CN1110010C - Method for automatically detecting the lost line of optical scanner - Google Patents
Method for automatically detecting the lost line of optical scanner Download PDFInfo
- Publication number
- CN1110010C CN1110010C CN98117198A CN98117198A CN1110010C CN 1110010 C CN1110010 C CN 1110010C CN 98117198 A CN98117198 A CN 98117198A CN 98117198 A CN98117198 A CN 98117198A CN 1110010 C CN1110010 C CN 1110010C
- Authority
- CN
- China
- Prior art keywords
- pixel
- value
- setting
- index
- gtg
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 230000003287 optical effect Effects 0.000 title claims abstract description 8
- 238000012360 testing method Methods 0.000 claims abstract description 22
- 230000002950 deficient Effects 0.000 claims description 3
- 238000006073 displacement reaction Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims 12
- FGUUSXIOTUKUDN-IBGZPJMESA-N C1(=CC=CC=C1)N1C2=C(NC([C@H](C1)NC=1OC(=NN=1)C1=CC=CC=C1)=O)C=CC=C2 Chemical compound C1(=CC=CC=C1)N1C2=C(NC([C@H](C1)NC=1OC(=NN=1)C1=CC=CC=C1)=O)C=CC=C2 FGUUSXIOTUKUDN-IBGZPJMESA-N 0.000 claims 2
- 238000001514 detection method Methods 0.000 description 10
- 230000005540 biological transmission Effects 0.000 description 3
- 230000000052 comparative effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 239000003513 alkali Substances 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
Images
Landscapes
- Image Processing (AREA)
Abstract
The present invention relates to a method for automatically detecting the lost line of an optical scanner, which can automatically detect the phenomenon of line loss and calculate the number of lost lines. The present invention has the technical scheme that after oblique lines of a test chart are read, a middle gray level value is calculated, and a standard difference is set; in a first row of features of the oblique lines, a feature whose gray level is near the middle grey scale value is searched; besides, the feature (Xi, Yj) serves as reference so as to start the comparison of the gray level value; the comparison adopts the order that the gray level of features which are positioned in (Xi, Yj) and (Xi-1, Yj+1) is firstly compared; if a comparison value exceeds a set value, the phenomenon of line loss exists; the number of lost lines can be accumulated in the process of the comparison, and the place where line loss exists can be taken.
Description
The present invention relates to a kind of detection method of image quality, refer to a kind of detection method that is applied in the lost line of optical scanner especially.
The factor of the image quality of influence scanning has many kinds, can design different test events at various possible factors.In the common image quality test, one of them test event is to detect at the phenomenon that goes offline.Cause the factor of lost line to have a lot, for example scanner step-out or vibration owing to motor when the optics module moves rubs, and makes reading of image produce interrupted phenomenon.Or the transmission system of scanner control is unstable, or the speed that reads of transmission system and image is inconsistent etc., all might produce situation about going offline.Therefore, make by the phenomenon that goes offline and to know the inner contingent problem of scanner by inference.For example, if each bar number that falls is all identical, has problem just represent Control Software.If the position that goes offline is all identical, then may be that motor or transmission system are out of joint.
The method of test can be utilized a test pattern (Calibration paper), on be painted with the oblique line of standard, after the scanning, the relatively image that is scanned and the oblique line of standard, the position and the bar number that go offline with judgement.Because oblique line is after amplification, the pixel at oblique line edge is arranged will not have the phenomenon that goes offline for stepped when the queueing discipline of ladder just can be found out.If fall a line, just then the ladder difference of pixel is two pixels, if fall two lines, just then the ladder difference of figure is three pixels or the like, the rest may be inferred.If when going offline in permissible scope, just then this scanner has qualified quality.Otherwise, then be non-type product, must do further maintenance.
The method that the judgement of using now goes offline must be through very complicated program.If in the time of will scanning the image of high-res, the image of scanning must be amplified tens of times, then with the ladder of manually comparing pixel on the oblique line one by one, compare the staircase rule of pixel more one by one, just can find out the place that goes offline.And, every figure must the whole story scanning for several times, with whether contraposition of the control of determining this scanner.In addition, artificial judgment has many problems, and not only speed is slow, and relates to subjective judgement, the standard of not only error rate height, and its quality may because of the people because of the time different, therefore can not provide consistent and effectively guarantee for the image quality of scanning.
Fundamental purpose of the present invention provides the method that a kind of automatic detection goes offline, and with correctly and apace by in the image that is scanned, judges whether scanner has the phenomenon that goes offline, and shows go offline local and calculate the number that goes offline.
