CN111738927A - Face recognition feature enhancement and denoising method and system based on histogram equalization - Google Patents
Face recognition feature enhancement and denoising method and system based on histogram equalization Download PDFInfo
- Publication number
- CN111738927A CN111738927A CN202010205550.2A CN202010205550A CN111738927A CN 111738927 A CN111738927 A CN 111738927A CN 202010205550 A CN202010205550 A CN 202010205550A CN 111738927 A CN111738927 A CN 111738927A
- Authority
- CN
- China
- Prior art keywords
- image
- channel
- pixel
- histogram equalization
- face
- 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 23
- 238000013507 mapping Methods 0.000 claims abstract description 16
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 13
- 108091006146 Channels Proteins 0.000 claims description 32
- 238000004364 calculation method Methods 0.000 claims description 11
- 230000011218 segmentation Effects 0.000 claims description 10
- 230000008859 change Effects 0.000 claims description 5
- 230000009467 reduction Effects 0.000 claims description 4
- 230000008569 process Effects 0.000 abstract description 7
- 238000007781 pre-processing Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 238000005286 illumination Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005315 distribution function Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Facsimile Image Signal Circuits (AREA)
- Studio Devices (AREA)
Abstract
The invention provides a face recognition feature enhancement and denoising method and system based on histogram equalization, wherein the method comprises the following steps: step 1, inputting a face image, and segmenting the face image according to a channel; step 2, acquiring the total number of pixels and the number of pixels corresponding to a preset pixel value for each segmented single-channel image; step 3, applying histogram equalization to each divided single-channel image, and determining the mapping relation between the original image pixel value and the equalization value; and 4, obtaining a single-channel face image after histogram equalization according to the mapping relation, and combining the single-channel face image after histogram equalization to obtain the face image which is finally processed. The image features after the processing are more obvious, and the method has better performance no matter in the training processing or preprocessing process of the face recognition algorithm.
Description
Technical Field
The invention relates to the field of image enhancement and computer vision, in particular to a face recognition feature enhancement and denoising method and system based on histogram equalization.
Background
In the process of training and using the face recognition algorithm, the quality of the face image directly influences the accuracy of the algorithm. In an actual scene, illumination is one of the main factors affecting the quality of a face image. Too strong or too weak light can affect the accuracy of extracting features from a face image by a face recognition algorithm, and even can cause loss of detail features of the face image in serious cases. The brightness information of the image is balanced through a histogram equalization algorithm, so that the brightness of the image is relatively uniform, and the consistency of the light information of the image in the face recognition process is ensured.
The traditional histogram equalization algorithm processes the input original face image through remapping of pixel values in the original image, and increases the range of the image pixel values, so that the brightness in the processed face image tends to be uniform. However, for a face image with low overall brightness, the pixel values of the pixels are mostly concentrated in a part with a small value, the variation range is small, the contrast is poor, and simultaneously, the whole image also has noise distribution. If histogram equalization is directly performed on the image, although the contrast of the face image can be improved, the influence of noise is amplified, and the requirement of image enhancement cannot be met.
Disclosure of Invention
In order to solve the defects in the prior art, the invention provides a face recognition feature enhancement and denoising method and system based on histogram equalization.
The invention provides a face recognition feature enhancement and denoising method based on histogram equalization, which comprises the following steps:
step 1, inputting a face image, and segmenting the face image according to a channel;
step 2, acquiring the total number of pixels and the number of pixels corresponding to a preset pixel value for each segmented single-channel image;
step 3, applying histogram equalization to each divided single-channel image, and determining the mapping relation between the original image pixel value and the equalized pixel value;
and 4, obtaining a single-channel face image after histogram equalization according to the mapping relation, and combining the single-channel face image after histogram equalization to obtain the face image which is finally processed.
Further, the step 1 specifically includes:
the face image is divided into a plurality of images of different channels, and for an image of which the RGB face image is divided into R, G, B three channels, if a single-channel gray image is input, the channel division is not performed, and an original histogram equalization algorithm is adopted.
Further, the step 2 includes that the number of pixels corresponding to the predetermined pixel value is the number of pixels at each level lower than the pixel threshold p;
for the statistics of the number of pixel points lower than the pixel threshold value p in the segmented single-channel image, the statistics of the number of pixels of corresponding pixel values of the image are as follows:
where p is the image pixel threshold, niThe number of pixel points for the ith pixel value.
Further, the step 3 specifically includes:
for each single-channel image, calculating a converted pixel value G according to a pixel value i in the original imageiCalculated as follows:
wherein, CiThe total number of pixel points is less than a pixel threshold value i, N is the total number of pixels of a single channel of an original face image, i is an image pixel value, p is a pixel threshold value, GiThrough this step, histogram equalization of each divided single-channel image is completed for the processed pixel values.
Further, the step 4 comprises:
and for each segmented single-channel face image, calculating to obtain a pixel value after each pixel is changed, obtaining a plurality of single-channel face images after histogram equalization from the pixel values after each pixel is changed, and combining the plurality of single-channel face images according to the original channel sequence to obtain the final image after noise reduction enhancement.
The invention also provides a face recognition feature enhancement and denoising system based on histogram equalization, which comprises:
the segmentation module is used for inputting a face image and segmenting the face image according to the channel;
the statistical module is used for acquiring the total number of pixels and the number of pixels corresponding to a preset pixel value for each segmented single-channel image; the number of pixels corresponding to each pixel value;
the calculation module is used for applying histogram equalization to each divided single-channel image and determining the mapping relation between the original image pixel value and the equalized pixel value;
and the output module is used for obtaining the single-channel face image after histogram equalization according to the mapping relation and obtaining the face image finally processed by combining the single-channel face image after histogram equalization.
Further, the segmentation module segments the face image into a plurality of images of different channels, and for an image of which the RGB face image is segmented into R, G, B three channels, if a single-channel grayscale image is input, the channel segmentation is not performed, and an original histogram equalization algorithm is used.
Further, after the RGB image is divided according to the channels, the statistics module applies the following statistics on the number of pixels with pixel values lower than the pixel value p in the divided single-channel image:
where p is the image pixel threshold, niIs the number of pixel points having a pixel value of i.
Further, the calculation module calculates a transformed pixel value G for each single-channel image according to a pixel value i in the original imageiCalculated as follows:
wherein, CiThe total number of pixel points is less than a pixel threshold value i, and N is a single-channel pixel of the original face imageTotal number, i is image pixel value, p is pixel threshold, GiThrough this step, histogram equalization of each divided single-channel image is completed for the processed pixel values.
Further, the output module obtains a pixel value of each pixel after the pixel change through calculation for each divided single-channel face image, obtains a plurality of single-channel face images after histogram equalization from the pixel value of each pixel after the pixel change, and obtains a final image after the enhanced noise reduction by combining the plurality of single-channel face images according to the original channel sequence.
Has the advantages that:
according to the technical scheme provided by the invention, when the histogram equalization is carried out to process the face image, the details such as color, texture and the like are prevented from being distorted, the image brightness is more uniform, and the common light noise in the face image is eliminated.
Drawings
FIG. 1 is a flowchart of a face recognition feature enhancement and denoising method based on histogram equalization according to the present invention.
Detailed Description
For a better understanding of the present invention, reference is made to the following description taken in conjunction with the accompanying drawings and examples. The invention provides a face recognition feature enhancement and denoising algorithm based on a histogram equalization image, so that the problems of uneven light and influence on face feature extraction and further on face recognition effect of a face image commonly existing in the face image are solved, illumination noise in the face image is reduced, and illumination in the face image is more uniform.
According to an embodiment of the present invention, a face recognition feature enhancement and denoising algorithm based on histogram equalization image is provided, as shown in fig. 1, including the following steps:
dividing an original image into a plurality of single-channel images according to channels; if the original image is an RGBA image, the image is divided into four single-channel images, and if the original image is an HSV image, the image is divided into three single-channel images; if the image is a GRB image, the image is divided into three single-channel images.
Acquiring the total number of pixels and the number of pixels corresponding to a preset pixel value for each segmented single-channel image;
according to the pixel distribution condition obtained by statistics, respectively applying a histogram equalization algorithm to each channel image for processing, and calculating to obtain the corresponding relation between the pixel value of the original image and the pixel value of the target image;
setting pixel values of all channels of the original face image pixels according to the mapping relation of the pixel values obtained by the previous step;
specifically, for each segmented single-channel image, the total number of pixels and the number of pixels corresponding to a predetermined pixel value are acquired; specifically, the number of pixels of different pixel values is found from the cumulative distribution function. Namely: for the statistics of the number of pixels below the pixel value p in the segmented single-channel image, the statistics of the number of pixels of the corresponding pixel value of the image are applied as follows:
where p is the image pixel threshold, niIs the number of pixel points having a pixel value of i.
Processing the original face image according to the mapping relationship between the pixel values in the original face image and the processed pixel values obtained in the above steps, specifically, the mapping relationship is calculated as follows:
for each single-channel image, calculating a converted pixel value G according to a pixel value i in the original imageiCalculated as follows:
wherein, CiThe total number of pixel points is less than a pixel threshold value i, N is the total number of pixels of a single channel of an original face image, i is an image pixel value, p is a pixel threshold value, GiThrough this step, histogram equalization of each divided single-channel image is completed for the processed pixel values. Calculating pixel points in each channel image according to the calculation methodAnd (3) obtaining an image after histogram equalization by using the processed pixel values, and finally combining the single-channel images to obtain a face image after histogram equalization, so that on one hand, image noise caused by violent light change is eliminated, and the face characteristics are highlighted.
Based on the same inventive concept, the invention provides a face recognition feature enhancement and denoising system based on histogram equalization, which can be divided into the following modules according to functions and logics, namely a segmentation module, a statistic module, a calculation module and an output module, wherein the main functions of the modules are further explained as follows:
the segmentation module is used for inputting a face image and segmenting the face image according to the channel;
the statistical module is used for acquiring the total number of pixels and the number of pixels corresponding to a preset pixel value for each segmented single-channel image;
the calculation module is used for applying histogram equalization to each divided single-channel image and determining the mapping relation between the original image pixel value and the equalized pixel value;
and the output module is used for obtaining the single-channel face image after histogram equalization according to the mapping relation and obtaining the face image finally processed by combining the single-channel face image after histogram equalization.
In the implementation process of the system provided by the invention, a segmentation module preprocesses an acquired face image, and divides the original face image into a plurality of independent single-channel images according to the specific condition of the original face image;
on the basis of preprocessing of the segmentation module, the statistic module applies the statistics of the number of pixels with corresponding pixel values of the image as follows for the statistics of the number of pixels with lower pixel values p in the segmented single-channel image according to the following calculation model:
where p is the image pixel threshold, niIs as followsNumber of pixel points of i pixel values.
Correspondingly, the calculation module calculates the mapping relationship between the pixel value of the original single-channel face image and the transformed pixel value based on the total number of pixels of the image and the number of pixels corresponding to each pixel value according to the following calculation model:
wherein, CiThe pixel value is less than the total number of the pixels of i, N is the total number of the pixels of a single channel of the original face image, and p is an image pixel threshold value. And finally, combining the processed single-channel images by an output module, and outputting the combined single-channel images as a final result.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above disclosure is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the scope of the invention.
Claims (10)
1. A face recognition feature enhancement and denoising method based on histogram equalization is characterized in that:
step 1, inputting a face image, and segmenting the face image according to a channel;
step 2, acquiring the total number of pixels and the number of pixels corresponding to a preset pixel value for each segmented single-channel image;
step 3, applying histogram equalization to each divided single-channel image, and determining the mapping relation between the original image pixel value and the equalized pixel value;
and 4, obtaining a single-channel face image after histogram equalization according to the mapping relation, and combining the single-channel face image after histogram equalization to obtain the face image which is finally processed.
2. The histogram equalized face recognition feature enhancement and denoising method of claim 1, wherein the step 1 specifically comprises:
the face image is divided into a plurality of images of different channels, and for an image of which the RGB face image is divided into R, G, B three channels, if a single-channel gray image is input, the channel division is not performed, and an original histogram equalization algorithm is adopted.
3. The histogram equalized face recognition feature enhancement and denoising method according to claim 1, wherein the step 2 includes that the number of pixels corresponding to the predetermined pixel value is the number of pixels at each level having a pixel value lower than a pixel threshold value p;
for the statistics of the number of pixel points lower than the pixel threshold value p in the segmented single-channel image, the statistics of the number of pixels of corresponding pixel values of the image are as follows:
where p is the image pixel threshold, niThe number of pixel points for the ith pixel value.
4. The histogram equalized face recognition feature enhancement and denoising method as claimed in claim 1, wherein said step 3 specifically comprises:
for each single-channel image, calculating a converted pixel value G according to a pixel value i in the original imageiCalculated as follows:
wherein, CiThe total number of pixel points is less than a pixel threshold value i, N is the total number of pixels of a single channel of an original face image, i is an image pixel value, p is a pixel threshold value, GiThrough this step, histogram equalization of each divided single-channel image is completed for the processed pixel values.
5. The histogram equalized face recognition feature enhancement and denoising method of claim 1, wherein the step 4 comprises:
and for each segmented single-channel face image, calculating to obtain a pixel value after each pixel is changed, obtaining a plurality of single-channel face images after histogram equalization from the pixel values after each pixel is changed, and combining the plurality of single-channel face images according to the original channel sequence to obtain the final image after noise reduction enhancement.
6. A face recognition feature enhancement and denoising system based on histogram equalization is characterized by comprising:
the segmentation module is used for inputting a face image and segmenting the face image according to the channel;
the statistical module is used for acquiring the total number of pixels and the number of pixels corresponding to a preset pixel value for each segmented single-channel image;
the calculation module is used for applying histogram equalization to each divided single-channel image and determining the mapping relation between the original image pixel value and the equalized pixel value;
and the output module is used for obtaining the single-channel face image after histogram equalization according to the mapping relation and obtaining the face image finally processed by combining the single-channel face image after histogram equalization.
7. The histogram equalization based face recognition feature enhancement and denoising system of claim 6, wherein the segmentation module segments the face image into a plurality of images of different channels, and for the RGB face image into R, G, B images of three channels, if the input is a single-channel gray image, the original histogram equalization algorithm is used without channel segmentation.
8. The histogram equalization based face recognition feature enhancement and denoising system of claim 6, wherein: the number of pixels corresponding to the preset pixel value refers to the number of pixels at each level with pixel values lower than a pixel threshold value p;
for the statistics of the number of pixels below the pixel value p in the segmented single-channel image, the statistics of the number of pixels of the corresponding pixel value of the image are applied as follows:
where p is the image pixel threshold, niThe number of pixel points for the ith pixel value.
9. The histogram equalization based face recognition feature enhancement and denoising system of claim 6, wherein the computation module computes, for each single channel image, transformed pixel values G from pixel values i in the original imageiCalculated as follows:
wherein, CiThe total number of pixel points is less than a pixel threshold value i, N is the total number of pixels of a single channel of an original face image, i is an image pixel value, p is a pixel threshold value, GiThrough this step, histogram equalization of each divided single-channel image is completed for the processed pixel values.
10. The histogram equalization based face recognition feature enhancement and denoising system of claim 6, wherein:
the output module obtains the pixel value of each pixel after the change through calculation for each divided single-channel face image, obtains a plurality of single-channel face images after histogram equalization through the pixel value of each pixel after the change, and obtains the final image after the enhanced noise reduction through combining the plurality of single-channel face images according to the original channel sequence.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010205550.2A CN111738927A (en) | 2020-03-23 | 2020-03-23 | Face recognition feature enhancement and denoising method and system based on histogram equalization |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010205550.2A CN111738927A (en) | 2020-03-23 | 2020-03-23 | Face recognition feature enhancement and denoising method and system based on histogram equalization |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111738927A true CN111738927A (en) | 2020-10-02 |
Family
ID=72646944
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010205550.2A Pending CN111738927A (en) | 2020-03-23 | 2020-03-23 | Face recognition feature enhancement and denoising method and system based on histogram equalization |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111738927A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114648455A (en) * | 2022-03-14 | 2022-06-21 | 青岛海信医疗设备股份有限公司 | Ultrasonic image processing method, electronic device and storage medium |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101430759A (en) * | 2008-12-04 | 2009-05-13 | 上海大学 | Optimized recognition pretreatment method for human face |
CN101873429A (en) * | 2010-04-16 | 2010-10-27 | 杭州海康威视软件有限公司 | Processing method and device of image contrast |
CN103914683A (en) * | 2013-12-31 | 2014-07-09 | 闻泰通讯股份有限公司 | Gender identification method and system based on face image |
CN105096282A (en) * | 2014-05-19 | 2015-11-25 | 厦门美图之家科技有限公司 | Image data defogging method based on histogram equalization |
CN105303152A (en) * | 2014-07-15 | 2016-02-03 | 中国人民解放军理工大学 | Human body re-recognition method |
CN107067385A (en) * | 2017-01-23 | 2017-08-18 | 上海兴芯微电子科技有限公司 | A kind of image enchancing method and device |
CN107203752A (en) * | 2017-05-25 | 2017-09-26 | 四川云图睿视科技有限公司 | A kind of combined depth study and the face identification method of the norm constraint of feature two |
CN108133463A (en) * | 2017-12-14 | 2018-06-08 | 中国北方车辆研究所 | The noise-reduction method and system of a kind of histogram-equalized image |
-
2020
- 2020-03-23 CN CN202010205550.2A patent/CN111738927A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101430759A (en) * | 2008-12-04 | 2009-05-13 | 上海大学 | Optimized recognition pretreatment method for human face |
CN101873429A (en) * | 2010-04-16 | 2010-10-27 | 杭州海康威视软件有限公司 | Processing method and device of image contrast |
CN103914683A (en) * | 2013-12-31 | 2014-07-09 | 闻泰通讯股份有限公司 | Gender identification method and system based on face image |
CN105096282A (en) * | 2014-05-19 | 2015-11-25 | 厦门美图之家科技有限公司 | Image data defogging method based on histogram equalization |
CN105303152A (en) * | 2014-07-15 | 2016-02-03 | 中国人民解放军理工大学 | Human body re-recognition method |
CN107067385A (en) * | 2017-01-23 | 2017-08-18 | 上海兴芯微电子科技有限公司 | A kind of image enchancing method and device |
CN107203752A (en) * | 2017-05-25 | 2017-09-26 | 四川云图睿视科技有限公司 | A kind of combined depth study and the face identification method of the norm constraint of feature two |
CN108133463A (en) * | 2017-12-14 | 2018-06-08 | 中国北方车辆研究所 | The noise-reduction method and system of a kind of histogram-equalized image |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114648455A (en) * | 2022-03-14 | 2022-06-21 | 青岛海信医疗设备股份有限公司 | Ultrasonic image processing method, electronic device and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Bora | Importance of image enhancement techniques in color image segmentation: a comprehensive and comparative study | |
Gao et al. | Sand-dust image restoration based on reversing the blue channel prior | |
CN108182671B (en) | Single image defogging method based on sky area identification | |
CN110969046B (en) | Face recognition method, face recognition device and computer-readable storage medium | |
CN109903294B (en) | Image processing method and device, electronic equipment and readable storage medium | |
CN109214996B (en) | Image processing method and device | |
CN107067375A (en) | A kind of image defogging method based on dark channel prior and marginal information | |
CN111489322A (en) | Method and device for adding sky filter to static picture | |
CN114298985B (en) | Defect detection method, device, equipment and storage medium | |
CN108898561B (en) | Defogging method, server and system for foggy image containing sky area | |
CN113392702B (en) | Target identification method based on self-adaptive image enhancement under weak illumination environment | |
CN111192213A (en) | Image defogging adaptive parameter calculation method, image defogging method and system | |
CN111738927A (en) | Face recognition feature enhancement and denoising method and system based on histogram equalization | |
CN112200755B (en) | Image defogging method | |
CN105184758B (en) | A kind of method of image defogging enhancing | |
CN107239761B (en) | Fruit tree branch pulling effect evaluation method based on skeleton angular point detection | |
GB2522663A (en) | A method of selecting a region of interest | |
Al-Ameen | Expeditious contrast enhancement for grayscale images using a new swift algorithm | |
CN116664608A (en) | Target detection and positioning method based on image enhancement | |
CN114998186B (en) | Method and system for detecting surface scab defect of copper starting sheet based on image processing | |
CN113781368B (en) | Infrared imaging device based on local information entropy | |
Peng et al. | An underwater attenuation image enhancement method with adaptive color compensation and detail optimization | |
CN114358131A (en) | Digital photo frame intelligent photo optimization processing system | |
CN115880181A (en) | Method, device and terminal for enhancing image contrast | |
CN113223098B (en) | Preprocessing optimization method for image color classification |
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 |