CN104394336B - Image outline sharpening method and system based on cmos image sensor - Google Patents
Image outline sharpening method and system based on cmos image sensor Download PDFInfo
- Publication number
- CN104394336B CN104394336B CN201410720346.9A CN201410720346A CN104394336B CN 104394336 B CN104394336 B CN 104394336B CN 201410720346 A CN201410720346 A CN 201410720346A CN 104394336 B CN104394336 B CN 104394336B
- Authority
- CN
- China
- Prior art keywords
- point
- decision
- image
- brightness value
- fac
- 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
Abstract
The invention discloses a kind of image outline sharpening method based on cmos image sensor and system, wherein, this method includes：A pixel is as decision-point on selection present image, and extracts the brightness value of neighbor pixel in decision-point periphery N × N neighborhoods；Whether it is profile point that the decision-point is judged by brightness value comparison in difference；High-pass filtering is carried out to it if the decision-point is profile point, high-frequency information is reduced, and calculate sharpening adjustment amount to be sharpened processing to the decision-point.By using method disclosed by the invention, image outline can be strengthened, image outline is apparent from.
Description
Technical field
The present invention relates to technical field of image processing, more particularly to a kind of image outline based on cmos image sensor are sharp
Change method.
Background technology
With developing rapidly for multimedia technology, various video electronic products are popularized at a terrific speed.Current
Video product can mainly realize display and the capture still image of video flowing.Fig. 1 gives is based on CMOS in the prior art
The Computer Vision basic functional principle schematic diagram of imaging sensor.As shown in figure 1, passing through figure in image acquisition unit first
The raw image data needed as sensor from extraneous acquisition；Then view data is passed to by image by image transmitting unit
Processing unit, including processes such as necessary compression, transmission and decompressions；Then in graphics processing unit to image system
The necessary processing that the self-defined or user that unites pre-sets；Treated image is finally converted into specific form and form
Exported.
But, now the Computer Vision based on cmos image sensor does not consider image outline in the art, because
And the profile of the image obtained is more obscured.
The content of the invention
It is an object of the invention to provide a kind of image outline sharpening method based on cmos image sensor and system, pass through
Edge contrast strengthens image outline, is apparent from image outline.
The purpose of the present invention is achieved through the following technical solutions：
A kind of image outline sharpening method based on cmos image sensor, this method includes：
A pixel is as decision-point on selection present image, and extracts adjacent pixel in decision-point periphery N × N neighborhoods
The brightness value of point；
Whether it is profile point that the decision-point is judged by brightness value comparison in difference；
High-pass filtering is carried out to it if the decision-point is profile point, high-frequency information is reduced, and calculate sharpening adjustment amount
To be sharpened processing to the decision-point.
Further, this method also includes：The step of IMAQ, image transmitting and image procossing；
Wherein, IMAQ is from the original view data of extraneous collection；
Image transmitting is that the original view data is compressed, transmitted and decompression；
Image procossing is that the view data after decompression is pre-processed to improve picture quality；Then, to pretreatment
Image afterwards carries out color interpolation processing, the rgb image data of acquisition；Color space is carried out to the rgb image data again to turn
Change, obtain YUV image data；The present image is then the YUV image.
Further, described extract in decision-point periphery N × N neighborhoods includes after the brightness value of neighbor pixel：
Calculate maximum brightness value Ymax, minimum luminance value Ymin and the luminance reference value of all pixels point in N × N neighborhoods
Ymean, is expressed as：
Ymax=max ([Y11, Y12 ..., YN1, YN2 ..., YNN])；
Ymin=min ([Y11, Y12 ..., YN1, YN2 ..., YNN])；
Ymean=(Ymax+Ymin)/2.
Further, it is described to judge whether the decision-point is that profile point includes by brightness value comparison in difference：
If Ymid-Ymean ﹥ T, the decision-point is profile point；Wherein, T is threshold value set in advance, and Ymid sentences to be described
The brightness value of fixed point.
Further, it is described that high-pass filtering is carried out to it if the decision-point is profile point, high-frequency information is reduced, and count
Calculate sharpening adjustment amount includes to be sharpened processing to the decision-point：
High-pass filtering is carried out, high-frequency information is reduced, its formula is：
Ydif=Ymid-Ymean；
Calculate and sharpen adjustment amount, its formula is：
Ydelta=Sharp_fac × Ydif；
Sharp_fac=fac_pos；
Wherein, Ydif and Ydelta is that Sharp_fac is sharpens gain, and fac_pos is just with positive and negative signed number
To sharpening gain；
The sharpening adjustment amount for calculating acquisition is added on the brightness value of the decision-point, Edge contrast is completed, is expressed as：
Yout=Ymid+Ydelta.
A kind of image outline sharpening system based on cmos image sensor, the system includes：
Point selection module is judged, for selecting on present image a pixel as decision-point；
Brightness value extraction module, the brightness value for extracting neighbor pixel in decision-point periphery N × N neighborhoods；
Profile point judge module, for judging whether the decision-point is profile point by brightness value comparison in difference；
Edge contrast module, for being profile point if the decision-point if carry out high-pass filtering to it, reduce high-frequency information,
And calculate sharpening adjustment amount to be sharpened processing to the decision-point.
Further, the system also includes：Image capture module, image transmission module and image processing module；
Wherein, described image acquisition module, for gathering original view data from extraneous；
Described image transport module, for being compressed, transmitting to the original view data and decompression；
Described image processing module, picture quality is improved for being pre-processed to the view data after decompression；So
Afterwards, color interpolation processing, the rgb image data of acquisition are carried out to pretreated image；The rgb image data is carried out again
Color space is changed, and obtains YUV image data；The present image is then the YUV image.
Further, described extract in decision-point periphery N × N neighborhoods includes after the brightness value of neighbor pixel：
Calculate maximum brightness value Ymax, minimum luminance value Ymin and the luminance reference value of all pixels point in N × N neighborhoods
Ymean, is expressed as：
Ymax=max ([Y11, Y12 ..., YN1, YN2 ..., YNN])；
Ymin=min ([Y11, Y12 ..., YN1, YN2 ..., YNN])；
Ymean=(Ymax+Ymin)/2.
Further, it is described to judge whether the decision-point is that profile point includes by brightness value comparison in difference：
If Ymid-Ymean ﹥ T, the decision-point is profile point；Wherein, T is threshold value set in advance, and Ymid sentences to be described
The brightness value of fixed point.
Further, it is described that high-pass filtering is carried out to it if the decision-point is profile point, high-frequency information is reduced, and count
Calculate sharpening adjustment amount includes to be sharpened processing to the decision-point：
If Ymid-Ymean ﹥ T, the decision-point is profile point；Wherein, T is threshold value set in advance, and Ymid sentences to be described
The brightness value of fixed point；
High-pass filtering is carried out, high-frequency information is reduced, its formula is：
Ydif=Ymid-Ymean；
Calculate and sharpen adjustment amount, its formula is：
Ydelta=Sharp_fac × Ydif；
Sharp_fac=fac_pos；
Wherein, Ydif and Ydelta is that Sharp_fac is sharpens gain, and fac_pos is just with positive and negative signed number
To sharpening gain；
The sharpening adjustment amount for calculating acquisition is added on the brightness value of the decision-point, Edge contrast is completed, is expressed as：
Yout=Ymid+Ydelta.
As seen from the above technical solution provided by the invention, brightness value of this method based on neighbor pixel is carried out
Edge contrast, can effectively handle the fuzzy situation of image outline；And this is simple and easy to apply, logical resource is taken less.
Brief description of the drawings
In order to illustrate the technical solution of the embodiments of the present invention more clearly, being used required in being described below to embodiment
Accompanying drawing be briefly described, it should be apparent that, drawings in the following description are only some embodiments of the present invention, for this
For the those of ordinary skill in field, on the premise of not paying creative work, other can also be obtained according to these accompanying drawings
Accompanying drawing.