Another object of the present invention is to propose a kind of scan image that can be applicable to all size automatic testing method that goes offline, and replacing artificial detection, and improves the effect that detects.
Another purpose of the present invention is to propose a kind of method that can detect lost line automatically, with the internal problem that produces by the phenomenon judgement that goes offline, and then the quality of guarantee product.
The present invention proposes a kind of automatic testing method that goes offline, comprise the following step: behind the oblique line of read test figure, GTG value in the middle of calculating one, and set a standard deviation, in the first row pixel of this oblique line, seek a GTG value near the pixel of this centre GTG value, and with this pixel (Xi, Yj) be benchmark, begin to do the comparison of GTG value.Its comparative sequence is, is positioned at relatively earlier that (Xi is Yj) with (Xi-1, the GTG of pixel Yj+1).If its fiducial value exceeds a setting value, just expression has the phenomenon that goes offline.But in order to have calculated several lines, must be again with (Xi-1, the pixel that Yj+1) faces mutually (Xi-2, Yj+1) relatively, always than to meeting a comparison condition of setting, just, (Xi, GTG Yj) is less than (Xi-1, Yj+1), and (Xi, GTG Yj) more than or equal to (Xi-2, Yj+1).If (Xi is Yj) with (Xi-1, the GTG difference of pixel Yj+1) is then represented not go offline in the error tolerance value, can continue the comparison of next column.The number that accumulative total goes offline in process relatively, and frame takes down the place of line, the just sum that goes offline of output and show the place that goes offline after relatively finishing.
Automatic testing method of the present invention is judged applicable to the image quality of arbitrary scanner, not only can effectively replace artificial judgement, more can reduce the generation of error, improves detection efficiency.And on screen, can demonstrate problematic place, and judge for further detecting, make detection more convenient.And, for the setting of standard deviation, more can adjust according to the scanner of different qualities, make its range of application more extensive.
Fig. 1 is the synoptic diagram of detection method of the present invention;
Fig. 2 is the decision flow chart of the present invention for the detection that goes offline;
Fig. 3 is the oblique line enlarged diagram that falls two line situations.
If oblique line is amplified to the shape that can see pixel, the pixel that just can see the edge of normal oblique line is arranged very regular, and its GTG is also very close.Part in the middle of its gray scale variation should be is the most black, thin out gradually to the both sides then, is boundary as if the central authorities with line, and then the arrangement on both sides and GTG value are symmetrical.If there is the situation that goes offline to take place, except GTG has had variation, the ladder figure of pixel also can manifest the situation of drop.
At the characteristic of the gray scale variation of oblique line, the present invention is on test pattern, and setting slope is the oblique lines of 45 degree.Certainly, the oblique line of other slope also can, but the slopes of 45 degree are owing to be half of 90 degree, shown pixel step therein is the most obvious, the best results that is therefore produced.As shown in Figure 1, slope be the oblique lines 11 of 45 degree after amplifying, on the edge, will produce as stair-stepping arrangement.Under situation about not going offline, every layer ladder difference should be a pixel.
The present invention is not to judge the number that goes offline by the drop of ladder, but is judged by the variation of GTG value on judging automatically.During judgement with GTG value in the middle of one and a standard deviation as the standard value of judging.The GTG that is produced with 8 bits (8bit) is an example, by complete black 0 to white 255 entirely, can produce the gray scale variation on 256 rank.Method of the present invention is got its intermediate value (128 ± standard deviation) standard value as a comparison.This is because of apparent in view by 128～255 and 128～0 gray scale variation, because than the difference that is easier to judge the GTG value.The setting of standard deviation then can be decided according to the scanner specification that will test.
As shown in Figure 1, the little lattice among Fig. 1 are represented a pixel, and the numeral in the lattice is the GTG value of this pixel.The GTG of intermediate portion part is complete black, and the GTG of both sides is symmetrical, (with the GTG value representation).256 middle GTG value is 128, and the tentative standard difference is 20, then gets the GTG standard value as a comparison of (128 ± 20).In Fig. 1, abscissa is made as X and ordinate is made as Y.Suppose that index j represents the pixel of j position on this ordinate, index i represents the locational pixel of i on this abscissa.If j=1; In Yj row, find out the GTG value near the GTG value of (128 ± 20).And the position of pixel on abscissa X to be found, as initial position.With the GTG value among Fig. 1 is example, Yj capable find the most approaching in the middle of the pixel of GTG value be 112.Then, with the GTG value 112 the position of pixel on abscissa X, as the initial position of Xi, and to establish i be 1.
Then, relatively more vertical seat bar Yj and the capable grey jump of Yj+1, promptly relatively be positioned at coordinate (Xi, Yj) pixel on be positioned at (Xi-1, Yj+1) pixel on, if (Xi, the GTG value of the pixel Yj) be positioned at (Xi-1, Yj+1) the GTG value that goes up pixel is in the error tolerance value, then expression does not go offline, can continue to check next column, promptly compare the capable and capable pixel of Yj+2 of Yj+1.As shown in Figure 1, be positioned at (its GTG value also is 112 for Xi-1, the Yj+1) pixel on, thus represent not go offline, can be with index j increase by 1, index i subtracts 1, to continue to check the comparison of next column.So compare the GTG value one by one and be 121,123,129 and 120 pixel, because its GTG value is all in the error tolerance value, so this oblique line of decidable does not go offline.
If (Xi, Yj) pixel on be positioned at (Xi-1, Yj+1) its GTG difference of the pixel on is not in the error tolerance value, then expression has a phenomenon that goes offline.(Xi, Yj), (Xi-1 Yj+1) reaches (Xi-2, Yj+1) pixel on to necessary the continuation relatively.When its fiducial value meet one set comparison condition the time, promptly (Xi, Yj) less than (Xi-1, Yj+1), and more than or equal to being positioned at (when Xi-2, pixel on Yj+1), then a line has been fallen in expression.If when not meeting the comparison condition of this setting, then relatively (Xi, Yj), (Xi-2 Yj+1) reaches (Xi-3, Yj+1) pixel in continuation.Carry out so repeatedly, meet the comparison condition of this setting up to result relatively.In the time of relatively, the place that number that accumulative total goes offline and frame take down line.After finishing, by the beginning of Yj+1 row, heavily be covered with and state comparison, again until the comparison of finishing the whole piece oblique line.At last, the total number that goes offline of output and show the place that goes offline.What must one carry is not need to compare colored lines in the detection that goes offline, because the problem that goes offline and color have nothing to do.Therefore, it is just enough to do test with GTG.
Show that for clear the present invention for the decision flow chart that goes offline, sees also Fig. 2.When the project of the selected test of user was the detection of oblique line, the user can be according to the specification and the desired quality of scanner, established standards difference.It judges flow process as shown in Figure 2:
When detecting, want earlier the oblique line of standard on the read test figure, be that 45 degree are the best, i.e. step 201 with gradient.In step 202, the oblique line of establishing criteria, scanner produce the image of this standard oblique line.In step 203, carry out the initialization of index, make i point to the pixel position of the most approaching middle GTG value of GTG value among the abscissa X.And make i=1; J=1; L=oblique line length (is unit with the pixel); M=0 (counter that m goes offline and uses for accumulative total); K=0 (k represents the index of displacement).Then, find out the GTG value the most approaching in the middle of the pixel of ash value, and the coordinate of setting this pixel be (Xi, Yj), i.e. step 204.In step 205, relatively coordinate is that (Xi is Yj) with (Xi-1, pixel Yj+1) then.Step 206 is the judgement of this fiducial value.If the GTG value comparative result of two pixels in the error tolerance value, just represent not go offline between those row of Yj and its next column, can directly carry out the comparison of next column again.But must check whether on the Yj+1 be that last has been listed as, so execution in step 211.If then the information of m bar line has been fallen in step 213 output, this moment is owing to m=0, the meaning of promptly not falling.If Yj+1 is not last row, then carry out the comparison of next column, so execution in step 210, increase by 1 with the index j that will indulge a bar Y, the index i of abscissa X subtracts 1+k, and execution in step 205 then, to carry out the comparison of a loop, up to the comparison of finishing all row of whole piece oblique line.
If (Xi, Yj) with (Xi-1, Yj+1) the GTG value of two pixels is not in the error tolerance value, then execution in step 207.This expression has the phenomenon that goes offline and takes place, thus the value of k is increased by 1, relatively the GTG of two pixels that face mutually of those row of Yj+1 (Xi-k, Yj+1), (Xi-(k+1), Yj+1).In step 208, judge that (Xi, Yj) GTG of pixel is whether less than (Xi-k, the Yj+1) GTG of pixel, and more than or equal to (Xi-(k+1), Yj+1) GTG of pixel.If just a line has only been fallen in expression, execution in step 212 makes m=m+1.If not, just will be in those row of Yj+1 with the index of i alkali 1 again, with pixel of those row of Yj+1 relatively one by one, up to (Xi, Yj) GTG of pixel is less than the GTG of that certain pixel of row of Yj+1, and the GTG of the pixel that faces mutually more than or equal to this pixel, i.e. step 208.If not, just execution in step 209: with (Xi-k, Yj+1), (Xi-(k+1), pixel frame Yj+1) get, and the position so that expression goes offline increases by 1 with m, and this represents that number of times relatively also just equals the number that goes offline.Then, execution in step 207 is to continue above-mentioned comparison.Enter another loop.At last, after all relatively finishing, the line that sum that output goes offline and display box are got.When the sum that goes offline goes offline during allowable value greater than predefined, judge that this scanner is defective; And when within the allowable value that goes offline of the sum that goes offline in predetermined set, judge that this scanner is qualified.
For further making the auditor understand above-mentioned flow process, with an embodiment method that goes offline of judging is described again.As shown in Figure 3, read (step 201～202) at the image of finishing 45 degree oblique lines, and after the initializing set value (step 203), the pixel of the most approaching middle GTG of ash value is benchmark (step 204) relatively in the middle of reading, finding GTG at those row of Yj is 136 pixel, because its GTG value is near 128.I is pointed to the position at this pixel place.If standard deviation is 20, m=0.Then relatively coordinate be (Xi, Yj) and (Xi-1, pixel (step 205) Yj+1), promptly 136 and 139.Because its difference is in standard deviation, so the index of ordinate Y is added 1, the index i that reaches abscissa X subtracts 1 (step 210), and execution in step 205 then.
Then compare 139 and 138 difference (step 205), judge whether in the error tolerance value (step 206).Because still in standard deviation, and arrive the bottom (step 211) of line as yet, so with the index j increase by 1 of ordinate Y, the index i of abscissa X subtracts 1+k (step 210).Heavily cover step 205 then, compare 138 and 179.Because its difference exceeds standard deviation, so execution in step 207.K=k+1 compares 138 and 178,179, and execution in step 208 then.Because 138＜178 and 138＞179, so continue execution in step 209; 179,178 pixel frame is taken out, m is increased by 1, the value of k adds 1 again.Execution in step 207 then.Compare 138,178,137.Because 138＜178 and 138＜179, so execution in step 212:m increases by 1 again, expression goes offline and increases by one.Then, execution in step 211 judges whether to finish the comparison of sliver.Owing to do not finish as yet, so execution in step 210 adds 1 with index j, and i=i-(1+k) is to carry out the comparison of next column.Then, execution in step 205 is to become the comparison of a loop.Relatively arrive end, execution in step 213 is with the output comparative result so always.Result of calculation, m=2 has fallen two lines altogether, and the place that goes offline also frame take out, conveniently to debate knowledge.
This flow process narrates with the figure of Fig. 1 and Fig. 3 and the method for expressing of coordinate for convenience of explanation.If the method for expressing of coordinate changes, or the change of the direction of oblique line, or relatively the order of pixel is changed into from left to right or is from bottom to top waited, neither disengaging spirit of the present invention.For example since black partly be online central authorities, and the both sides of central authorities be symmetry, so relatively opposite side also can be used the said method flow process, just the comparison palpus of step 208 will less than change into greater than, and more than or equal to change into smaller or equal to.This be because black partly be in the centre, when making comparisons with its left side, abscissa is just shallow more to its GTG that moves to left more.
Claims (14)
1, a kind of automatic testing method of lost line of optical scanner, in order to behind the image of the oblique line of optical scanner read test figure,, judge whether the oblique line of this scanning has the phenomenon that goes offline according to a standard difference, and export the number that goes offline, it is characterized in that: comprise step:
The index i of a, initialization one abscissa X, the index j of an ordinate Y, a displacement index k, and counter;
B, setting one error tolerance value;
C, in the pixel of first row of this oblique line, find out a GTG value, and this pixel is on the right side of the pixel with maximum gray value near the pixel of this centre GTG value, and the coordinate values of setting this pixel be (Xi, Yj);
D, relatively this pixel (Xi is Yj) with the pixel of the next column of this pixel (Xi-1, GTG value Yj+1), and export first fiducial value;
E, when this first fiducial value is in the scope of this error tolerance value, the move right index j of k+1 position and this ordinate Y of the index i of this abscissa X is increased by 1, and execution in step (d);
F, when this first fiducial value exceeds in the scope of this error tolerance value, relatively this pixel (Xi, Yj) with two pixels that face mutually of the next column of this pixel (Xi-k, Yj+1), (Xi-(k+1), GTG value Yj+1), and export second fiducial value;
G, judge whether this second fiducial value meets a comparison condition of setting;
H, when this second fiducial value meets the comparison condition of this setting, counter is increased by 1, and execution in step (d);
I, when this second fiducial value does not meet the comparison condition of this setting, frame get this be positioned at (Xi-k, Yj+1) and (Xi-(k+1), the Yj+1) pixel of coordinate increase by 1 with this counter, and execution in step f;
J, when judging that j adds 1 when equaling the oblique line length overall, the output result of determination.
2, automatic inspection as claimed in claim 1 side method is characterized in that: the oblique line of this test pattern is the oblique lines of 45 degree.
3, automatic inspection as claimed in claim 1 side method, it is characterized in that: wherein above-mentioned error tolerance value is set for the specification of foundation scanner.
4, automatic inspection as claimed in claim 1 side method is characterized in that: wherein above-mentioned steps (a) equals 1 for setting abscissa index i, and ordinate index j equals 1, and carry digit k equals zero, and counter equals zero.
5, automatic inspection as claimed in claim 1 side method is characterized in that: wherein above-mentioned steps (a) more comprises the length that step: L sets oblique line.
6, automatic inspection as claimed in claim 1 side method, it is characterized in that: wherein the comparison condition of the described setting of above-mentioned steps (g) is for working as (Xi, Yj) GTG value is less than being positioned at (Xi-k, Yj+1) pixel on, and (Xi, Yj) GTG value is more than or equal to being positioned at (Xi-(k+1), Yj+1) pixel on.
7, automatic inspection as claimed in claim 1 side method, it is characterized in that: above-mentioned j comprises step:
The number that goes offline is allowed in m, setting one;
N, when the number of above-mentioned counter is in this allows the number that goes offline, judge that this scanner is qualified;
O, when the number of above-mentioned counter exceeds this and allows in the number that goes offline, judge that this scanner is defective.
8, a kind of automatic testing method of lost line of optical scanner, in order to behind the image of the oblique line of optical scanner read test figure,, judge whether the oblique line of this scanning has the phenomenon that goes offline according to a standard difference, and export the number that goes offline, it is characterized in that: comprise step:
The index i of a, initialization one abscissa X, the index j of an ordinate Y, a displacement index k, and counter;
B, setting one error tolerance value;
C, in the pixel of first row of this oblique line, find out a GTG value, and this pixel is on the right side of the pixel with maximum gray value near the pixel of this centre GTG value, and the coordinate values of setting this pixel be (Xi, Yj);
D, relatively this pixel (Xi is Yj) with the pixel of the next column of this pixel (Xi-1, GTG value Yj+1), and export first fiducial value;
E, when this first fiducial value is in the scope of this error tolerance value, the index i of this abscissa X is increased by 1 to the index j of move to left k+1 position and this ordinate Y, and execution in step (d);
F, when this first fiducial value exceeds in the scope of this error tolerance value, relatively (Xi is Yj) with the two pixel (Xi+k that face mutually of the next column of this pixel for this pixel, Yj+1) (Xi+k), Yj+1), (Xi+ (k+1), Yj+1) GTG value, and export second fiducial value;
G, judge whether this second fiducial value meets a comparison condition of setting;
H, when this second fiducial value meets the comparison condition of this setting, counter is increased by 1, and execution in step (d);
I, when this second fiducial value does not meet the comparison condition of this setting, frame get this be positioned at (Xi+k, Yj+1), (Xi+ (k+1), the Yj+1) pixel of coordinate increase by 1 with this counter, and execution in step f;
J, when judging that j adds 1 when equaling the oblique line length overall, the output result of determination.
9, automatic inspection as claimed in claim 8 side method is characterized in that: the oblique line of this test pattern is the oblique lines of 45 degree.
10, automatic inspection as claimed in claim 8 side method, it is characterized in that: wherein above-mentioned error tolerance value is set for the specification of foundation scanner.
11, automatic inspection as claimed in claim 8 side method is characterized in that: wherein above-mentioned steps (a) equals 1 for setting abscissa index i, and ordinate index j equals 1, and carry digit k equals zero, and counter equals zero.
12, automatic inspection as claimed in claim 8 side method is characterized in that: wherein above-mentioned steps (a) more comprises step: L, sets the length of oblique line.
13, automatic inspection as claimed in claim 8 side method, it is characterized in that: wherein the comparison condition of the described setting of above-mentioned steps (g) is for working as (Xi, Yj) GTG value is greater than being positioned at (Xi+k, Yj+1) the GTG value on, and (Xi, Yj) GTG value is smaller or equal to being positioned at (Xi+ (k+1), Yj+1) the GTG value on.
14, automatic inspection as claimed in claim 8 side method, it is characterized in that: above-mentioned j comprises step:
The number that goes offline is allowed in m, setting one;
N, when the number of above-mentioned counter is in this allows the number that goes offline, judge that this scanner is qualified;
O, when the number of above-mentioned counter exceeds this and allows in the number that goes offline, judge that this scanner is defective.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN98117198A CN1110010C (en) | 1998-08-18 | 1998-08-18 | Method for automatically detecting the lost line of optical scanner |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN98117198A CN1110010C (en) | 1998-08-18 | 1998-08-18 | Method for automatically detecting the lost line of optical scanner |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN1245321A CN1245321A (en) | 2000-02-23 |
| CN1110010C true CN1110010C (en) | 2003-05-28 |
Family
ID=5225405
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN98117198A Expired - Fee Related CN1110010C (en) | 1998-08-18 | 1998-08-18 | Method for automatically detecting the lost line of optical scanner |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN1110010C (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101326549B (en) * | 2005-12-05 | 2013-06-19 | 全视技术有限公司 | Method for detecting streaks in digital images |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1244156A (en) * | 1996-12-09 | 2000-02-09 | 美国3M公司 | Uv protected syndiotactic polystyrene overlay films |
-
1998
- 1998-08-18 CN CN98117198A patent/CN1110010C/en not_active Expired - Fee Related
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1244156A (en) * | 1996-12-09 | 2000-02-09 | 美国3M公司 | Uv protected syndiotactic polystyrene overlay films |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101326549B (en) * | 2005-12-05 | 2013-06-19 | 全视技术有限公司 | Method for detecting streaks in digital images |
Also Published As
| Publication number | Publication date |
|---|---|
| CN1245321A (en) | 2000-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114997009B (en) | Bridge bearing capacity rapid assessment method based on machine vision and model correction | |
| US4642813A (en) | Electro-optical quality control inspection of elements on a product | |
| JP3039954B2 (en) | Character recognition method and apparatus | |
| US11640660B2 (en) | Industrial internet of things, control methods and storage medium based on machine visual detection | |
| JP2020181532A (en) | Image determination device and image determination method | |
| CN1041445A (en) | The discrimination method of metal surface and device | |
| CN1203229C (en) | Method and device for evaluating defect in flat textile structures | |
| CN1110010C (en) | Method for automatically detecting the lost line of optical scanner | |
| US4959869A (en) | Method for determining binary coding threshold value | |
| CN100474878C (en) | Image quality prediction method and apparatus and fault diagnosis system | |
| CN113592868A (en) | Method for detecting black and gray of glass fiber cloth cover | |
| CN112653884A (en) | Method for evaluating quality of screen | |
| US5432868A (en) | Information medium recognition device | |
| JPH07239938A (en) | Inspection method | |
| US6747619B1 (en) | Method of evaluating front of screen quality and apparatus for evaluating front of screen quality using the same | |
| CN114677670B (en) | Method for automatically identifying and positioning identity card tampering | |
| CN117557487A (en) | Smooth object highlight removing method and system based on pix2pixHD and defect detecting device | |
| US6373983B1 (en) | Method for detecting the occurrence of missing lines on images generated by an optical scanner | |
| JP2859124B2 (en) | Surface strain judgment method | |
| CN114119479A (en) | Industrial production line quality monitoring method based on image recognition | |
| CN114210741B (en) | Strip steel surface roughness online detection device and method | |
| CN115206528A (en) | Mental health evaluation system and method based on software data analysis | |
| CN100378753C (en) | Method of determining the region of interest in images of skin prints | |
| CN1076110C (en) | Detection method for monochrome line and color line in optical scanner | |
| JPH07113612B2 (en) | Steel sheet surface defect inspection device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C06 | Publication | ||
| PB01 | Publication | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: GR Ref document number: 1052331 Country of ref document: HK |
|
| C19 | Lapse of patent right due to non-payment of the annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |