CN104976951A - Device and method for identifying image - Google Patents
Device and method for identifying image Download PDFInfo
- Publication number
- CN104976951A CN104976951A CN201410167796.XA CN201410167796A CN104976951A CN 104976951 A CN104976951 A CN 104976951A CN 201410167796 A CN201410167796 A CN 201410167796A CN 104976951 A CN104976951 A CN 104976951A
- Authority
- CN
- China
- Prior art keywords
- image
- pixel
- those
- sidelines
- cornerwise
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000012545 processing Methods 0.000 claims description 71
- 238000005259 measurement Methods 0.000 claims description 31
- 238000012360 testing method Methods 0.000 claims description 30
- 230000014509 gene expression Effects 0.000 claims description 12
- 238000010586 diagram Methods 0.000 description 21
- 230000000875 corresponding effect Effects 0.000 description 16
- 238000012937 correction Methods 0.000 description 6
- NHDHVHZZCFYRSB-UHFFFAOYSA-N pyriproxyfen Chemical compound C=1C=CC=NC=1OC(C)COC(C=C1)=CC=C1OC1=CC=CC=C1 NHDHVHZZCFYRSB-UHFFFAOYSA-N 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 1
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 1
- 229910052782 aluminium Inorganic materials 0.000 description 1
- 239000004411 aluminium Substances 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Image Analysis (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention provides a device and a method for identifying an image. The method has the following steps. First, a first image carrying an object is captured by an image recognition device. Then, the length of the first diagonal line and the length of the second diagonal line of the object are calculated according to the first image. And outputting the identification result when the ratio of the first diagonal length to the second diagonal length is within a first range. The method can help a user to know the shape of the object and the size of the object by capturing the image of the object.
Description
Technical field
The present invention relates to a kind of devices and methods therefor of identification image, particularly the devices and methods therefor of the shape of object and the identification image of size in a kind of identification image.
Background technology
In assembly line, when being assembled by two articles, the measurement size of object and the shape of identification object are a ring indispensable in assembling process.For example, when group glasses in aluminium frame, if excessive compression causes composition surface sharp projection, or the opening that incomplete closely sealed formation is sharp, likely can cause packaging personnel or be the injury to personnel of standing in terminal client group.In another example, if modular shape changes, in terminal client place with carry on the back rail in conjunction with time, slight situation is that reluctantly group is vertical, causes locking point to have stress-retained, through likely causing the more serious or disabler of distortion after a while; Serious distortion is even chain all cannot be carried out admittedly, causes the loss of client and manufacturer itself.
But, in the size of existing manual measurement object and the shape of visual identification object, still there is many problems.For example, survey crew may be not easy to measure (if object corner is circular arc) because of misunderstanding band tape graduation or the shape of object own on measurement object, and then causes on identification object and have situation about cannot assemble because of above-mentioned error.And if all need to use aforementioned manual type to measure to each object in assembly line, the lifting for the efficiency of assembly line also belong to difficulty.
Summary of the invention
Because above problem, the object of the present invention is to provide a kind of devices and methods therefor of identification image, by be compared to object in pick-up image the number of pixel to judge the shape of object, and by the number of the pixel of measuring object in the physical size of object and image, obtain the size of object, can learn the shape of object and the size of object by means of only the image of acquisition object to help user.
Method according to the identification image disclosed by the present invention comprises the following steps: the device first utilizing identification image, and acquisition is loaded with the first image of object.Then, according to the first image, first cornerwise length and second cornerwise length of object is calculated.And, when the ratio of the first catercorner length and the second catercorner length is in the first scope, export identification result.
Device according to the identification image disclosed by the present invention has image acquisition module and image processing module.Described image acquisition module has the image of object in order to acquisition.Described image processing module couples image acquisition module, image processing module performs image edge detection program to obtain the position in multiple sidelines of object from image, image processing module also obtains the first diagonal line and second cornerwise position in multiple diagonal line of object in image according to the position in multiple sidelines of object, calculates the number of the pixel on the first diagonal line and second cornerwise position, and judges that the ratio of number of the first diagonal line and second cornerwise pixel is whether in the first scope.Wherein when the ratio of the number of the first diagonal line and second cornerwise pixel is in the first scope, export an identification result.
In sum, in identification image of the present invention, the device and method of object can by execution one sideline trace routine to obtain multiple sideline of object in image and to be obtained multiple diagonal line of object by multiple sidelines of object, last again by the number of pixel each other on the multiple cornerwise position being compared to object in image to judge the shape of object, allow user can learn the shape of object by the image of acquisition object.