The Computer Vision base based on cmos image sensor in the prior art that Fig. 1 provides for background of invention
This operation principle schematic diagram；
Fig. 2 is a kind of stream for image outline sharpening method based on cmos image sensor that the embodiment of the present invention one is provided
Cheng Tu；
Fig. 3 is a kind of showing for image outline sharpening system based on cmos image sensor that the embodiment of the present invention two is provided
It is intended to.
Embodiment
With reference to the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Ground is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.Based on this
The embodiment of invention, the every other implementation that those of ordinary skill in the art are obtained under the premise of creative work is not made
Example, belongs to protection scope of the present invention.
Embodiment one
Fig. 2 is a kind of stream for image outline sharpening method based on cmos image sensor that the embodiment of the present invention one is provided
Cheng Tu.As shown in Fig. 2 this method includes：
A pixel is as decision-point in step 21, selection present image, and extracts in decision-point periphery N × N neighborhoods
The brightness value of neighbor pixel.
In the embodiment of the present invention, the present image can be YUV image；Before the step 21 is performed, in addition to：
The step of IMAQ, image transmitting and image procossing；
Wherein, IMAQ is from the original view data of extraneous collection；
Image transmitting is that the original view data is compressed, transmitted and decompression；
Image procossing is that the view data after decompression is pre-processed to improve picture quality；Then, to pretreatment
Image afterwards carries out color interpolation processing, the rgb image data of acquisition；Color space is carried out to the rgb image data again to turn
Change, obtain YUV image data；The present image is then the YUV image.
Described extract in decision-point periphery N × N neighborhoods includes after the brightness value of neighbor pixel：Calculate N × N neighborhoods
Maximum brightness value Ymax, the minimum luminance value Ymin and luminance reference value Ymean of interior all pixels point, are expressed as：
Ymax=max ([Y11, Y12 ..., YN1, YN2 ..., YNN])；
Ymin=min ([Y11, Y12 ..., YN1, YN2 ..., YNN])；
Ymean=(Ymax+Ymin)/2.
The numerical value of the N can be set according to the actual requirements, for example, 3 can be set to.
Step 22, by brightness value comparison in difference judge whether the decision-point is profile point.
In the embodiment of the present invention, if it is determined that the brightness value Ymid and luminance reference value Ymean of point difference are sufficiently large, then it is assumed that
The decision-point is profile point；Otherwise, it is not profile point.
I.e., it is possible to be expressed as：If Ymid-Ymean ﹥ T, the decision-point is profile point；Otherwise, it is not profile point；The T
For threshold value set in advance, the size of the value can according to the actual requirements or experience is set.
Step 23, if the decision-point is profile point carry out high-pass filtering to it, reduce high-frequency information, and calculate sharpening
Adjustment amount to the decision-point is sharpened processing.
The carry out high-pass filtering, reduces high-frequency information, and its formula is：
Ydif=Ymid-Ymean；
Described calculate sharpens adjustment amount, and its formula is：
Ydelta=Sharp_fac × Ydif；
Sharp_fac=fac_pos；
Wherein, Ydif and Ydelta is with positive and negative signed number；Sharp_fac is sharpening gain；Ymid is described
The brightness value of decision-point；Fac_pos is positive sharpening gain (i.e. when the decision-point is that profile point sharpening adjustment amount is positive sharp
Change gain).
The sharpening adjustment amount for calculating acquisition is added on the brightness value of the decision-point, Edge contrast is completed, is expressed as：
Yout=Ymid+Ydelta.
In addition, if it is determined that when point is not profile point, it would however also be possible to employ above-mentioned formula is adjusted, and is divided into the following two kinds situation：
If 1) Ymid >=Ymean, but the two difference is less than T；Positive sharpening Gain tuning, i.e. Sharp_fac can also now be carried out
=fac_pos；If 2) Ymid<Ymean, now carries out negative sense and sharpens Gain tuning, i.e. Sharp_fac=fac_neg, fac_
Neg is to sharpen gain with negative sense.
