CN102136068A - Average grey-based method for extracting effective information region of range gating image - Google Patents
Average grey-based method for extracting effective information region of range gating image Download PDFInfo
- Publication number
- CN102136068A CN102136068A CN 201110079661 CN201110079661A CN102136068A CN 102136068 A CN102136068 A CN 102136068A CN 201110079661 CN201110079661 CN 201110079661 CN 201110079661 A CN201110079661 A CN 201110079661A CN 102136068 A CN102136068 A CN 102136068A
- Authority
- CN
- China
- Prior art keywords
- effective information
- average gray
- value
- image
- zone
- 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.)
- Granted
Links
Images
Abstract
The invention discloses an average grey-based method for extracting an effective information region of a range gating image. The method comprises the following steps: calculating an initial threshold by utilizing priori knowledge; extracting an effective information region of an original image by utilizing the initial threshold; calculating an average grey value of an edge part of the extracted information region according to the edge part; acquiring a largest eight-connected region of an image background according to a cut result of the initial threshold, wherein the average grey value of the largest eight-connected region is approximate to that of a background region, and the average value of the largest eight-connected region is used as an average grey value of the background region; and comparing the average value of a strip region at the edge of the effective information region with the average grey value of the background region, measuring whether a final cut result cuts information and noise optimally or not by the difference of the average value of the strip region at the edge of the effective information region and the average value of the background region, adjusting the value of the initial threshold if the difference is not in an acceptable range, and performing iterative operation on the adjusted value used as a new initial threshold until the difference is in an acceptable range.
Description
Technical field
The present invention relates to technical field of computer vision, relate to a kind of extracting method of the range gating image effective information district based on average gray.
Background technology
The range gating technique of laser imaging has become the focus of domestic and international research, mainly be because this technology can be worked unglazed the photograph under the conditions environmental at night, operating distance is far away, and has abilities such as real broken mist, rain, snow, can use under the lower environment of visibility., have a wide range of applications in fields such as remote night vision, Underwater Target Detection and three-dimensional imagings.
By the time-delay between control strobe pulse and the laser pulse, the range gating imaging system can realize the imaging to the particular space section.According to the information characteristics of sectioning image, image can be divided into effective information district and noise range.Wherein the echoed signal that forms after the effective information district laser radiation target is produced by collection, and the noise range is the driftlessness echoed signal then, mainly is atmospheric turbulence noise and system device noise etc.But under the effect of echo broadening effect, block of information and noise range are difficult to distinguish.The echo broadening effect is the build-in attribute of range-gated imaging technique.Under the effect of this effect, introduced a signaling zone and tail signaling zone respectively at the head and the afterbody of the corresponding block of information of space section, this two parts zone is the transitional region of block of information and noise range just.It is significant for definite system imaging interval and operating distance accurately to distinguish effective information district and noise range, the especially application aspect three-dimensional imaging.
Be head it off, can adopt image process method to realize the extraction of block of information.Image processing techniques is to adopt computing machine that image is analyzed, and according to the relation between each pixel of image carry out image classification, cut apart to reach required result's technology.Image processing techniques has guaranteed also can restore real scene in low-qualityer image, and final scene is being shown important meaning.The extraction in the present image information district binarization methods that adopt based on grey level histogram more, and start with from the entropy of computed image and maximum between-cluster variance etc. and to obtain final segmentation threshold.This class algorithm has only been considered image and background evident difference, and can't provide accurate extraction result to the part that image border and background differ less.This type of image segmentation result then more is used for the bigger part of image border graded, and range gating laser night vision image is difficult to obtain the extraction of accurate effective information district with these class methods.
Summary of the invention
(1) technical matters that will solve
Can't accurately extract the problem in effective information district at the prior art that echo broadening effect feature of image causes, the present invention proposes a kind of extracting method of the range gating image effective information district based on average gray, accurately extract the purpose in effective information district with the influence that reaches echo broadening effect and system noise down.