Describe the present invention below in conjunction with the drawings and specific embodiments, but not as a limitation of the invention.
Accompanying drawing explanation
Fig. 1 is according to the functional-block diagram of the device of the identification image of one embodiment of the invention;
Fig. 2 is according to the side view of the image of the acquisition object of one embodiment of the invention;
Fig. 3 is according to the schematic diagram with the image of object of one embodiment of the invention;
Fig. 4 is according to the schematic diagram with the partial image of object of one embodiment of the invention;
Fig. 5 is according to the functional-block diagram of the device identification image of the correction identification image of one embodiment of the invention;
Fig. 6 is according to the process flow diagram of the method for the identification image of one embodiment of the invention;
Fig. 7 is according to the process flow diagram of the method for the device of the correction identification image of one embodiment of the invention.
Wherein, Reference numeral
The device of 10 identification images
102 image acquisition modules
104 image processing modules
12 objects
14 images
1412 pixels
1414 pixels
1416 pixels
1418 pixels
1420 pixels
1422 pixels
1424 pixels
1426 pixels
1428 pixels
16 platforms
18 standard test pieces
L1, L2, L3, L4 sideline
DI1, DI2 diagonal line
Embodiment
Below detailed features of the present invention and advantage is described in embodiments in detail, its content is enough to make any relevant art of haveing the knack of understand technology contents of the present invention and implement according to this, and content, right and the accompanying drawing disclosed by this instructions, any relevant art of haveing the knack of can understand the object and advantage that the present invention is correlated with easily.Following embodiment further describes viewpoint of the present invention, but non-to limit category of the present invention anyways.
Refer to Fig. 1, Fig. 1 is the functional-block diagram of the device of identification image according to an embodiment of the invention.As shown in Figure 1, in identification image, object device 10 comprises image acquisition module 102 and image processing module 104, and wherein, image processing module 104 couples image acquisition module 102.
See also Fig. 1, Fig. 2 and Fig. 3, wherein Fig. 2 is the side view of the image capturing object according to an embodiment of the invention, and Fig. 3 is the schematic diagram of the image according to an embodiment of the invention with object.As shown in FIG., image acquisition module 102 has the image 14 of object 12 in order to acquisition.Furthermore, when user is for identification object 12, user first can be about to object 12 and be placed in parallel on a platform 16, and platform 16 is the belows being positioned over object device 10 in identification image, and user controls image acquisition module 102 wherein has object 12 image 14 with acquisition again.In enforcement, image acquisition module 102 can be but be not limited to camera lens, suitable photographic equipment that camera lens, network take the photograph device camera lens or other capturing images 14.
Then, aforementioned image processing module 104 performs image edge detection program to obtain the position in multiple sidelines of object 12 from image 14, and image processing module 104 also obtains the position of diagonal line DI1 and diagonal line DI2 in multiple diagonal line of object 12 in image 14 according to the position of multiple sideline L1, L2, L3, L4 of object 12.For example, after image acquisition module 102 acquisition has the image 14 of object 12 (such as rectangle), be sent to image processing module 104 by image 14 and carry out image edge detection program, the function mode of its image edge detection program is detailed later.Behind sideline L1, L2, L3, L4 of being looked for out object 12 by aforementioned image edge detection program when image processing module 104 position in image 14, namely the position of intersecting point of sideline L1 and sideline L2 and sideline L4 is passed through, and the position of intersecting point of sideline L3 and sideline L2 and sideline L4, find out diagonal line DI1 and the position of diagonal line DI2 in image 14.Image processing module 104 can be but be not limited to microprocessor (micro processor), image processor (graphics processing unit), central processing unit (central process unit) or other are suitable for the element of calculation process, but the present invention is not as limit.
Image processing module 104 calculates the number of the pixel on the position of diagonal line DI1 and diagonal line DI2, and judges that the ratio of number of pixel of diagonal line DI1 and diagonal line DI2 is whether in the first scope.When image processing module 104 judges that the ratio of the number of the pixel of diagonal line DI1 and diagonal line DI2 is in the first scope, then export an identification result.Furthermore, after image processing module 104 obtains the position of diagonal line DI1 and diagonal line DI2, namely diagonally DI1 and diagonal line DI2 calculates the number of pixel of diagonal line DI1 and the number of the pixel of diagonal line DI2 respectively.
Then, after the number of the number of pixel calculating diagonal line DI1 than the pixel of diagonal line DI2, by the number of the pixel of diagonal line DI1 with the number of the pixel of diagonal line DI2 divided by obtaining a ratio value.If the ratio value obtained is in the first scope time (scope of such as 0.9 to 1.1), represent diagonal line DI1 or gap equal with the number of the pixel of diagonal line DI2 within the acceptable range, also diagonal line DI1 or gap equal with the physical length of diagonal line DI2 is represented within the acceptable range, now namely export an identification result, this identification result can be the object 12 judging identification is rectangles, or judge the object 12 of identification be pentagon, hexagon also or any polygonal shape, the present invention is not as limit.
Refer to Fig. 4, Fig. 4 is the schematic diagram of the partial image according to an embodiment of the invention with object.As shown in Figure 4, aforementioned image edge detection program is whether the pixel 1420 for comparing image 14 is greater than threshold value with the difference of the GTG angle value of other pixels 1412,1418,1420, when the pixel 1420 of image compare other pixels 1412,1414, the difference of the GTG angle value of 1416 ... 1428 be greater than threshold value time, the position of pixel 1420 in image 14 is the position of the pixel of multiple sideline L1, L2, L3, L4 of object 12, and wherein pixel 1420 is adjacent to pixel 142.In other words, when user by parallel for object 12 be placed on image acquisition module 102 times time, user by placing a light source below object 12, the location of pixels placed by object 12 can because object 12 itself covers some light, and be low than the brightness of other location of pixels not placing object 12, add the pixel intensity in the edge positions placing object 12, the characteristic of larger gap can be had than the brightness of the location of pixels outside adjacent sideline, compare the difference of the GTG angle value of the pixel that in image 14, each pixel is adjacent.
Illustrate in this with an example, the image 14 with object 12 after the image 14 of acquisition one object 12 (such as pentagon), is then sent to image processing module 104 by image acquisition module 102.Image processing module 104 calculates the GTG angle value of each pixel in image 14, and start centered by pixel 1420 respectively with adjacent other pixels 1412,1414, whether 1416 ... 1428 difference that calculates two GTG angle value be greater than a threshold value (such as whether being greater than 125).The GTG angle value of such as pixel 1420 is 255, and be respectively 10,20,50 adjacent to the GTG angle value of the pixel 1412,1418,1424 of the left of pixel 1420, GTG angle value adjacent to the pixel 1416,1422,1428 of the right of pixel 1420 is respectively 168,175,192, and the GTG angle value of the pixel 1414 adjacent to the top of pixel 1420 and the pixel 1426 in the below of pixel 1420 is respectively 245 and 252.When the GTG angle value of pixel 1420 being subtracted each other with the shade of gray of pixel 1412,1418,1424 respectively, its difference is all greater than threshold value.And the GTG angle value of pixel 1420 is all less than threshold value respectively compared with the GTG angle value of pixel 1416,1422,1428 and the GTG angle value of pixel 1414,1426.Now image processing module 104 can judge the left side bearing of pixel 1420 as object 12.
Moreover, for making the GTG angle value of the pixel on sideline of the present invention can with the shade of gray value difference of adjacent pixel outside sideline apart from more obvious, quantity of light source of the present invention can be multiple, and the position of this little light source also not only can be placed on the below of object 12, also can according to the demand of user's situation, be placed on multiple diverse location, the sideline of object 12 of the present invention can be obtained more accurately.
In addition, image processing module 104 has more and receives multiple measurement numerical value, wherein each measures numerical value is be the multiple sideline L1 of correspondence, L2, L3, L4 or multiple diagonal line DI1, the physical length of DI2 one of them, and image processing module 104 is more in performing image edge detection program to obtain multiple sideline L1 of object 12 from image, L2, L3, behind the position of L4, according to the above-mentioned measurement numerical value received and this corresponding a little sideline L1, L2, L3, L4 or this little diagonal line DI1, one relational expression of the number of the pixel on the position of DI2 is to calculate the size of pixel 142.In an embodiment, user can measure sideline L1, L2, L3, L4 of this object 12 and the physical length of two diagonal line DI1, DI2 in advance, and to be inputed to by above-mentioned measurement numerical value in identification image in object device 10.And image processing module 104 can because the number of pixel on the physical length of aforementioned sideline L1, L2, L3, L4 of calculating and two diagonal line DI1, DI2 and its position be to calculate the size of the pixel of image.
In another embodiment, when object 12 is pentagon, user before the pentagonal image of acquisition, can measure this pentagonal five length of sides and three cornerwise physical lengths, and be inputed to by above-mentioned measurement numerical value in identification image in object device 10 in advance.Image processing module 104 obtains pentagonal 5 positions of the length of side in image according to aforementioned image edge detection program again, and Yu Houzai obtains pentagonal 3 positions of diagonal line in image according to the position of five length of sides.Finally, image processing module 104 is again according to the length of side and cornerwise physical length of input, and the number of pixel on this little length of side and the position of diagonal line in image, can calculate the size of the pixel of image 14.
Foregoing relationships can be:
Wherein, total ratio is that each is measured one of them the ratio of number of pixel of numerical value and this corresponding a little sideline L1, L2, L3, L4 or corresponding this little diagonal line DI1, DI2 and is added, the quantity that measurement number is received multiple measurement numerical value.For example, when after the physical length measuring sideline L1, L2, L3, L4 and two diagonal line DI1, DI2, image processing module 104 by the length of sideline L1 divided by the number of the pixel on the L1 of sideline to obtain the ratio of sideline L1.Afterwards image processing module 104 again by the length of sideline L2 divided by the number of the pixel on the L2 of sideline to obtain the ratio of sideline L2, thereafter by that analogy, to obtain the ratio of 4 sidelines L1, L2, L3, L4 and 2 diagonal line DI1, DI2.Processing module 104 again row to be done sums average (being added divided by 6 by these 6 ratios) to these 6 ratios, obtains the size of the pixel of image.
Except aforementioned described relational expression, its relational expression can also be use the mode of weighted mean to calculate the size of pixel 142, and relational expression is as follows:
Wherein, total length is added with weighted type for optionally this being measured a bit numerical value, and the number of total pixel is that the number of this little cornerwise pixel this being measured a bit this little sideline corresponding to numerical value or correspondence is added.Further, for making the size of the pixel 142 obtained can be more accurate, processing module 104 can to wherein some measure numerical value give higher weight, such as because of two diagonal line DI1, length comparatively other sidelines L1 of DI2, L2, L3, L4 is for long, its two diagonal line DI1, the number of the pixel of DI2 is also than other sidelines L1, L2, L3, the number of the pixel of L4 is many, if give two cornerwise length higher weights (such as 1.4), the error of its single pixel calculated, can be less than the error calculating single pixel to not giving weight, that is the size of the single pixel calculated can be more accurate.
Except as described, the present invention does not limit and need measure sideline L1, L2, L3, L4 and two diagonal line DI1, whole physical lengths of DI2 can be calculated the size of the pixel of image 14, if only measure sideline L1, sideline L3 and diagonal line DI1, can also be drawn the size of the pixel of image 14 by above-mentioned two relational expressions, the present invention is not limited in this.
Moreover, in identification image, object device 10 can more comprise storage module 106, storage module 106 in order to store the measurement numerical value of the GTG angle value of each pixel in image, the position of storing articles 12 sideline L1, L2, L3, L4 and diagonal line DI1, DI2 in image 14 and the number storing the pixel on it and each sideline L1, L2, L3, the L4 received and diagonal line DI1, DI2, and stores the size of the pixel 142 calculated to have the image of next object to calculate the size of next object by acquisition.
In addition to the foregoing, the present invention has more the correction program of the device 10 correcting identification image, sees also Fig. 1 and Fig. 5, and Fig. 5 is according to the functional-block diagram of the device identification image of the correction identification image of one embodiment of the invention.As shown in FIG., image acquisition module 102 acquisition is loaded with second image (not being plotted in diagram) of standard test piece 18.Then, multiple sidelines (the not being plotted in diagram) position of image processing module 104 appreciative standard test piece 18 from the second image, as previously mentioned, therefore not in this to go forth for its identification mode.Image processing module 104 reads the number of pixels on multiple edge positions of aforementioned standard test piece 18, and after having read, physical length and corresponding multiple number of pixels in multiple sidelines of the manual measurement standard test piece 18 that image processing module 104 i.e. comparison receives, to calculate to obtain physical length corresponding to each pixel (not being plotted in diagram).
After image processing module 104 obtains physical length corresponding to each pixel, image processing module 104 footpath row send command signal to image acquisition module 102, and instruction image acquisition module 102 captures the 3rd image (not being plotted in diagram).Image acquisition module 102 in acquisition, is sent to processing module 104 by the 3rd image and carries out image processing, to obtain the number of pixels on multiple edge positions of the 3rd image Plays test piece 18 after the 3rd image.Processing module 104 is by physical length corresponding to aforementioned each calculated pixel, and the number of pixels on multiple edge positions of the standard test piece 18 obtained from the 3rd image, calculates the length in multiple sidelines of standard test piece 18.
When processing module 104 obtains the physical length in multiple sidelines of above-mentioned manual measurement standard test piece 18, and by the 3rd image physical length corresponding with each pixel obtain the length in the multiple sidelines calculated after, whether processing module 104 judges the ratio of aforementioned two length in the second scope (such as 0.9 to 1.1), if when processing module 104 judges that its ratio is in the second scope, then processing module 104 stops correction program.If when processing module 104 judges that aforementioned ratio is not in the second scope, then processing module 104 can send a command signal to image acquisition module 102, instruction image acquisition module 102 captures one the 4th image (not being plotted in diagram) more again, and re-executes the correction program step of the device 10 of aforementioned corrected identification image.
Have to make art and usually know that the knowledgeable more can understand object device in identification image of the present invention, in identification image of the present invention of below arranging in pairs or groups, article is described further.See also Fig. 1, Fig. 2 and Fig. 6, Fig. 6 is the process flow diagram of the method for the identification image of foundation one embodiment of the invention.As shown in Figure 6, in step S400, image processing module 104 receives multiple measurement numerical value, wherein each measure numerical value be for multiple sideline of corresponding object 12 or multiple cornerwise physical length one of them.In step S402, image acquisition module 102 acquisition has the image 14 of object 12.In step S404, image processing module 104 performs image edge detection program to obtain the position of multiple sideline L1, L2, L3, L4 of this object 12 from image 14.
In step S406, image processing module 104 obtains the position of diagonal line DI1 and diagonal line DI2 in multiple diagonal line of object 12 in image 14 according to the position of multiple sideline L1, L2, L3, L4 of object 12, image processing module 104.In step S408, image processing module 104 calculates the number of the pixel on the diagonal line DI1 of object in image and the position of diagonal line DI2.In step S410, image processing module 104 calculates the number of the pixel on the position of sideline L1, L2, L3, L4 of object 12 in image.In step S412, image processing module 104, according to the number of the pixel on sideline L1, L2, L3, L4 of object 12 and the position of diagonal line DI1, DI2, calculates the size of the pixel of image 14.In step S414, image processing module 104 judges whether the number ratio of the pixel of diagonal line DI1 and diagonal line DI2 is in the first scope.In step S416, when the number ratio that image processing module 104 judges the pixel of diagonal line DI1 and diagonal line DI2 is in the first scope, image processing module 104 exports an identification result, and namely this identification result judges that object 12 is as rectangle.In step S418, when the number ratio that image processing module 104 judges the pixel of diagonal line DI1 and diagonal line DI2 is not in the first scope, image processing module 104 exports another identification result, this identification result and for judge object 12 not as rectangle.
It should be noted that the order of abovementioned steps S400, step S402, step S404 and step S406 can convert, for example, the present invention can be first carry out step S402, step S404 and step S406 after, then row carries out the action of step S400.Moreover, the order of step S408 and step S410 also can be exchanged, after first can calculating the number of the pixel on the position of sideline L1, L2, L3, L4 of object 12 in image 14, row calculates the number of the pixel on the position of diagonal line DI1, DI2 of object 12 in image 14 again, end is seen user's demand and determines, and the present invention is not limited in this.
Then, see also Fig. 1, Fig. 2 and the 7th figure, the 7th figure is the process flow diagram of the method for the device of the correction identification image of foundation one embodiment of the invention.As shown in FIG., in step S500, image processing module 104 receives the physical length in multiple sidelines of manual measurement standard test piece 18.In step S502, image acquisition module 102 acquisition is loaded with second image (not being plotted in diagram) of standard test piece 18.In step S504, image processing module 104 reads the multiple number of pixels on multiple sidelines (the not being plotted in diagram) position of standard test piece 18.In step S506, physical length and corresponding multiple number of pixels in multiple sidelines of image processing module 104 comparison standard test piece 18, to calculate to obtain physical length corresponding to each pixel (not being plotted in diagram).In step S508, image acquisition module 102 acquisition is loaded with the 3rd image (not being plotted in diagram) of standard test piece 18.
In step S510, image processing module 104, according to the 3rd image and physical length corresponding to each pixel, calculates the length in multiple sidelines of standard test piece 18.In step S512, whether the physical length in multiple sidelines of image processing module 104 criterion test piece 18, with the ratio of the length calculated by the 3rd image, in the second scope.The physical length in multiple sidelines of image processing module 104 criterion test piece 18, with when the ratio of the length calculated by the 3rd image is not in the second scope, then footpath row performs in the method for image identification of the present invention again from step S500, corrects the method for the device of identification image.In step S514, if the physical length in multiple sidelines of image processing module 104 criterion test piece 18, with when the ratio of the length calculated by the 3rd image is in the second scope, then image processing module 104 footpath row terminate correction program, namely start thereafter the method (step S400) of image identification of the present invention.
In sum, in identification image of the present invention, object device can by execution one sideline trace routine to obtain multiple sideline of object in image and to be obtained multiple diagonal line of object by multiple sidelines of object.Last again by the number of pixel each other on the multiple cornerwise position being compared to object in image, allow user can learn the shape of object by the image capturing object.In addition, the present invention is more by measuring the sideline of object and cornerwise physical length, with the number of pixel on the sideline of object in image and diagonal line, to obtain the size of the pixel in image, user is allowed not need to measure all object sizes, only need the physical length of measurement first object, other follow-up objects directly by the image of acquisition object, and can obtain the physical length in the sideline of follow-up object by the Pixel Dimensions of image.
Moreover, the present invention has more the correction program of the device correcting identification image, pass through the multiple number of pixels on multiple edge positions of the second captured image Plays test piece, and the physical length in multiple sidelines of manual measurement standard test piece, to calculate physical length corresponding to pixel.And by physical length corresponding to pixel and the 3rd image that captures to obtain the length in multiple sidelines of the standard test piece calculated.Finally, the physical length being judged multiple sidelines of manual measurement again by processing module and the ratio of the length in multiple sidelines calculated, whether be greater than the second scope, allow the device of identification image can self-correction and do not need by user's manual correction, and increase the precision of the measurement object of assembly line.
Certainly; the present invention also can have other various embodiments; when not deviating from the present invention's spirit and essence thereof; those of ordinary skill in the art are when making various corresponding change and distortion according to the present invention, but these change accordingly and are out of shape the protection domain that all should belong to the claim appended by the present invention.
Claims (10)
1. a method for identification image, is characterized in that, comprising:
Utilize the device of an identification image, acquisition is loaded with one first image of an object;
According to this first image, calculate one first cornerwise length and one second cornerwise length of this object; And
When the ratio of this first catercorner length and this second catercorner length is in one first scope, export an identification result.
2. the method for identification image according to claim 1, is characterized in that, the step of the first catercorner length and the second catercorner length that calculate this object comprises:
Perform a sideline trace routine to obtain the position in multiple sidelines of this object from this first image; And
According to the position in those sidelines of this object, obtain this first diagonal line and this second cornerwise position of this object in this first image, and the number of pixels read on this first diagonal line and this second cornerwise position, to calculate to obtain this first catercorner length of this object and this second catercorner length.
3. the method for identification image according to claim 2, it is characterized in that, this image edge detection program is whether the difference comparing one first pixel of this first image and the GTG angle value of one second pixel is greater than a threshold value, when the difference of this first pixel of this first image and the GTG angle value of this second pixel is greater than this threshold value, the position of this first pixel in this first image is the position of the pixel in those sidelines of this object, and wherein this second pixel is adjacent to this first pixel.
4. the method for identification image according to claim 3, is characterized in that, more comprise:
Receive multiple measurement numerical value, wherein each this measurement numerical value be those sidelines corresponding or those cornerwise physical lengths one of them; And
In this image edge detection program of execution with after obtain the step of the position in those sidelines of this object from this first image, the relational expression measuring numerical value and those sidelines and those cornerwise positions according to those obtains and exports the size of the pixel of this first image.
5. the method for identification image according to claim 4, is characterized in that, this relational expression is:
Wherein, this total ratio is that those measurement numerical value are added with the ratio of those corresponding sidelines and those cornerwise number of pixels, and this measurement number is the quantity of this received measurement numerical value.
6. the method for identification image according to claim 4, is characterized in that, this relational expression is:
Wherein, this total length is added with weighted type for optionally those being measured numerical value, and the number of this total pixel is be added by those cornerwise number of pixels of those sidelines of correspondence or correspondence.
7. the method for identification image according to claim 1, is characterized in that, utilizes the device of this identification image, before acquisition is loaded with the step of this first image of this object, comprising:
Correct the device of this identification image, wherein the correction program of the device of this identification image comprises:
A () receives the physical length in multiple sidelines of manual measurement one standard test piece;
B () utilizes the device of this identification image, acquisition is loaded with one second image of this standard test piece;
C (), according to this second image, reads the multiple number of pixels on the position in those sidelines of this standard test piece;
D physical length and those corresponding number of pixels in those sidelines of this standard test piece of () comparison, to calculate to obtain physical length corresponding to each this pixel;
E () utilizes the device of this identification image again, acquisition is loaded with one the 3rd image of this standard test piece;
F (), according to the 3rd image and physical length corresponding to each this pixel, calculates the length in those sidelines of this standard test piece; And
Whether the ratio of g physical length that () judges those sidelines of this standard test piece and the length calculated by the 3rd image is in one second scope;
If when the ratio of the physical length wherein judging those sidelines of this standard test piece and the length calculated by the 3rd image is in this second scope, terminate correction program, if when the ratio of the physical length judging those sidelines of this standard test piece and the length calculated by the 3rd image is not in this second scope, repeat step (a) to (g).
8. a device for identification image, is characterized in that, comprising:
One image acquisition module, has an image of an object in order to acquisition; And
One image processing module, couple this image acquisition module, this image processing module performs a sideline trace routine to obtain the position in multiple sidelines of this object from this image, this image processing module also obtains one first diagonal line and one second cornerwise position in multiple diagonal line of this object in this image, the number of pixels calculated on this first diagonal line and this second cornerwise position according to the position in those sidelines of this object, and judges that the ratio of this first diagonal line and this second cornerwise number of pixels is whether in one first scope;
Wherein when the ratio of this first diagonal line and this second cornerwise number of pixels is in this first scope, export an identification result.
9. the device of identification image according to claim 8, it is characterized in that, this image edge detection program is whether the difference comparing one first pixel of this image and the GTG angle value of one second pixel is greater than a threshold value, when the difference of this first pixel of this image and the GTG angle value of this second pixel is greater than this threshold value, this position of the first pixel in this image is the position of the pixel in those sidelines of this object, wherein this second pixel is adjacent to this first pixel, this image processing module receives multiple measurement numerical value, wherein each this measurement numerical value be those sidelines corresponding or those cornerwise physical lengths one of them, and this image processing module more in perform this image edge detection program with the position obtaining those sidelines of this object from this image after, the relational expression measuring numerical value and those sidelines and those cornerwise positions according to those obtains and exports the size of the pixel of this image, wherein this relational expression is:
Wherein, this total ratio is that those measurement numerical value are added with the ratio of those corresponding sidelines and those cornerwise number of pixels, and this measurement number is the quantity of those received measurement numerical value.
10. the device of identification image according to claim 8, it is characterized in that, this image edge detection program is whether the difference comparing one first pixel of this image and the GTG angle value of one second pixel is greater than a threshold value, when the difference of this first pixel of this image and the GTG angle value of this second pixel is greater than this threshold value, this position of the first pixel in this image is the position of the pixel in those sidelines of this object, wherein this second pixel is adjacent to this first pixel, this image processing module receives multiple measurement numerical value, wherein each this measurement numerical value be those sidelines corresponding or those cornerwise physical lengths one of them, and this image processing module more in perform this image edge detection program with the position obtaining those sidelines of this object from this image after, the relational expression measuring numerical value and those sidelines and those cornerwise positions according to those obtains and exports the size of the pixel of this image, wherein this relational expression is:
Wherein, this total length is added with weighted type for optionally those being measured numerical value, and the number of this total pixel is be added by those cornerwise number of pixels of those sidelines of correspondence or correspondence.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| TW103113094A TWI507678B (en) | 2014-04-09 | 2014-04-09 | Device and method for identifying an object |
| TW103113094 | 2014-04-09 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104976951A true CN104976951A (en) | 2015-10-14 |
Family
ID=54273694
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410167796.XA Pending CN104976951A (en) | 2014-04-09 | 2014-04-24 | Device and method for identifying image |
Country Status (3)
| Country | Link |
|---|---|
| JP (1) | JP2015201193A (en) |
| CN (1) | CN104976951A (en) |
| TW (1) | TWI507678B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023195456A1 (en) * | 2022-04-04 | 2023-10-12 | 京セラ株式会社 | Electronic instrument, and method for controlling electronic instrument |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS6319084A (en) * | 1986-07-11 | 1988-01-26 | Konica Corp | Printing quality evaluating method |
| JPH01231184A (en) * | 1988-03-11 | 1989-09-14 | Oki Electric Ind Co Ltd | Detecting device for abnormality of area shape |
| JPH09329413A (en) * | 1996-06-07 | 1997-12-22 | Honda Motor Co Ltd | Inspection device and method for assembling of transmission gear assembly shaft |
| CN1551036A (en) * | 2003-04-23 | 2004-12-01 | 重机公司 | Part recognizing method and device |
| CN101191994A (en) * | 2006-12-01 | 2008-06-04 | 鸿富锦精密工业（深圳）有限公司 | Optical look angle measuring systems and its measuring method |
| JP2013114547A (en) * | 2011-11-30 | 2013-06-10 | Canon Inc | Image processing device, image processing program, robot apparatus, and image processing method |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6137893A (en) * | 1996-10-07 | 2000-10-24 | Cognex Corporation | Machine vision calibration targets and methods of determining their location and orientation in an image |
| JP4205004B2 (en) * | 2004-03-26 | 2009-01-07 | Ｓｒｉスポーツ株式会社 | Calibration method |
| CN101672620B (en) * | 2008-09-08 | 2011-01-05 | 鸿富锦精密工业（深圳）有限公司 | Electronic device and method for measuring size of object |
| US7710558B2 (en) * | 2008-09-11 | 2010-05-04 | Litesentry Corporation | Automated online measurement of glass part geometry |
-
2014
- 2014-04-09 TW TW103113094A patent/TWI507678B/en not_active IP Right Cessation
- 2014-04-24 CN CN201410167796.XA patent/CN104976951A/en active Pending
-
2015
- 2015-04-01 JP JP2015074843A patent/JP2015201193A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS6319084A (en) * | 1986-07-11 | 1988-01-26 | Konica Corp | Printing quality evaluating method |
| JPH01231184A (en) * | 1988-03-11 | 1989-09-14 | Oki Electric Ind Co Ltd | Detecting device for abnormality of area shape |
| JPH09329413A (en) * | 1996-06-07 | 1997-12-22 | Honda Motor Co Ltd | Inspection device and method for assembling of transmission gear assembly shaft |
| CN1551036A (en) * | 2003-04-23 | 2004-12-01 | 重机公司 | Part recognizing method and device |
| CN101191994A (en) * | 2006-12-01 | 2008-06-04 | 鸿富锦精密工业（深圳）有限公司 | Optical look angle measuring systems and its measuring method |
| JP2013114547A (en) * | 2011-11-30 | 2013-06-10 | Canon Inc | Image processing device, image processing program, robot apparatus, and image processing method |
Also Published As
| Publication number | Publication date |
|---|---|
| TW201538964A (en) | 2015-10-16 |
| JP2015201193A (en) | 2015-11-12 |
| TWI507678B (en) | 2015-11-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110476056B (en) | Visual detection method, detection equipment and robot | |
| US8121400B2 (en) | Method of comparing similarity of 3D visual objects | |
| CN105430376B (en) | A kind of detection method and device of panorama camera uniformity | |
| KR101121034B1 (en) | System and method for obtaining camera parameters from multiple images and computer program products thereof | |
| CN104168478B (en) | Based on the video image color cast detection method of Lab space and relevance function | |
| CN111210468A (en) | Image depth information acquisition method and device | |
| US8199202B2 (en) | Image processing device, storage medium storing image processing program, and image pickup apparatus | |
| CN109520706B (en) | Screw hole coordinate extraction method of automobile fuse box | |
| CN106600648A (en) | Stereo coding target for calibrating internal parameter and distortion coefficient of camera and calibration method thereof | |
| CN110268221B (en) | Cord measuring device and cord measuring method | |
| CN112200771B (en) | Height measurement method, device, equipment and medium | |
| CN110360991A (en) | A kind of photogrammetric survey method, device and storage medium | |
| CN105744268A (en) | Camera shielding detection method and device | |
| CN107360418B (en) | Panoramic camera color consistency judging system and method | |
| CN107490342A (en) | A kind of cell phone appearance detection method based on single binocular vision | |
| US20150226541A1 (en) | Imaging apparatus | |
| CN109074663A (en) | Object volume measuring method, related device and computer readable storage medium | |
| CN111387987A (en) | Height measuring method, device, equipment and storage medium based on image recognition | |
| CN104976951A (en) | Device and method for identifying image | |
| CN103200349A (en) | Scanned image color cast automatic detection method | |
| CN105447880A (en) | Box-office attendance verification method, device and system | |
| CN112419390A (en) | Method and system for measuring height of human body | |
| CN103063139A (en) | Device and method for dimension measurement | |
| CN111932642B (en) | Method, device and equipment for measuring and calculating volume of structural crack and storage medium | |
| JP2005309651A (en) | Shading processor and shading processing method for imaging element and imaging device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20151014 |
|
| WD01 | Invention patent application deemed withdrawn after publication |