Wherein, above-mentioned parameter fac_pos and fac_neg size can according to the actual requirements or experience is set.
By such scheme as can be seen that the sharpening adjustment amount in the embodiment of the present invention is acted in brightness, based on this
Processing mode can also link with skin tone signal, effectively handle the effect on facial contour.
After above-mentioned processing, the view data after processing is exported according to the form and form of formulation.
The scheme of the embodiment of the present invention has the following advantages that and feature in terms of existing technologies, mainly：
1) the inventive method is simple and easy to apply, takes logical resource less；
2) present invention function without using when, be not turned on arithmetic logic, reduce power consumption；
3) brightness value based on neighbor pixel is sharpened processing, can effectively handle the fuzzy feelings of image outline
Condition.
Embodiment two
A kind of image outline sharpening system based on cmos image sensor that the embodiment of the present invention two is provided；System master
Including：
Point selection module 311 is judged, for selecting on present image a pixel as decision-point；
Brightness value extraction module 312, the brightness value for extracting neighbor pixel in decision-point periphery N × N neighborhoods；
Profile point judge module 313, for judging whether the decision-point is profile point by brightness value comparison in difference；
Edge contrast module 314, for being profile point if the decision-point if carry out high-pass filtering to it, reduction high frequency letter
Breath, and calculate sharpening adjustment amount to be sharpened processing to the decision-point.
Further, the system also includes：Image capture module 32, image transmission module 33 and image processing module 34；
Wherein, described image acquisition module 32, for gathering original view data from extraneous；
Described image transport module 33, for being compressed, transmitting to the original view data and decompression；
Described image processing module 34, picture quality is improved for being pre-processed to the view data after decompression；
Then, color interpolation processing, the rgb image data of acquisition are carried out to pretreated image；The rgb image data is entered again
Row color space is changed, and obtains YUV image data；The present image is then the YUV image.
Further, described extract in decision-point periphery N × N neighborhoods includes after the brightness value of neighbor pixel：
Calculate maximum brightness value Ymax, minimum luminance value Ymin and the luminance reference value of all pixels point in N × N neighborhoods
Ymean, is expressed as：
Ymax=max ([Y11, Y12 ..., YN1, YN2 ..., YNN])；
Ymin=min ([Y11, Y12 ..., YN1, YN2 ..., YNN])；
Ymean=(Ymax+Ymin)/2.
Further, it is described to judge whether the decision-point is that profile point includes by brightness value comparison in difference：
If Ymid-Ymean ﹥ T, the decision-point is profile point；Wherein, T is threshold value set in advance, and Ymid sentences to be described
The brightness value of fixed point.
Further, it is described that high-pass filtering is carried out to it if the decision-point is profile point, high-frequency information is reduced, and count
Calculate sharpening adjustment amount includes to be sharpened processing to the decision-point：
If Ymid-Ymean ﹥ T, the decision-point is profile point；Wherein, T is threshold value set in advance, and Ymid sentences to be described
The brightness value of fixed point；
High-pass filtering is carried out, high-frequency information is reduced, its formula is：
Ydif=Ymid-Ymean；
Calculate and sharpen adjustment amount, its formula is：
Ydelta=Sharp_fac × Ydif；
Sharp_fac=fac_pos；
Wherein, Ydif and Ydelta is that Sharp_fac is sharpens gain, and fac_pos is just with positive and negative signed number
To sharpening gain；
The sharpening adjustment amount for calculating acquisition is added on the brightness value of the decision-point, Edge contrast is completed, is expressed as：
Yout=Ymid+Ydelta.
In addition, if it is determined that when point is not profile point, it would however also be possible to employ above-mentioned formula is adjusted, and is divided into the following two kinds situation：
If 1) Ymid >=Ymean, but the two difference is less than T；Positive sharpening Gain tuning, i.e. Sharp_fac can also now be carried out
=fac_pos；If 2) Ymid<Ymean, now carries out negative sense and sharpens Gain tuning, i.e. Sharp_fac=fac_neg, fac_
Neg is to sharpen gain with negative sense.
