CN101794435A - Binary image noise-reduction method based on integral graph and binary image processing system - Google Patents
Binary image noise-reduction method based on integral graph and binary image processing system Download PDFInfo
- Publication number
- CN101794435A CN101794435A CN 201010117233 CN201010117233A CN101794435A CN 101794435 A CN101794435 A CN 101794435A CN 201010117233 CN201010117233 CN 201010117233 CN 201010117233 A CN201010117233 A CN 201010117233A CN 101794435 A CN101794435 A CN 101794435A
- Authority
- CN
- China
- Prior art keywords
- value
- pixel point
- pixel
- integral
- foreground pixel
- 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
- 238000012545 processing Methods 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 title claims abstract description 27
- 101100311460 Schizosaccharomyces pombe (strain 972 / ATCC 24843) sum2 gene Proteins 0.000 claims description 39
- 101100116390 Schizosaccharomyces pombe (strain 972 / ATCC 24843) ded1 gene Proteins 0.000 claims description 17
- 238000004364 calculation method Methods 0.000 claims description 11
- 230000015572 biosynthetic process Effects 0.000 claims description 7
- 239000000284 extract Substances 0.000 claims description 7
- 238000012217 deletion Methods 0.000 claims description 4
- 230000037430 deletion Effects 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 abstract description 5
- 238000011946 reduction process Methods 0.000 abstract description 4
- 239000006002 Pepper Substances 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000010339 dilation Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
Images
Landscapes
- Image Processing (AREA)
Abstract
The invention relates to an image processing technology, in particular to a binary image noise-reduction technology. The invention provides a binary image noise-reduction method based on an integral graph, which is used for extracting and deleting noise points to ensure that shape characteristics of target images is not influenced by the noise reduction process, and the invention provides a binary image processing system. Through calculating the sum of a plurality of integral graph values of prospect pixel points and comparing the sizes of set thresholds, the noise points are extracted, the implementation is simple and fast, and spots and burrs in the binary image are effectively removed without influencing the shape characteristics of the target image.
Description
Technical field
The present invention relates to image processing techniques, be specifically related to the bianry image noise reduction technology.
Background technology
Digitized bianry image is very extensive in application in engineering, mostly requires earlier the image that collects to be carried out binaryzation as Application for Field such as pattern-recognition and machine vision, to carry out follow-up graphical analysis.There is noise usually in original image, although proposed a lot of binarization methods, also can't avoid the existence of noise in the binary image, can influence the subsequent treatment to image like this, is necessary so binary image is carried out noise reduction.
The method of bianry image noise reduction and method to rgb image and gray level image are not quite similar, because the noise of bianry image is different from salt-pepper noise and white Gaussian noise in one gray level image or the rgb image.Suppose that white pixel is represented foreground image in the bianry image, black picture element is represented background, and conclusion is got up, and the noise in the bianry image has following three kinds: have the isolated zonule of white in (1) black background, be referred to as spot; (2) the small depression of the marginal existence of white prospect pattern is referred to as hole; (3) the small projection of the marginal existence of white prospect pattern is referred to as burr.
At the bianry image noise behavior, a lot of methods at the bianry image noise reduction have been proposed at present." Mathematicalmorphology and its applications to image and signal processing " is (referring to J Goutsias, L Vincent, D S Bloomberg.Mathematical morphology and its application to image andsignal processing[M] .Boston:Kluwer Academic Publisher, 2000) propose to carry out noise reduction, reach the purpose of noise reduction by erosion operation or dilation operation with Mathematical Morphology Method.Use morphology to carry out noise reduction, at different images, the selection of template and template operation times is just different, and, morphological method is with a specific structural element group entire image to be carried out traversal processing, can not treat with a certain discrimination noise and effective information, so in noise reduction process in order thoroughly to remove noise, easily the effective information in the image is removed, will be unfavorable for the latter feature calculation of parameter like this.
Summary of the invention
Technical matters to be solved by this invention is, provides a kind of noise spot is extracted and deletion, and the style characteristic that guarantees target image is not subjected to the bianry image noise-reduction method based on integrogram of noise reduction process influence; Also for realizing that this method provides a kind of binary Images Processing system.
The present invention solves the problems of the technologies described above the technical scheme that is adopted to be, the bianry image noise-reduction method based on integrogram may further comprise the steps:
A, along from left to right, top-down direction, the first integral figure value of foreground pixel point is calculated in pointwise; Along right-to-left, from bottom to top direction, the second integral figure value of foreground pixel point is calculated in pointwise;
Whether b, the first integral figure value of judging foreground pixel point correspondence and second integral figure value sum be less than setting threshold, and in this way, this foreground pixel point is a noise spot, deletes this foreground pixel point; As not, keep this foreground pixel point.
The first integral figure value of described foreground pixel point is sum1 (d)=sum1 (b)+sum1 (c)-sum1 (a)+1;
The second integral figure value of described foreground pixel point is sum2 (d)=sum2 (e)+sum2 (f)-sum2 (g)+1;
Wherein, d represents current foreground pixel point, and a represents to be positioned at current foreground pixel and puts upper left neighbor pixel, and b represents to be positioned at the neighbor pixel directly over the current foreground pixel point, and c represents to be positioned at the neighbor pixel of current foreground pixel point front-left; E represents to be positioned at the neighbor pixel of current foreground pixel point front-left; F represents to be positioned at the neighbor pixel under the current foreground pixel point; G represents to be positioned at current foreground pixel and puts bottom-right neighbor pixel; The pixel value sum of the rectangular area of formation between the upper left pixel point of sum1 () expression current pixel point and image; The pixel value sum of the rectangular area that forms between the pixel of the lower right of sum2 () expression current pixel point and image; The initial value of sum1 (), sum2 () is 0.
Image processing system, comprise image capture module, image binaryzation module, it is characterized in that, also comprise the bianry image noise reduction module, described bianry image noise reduction module comprises processing unit, first integral figure value register, second integral figure value register, integrogram value summation register, threshold register;
Described processing unit is used for extracting bianry image each point pixel value from left to right, from top to bottom, carries out the first integral figure value of each foreground pixel point and calculates, and deposits result of calculation in first integral figure value register; Extract bianry image each point pixel value from right to left, from bottom to top, carry out the second integral figure value of each foreground pixel point and calculate, deposit result of calculation in second integral figure value register; First integral figure value, second integral figure value that each foreground pixel point is corresponding are sued for peace, and the summed result that each foreground pixel point is corresponding deposits integrogram value summation register in; The summed result that predetermined threshold value is corresponding with each foreground pixel point compares, and the deletion summed result keeps the foreground pixel point of summed result more than or equal to predetermined threshold value less than the foreground pixel point of predetermined threshold value;
Described first integral figure value register is used to deposit the first integral figure value of each foreground pixel point;
Described second integral figure value register is used to deposit the second integral figure value of each foreground pixel point;
Described integrogram value summation register is used to deposit the corresponding summed result of each foreground pixel point.
Concrete, processing module is calculated in the following manner the first integral figure value of foreground pixel point and is realized:
sum1(d)＝sum1(b)+sum1(c)-sum1(a)+1；
Wherein, d represents current foreground pixel point, and a represents to be positioned at current foreground pixel and puts upper left neighbor pixel, and b represents to be positioned at the neighbor pixel directly over the current foreground pixel point, and c represents to be positioned at the neighbor pixel of current foreground pixel point front-left; The pixel value sum of the rectangular area of formation between the upper left pixel point of sum1 () expression current pixel point and image;
Processing module is calculated in the following manner the second integral figure value of foreground pixel point and is realized:
sum2(d)＝sum2(e)+sum2(f)-sum2(g)+1；
Wherein, d represents current foreground pixel point, and e represents to be positioned at the neighbor pixel of current foreground pixel point front-left; F represents to be positioned at the neighbor pixel under the current foreground pixel point; G represents to be positioned at current foreground pixel and puts bottom-right neighbor pixel; The pixel value sum of the rectangular area that forms between the pixel of the lower right of sum2 () expression current pixel point and image; The initial value of sum1 (), sum2 () is 0.
The invention has the beneficial effects as follows that noise-reduction method implements simply, fast, noise spot is extracted, eliminate spot, burr in the bianry image effectively, do not influence the style characteristic of target image by judgement with setting threshold.
Description of drawings
Fig. 1 is embodiment 1 a noise-reduction method process flow diagram;
Fig. 2 is the integrogram signal of foreground pixel point;
Fig. 3 (a) is not for passing through the bianry image of noise reduction process; Fig. 3 (b) is for using the bianry image after embodiment 1 described noise-reduction method is handled, and setting threshold is 10; Fig. 3 (c) is for using the bianry image after embodiment 1 described noise-reduction method is handled, and setting threshold is 20.
Fig. 4 is embodiment 1 system chart.
Embodiment
When carrying out binary image, the gray scale of background pixel point is set to zero, and the pixel of gray-scale value non-zero is the foreground pixel point.
Bianry image noise-reduction method flow process as shown in Figure 1.
S1: from left to right, top-down pointwise reads in pixel, calculates the integrogram value of each pixel of gray-scale value non-zero, as the formula (1):
sum1(d)＝sum1(b)+sum1(c)-sum1(a)+1；(1)
S2: pixel is read in right-to-left, pointwise from bottom to top, calculates the integrogram value of each pixel of gray-scale value non-zero, as the formula (2):
sum2(d)＝sum2(e)+sum2(f)-sum2(g)+1；(2)
As shown in Figure 2, d represents current foreground pixel point, and a represents to be positioned at current foreground pixel and puts upper left neighbor pixel, and b represents to be positioned at the neighbor pixel directly over the current foreground pixel point, and c represents to be positioned at the neighbor pixel of current foreground pixel point front-left; E represents to be positioned at the neighbor pixel of current foreground pixel point front-left; F represents to be positioned at the neighbor pixel under the current foreground pixel point; G represents to be positioned at current foreground pixel and puts bottom-right neighbor pixel; The pixel value sum of the rectangular area that forms between the upper left pixel point O1 of pixel (current pixel point) in sum1 () the expression bracket and image is as the pixel value sum of the rectangular area that forms between the upper left pixel point O1 of sum1 (a) remarked pixel point a and image; The pixel value sum of the rectangular area that forms between the lower right pixel O2 of sum2 () expression current pixel point and image.As the neighbor pixel of current foreground pixel point and correspondence position, then the pixel value sum of the rectangular area of formation is defaulted as 0 between lower right of this phase bell pixel and image or the upper left pixel point.
S3: integrogram value summation sum1 (the d)+sum2 (d) with each pixel of gray-scale value non-zero obtains for twice, judge this pixel less than setting threshold T, in this way, this pixel is a noise spot, deletes this pixel (be about to this gray values of pixel points and be made as zero); Otherwise, keep this pixel (promptly no longer adjusting this gray values of pixel points).
Be shown in as Fig. 3 (a) and carry out before the noise reduction, spot in the bianry image, burr are more; Fig. 3 (b) is 10 o'clock for getting setting threshold T, carries out noise reduction design sketch afterwards, and most spot, burr are eliminated among the former figure; Further, carry out the adjustment of setting threshold T again according to actual environment, setting threshold T is set to 20 again, the effect behind noise reduction such as Fig. 3 (c), and the prospect of bianry image is clear, the background noiseless.Evidence, noise-reduction method of the present invention can be eliminated noise spot well under the prerequisite of the style characteristic that keeps target image when the choose reasonable threshold value.
As shown in Figure 4, the binary Images Processing system comprises image capture module, image binaryzation module, bianry image noise reduction module, and image capture module links to each other with the image binaryzation module, and the bianry image noise reduction module links to each other with the image binaryzation module.Image capture module takes and obtains video image to monitoring scene, the image binaryzation module is carried out binary conversion treatment to the video image that collects, and the binary image noise reduction module is again to utilizing integrogram to calculate the noise of removing in the bianry image.Wherein, the bianry image noise reduction module comprises processing unit, first integral figure value register, second integral figure value register, integrogram value summation register, threshold register; First integral figure value register, second integral figure value register, integrogram value summation register, threshold register link to each other with processing unit respectively.
Processing unit is used for extracting bianry image each point pixel value from left to right, from top to bottom, carries out the calculating of integrogram value of each pixel of gray-scale value non-zero, as the formula (1), deposits result of calculation in first integral figure value register; Extract bianry image each point pixel value from right to left, from bottom to top, carry out the calculating of integrogram value of each pixel of gray-scale value non-zero, as the formula (2), deposit result of calculation in second integral figure value register; Two integrogram values that each foreground pixel point is corresponding are sued for peace, and the summed result that each foreground pixel point is corresponding deposits integrogram value summation register in; The summed result that predetermined threshold value T is corresponding with each foreground pixel point compares, and the deletion summed result keeps the foreground pixel point of summed result more than or equal to predetermined threshold value less than the foreground pixel point of predetermined threshold value;
First integral figure value register is used to deposit the first integral figure value sum1 (d) of each foreground pixel point;
Second integral figure value register is used to deposit the second integral figure value sum2 (d) of each foreground pixel point;
Integrogram value summation register is used to deposit corresponding summed result sum1 (the d)+sum2 (d) of each foreground pixel point.
Embodiment 2
In order to make noise reduction more accurate, can expand embodiment 1, when calculated product component value, improve, from four direction difference calculated product component value, from top to down from left to right promptly, from right to left from go up down, go up from descending from left to right, four direction calculated product component value from top to down from right to left, judge to determine by setting threshold T whether this foreground pixel point is noise spot then.
As shown in Figure 2, when judging current foreground pixel point d, consider that not only neighbor pixel a, the b, c, e, f, the g that implement in 1 also need the current foreground pixel of many considerations put the neighbor pixel i of top-right neighbor pixel h and current foreground pixel point lower left.
Bianry image noise-reduction method flow process also need be carried out before its step S3 on the basis of embodiment 1:
From left to right, pointwise from bottom to top reads in pixel, calculates the integrogram value of each pixel of gray-scale value non-zero, as the formula (3), the pixel value sum of the rectangular area that forms between the lower left pixel O3 of sum3 () expression current pixel point and image:
sum3(d)＝sum3(c)+sum3(f)-sum3(i)+1；(3)
Pixel is read in right-to-left, top-down pointwise, calculates the integrogram value of each pixel of gray-scale value non-zero, as the formula (4), and the pixel value sum of the rectangular area that forms between the upper right side pixel O4 of sum4 () expression current pixel point and image:
sum4(d)＝sum4(b)+sum4(e)-sum4(h)+1；(4)
Among the step S3, the integrogram value summed result that compares with setting threshold T should be four integrogram value summation sum1 (d)+sum2 (d)+sum3 (d)+sum4 (d) that the foreground pixel point obtains.
Accordingly, in system, the bianry image noise reduction module also need increase third integral figure value register, the 4th integrogram value register, and third integral figure value register, the 4th integrogram value register link to each other with processing unit respectively;
On the basis of embodiment 1, processing unit also is used for from left to right, extracts bianry image each point pixel value from bottom to top, carry out the calculating of integrogram value of each pixel of gray-scale value non-zero, as the formula (3), deposit result of calculation in third integral figure value register; Extract bianry image each point pixel value from right to left, from top to bottom, carry out the calculating of integrogram value of each pixel of gray-scale value non-zero, as the formula (4), deposit result of calculation in the 4th integrogram value register; Four integrogram values that each foreground pixel point is corresponding are sued for peace, and the summed result that each foreground pixel point is corresponding deposits integrogram value summation register in;
Third integral figure value register is used to deposit the third integral figure value sum3 (d) of each foreground pixel point;
The 4th integrogram value register is used to deposit the 4th integrogram value sum4 (d) of each foreground pixel point;
Integrogram value summation register is used to deposit corresponding summed result sum1 (d)+sum2 (d)+sum3 (the d)+sum4 (d) of each foreground pixel point.
Though the present invention describes in conjunction with 2 embodiment; but those skilled in the art can be to wherein some feature appropriate change or apply it to other field to solve the technical matters that the present invention was claimed in addition; particularly among the embodiment from top to down from left to right; on from right to left from descending; on from left to right from descending; the four direction integrogram value of carrying out is calculated from top to down from right to left; can adjust its order arbitrarily; also can choose two wantonly and calculate to four direction, in 4 directions provided herein, make up the replacement that is equal to that all is considered as with the application's technical scheme required for protection arbitrarily.Those skilled in the art on the basis of present embodiment, carry out all relevant be equal to the protection field that replacements, expansion and application all should fall into the application.
Claims (8)
1. based on the bianry image noise-reduction method of integrogram, it is characterized in that, may further comprise the steps:
A, along from left to right, top-down direction, the first integral figure value of foreground pixel point is calculated in pointwise; Along right-to-left, from bottom to top direction, the second integral figure value of foreground pixel point is calculated in pointwise;
Whether b, the first integral figure value of judging foreground pixel point correspondence and second integral figure value sum be less than setting threshold, and in this way, this foreground pixel point is a noise spot, deletes this foreground pixel point; As not, keep this foreground pixel point.
2. according to claim 1 based on the bianry image noise-reduction method of integrogram, it is characterized in that,
The first integral figure value of described foreground pixel point is sum1 (d)=sum1 (b)+sum1 (c)-sum1 (a)+1;
The second integral figure value of described foreground pixel point is sum2 (d)=sum2 (e)+sum2 (f)-sum2 (g)+1;
Wherein, d represents current foreground pixel point, and a represents to be positioned at current foreground pixel and puts upper left neighbor pixel, and b represents to be positioned at the neighbor pixel directly over the current foreground pixel point, and c represents to be positioned at the neighbor pixel of current foreground pixel point front-left; E represents to be positioned at the neighbor pixel of current foreground pixel point front-left; F represents to be positioned at the neighbor pixel under the current foreground pixel point; G represents to be positioned at current foreground pixel and puts bottom-right neighbor pixel; The pixel value sum of the rectangular area of formation between the upper left pixel point of sum1 () expression current pixel point and image; The pixel value sum of the rectangular area that forms between the pixel of the lower right of sum2 () expression current pixel point and image; The initial value of sum1 (), sum2 () is 0.
3. according to claim 1 based on the bianry image noise-reduction method of integrogram, it is characterized in that, also comprise among the step a, along from left to right, direction from bottom to top, the third integral figure value of foreground pixel point is calculated in pointwise; Along right-to-left, top-down direction, the 4th integrogram value of foreground pixel point is calculated in pointwise;
Whether judge foreground pixel point corresponding first integral figure value, second integral figure value, third integral figure value and the 4th integrogram value sum among the step b less than setting threshold, in this way, this foreground pixel point is a noise spot, deletes this foreground pixel point; As not, keep this foreground pixel point.
As described in the claim 3 based on the bianry image noise-reduction method of integrogram, it is characterized in that,
The first integral figure value of described foreground pixel point is sum1 (d)=sum1 (b)+sum1 (c)-sum1 (a)+1;
The second integral figure value of described foreground pixel point is sum2 (d)=sum2 (e)+sum2 (f)-sum2 (g)+1;
The third integral figure value of described foreground pixel point is sum3 (d)=sum3 (c)+sum3 (f)-sum3 (i)+1;
The 4th integrogram value of described foreground pixel point is sum4 (d)=sum4 (b)+sum4 (e)-sum4 (h)+1;
Wherein, d represents current foreground pixel point, and a represents to be positioned at current foreground pixel and puts upper left neighbor pixel, and b represents to be positioned at the neighbor pixel directly over the current foreground pixel point, and c represents to be positioned at the neighbor pixel of current foreground pixel point front-left; E represents to be positioned at the neighbor pixel of current foreground pixel point front-left; F represents to be positioned at the neighbor pixel under the current foreground pixel point; G represents to be positioned at current foreground pixel and puts bottom-right neighbor pixel; H represents to be positioned at current foreground pixel and puts top-right neighbor pixel; I represents to be positioned at the neighbor pixel of current foreground pixel point lower left; The pixel value sum of the rectangular area of formation between the upper left pixel point of sum1 () expression current pixel point and image; The pixel value sum of the rectangular area that forms between the pixel of the lower right of sum2 () expression current pixel point and image; The pixel value sum of the rectangular area that forms between the pixel of the lower left of sum3 () expression current pixel point and image; The pixel value sum of the rectangular area that forms between the pixel of the upper right side of sum4 () expression current pixel point and image; The initial value of sum1 (), sum2 (), sum3 (), sum4 () is 0.
5. image processing system, comprise image capture module, image binaryzation module, image capture module links to each other with the image binaryzation module, it is characterized in that, also comprise the bianry image noise reduction module, the bianry image noise reduction module links to each other with the image binaryzation module, and described bianry image noise reduction module comprises processing unit, first integral figure value register, second integral figure value register, integrogram value summation register, threshold register;
Described processing unit is used for extracting bianry image each point pixel value from left to right, from top to bottom, carries out the first integral figure value of each foreground pixel point and calculates, and deposits result of calculation in first integral figure value register; Extract bianry image each point pixel value from right to left, from bottom to top, carry out the second integral figure value of each foreground pixel point and calculate, deposit result of calculation in second integral figure value register; First integral figure value, second integral figure value that each foreground pixel point is corresponding are sued for peace, and the summed result that each foreground pixel point is corresponding deposits integrogram value summation register in; The summed result that predetermined threshold value is corresponding with each foreground pixel point compares, and the deletion summed result keeps the foreground pixel point of summed result more than or equal to predetermined threshold value less than the foreground pixel point of predetermined threshold value;
Described first integral figure value register is used to deposit the first integral figure value of each foreground pixel point;
Described second integral figure value register is used to deposit the second integral figure value of each foreground pixel point;
Described integrogram value summation register is used to deposit the corresponding summed result of each foreground pixel point.
6. as image processing system as described in the claim 5, it is characterized in that processing module is calculated in the following manner the first integral figure value of foreground pixel point and realized:
sum1(d)＝sum1(b)+sum1(c)-sum1(a)+1；
Wherein, d represents current foreground pixel point, and a represents to be positioned at current foreground pixel and puts upper left neighbor pixel, and b represents to be positioned at the neighbor pixel directly over the current foreground pixel point, and c represents to be positioned at the neighbor pixel of current foreground pixel point front-left; The pixel value sum of the rectangular area of formation between the upper left pixel point of sum1 () expression current pixel point and image;
Processing module is calculated in the following manner the second integral figure value of foreground pixel point and is realized:
sum2(d)＝sum2(e)+sum2(f)-sum2(g)+1；
Wherein, d represents current foreground pixel point, and e represents to be positioned at the neighbor pixel of current foreground pixel point front-left; F represents to be positioned at the neighbor pixel under the current foreground pixel point; G represents to be positioned at current foreground pixel and puts bottom-right neighbor pixel; The pixel value sum of the rectangular area that forms between the pixel of the lower right of sum2 () expression current pixel point and image; The initial value of sum1 (), sum2 () is 0.
7. as image processing system as described in the claim 5, it is characterized in that, also comprise third integral figure value register, the 4th integrogram value register;
Described processing unit also is used for from left to right, extracts bianry image each point pixel value from bottom to top, carries out the third integral figure value of each foreground pixel point and calculates, and deposits result of calculation in third integral figure value register; Extract bianry image each point pixel value from right to left, from top to bottom, carry out the 4th integrogram value of each foreground pixel point and calculate, deposit result of calculation in the 4th integrogram value register; First integral figure value, second integral figure value, third integral figure value and the 4th integrogram value that each foreground pixel point is corresponding are sued for peace, and the summed result that each foreground pixel point is corresponding deposits integrogram value summation register in.
8. as image processing system as described in the claim 7, it is characterized in that processing module realizes respectively in the following manner to the calculating of the first integral figure value of foreground pixel point, second integral figure value, third integral figure value, the 4th integrogram value:
sum1(d)＝sum1(b)+sum1(c)-sum1(a)+1；
sum2(d)＝sum2(e)+sum2(f)-sum2(g)+1；
sum3(d)＝sum3(c)+sum3(f)-sum3(i)+1；
sum4(d)＝sum4(b)+sum4(e)-sum4(h)+1；
Wherein, d represents current foreground pixel point, and a represents to be positioned at current foreground pixel and puts upper left neighbor pixel, and b represents to be positioned at the neighbor pixel directly over the current foreground pixel point, and c represents to be positioned at the neighbor pixel of current foreground pixel point front-left; E represents to be positioned at the neighbor pixel of current foreground pixel point front-left; F represents to be positioned at the neighbor pixel under the current foreground pixel point; G represents to be positioned at current foreground pixel and puts bottom-right neighbor pixel; H represents to be positioned at current foreground pixel and puts top-right neighbor pixel; I represents to be positioned at the neighbor pixel of current foreground pixel point lower left; The pixel value sum of the rectangular area of formation between the upper left pixel point of sum1 () expression current pixel point and image; The pixel value sum of the rectangular area that forms between the pixel of the lower right of sum2 () expression current pixel point and image; The pixel value sum of the rectangular area that forms between the pixel of the lower left of sum3 () expression current pixel point and image; The pixel value sum of the rectangular area that forms between the pixel of the upper right side of sum4 () expression current pixel point and image; The initial value of sum1 (), sum2 (), sum3 (), sum4 () is 0.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010101172331A CN101794435B (en) | 2010-03-04 | 2010-03-04 | Binary image noise-reduction method based on integral graph and binary image processing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010101172331A CN101794435B (en) | 2010-03-04 | 2010-03-04 | Binary image noise-reduction method based on integral graph and binary image processing system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101794435A true CN101794435A (en) | 2010-08-04 |
| CN101794435B CN101794435B (en) | 2011-04-20 |
Family
ID=42587108
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2010101172331A Active CN101794435B (en) | 2010-03-04 | 2010-03-04 | Binary image noise-reduction method based on integral graph and binary image processing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101794435B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102117409A (en) * | 2011-02-28 | 2011-07-06 | 华南理工大学 | Hardware feature box for searching and traversing feathers based on integrogram |
| CN102117326A (en) * | 2011-02-28 | 2011-07-06 | 华南理工大学 | Traversal method used for searching image features |
| CN103473518A (en) * | 2013-08-20 | 2013-12-25 | 成都三泰电子实业股份有限公司 | Waybill information input and black-and-white block coding and decoding system |
| CN103488965A (en) * | 2013-08-20 | 2014-01-01 | 成都三泰电子实业股份有限公司 | Freight note information inputting and colored color-lump encoding-decoding system |
| CN104463792A (en) * | 2014-11-12 | 2015-03-25 | 迪堡金融设备有限公司 | Method and device used for removing noisy point in binarized image |
| CN104921698A (en) * | 2015-07-13 | 2015-09-23 | 中北大学 | Method for correcting corneal curvature instrument system astigmatism |
| CN108363986A (en) * | 2018-03-07 | 2018-08-03 | 曲阜师范大学 | Face literary sketch system based on improved sobel method and contour extraction method |
| CN109543686A (en) * | 2018-10-24 | 2019-03-29 | 重庆师范大学 | Character recognition based on adaptive multi-thresholding pre-processes binarization method |
| CN109822231A (en) * | 2019-02-15 | 2019-05-31 | 英特尔产品（成都）有限公司 | Method and apparatus of the detection for the quality of the laser beam of Wafer Dicing |
| CN110047083A (en) * | 2019-04-01 | 2019-07-23 | 江西博微新技术有限公司 | Image noise recognition methods, server and storage medium |
| CN114666523A (en) * | 2022-03-30 | 2022-06-24 | 湖南格为科技有限公司 | Energy-saving liquid crystal television capable of automatically adapting to human eye brightness |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11234526A (en) * | 1998-02-16 | 1999-08-27 | Kokusai Electric Co Ltd | Device for decreasing noise in image |
| US7110612B1 (en) * | 2001-10-11 | 2006-09-19 | Pixelworks, Inc. | Weighted absolute difference based noise reduction method and apparatus |
| CN101187984A (en) * | 2007-12-05 | 2008-05-28 | 北京中星微电子有限公司 | An image detection method and device |
| CN101465001A (en) * | 2008-12-31 | 2009-06-24 | 昆山锐芯微电子有限公司 | Method for detecting image edge based on Bayer RGB |
-
2010
- 2010-03-04 CN CN2010101172331A patent/CN101794435B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11234526A (en) * | 1998-02-16 | 1999-08-27 | Kokusai Electric Co Ltd | Device for decreasing noise in image |
| US7110612B1 (en) * | 2001-10-11 | 2006-09-19 | Pixelworks, Inc. | Weighted absolute difference based noise reduction method and apparatus |
| CN101187984A (en) * | 2007-12-05 | 2008-05-28 | 北京中星微电子有限公司 | An image detection method and device |
| CN101465001A (en) * | 2008-12-31 | 2009-06-24 | 昆山锐芯微电子有限公司 | Method for detecting image edge based on Bayer RGB |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102117409A (en) * | 2011-02-28 | 2011-07-06 | 华南理工大学 | Hardware feature box for searching and traversing feathers based on integrogram |
| CN102117326A (en) * | 2011-02-28 | 2011-07-06 | 华南理工大学 | Traversal method used for searching image features |
| CN102117409B (en) * | 2011-02-28 | 2013-01-09 | 华南理工大学 | Hardware feature box for searching and traversing feathers based on integrogram |
| CN103488965B (en) * | 2013-08-20 | 2016-06-15 | 成都我来啦网格信息科技有限公司 | Waybill typing and colored color lump coding/decoding system |
| CN103473518B (en) * | 2013-08-20 | 2016-06-15 | 成都我来啦网格信息科技有限公司 | Waybill typing and black and white color lump coding/decoding system |
| CN103473518A (en) * | 2013-08-20 | 2013-12-25 | 成都三泰电子实业股份有限公司 | Waybill information input and black-and-white block coding and decoding system |
| CN103488965A (en) * | 2013-08-20 | 2014-01-01 | 成都三泰电子实业股份有限公司 | Freight note information inputting and colored color-lump encoding-decoding system |
| CN104463792A (en) * | 2014-11-12 | 2015-03-25 | 迪堡金融设备有限公司 | Method and device used for removing noisy point in binarized image |
| CN104921698A (en) * | 2015-07-13 | 2015-09-23 | 中北大学 | Method for correcting corneal curvature instrument system astigmatism |
| CN108363986B (en) * | 2018-03-07 | 2021-08-13 | 曲阜师范大学 | Face shorthand system based on improved Sobel operator and contour extraction method |
| CN108363986A (en) * | 2018-03-07 | 2018-08-03 | 曲阜师范大学 | Face literary sketch system based on improved sobel method and contour extraction method |
| CN109543686A (en) * | 2018-10-24 | 2019-03-29 | 重庆师范大学 | Character recognition based on adaptive multi-thresholding pre-processes binarization method |
| CN109543686B (en) * | 2018-10-24 | 2023-04-25 | 重庆师范大学 | Character recognition preprocessing binarization method based on self-adaptive multi-threshold |
| CN109822231A (en) * | 2019-02-15 | 2019-05-31 | 英特尔产品（成都）有限公司 | Method and apparatus of the detection for the quality of the laser beam of Wafer Dicing |
| CN110047083A (en) * | 2019-04-01 | 2019-07-23 | 江西博微新技术有限公司 | Image noise recognition methods, server and storage medium |
| CN110047083B (en) * | 2019-04-01 | 2021-01-29 | 江西博微新技术有限公司 | Image noise point identification method, server and storage medium |
| CN114666523A (en) * | 2022-03-30 | 2022-06-24 | 湖南格为科技有限公司 | Energy-saving liquid crystal television capable of automatically adapting to human eye brightness |
| CN114666523B (en) * | 2022-03-30 | 2023-10-27 | 湖南格为科技有限公司 | Energy-saving liquid crystal television capable of automatically adapting to human eye brightness |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101794435B (en) | 2011-04-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101794435B (en) | Binary image noise-reduction method based on integral graph and binary image processing system | |
| CN110163219B (en) | Target detection method based on image edge recognition | |
| JP4668921B2 (en) | Object detection in images | |
| CN106780486A (en) | A kind of Surface Defects in Steel Plate image extraction method | |
| CN102831472A (en) | People counting method based on video flowing image processing | |
| CN111967394B (en) | Forest fire smoke root node detection method based on dynamic and static grid fusion strategy | |
| CN105447489B (en) | A kind of character of picture OCR identifying system and background adhesion noise cancellation method | |
| CN104063866A (en) | Method for detecting granularity in ore transmission process | |
| CN101706959A (en) | Method for extracting surface defects of metal sheets and strips on basis of two-dimensional information entropy | |
| CN105931259A (en) | High voltage transmission line extraction method based on morphology processing and device | |
| CN109850518B (en) | Real-time mining adhesive tape early warning tearing detection method based on infrared image | |
| JP2004265264A (en) | Image processor | |
| CN103729828A (en) | Video rain removing method | |
| CN112115875A (en) | Forest fire smoke root detection method based on dynamic and static combination area stacking strategy | |
| Shi et al. | Image enhancement for degraded binary document images | |
| Russell et al. | Vehicle detection based on color analysis | |
| CN109558881B (en) | Dangerous rock collapse monitoring method based on computer vision | |
| CN109426770B (en) | Iris identification method | |
| CN111178111A (en) | Two-dimensional code detection method, electronic device, storage medium and system | |
| Nguyen et al. | An improved real-time blob detection for visual surveillance | |
| JP2017033506A (en) | Road surface detection device and road surface detection method | |
| CN101719273A (en) | On-line self-adaptation extraction method of metallurgy strip surface defect based on one-dimension information entropy | |
| Zhu | Moving Objects Detection and Segmentation Based on Background Subtraction and Image Over-Segmentation. | |
| CN111105408B (en) | Building surface crack detection method and system based on image processing | |
| Huang et al. | The precise recognition of moving object in complex background |
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 | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Binary image noise-reduction method based on integral graph and binary image processing system Effective date of registration: 20150119 Granted publication date: 20110420 Pledgee: The Agricultural Bank of Chengdu branch of Limited by Share Ltd China Chengdu Pledgor: Chengdu Santai Electronic Industry Co., Ltd. Registration number: 2015510000005 |
|
| PLDC | Enforcement, change and cancellation of contracts on pledge of patent right or utility model | ||
| C56 | Change in the name or address of the patentee |
Owner name: CHENGDU SANTAI HOLDINGS GROUP CO., LTD. Free format text: FORMER NAME: CHENGDU SANTAI ELECTRONIC INDUSTRY CO., LTD. |
|
| CP01 | Change in the name or title of a patent holder |
Address after: 610091 Jinniu District high tech Industrial Park, Sichuan, Sichuan West Road, No. 42, No. Patentee after: Holding Group Plc of Chengdu three Thailand Address before: 610091 Jinniu District high tech Industrial Park, Sichuan, Sichuan West Road, No. 42, No. Patentee before: Chengdu Santai Electronic Industry Co., Ltd. |
|
| PLDC | Enforcement, change and cancellation of contracts on pledge of patent right or utility model | ||
| PM01 | Change of the registration of the contract for pledge of patent right |
Change date: 20160205 Registration number: 2015510000005 Pledgor after: Holding Group Plc of Chengdu three Thailand Pledgor before: Chengdu Santai Electronic Industry Co., Ltd. |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Date of cancellation: 20160229 Granted publication date: 20110420 Pledgee: The Agricultural Bank of Chengdu branch of Limited by Share Ltd China Chengdu Pledgor: Holding Group Plc of Chengdu three Thailand Registration number: 2015510000005 |
|
| PLDC | Enforcement, change and cancellation of contracts on pledge of patent right or utility model | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Binary image noise-reduction method based on integral graph and binary image processing system Effective date of registration: 20160317 Granted publication date: 20110420 Pledgee: The Agricultural Bank of Chengdu branch of Limited by Share Ltd China Chengdu Pledgor: Holding Group Plc of Chengdu three Thailand Registration number: 2016510000008 |
|
| PLDC | Enforcement, change and cancellation of contracts on pledge of patent right or utility model | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Date of cancellation: 20210129 Granted publication date: 20110420 Pledgee: The Agricultural Bank of Chengdu branch of Limited by Share Ltd. China Chengdu Pledgor: CHENGDU SANTAI HOLDING GROUP Co.,Ltd. Registration number: 2016510000008 |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210225 Address after: 215300 room 313, No.2, xugongqiao Road, Huaqiao Town, Kunshan City, Suzhou City, Jiangsu Province Patentee after: Dimension financial outsourcing services (Suzhou) Co.,Ltd. Address before: 610091 No. 42 Shu West Road, Jinniu District hi tech Industrial Park, Sichuan, Chengdu Patentee before: CHENGDU SANTAI HOLDING GROUP Co.,Ltd. |
|
| TR01 | Transfer of patent right | ||
| CP03 | Change of name, title or address |
Address after: 215332 room 1411, building a, Zhongke innovation Plaza, No. 1555, Greenland Avenue, Huaqiao Town, Kunshan City, Suzhou City, Jiangsu Province Patentee after: Dimension information technology (Suzhou) Co.,Ltd. Address before: 215300 room 313, No.2, xugongqiao Road, Huaqiao Town, Kunshan City, Suzhou City, Jiangsu Province Patentee before: Dimension financial outsourcing services (Suzhou) Co.,Ltd. |
|
| CP03 | Change of name, title or address |