(2) technical scheme
For achieving the above object, technical scheme provided by the invention is as follows:
A kind of extracting method of the range gating image effective information district based on average gray, this method comprises:
Utilize priori to calculate initial threshold, utilize this initial threshold that original image is carried out the extraction in effective information district, calculate the average gray value at this edge, block of information according to the marginal portion of obtaining, block of information; According to the segmentation result of initial threshold, obtain maximum eight connected regions of image background, the average gray value and the background area average gray value of these maximum eight connected regions are close, utilize the mean value of these maximum eight connected regions to distinguish average gray value as a setting; Relatively whether effective information area edge belt-like zone mean value and background area average gray value are weighed final segmentation result with the difference of the two and optimally information and noise are cut apart; If the difference of the two is in tolerance interval, then final segmentation result is optimally cut apart information and noise, and finishes; If the difference of the two is not in tolerance interval, then final segmentation result is not optimally cut apart information and noise, initial threshold is carried out threshold value adjustment operation, carries out iterative operation as new initial threshold, until the two difference in tolerance interval.
In the such scheme, the described priori of utilizing is calculated initial threshold, be to utilize grey level histogram, begin to add up number of pixels on each gray level from minimum gray level, when pixel count reaches the certain proportion of image total pixel number on the minimum gray level, this gray level is decided to be the initial threshold of algorithm.Described certain proportion is a priori, determines according to system's characteristics and area surroundings characteristics, can be partitioned into most information scene; Described initial threshold should be not excessive, otherwise with it indirect assignment, to prevent the more Algorithm Error that causes of information in the image; According to the feature of image that night, laser became, described initial threshold should be below 10.
In the such scheme, the described extraction that utilizes initial threshold original image to be carried out the effective information district, be to utilize binaryzation, morphological operation to carry out the extraction in effective information district when utilizing initial threshold to carry out the extraction in effective information district, specifically comprise: utilize this initial threshold to carry out image binaryzation, and expansive working is carried out in the block of information in the image; The noise of noise range has obtained reinforcement equally in this process, by the judgement to the area of eight connected regions, regards as noise with handling the less zone of number of pixels, back, and is included into the noise range.
In the such scheme, described definite background area average gray value method, be that morphology methods is adopted in the extraction of largest connected background area, specifically comprise: the image that takes out the effective information district as the noise range, operation is corroded in the noise range, to remove the influence of the effective information area edge that may exist, obtain some eight connected regions after the corrosion operation; By adding up the number that each eight connected region comprises pixel, get eight wherein maximum connected regions, be required maximum eight connected regions; Calculate the average gray value of the average gray value of this eight connected region as the noise range, calculate each regional average gray value for calculating the mean value of all gray values of pixel points in this zone, its computing formula is as follows:
In the above-mentioned formula, Avalue is an average gray value, and i represents i pixel in this zone, and it is n that n represents the pixel count in this zone, and fi is i gray values of pixel points in the zone for this reason then.
In the such scheme, the outermost width that described effective information area edge belt-like zone is gained effective information district is the banded contour area of two pixels; Expansive working is done in the district to the gained effective information, uses expansion results to deduct the preceding image that expands, and can obtain the outside, edge in effective information district.
In the such scheme, the difference of described effective information area edge belt-like zone mean value and background area average gray value, be effective information area edge belt-like zone mean value subtracting background district average gray value, the overall brightness in effective information district is higher than the background area, influence effective information area edge belt-like zone mean value near the background area average gray value and be subjected to the echo broadening effect, so after the effective information district extracted accurately, the difference of the two should be in the positive small range.
In the such scheme, described the two difference is in tolerance interval, be meant effective information area edge belt-like zone mean value greater than the background area average gray value, and the echo broadening effect makes effective information area edge gray scale near background, so the difference of the two should be less than a threshold value.
In the such scheme, described initial threshold is carried out in the threshold value adjustment operation, threshold value adjustment operation is divided into two basic directions of adjusting: threshold value increases or threshold value reduces, concrete grammar is: effective information area edge belt-like zone mean value is compared with the background area average gray value, if the difference of effective information area edge belt-like zone mean value and background area average gray value is higher than set threshold value, then this threshold value is deducted 1, as new threshold value, carry out iterative operation with this; If effective information area edge belt-like zone mean value and background area average gray value differ less, it is excessive that then possibility is extracted in the block of information, and former threshold value is added 1 as new threshold value, carries out interative computation; When the difference of effective information area edge belt-like zone mean value and background area average gray value met the requirements, then the gained result was net result.
(3) beneficial effect
From technique scheme as can be seen, the present invention has following beneficial effect:
1, utilizes the present invention, because having introduced image border average gray information processing result judges, the extraction situation of effective information area edge can directly influence processing procedure, so, the method has good adaptability to the soft edge phenomenon that the echo broadening effect brings, and can extract the image border under the influence of echo broadening effect exactly.
2, utilize the present invention, because what utilize is the average gray in zone, make this function reduce greatly to the variation sensitivity of gradation of image, so, this algorithm can be used in the violent range gating laser night vision image of variation of image grayscale well, also can accurately extract the effective information district when picture quality is low.
Description of drawings
Fig. 1 is the method flow diagram of the extraction in the range gating image effective information district based on average gray provided by the invention;
Fig. 2 is the belt-like zone synoptic diagram that the present invention is based on, and wherein a is an effective information district synoptic diagram; B is the synoptic diagram of belt-like zone;
Fig. 3 is the belt-like zone position view of actual picture, and wherein a is an original image, and b is the belt-like zone of two pixels in edge in the effective information district of getting, and c is that the noise of two pixels removes belt-like zone around the block of information;
Fig. 4 utilizes this invention gained result and law, maximum entropy method (MEM) gained result's contrast greatly, and wherein a is an original image; B extracts the result for the effective information district that adopts big law; The result of c for adopting maximum entropy method to obtain; D is for adopting the result of the inventive method; Result of the present invention obviously is better than preceding two kinds of methods.
Main element symbol description: S is the effective information district among the figure, and SE is the edge in effective information district, and B is the noise range, and BE is the edge that the effective information district is pressed close in the noise range.
Embodiment
For making the purpose, technical solutions and advantages of the present invention clearer, below in conjunction with specific embodiment, and with reference to accompanying drawing, the present invention is described in more detail.
The objective of the invention is to design the influence that a kind of algorithm overcomes echo broadening effect in the range gating laser night vision image, by adopting method based on average gray, obtain effective information zone accurately, reached practical effect, obtained block of information result accurately.
Fig. 1 is the method flow diagram of the extraction in the range gating image effective information district based on average gray provided by the invention, this method comprises: utilize priori to calculate initial threshold, utilize this initial threshold that original image is carried out the extraction in effective information district, calculate this marginal portion, block of information average gray value according to the marginal portion of obtaining, block of information; According to the segmentation result of initial threshold, obtain maximum eight connected regions of image background, the average gray value and the background area average gray value of these maximum eight connected regions are close, utilize the mean value of these maximum eight connected regions to distinguish average gray value as a setting; Relatively whether effective information area edge belt-like zone mean value and background area average gray value are weighed final segmentation result with the difference of the two and optimally information and noise are cut apart; If the difference of the two is in tolerance interval, then final segmentation result is optimally cut apart information and noise, and finishes; If the difference of the two is not in tolerance interval, then final segmentation result is not optimally cut apart information and noise, initial threshold is carried out threshold value adjustment operation, carries out iterative operation as new initial threshold, until the two difference in tolerance interval.
Wherein, the described priori of utilizing is calculated initial threshold, is to utilize grey level histogram, begins to add up number of pixels on each gray level from minimum gray level, when pixel count reaches the certain proportion of image total pixel number on the minimum gray level, this gray level is decided to be the initial threshold of algorithm.Described certain proportion is a priori, determines according to system's characteristics and area surroundings characteristics, can be partitioned into most information scene; Described initial threshold should be not excessive, otherwise with it indirect assignment, to prevent the more Algorithm Error that causes of information in the image; According to the feature of image that night, laser became, described initial threshold should be below 10.
The described extraction that utilizes initial threshold original image to be carried out the effective information district, be to utilize binaryzation, morphological operation to carry out the extraction in effective information district when utilizing initial threshold to carry out the extraction in effective information district, specifically comprise: utilize this initial threshold to carry out image binaryzation, and expansive working is carried out in the block of information in the image; The noise of noise range has obtained reinforcement equally in this process, by the judgement to the area of eight connected regions, regards as noise with handling the less zone of number of pixels, back, and is included into the noise range.
Described definite background area average gray value method, be that morphology methods is adopted in the extraction of largest connected background area, specifically comprise: the image that takes out the effective information district as the noise range, operation is corroded in the noise range, to remove the influence of the effective information area edge that may exist, obtain some eight connected regions after the corrosion operation; By adding up the number that each eight connected region comprises pixel, get eight wherein maximum connected regions, be required maximum eight connected regions; Calculate the average gray value of the average gray value of this eight connected region as the noise range, calculate each regional average gray value for calculating the mean value of all gray values of pixel points in this zone, its computing formula is as follows:
In the above-mentioned formula, Avalue is an average gray value, and i represents i pixel in this zone, and it is n that n represents the pixel count in this zone, and fi is i gray values of pixel points in the zone for this reason then.
The outermost width that described effective information area edge belt-like zone is gained effective information district is the banded contour area of two pixels; Expansive working is done in the district to the gained effective information, uses expansion results to deduct the preceding image that expands, and can obtain the outside, edge in effective information district.
The difference of described effective information area edge belt-like zone mean value and background area average gray value, be effective information area edge belt-like zone mean value subtracting background district average gray value, the overall brightness in effective information district is higher than the background area, influence effective information area edge belt-like zone mean value near the background area average gray value and be subjected to the echo broadening effect, so after the effective information district extracted accurately, the difference of the two should be in the positive small range.
Described the two difference be meant effective information area edge belt-like zone mean value greater than the background area average gray value, and the echo broadening effect makes effective information area edge gray scale near background, so the difference of the two should be less than a threshold value in tolerance interval.
Described initial threshold is carried out in the threshold value adjustment operation, threshold value adjustment operation is divided into two basic directions of adjusting: threshold value increases or threshold value reduces, concrete grammar is: effective information area edge belt-like zone mean value is compared with the background area average gray value, if the difference of effective information area edge belt-like zone mean value and background area average gray value is higher than set threshold value, then this threshold value is deducted 1, as new threshold value, carry out iterative operation with this; If effective information area edge belt-like zone mean value and background area average gray value differ less, it is excessive that then possibility is extracted in the block of information, and former threshold value is added 1 as new threshold value, carries out interative computation; When the difference of effective information area edge belt-like zone mean value and background area average gray value met the requirements, then the gained result was net result.
Embodiment
Obtain initial threshold by statistics and the method for estimating the suitable minimum gray level of effective information district area ratio.As effective information district among Fig. 1 is 9 pixels, and all images is 25 pixels, can estimate to be<0.5, perhaps>0.3 etc.
The most of pixel in the block of information of range gating laser imaging image is than noise range brightness height, and according to the pixel quantity of this ratio and image, the picture noise that can obtain estimating removes pixel quantity.The grey level histogram of image is begun statistics from lowermost level, when the background pixel that reaches this ratio representative when the total quantity of grey level histogram low side is counted, the gray level that finally stops to locate is decided to be initial threshold.When so threshold value is greater than the empirical value of this area background, the maximum empirical value of this area is decided to be initial threshold.
Utilize this initial threshold that image is operated, the initial effective information district that obtains image extracts.Obtain the S zone shown in Fig. 1 (a).S district and N district are done preliminary the differentiation.
Extract the error of bringing not to the utmost in order to reduce the effective information district as far as possible, image is done expansive working, compression noise district area.And to the compression after the noise range add up eight connected regions, obtain the area maximum connected region representative image noise range, utilize formula (1) to calculate this regional average gray value.Be designated as AvalueSN.
Utilize morphological operation, the image that utilized for the 3rd step obtained obtains two belt-like zones: the fringe region in effective information district as the E district among Fig. 1 (b), is the edge belt-like zone of effective information district S; Noise removes to be surrounded by the belt-like zone in effective information district, as the N district among Fig. 1 (b).
Utilize formula (1) to calculate and go on foot two the belt-like zones calculating average gray value separately that obtains the 3rd.Be respectively AvalueS and AvalueN.
Relatively the value of AvalueN and AvalueSN is slightly larger than AvalueSN within the specific limits as if AvalueN, and then the extraction of key diagram picture is accurately, and the extraction result in the 3rd step can be used as final extraction result.If AvalueN is bigger than certain threshold value than AvalueSN, illustrate that then the effective information district that is extracted is littler than authentic and valid block of information, then selection of threshold is excessive.Initial threshold is done-1 operation, obtain new threshold value, returned for second step, the beginning iterative process.
If AvalueN is more smaller than AvalueSN, equate or differ very little, the extraction that the effective information district then is described may be excessive, then judges the relation of AvalueS and AvalueSN, if the certain threshold value of AvalueS serious offense AvalueSN, then accurately locate in the effective information district, as net result.Otherwise, threshold value is done+1 operation, thereby is dwindled gained effective information district.Bring this new threshold value into the 3rd step, the beginning iteration is until obtaining accepting the result.
To final extraction result, calculate the average relative gradient value of two belt-like zones of the 3rd step gained, be designated as AgradS and AgradN, if AgradS greater than the AgradN certain value, illustrates that then the result is an acceptable, during result's extraction accurately.The processing image that can be used as next step uses.
Above-described specific embodiment; purpose of the present invention, technical scheme and beneficial effect are further described; institute is understood that; the above only is specific embodiments of the invention; be not limited to the present invention; within the spirit and principles in the present invention all, any modification of being made, be equal to replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (9)
1. extracting method based on the range gating image effective information district of average gray is characterized in that this method comprises:
Utilize priori to calculate initial threshold, utilize this initial threshold that original image is carried out the extraction in effective information district, calculate the average gray value of this marginal portion according to the marginal portion of obtaining, block of information; According to the segmentation result of initial threshold, obtain maximum eight connected regions of image background, the average gray value and the background area average gray value of these maximum eight connected regions are close, utilize the mean value of these maximum eight connected regions to distinguish average gray value as a setting; Relatively whether effective information area edge belt-like zone mean value and background area average gray value are weighed final segmentation result with the difference of the two and optimally information and noise are cut apart; If the difference of the two is in tolerance interval, then final segmentation result is optimally cut apart information and noise, and finishes; If the difference of the two is not in tolerance interval, then final segmentation result is not optimally cut apart information and noise, initial threshold is carried out threshold value adjustment operation, carries out iterative operation as new initial threshold, until the two difference in tolerance interval.
2. the extracting method in the range gating image effective information district based on average gray according to claim 1, it is characterized in that, the described priori of utilizing is calculated initial threshold, be to utilize grey level histogram, begin to add up number of pixels on each gray level from minimum gray level, when pixel count reaches the certain proportion of image total pixel number on the minimum gray level, this gray level is decided to be the initial threshold of algorithm.
3. the extracting method in the range gating image effective information district based on average gray according to claim 2 is characterized in that described certain proportion is a priori, determines according to system's characteristics and area surroundings characteristics, can be partitioned into most information scene; Described initial threshold should be not excessive, otherwise with it indirect assignment, to prevent the more Algorithm Error that causes of information in the image; According to the feature of image that night, laser became, described initial threshold should be below 10.
4. the extracting method in the range gating image effective information district based on average gray according to claim 1, it is characterized in that, the described extraction that utilizes initial threshold original image to be carried out the effective information district, be to utilize binaryzation, morphological operation to carry out the extraction in effective information district when utilizing initial threshold to carry out the extraction in effective information district, specifically comprise:
Utilize this initial threshold to carry out image binaryzation, and expansive working is carried out in the block of information in the image; The noise of noise range has obtained reinforcement equally in this process, by the judgement to the area of eight connected regions, regards as noise with handling the less zone of number of pixels, back, and is included into the noise range.
5. the extracting method in the range gating image effective information district based on average gray according to claim 1, it is characterized in that, described definite background area average gray value method is that morphology methods is adopted in the extraction of largest connected background area, specifically comprises:
The image that takes out the effective information district as the noise range, is corroded operation to the noise range,, obtain some eight connected regions after the corrosion operation to remove the influence of the effective information area edge that may exist; By adding up the number that each eight connected region comprises pixel, get eight wherein maximum connected regions, be required maximum eight connected regions; Calculate the average gray value of the average gray value of this eight connected region as the noise range, calculate each regional average gray value for calculating the mean value of all gray values of pixel points in this zone, its computing formula is as follows:
In the above-mentioned formula, Avalue is an average gray value, and i represents i pixel in this zone, and it is n that n represents the pixel count in this zone, and fi is i gray values of pixel points in the zone for this reason then.
6. the extracting method in the range gating image effective information district based on average gray according to claim 1, it is characterized in that the outermost width that described effective information area edge belt-like zone is gained effective information district is the banded contour area of two pixels; Expansive working is done in the district to the gained effective information, uses expansion results to deduct the preceding image that expands, and can obtain the outside, edge in effective information district.
7. the extracting method in the range gating image effective information district based on average gray according to claim 1, it is characterized in that, the difference of described effective information area edge belt-like zone mean value and background area average gray value, be effective information area edge belt-like zone mean value subtracting background district average gray value, the overall brightness in effective information district is higher than the background area, influence effective information area edge belt-like zone mean value near the background area average gray value and be subjected to the echo broadening effect, so after the effective information district extracted accurately, the difference of the two should be in the positive small range.
8. the extracting method in the range gating image effective information district based on average gray according to claim 1, it is characterized in that, described the two difference is in tolerance interval, be meant that effective information area edge belt-like zone mean value is greater than the background area average gray value, and the echo broadening effect makes effective information area edge gray scale near background, so the difference of the two should be less than a threshold value.
9. the extracting method in the range gating image effective information district based on average gray according to claim 1, it is characterized in that, described initial threshold is carried out in the threshold value adjustment operation, threshold value adjustment operation is divided into two basic directions of adjusting: threshold value increases or threshold value reduces, and concrete grammar is:
Effective information area edge belt-like zone mean value is compared with the background area average gray value, if the difference of effective information area edge belt-like zone mean value and background area average gray value is higher than set threshold value, then this threshold value is deducted 1, as new threshold value, carry out iterative operation with this; If effective information area edge belt-like zone mean value and background area average gray value differ less, it is excessive that then possibility is extracted in the block of information, and former threshold value is added 1 as new threshold value, carries out interative computation; When the difference of effective information area edge belt-like zone mean value and background area average gray value met the requirements, then the gained result was net result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2011100796614A CN102136068B (en) | 2011-03-31 | 2011-03-31 | Average grey-based method for extracting effective information region of range gating image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2011100796614A CN102136068B (en) | 2011-03-31 | 2011-03-31 | Average grey-based method for extracting effective information region of range gating image |
Publications (2)
Publication Number | Publication Date |
---|---|
CN102136068A true CN102136068A (en) | 2011-07-27 |
CN102136068B CN102136068B (en) | 2012-11-21 |
Family
ID=44295850
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2011100796614A Active CN102136068B (en) | 2011-03-31 | 2011-03-31 | Average grey-based method for extracting effective information region of range gating image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102136068B (en) |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104008384A (en) * | 2013-02-26 | 2014-08-27 | 山东新北洋信息技术股份有限公司 | Character identification method and character identification apparatus |
US9123123B2 (en) | 2012-05-22 | 2015-09-01 | Ricoh Company, Ltd. | Pattern processing device, pattern processing method, and pattern processing program |
CN105354575A (en) * | 2015-10-21 | 2016-02-24 | 江苏科技大学 | Image binarization threshold determination method in sea-sky-line detection |
CN105894528A (en) * | 2016-05-04 | 2016-08-24 | 南京航空航天大学 | Image processing method for refueling taper sleeve capable of threshold self-adaption |
CN106097345A (en) * | 2016-06-14 | 2016-11-09 | 三亚深海科学与工程研究所 | A kind of linear target dividing method and segmenting system |
CN106204661A (en) * | 2016-06-23 | 2016-12-07 | 青岛海信电器股份有限公司 | Picture effectiveness recognition methods, device and intelligent terminal |
WO2018082332A1 (en) * | 2016-11-07 | 2018-05-11 | 深圳光启合众科技有限公司 | Image processing method and device, and robot |
CN108304781A (en) * | 2017-12-29 | 2018-07-20 | 华中科技大学 | A kind of face battle array Geiger APD laser imaging radar image pre-processing methods |
CN108648258A (en) * | 2018-04-26 | 2018-10-12 | 中国科学院半导体研究所 | Image calculating for laser night vision homogenizes Enhancement Method |
CN109840912A (en) * | 2019-01-02 | 2019-06-04 | 厦门美图之家科技有限公司 | The modification method of abnormal pixel and equipment is calculated in a kind of image |
CN111398986A (en) * | 2020-04-03 | 2020-07-10 | 中国科学院半导体研究所 | Frame correlation gating three-dimensional imaging method and system based on mark frame |
CN112581490A (en) * | 2020-12-28 | 2021-03-30 | 西安理工大学 | Method for extracting foreground region in complex curved surface interferometry |
CN112710250A (en) * | 2020-11-23 | 2021-04-27 | 武汉光谷卓越科技股份有限公司 | Three-dimensional measurement method based on line structured light and sensor |
CN113057676A (en) * | 2019-10-18 | 2021-07-02 | 深圳北芯生命科技有限公司 | Image noise reduction method of IVUS system |
CN113112432A (en) * | 2021-05-13 | 2021-07-13 | 广州道一科学技术有限公司 | Method for automatically identifying image strips |
CN113516584A (en) * | 2021-09-14 | 2021-10-19 | 风脉能源(武汉)股份有限公司 | Image gray processing method and system and computer storage medium |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101093539A (en) * | 2007-07-27 | 2007-12-26 | 哈尔滨工程大学 | Matching identification method by extracting characters of vein from finger |
CN101127117A (en) * | 2007-09-11 | 2008-02-20 | 华中科技大学 | Method for segmenting blood vessel data using serial DSA image |
-
2011
- 2011-03-31 CN CN2011100796614A patent/CN102136068B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101093539A (en) * | 2007-07-27 | 2007-12-26 | 哈尔滨工程大学 | Matching identification method by extracting characters of vein from finger |
CN101127117A (en) * | 2007-09-11 | 2008-02-20 | 华中科技大学 | Method for segmenting blood vessel data using serial DSA image |
Cited By (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9454824B2 (en) | 2012-05-22 | 2016-09-27 | Ricoh Company, Ltd. | Pattern processing device, pattern processing method, and pattern processing program |
US9123123B2 (en) | 2012-05-22 | 2015-09-01 | Ricoh Company, Ltd. | Pattern processing device, pattern processing method, and pattern processing program |
CN103428511B (en) * | 2012-05-22 | 2016-02-24 | 株式会社理光 | Image disposal device and pattern treatment method |
WO2014131339A1 (en) * | 2013-02-26 | 2014-09-04 | 山东新北洋信息技术股份有限公司 | Character identification method and character identification apparatus |
CN104008384A (en) * | 2013-02-26 | 2014-08-27 | 山东新北洋信息技术股份有限公司 | Character identification method and character identification apparatus |
CN105354575A (en) * | 2015-10-21 | 2016-02-24 | 江苏科技大学 | Image binarization threshold determination method in sea-sky-line detection |
CN105354575B (en) * | 2015-10-21 | 2018-05-22 | 江苏科技大学 | Image binaryzation threshold value determines method in a kind of sea horizon detection |
CN105894528A (en) * | 2016-05-04 | 2016-08-24 | 南京航空航天大学 | Image processing method for refueling taper sleeve capable of threshold self-adaption |
CN106097345A (en) * | 2016-06-14 | 2016-11-09 | 三亚深海科学与工程研究所 | A kind of linear target dividing method and segmenting system |
CN106204661A (en) * | 2016-06-23 | 2016-12-07 | 青岛海信电器股份有限公司 | Picture effectiveness recognition methods, device and intelligent terminal |
CN106204661B (en) * | 2016-06-23 | 2020-05-05 | 海信视像科技股份有限公司 | Picture validity identification method and device and intelligent terminal |
WO2018082332A1 (en) * | 2016-11-07 | 2018-05-11 | 深圳光启合众科技有限公司 | Image processing method and device, and robot |
CN108090924A (en) * | 2016-11-07 | 2018-05-29 | 深圳光启合众科技有限公司 | Image processing method and device, robot |
CN108090924B (en) * | 2016-11-07 | 2020-03-10 | 深圳光启合众科技有限公司 | Image processing method and device and robot |
CN108304781A (en) * | 2017-12-29 | 2018-07-20 | 华中科技大学 | A kind of face battle array Geiger APD laser imaging radar image pre-processing methods |
CN108648258A (en) * | 2018-04-26 | 2018-10-12 | 中国科学院半导体研究所 | Image calculating for laser night vision homogenizes Enhancement Method |
CN109840912A (en) * | 2019-01-02 | 2019-06-04 | 厦门美图之家科技有限公司 | The modification method of abnormal pixel and equipment is calculated in a kind of image |
CN109840912B (en) * | 2019-01-02 | 2021-05-04 | 厦门美图之家科技有限公司 | Method for correcting abnormal pixels in image and computing equipment |
CN113057676A (en) * | 2019-10-18 | 2021-07-02 | 深圳北芯生命科技有限公司 | Image noise reduction method of IVUS system |
CN111398986A (en) * | 2020-04-03 | 2020-07-10 | 中国科学院半导体研究所 | Frame correlation gating three-dimensional imaging method and system based on mark frame |
CN111398986B (en) * | 2020-04-03 | 2023-06-20 | 中国科学院半导体研究所 | Frame correlation gating three-dimensional imaging method and imaging system based on mark frame |
CN112710250A (en) * | 2020-11-23 | 2021-04-27 | 武汉光谷卓越科技股份有限公司 | Three-dimensional measurement method based on line structured light and sensor |
CN112581490A (en) * | 2020-12-28 | 2021-03-30 | 西安理工大学 | Method for extracting foreground region in complex curved surface interferometry |
CN113112432A (en) * | 2021-05-13 | 2021-07-13 | 广州道一科学技术有限公司 | Method for automatically identifying image strips |
CN113516584A (en) * | 2021-09-14 | 2021-10-19 | 风脉能源(武汉)股份有限公司 | Image gray processing method and system and computer storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN102136068B (en) | 2012-11-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102136068B (en) | Average grey-based method for extracting effective information region of range gating image | |
CN103942803B (en) | SAR (Synthetic Aperture Radar) image based automatic water area detection method | |
CN102542289B (en) | Pedestrian volume statistical method based on plurality of Gaussian counting models | |
CN107563347B (en) | Passenger flow counting method and device based on TOF camera | |
CN106096525B (en) | A kind of compound lane recognition system and method | |
CN102494675B (en) | High-speed visual capturing method of moving target features | |
CN108399403B (en) | Vehicle distance detection method based on license plate size calculation | |
CN107808383B (en) | Rapid detection method for SAR image target under strong sea clutter | |
CN106128121B (en) | Vehicle queue length fast algorithm of detecting based on Local Features Analysis | |
CN101286239A (en) | Aerial shooting traffic video frequency vehicle rapid checking method | |
CN106650553A (en) | License plate recognition method and system | |
CN104183127A (en) | Traffic surveillance video detection method and device | |
CN103778627B (en) | A kind of marine site based on SAR image oil spilling detection method | |
CN106815583B (en) | Method for positioning license plate of vehicle at night based on combination of MSER and SWT | |
CN109272548B (en) | Method for measuring diameter of bubbles in flotation process | |
CN1984236A (en) | Method for collecting characteristics in telecommunication flow information video detection | |
CN105069460A (en) | ISAR image ship target feature extraction method | |
CN105654091A (en) | Detection method and apparatus for sea-surface target | |
CN103544502A (en) | High-resolution remote-sensing image ship extraction method based on SVM | |
CN102663385B (en) | Detection method for spot target on satellite | |
CN116758059A (en) | Visual nondestructive testing method for roadbed and pavement | |
CN109489724A (en) | A kind of tunnel safe train operation environment comprehensive detection device and detection method | |
CN102915545A (en) | OpenCV(open source computer vision library)-based video target tracking algorithm | |
CN107798293A (en) | A kind of crack on road detection means | |
CN107844772A (en) | A kind of motor vehicle automatic testing method based on movable object tracking |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right |
Effective date of registration: 20201215 Address after: Room 414, building 1, No. 3, Xingfu West Street, Beifang Town, Huairou District, Beijing Patentee after: Beijing Zhongke Shengshi Technology Co., Ltd Address before: 100083 No. 35, Qinghua East Road, Beijing, Haidian District Patentee before: Institute of Semiconductors, Chinese Academy of Sciences |
|
TR01 | Transfer of patent right |