Wherein, above-mentioned parameter fac_pos and fac_neg size can according to the actual requirements or experience is set.
Module 311-314 in the embodiment of the present invention can also be integrated in a module and " realize mould in sharpening module 31 "
Block 311-314 function, it is specific as shown in Figure 3.
It should be noted that the specific implementation for the function that each functional module included in said system is realized exists
Have a detailed description, therefore repeated no more herein in each embodiment above.
It is apparent to those skilled in the art that, for convenience and simplicity of description, only with above-mentioned each function
The division progress of module is for example, in practical application, as needed can distribute above-mentioned functions by different function moulds
Block is completed, i.e., the internal structure of system is divided into different functional modules, to complete all or part of work(described above
Energy.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment can
To be realized by software, the mode of necessary general hardware platform can also be added to realize by software.Understood based on such,
The technical scheme of above-described embodiment can be embodied in the form of software product, the software product can be stored in one it is non-easily
The property lost storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in, including some instructions are to cause a computer to set
Standby (can be personal computer, server, or network equipment etc.) performs the method described in each embodiment of the invention.
The foregoing is only a preferred embodiment of the present invention, but protection scope of the present invention be not limited thereto,
Any one skilled in the art is in the technical scope of present disclosure, the change or replacement that can be readily occurred in,
It should all be included within the scope of the present invention.Therefore, protection scope of the present invention should be with the protection model of claims
Enclose and be defined.
Claims (4)
1. a kind of image outline sharpening method based on cmos image sensor, it is characterised in that this method includes：
A pixel is as decision-point on selection present image, and extracts neighbor pixel in decision-point periphery N × N neighborhoods
Brightness value；Extract in decision-point periphery N × N neighborhoods includes after the brightness value of neighbor pixel：Calculate institute in N × N neighborhoods
There are maximum brightness value Ymax, the minimum luminance value Ymin and luminance reference value Ymean of pixel, be expressed as：Ymax=max
([Y11,Y12,…,YN1,YN2,...,YNN])；Ymin=min ([Y11, Y12 ..., YN1, YN2 ..., YNN])；Ymean
=(Ymax+Ymin)/2；
Whether it is profile point that the decision-point is judged by brightness value comparison in difference, including：If Ymid-Ymean ﹥ T, this is sentenced
Pinpoint as profile point；Wherein, T is threshold value set in advance, and Ymid is the brightness value of the decision-point；
High-pass filtering is carried out to it if the decision-point is profile point, reduces high-frequency information, and calculate sharpening adjustment amount to come pair
The decision-point is sharpened processing；Step is as follows：
High-pass filtering is carried out, high-frequency information is reduced, its formula is：
Ydif=Ymid-Ymean；
Calculate and sharpen adjustment amount, its formula is：
Ydelta=Sharp_fac × Ydif；
Sharp_fac=fac_pos；
Wherein, Ymean is luminance reference value, and Ymid is the brightness value of decision-point, and Ydif and Ydelta is to have symbol with positive and negative
Number, Sharp_fac is sharpens gain, and fac_pos sharpens gain to be positive；
The sharpening adjustment amount for calculating acquisition is added on the brightness value of the decision-point, Edge contrast is completed, is expressed as：
Yout=Ymid+Ydelta.
2. according to the method described in claim 1, it is characterised in that this method also includes：IMAQ, image transmitting and image
The step of processing；
Wherein, IMAQ is from the original view data of extraneous collection；
Image transmitting is that the original view data is compressed, transmitted and decompression；
Image procossing is that the view data after decompression is pre-processed to improve picture quality；Then, to pretreated
Image carries out color interpolation processing, the rgb image data of acquisition；Color space conversion is carried out to the rgb image data again, obtained
Obtain YUV image data；The present image is then the YUV image.
3. a kind of image outline sharpening system based on cmos image sensor, it is characterised in that the system includes：
Point selection module is judged, for selecting on present image a pixel as decision-point；
Brightness value extraction module, the brightness value for extracting neighbor pixel in decision-point periphery N × N neighborhoods；
Extract in decision-point periphery N × N neighborhoods includes after the brightness value of neighbor pixel：Calculate all pictures in N × N neighborhoods
Maximum brightness value Ymax, the minimum luminance value Ymin and luminance reference value Ymean of vegetarian refreshments, are expressed as：Ymax=max ([Y11,
Y12,…,YN1,YN2,...,YNN])；Ymin=min ([Y11, Y12 ..., YN1, YN2 ..., YNN])；Ymean=(Ymax
+Ymin)/2；
Profile point judge module, for judging whether the decision-point is profile point by brightness value comparison in difference：Including：If
Ymid-Ymean ﹥ T, then the decision-point is profile point；Wherein, T is threshold value set in advance, and Ymid is the brightness of the decision-point
Value；
Edge contrast module, for being profile point if the decision-point if carry out high-pass filtering to it, reduce high-frequency information, and count
Calculate and sharpen adjustment amount to be sharpened processing to the decision-point；Step is as follows：
High-pass filtering is carried out, high-frequency information is reduced, its formula is：
Ydif=Ymid-Ymean；
Calculate and sharpen adjustment amount, its formula is：
Ydelta=Sharp_fac × Ydif；
Sharp_fac=fac_pos；
Wherein, Ymean is luminance reference value, and Ymid is the brightness value of decision-point, and Ydif and Ydelta is to have symbol with positive and negative
Number, Sharp_fac is sharpens gain, and fac_pos sharpens gain to be positive；
The sharpening adjustment amount for calculating acquisition is added on the brightness value of the decision-point, Edge contrast is completed, is expressed as：
Yout=Ymid+Ydelta.
4. system according to claim 3, it is characterised in that the system also includes：Image capture module, image transmitting mould
Block and image processing module；
Wherein, described image acquisition module, for gathering original view data from extraneous；
Described image transport module, for being compressed, transmitting to the original view data and decompression；
Described image processing module, picture quality is improved for being pre-processed to the view data after decompression；Then, it is right
Pretreated image carries out color interpolation processing, the rgb image data of acquisition；Color is carried out to the rgb image data again
Space is changed, and obtains YUV image data；The present image is then the YUV image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410720346.9A CN104394336B (en) | 2014-12-01 | 2014-12-01 | Image outline sharpening method and system based on cmos image sensor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410720346.9A CN104394336B (en) | 2014-12-01 | 2014-12-01 | Image outline sharpening method and system based on cmos image sensor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104394336A CN104394336A (en) | 2015-03-04 |
| CN104394336B true CN104394336B (en) | 2017-10-27 |
Family
ID=52612165
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410720346.9A Active CN104394336B (en) | 2014-12-01 | 2014-12-01 | Image outline sharpening method and system based on cmos image sensor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104394336B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110909571B (en) * | 2018-09-17 | 2022-05-03 | 武汉资联虹康科技股份有限公司 | High-precision face recognition space positioning method |
| CN109724983B (en) * | 2018-11-13 | 2021-04-27 | 新昌县馁侃农业开发有限公司 | Refrigerator integrity analysis platform |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1892696A (en) * | 2005-07-08 | 2007-01-10 | 深圳迈瑞生物医疗电子股份有限公司 | Supersonic image edge-sharpening and speck-inhibiting method |
| CN1956556A (en) * | 2005-10-27 | 2007-05-02 | 联发科技股份有限公司 | Edge compensated feature detector and method thereof, and image system |
| CN101102515A (en) * | 2006-07-03 | 2008-01-09 | 三星电子株式会社 | Apparatus and method for correcting edge in an image |
| CN101364303A (en) * | 2008-09-23 | 2009-02-11 | 四川长虹电器股份有限公司 | Edge extracting and processing method |
| CN101452573A (en) * | 2007-12-04 | 2009-06-10 | 比亚迪股份有限公司 | Image edge enhancing method |
| CN101727659A (en) * | 2008-10-31 | 2010-06-09 | 比亚迪股份有限公司 | Method and system for enhancing image edge |
| CN101799866A (en) * | 2010-03-31 | 2010-08-11 | 拓维信息系统股份有限公司 | Method for positioning facial organs of cartoon character on mobile phone |
| CN102547304A (en) * | 2011-12-31 | 2012-07-04 | 蔡静 | Device for obtaining video image data and method therefore |
-
2014
- 2014-12-01 CN CN201410720346.9A patent/CN104394336B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1892696A (en) * | 2005-07-08 | 2007-01-10 | 深圳迈瑞生物医疗电子股份有限公司 | Supersonic image edge-sharpening and speck-inhibiting method |
| CN1956556A (en) * | 2005-10-27 | 2007-05-02 | 联发科技股份有限公司 | Edge compensated feature detector and method thereof, and image system |
| CN101102515A (en) * | 2006-07-03 | 2008-01-09 | 三星电子株式会社 | Apparatus and method for correcting edge in an image |
| CN101452573A (en) * | 2007-12-04 | 2009-06-10 | 比亚迪股份有限公司 | Image edge enhancing method |
| CN101364303A (en) * | 2008-09-23 | 2009-02-11 | 四川长虹电器股份有限公司 | Edge extracting and processing method |
| CN101727659A (en) * | 2008-10-31 | 2010-06-09 | 比亚迪股份有限公司 | Method and system for enhancing image edge |
| CN101799866A (en) * | 2010-03-31 | 2010-08-11 | 拓维信息系统股份有限公司 | Method for positioning facial organs of cartoon character on mobile phone |
| CN102547304A (en) * | 2011-12-31 | 2012-07-04 | 蔡静 | Device for obtaining video image data and method therefore |
Non-Patent Citations (2)
| Title |
|---|
| 图像局部方向均值边缘检测算法;郑秀清、何坤、周激流;《电子科技大学学报》;20110930;第40卷(第5期);全文 * |
| 图像边缘检测经典算法研究综述;管宋蕊、丁辉;《首都师范大学学报(自然科学版)》;20091031;第30卷;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104394336A (en) | 2015-03-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110689500B (en) | Face image processing method and device, electronic equipment and storage medium | |
| CN104952036A (en) | Facial beautification method and electronic equipment in real-time video | |
| CN112837251B (en) | Image processing method and device | |
| CN107659799B (en) | Image pickup apparatus, image processing method, and storage medium | |
| US20190188534A1 (en) | Methods and systems for converting a line drawing to a rendered image | |
| CN107424137B (en) | Text enhancement method and device, computer device and readable storage medium | |
| CN111967319B (en) | Living body detection method, device, equipment and storage medium based on infrared and visible light | |
| CN106530309A (en) | Video matting method and system based on mobile platform | |
| CN105791636A (en) | Video processing system | |
| WO2020108010A1 (en) | Video processing method and apparatus, electronic device and storage medium | |
| CN103366390A (en) | Terminal, image processing method and device thereof | |
| CN104394336B (en) | Image outline sharpening method and system based on cmos image sensor | |
| WO2023056950A1 (en) | Image processing method and electronic device | |
| CN106997608A (en) | A kind of method and device for generating halation result figure | |
| CN105763747A (en) | Mobile terminal for achieving high-quality real-time facial beautification | |
| CN103985102A (en) | Image processing method and system | |
| CN105976309A (en) | High-efficiency and easy-parallel implementation beauty mobile terminal | |
| CN201726464U (en) | Novel video image sharpening processing device | |
| Zhang et al. | Hardware implementation for haze removal with adaptive filtering | |
| CN103136530A (en) | Method for automatically recognizing target images in video images under complex industrial environment | |
| CN110991325A (en) | Model training method, image recognition method and related device | |
| CN115063800B (en) | Text recognition method and electronic equipment | |
| CN108491820B (en) | Method, device and equipment for identifying limb representation information in image and storage medium | |
| EP4047547A1 (en) | Method and system for removing scene text from images | |
| CN111383289A (en) | Image processing method, image processing device, terminal equipment and computer readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |