Single image defogging method based on sky region probability segmentation | |
| CN106412448B (en) | Wide dynamic range processing method and system based on single frame image | |
| CN113592776A (en) | Image processing method and device, electronic device and storage medium | |
| CN112508816B (en) | Infrared image sharpening method, sharpening processing system and terminal equipment | |
| CN111415317B (en) | Image processing method and device, electronic equipment and computer readable storage medium | |
| CN105631854A (en) | FPGA platform-based self-adaptive image definition evaluation algorithm | |
| CN116681606A (en) | Underwater uneven illumination image enhancement method, system, equipment and medium | |
| Dar et al. | An enhanced adaptive histogram equalization based local contrast preserving technique for HDR images | |
| US6323855B1 (en) | Sharpening edge features in digital image providing high frequency edge enhancement | |
| Galetto et al. | Edge-aware filter based on adaptive patch variance weighted average | |
| CN112669222A (en) | Digital image defogging method based on wavelet domain histogram equalization | |
| CN112233037B (en) | Image enhancement system and method based on image segmentation | |
| Ramya et al. | A novel method for the contrast enhancement of fog degraded video sequences | |
| CN110400270B (en) | License plate defogging method utilizing image decomposition and multiple correction fusion | |
| CN112884662A (en) | Three-dimensional digital map image processing method based on aerial image of aircraft |
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 |