CN104077767A - Method and device for detecting edge of business card - Google Patents
Method and device for detecting edge of business card Download PDFInfo
- Publication number
- CN104077767A CN104077767A CN201310117732.4A CN201310117732A CN104077767A CN 104077767 A CN104077767 A CN 104077767A CN 201310117732 A CN201310117732 A CN 201310117732A CN 104077767 A CN104077767 A CN 104077767A
- Authority
- CN
- China
- Prior art keywords
- yardstick
- filtering
- carried out
- business card
- straight
- 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
Abstract
The embodiment of the invention provides a method and device for detecting an edge of a business card. The method comprises the steps that filtering of a first scale is carried out on a picture containing the business card to remove noise in the background; straight line detection is carried out on filtering results of the first scale; continuity judgment is carried out on the detected straight line, and therefore the edge of the business card is obtained. According to the method, rapid detection of the edge of the business card is achieved, and interference of character false straight lines in the business card is avoided.
Description
Technical field
The embodiments of the present invention relate to image processing, and relate more specifically to a kind of method and apparatus that detects business card edge.
Background technology
Business card rim detection is mainly used in the take pictures cutting of result of business card scan result and business card, cutting name panel region out can be done perspective transform and carry out business card rectification, and the business card after rectification is preserved and all had great importance for business card OCR identification, business card demonstration, business card.For scanned business card, due to a location and Rotation, so the edge of business card still keeps rectangular configuration; And for taking pictures business card, owing to there is 3D perspective problem, the edge of business card is no longer rectangular configuration, the difficulty of rim detection is larger comparatively speaking.
At present, business card rim detection is mainly divided two classes, and a class is the method based on cutting apart, and these class methods adopt dynamic thresholding method or region-growing method etc. to Image Segmentation Using, to obtaining two points of results of business card and background.The business card photo effect that these class methods are single to background, background prospect contrast is high is better, but cannot process background relative complex or prospect background in the not high situation of some local contrast.Another kind of method is the method based on straight-line detection, adopts hough to convert the straight line of detected image, then analyzes the probability that certain straight line belongs to edge.The method calculated amount is very large, and is very easy to be disturbed by the straight line of literal line.
Therefore, need now a kind of method and apparatus that business card rim detection can be carried out fast and avoid the detection business card edge of the straight line interference of the literal line on business card.
Summary of the invention
One object of the present invention is to provide a kind of method and apparatus that detects business card edge.The method and device can be carried out rapidly business card rim detection and avoid the capable interference of word ideal lines on business card.
According to a first aspect of the invention, provide a kind of method that detects business card edge, having comprised:
The picture that comprises business card is carried out to the filtering of the first yardstick, to remove the noise in background;
Filtering result to described the first yardstick is carried out straight-line detection;
The straight line detecting is carried out to continuity judgement, thereby obtain the edge of described business card.
According to one embodiment of present invention, if the filtering of carrying out described the first yardstick can not obtain the edge of described business card, further the picture that comprises described business card is carried out the filtering of the second yardstick, further the filtering result of described the second yardstick is carried out described straight-line detection and further detected straight line carried out to continuity judgement, wherein said the second yardstick is less than described the first yardstick.
According to further embodiment of the present invention, if the filtering of carrying out described the second yardstick still can not obtain the edge of described business card, further the picture that comprises described business card is carried out the filtering of the 3rd yardstick, further the filtering result of described the 3rd yardstick is carried out described straight-line detection and further detected straight line carried out to described continuity judgement, wherein said the 3rd yardstick is less than described the second yardstick.
According to one embodiment of present invention, described filtering comprises gaussian filtering.
According to one embodiment of present invention, described straight-line detection comprises fast discrete hough straight-line detection.
According to one embodiment of present invention, the judgement of described continuity comprises the absolute value of the distance between two points of arbitrary neighborhood that judge in the point set space that detected straight line is corresponding.
According to a second aspect of the invention, provide a kind of method that detects business card edge, having comprised:
Business card in picture is divided into upper and lower Liang Geban district and Liang Geban district, left and right;
Four subgraphs in upper and lower Liang Geban district and Liang Geban district, left and right are carried out respectively to the filtering of the first yardstick, to remove respectively the noise in background;
Filtering result to described the first yardstick is carried out straight-line detection; And
The straight line detecting is carried out to continuity judgement, thereby obtain respectively four edges of described business card.
According to one embodiment of present invention, if the filtering of described the first yardstick that the arbitrary subgraph in described four subgraphs is carried out, can not obtain edge corresponding to described arbitrary subgraph, further carry out the filtering of the second yardstick to this arbitrary subgraph, further the filtering result of described the second yardstick is carried out described straight-line detection and further detected straight line carried out to continuity judgement, wherein said the second yardstick is less than described the first yardstick.
According to further embodiment of the present invention, if the filtering of described the second yardstick that the arbitrary subgraph in described four subgraphs is carried out, can not obtain edge corresponding to described arbitrary subgraph, further carry out the filtering of the 3rd yardstick to this arbitrary subgraph, further the filtering result of described the 3rd yardstick is carried out described straight-line detection and further detected straight line carried out to described continuity judgement, wherein said the 3rd yardstick is less than described the second yardstick.
According to a third aspect of the invention we, provide a kind of device that detects business card edge, having comprised:
Wave filter, for the picture that comprises described business card being carried out to the filtering of the first yardstick, to remove the noise in background;
Straight-line detection device, carries out straight-line detection for the filtering result to described the first yardstick;
Continuity detector, for the straight line detecting is carried out to continuity judgement, thereby obtains described business card edge.
According to one embodiment of present invention, if the filtering of carrying out described the first yardstick can not obtain the edge of described business card, described wave filter is further carried out the filtering of the second yardstick to the picture that comprises described business card, described straight-line detection device further the filtering result of described the second yardstick is carried out to described straight-line detection and described continuity detector further carries out continuity judgement to detected straight line, and wherein said the second yardstick is less than described the first yardstick.
According to further embodiment of the present invention, if the filtering of carrying out described the second yardstick still can not obtain the edge of described business card, described wave filter is further carried out the filtering of the 3rd yardstick to the picture that comprises described business card, described straight-line detection device further the filtering result of described the 3rd yardstick is carried out to described straight-line detection and described continuity detector further carries out described continuity judgement to detected straight line, and wherein said the 3rd yardstick is less than described the second yardstick.
According to a forth aspect of the invention, provide a kind of device that detects business card edge, having comprised:
Subgraph dispenser, for being divided into the business card of picture in upper and lower Liang Geban district and Liang Geban district, left and right;
Wave filter, for four subgraphs in upper and lower Liang Geban district and Liang Geban district, left and right being carried out respectively to the filtering of the first yardstick, to remove respectively the noise in background;
Straight-line detection device, carries out straight-line detection for the filtering result to described the first yardstick; And
Continuity detector, for the straight line detecting is carried out to continuity judgement, thereby obtains respectively four edges of described business card.
According to one embodiment of present invention, if the filtering of described the first yardstick that arbitrary subgraph of described four subgraphs is carried out, can not obtain edge corresponding to described arbitrary subgraph, described wave filter is further carried out the filtering of the second yardstick to this arbitrary subgraph, described straight-line detection device further the filtering result of described the second yardstick is carried out to described straight-line detection and described continuity detector further carries out continuity judgement to detected straight line, and wherein said the second yardstick is less than described the first yardstick.
According to further embodiment of the present invention, if the filtering of described the second yardstick that arbitrary subgraph of described four subgraphs is carried out, can not obtain edge corresponding to described arbitrary subgraph, described wave filter is further carried out the filtering of the 3rd yardstick to described arbitrary subgraph, described straight-line detection device further the filtering result of described the 3rd yardstick is carried out to described straight-line detection and described continuity detector further carries out described continuity judgement to detected straight line, and wherein said the 3rd yardstick is less than described the second yardstick.
Brief description of the drawings
In the time reading by reference to the accompanying drawings below to the detailed description of exemplary embodiment, these and other object, feature and advantage will become apparent, in the accompanying drawings:
Fig. 1 is the process flow diagram that detects according to an embodiment of the invention the method at business card edge;
Fig. 2 is the installation drawing at detection business card according to an embodiment of the invention edge;
Fig. 3 is the process flow diagram of detection business card edge method according to another embodiment of the invention;
Fig. 4 is the installation drawing at detection business card edge according to another embodiment of the invention; And
Fig. 5 A and Fig. 5 B are the effect schematic diagram of carrying out the method front and back, detection business card edge of embodiments of the invention.
Embodiment
Process flow diagram in accompanying drawing and block diagram, illustrate according to architectural framework in the cards, function and the operation of the device of various embodiments of the invention, method and computer program product.In this, the each square frame in process flow diagram or block diagram can represent a part for module, program segment or a code, and a part for described module, program segment or code comprises one or more for realizing the executable instruction of logic function of regulation.Also it should be noted that what the function marking in square frame also can be marked to be different from accompanying drawing occurs in sequence in some realization as an alternative.For example, in fact the square frame that two adjoining lands represent can be carried out substantially concurrently, and they also can be carried out by contrary order sometimes, and this determines according to related function.Also be noted that, the combination of the square frame in each square frame and block diagram and/or process flow diagram in block diagram and/or process flow diagram, can realize by the special hardware based system of the function putting rules into practice or operation, or can realize with the combination of specialized hardware and computer instruction.
To only describe various embodiment of the present invention in detail by exemplary approach now.
Fig. 1 shows the process flow diagram of detection business card according to an embodiment of the invention edge method.Step starts from S101.
Step S110, carries out the filtering of the first yardstick to the picture that comprises business card, to remove the noise in background.
The object of this step is image to carry out smoothly, removes the noise in complex background.According to various embodiments of the present invention, described filtering is preferably gaussian filtering.But it will be understood by those skilled in the art that other filtering for realizing the noise of removing complex background are also suitable for, for example mean filter.In addition, those skilled in the art should also be understood that the filtering of different scale, to the treatment effect difference of image, such as the larger filtering of yardstick, larger to the smoothing effect of image, can effectively suppress the ground unrest of image, and the edge of image is thickened; And the less filtering of yardstick is less to the smoothing effect of image, now poor to the inhibition ability of ground unrest, but can reflect better the marginal position of image.
In the present embodiment, preferably higher scale is carried out filtering as the first yardstick to the picture that comprises described business card.The favourable part of doing is like this in the time selecting higher scale to carry out filtering, can suppress rapidly the ground unrest of image, the corresponding calculated amount of minimizing subsequent step, thereby obtains rapidly the edge of business card.
Step S120, carries out straight-line detection to the filtering result of described the first yardstick;
According to embodiments of the invention, the step of this straight-line detection can comprise carries out self-adaption binaryzation to the filtering result of gained, obtains the binary map about this image, then carries out above-mentioned straight-line detection for this binary map.
In the present embodiment, this straight-line detection is preferably hough straight-line detection, but it will be understood by those skilled in the art that the straight-line detection of other modes is also feasible.
In this straight-line detection process, also preferably include maintain a dynamic point set space store binary picture in corresponding point, store in particular the point that detected straight line is corresponding.
Step S130, carries out continuity judgement to the straight line detecting, thereby obtains the edge of described business card.
This step is for getting rid of the interference that word ideal lines is capable.Those skilled in the art know, and due to the relation of filtering, in detected straight line, will inevitably have the capable interference of ideal lines producing because of the literal line on business card.But it should be noted that because ideal lines works and often produced by word, thus ideal lines capable be not continuous, this has formed with respect to real linear rows important difference.Those skilled in the art can utilize such difference by real linear rows and ideal lines is capable distinguishes, thereby it is capable to exclude ideal lines.Those skilled in the art be further appreciated that from detected straight line, exclude ideal lines capable after remaining linear rows will be the edge that will detect business card.According to embodiments of the invention, this step realizes by detected straight line is carried out to continuity judgement, this continuity judgement preferably judges by the absolute value of the distance between two points of arbitrary neighborhood in point set space corresponding to detected straight line, in the time that this absolute value is less than predetermined threshold, judge that these two points are continuous, otherwise be discontinuous.The straight line now obtaining is the edge of the business card that will detect.In some cases, alternatively, also comprise the judgement of ratio between length, height and/or the length and width to detected straight line, thereby can exclude further false edge line.Favourable part is like this more accurately to determine four edges of business card.Further, in each embodiment, can also be to detecting that business card edge corrects, to obtain conventional rectangle business card edge.
As previously mentioned, the preferred higher scale of the present invention for example, is carried out filtering as the first yardstick (, Gauss's yardstick δ=4) to the picture that comprises described business card.But those skilled in the art also will understand, the first scale filter blurred picture excessively of this higher scale, even likely the business card edge detecting is wished in elimination.
Therefore, in the case of not determining completely this business card edge according to above-mentioned step, the present invention will preferably further (for example carry out the second yardstick to the picture that comprises described business card, Gauss's yardstick δ=3) filtering, further the filtering result of described the second yardstick is carried out described straight-line detection and further detected straight line carried out to continuity judgement, thereby the edge that obtains business card, wherein said the second yardstick is less than described the first yardstick.It is pointed out that now the edge of this business card can pass through separately this second yardstick, or obtain in conjunction with the first yardstick.
Further, if still can not determine this business card edge according to the filtering of the second yardstick, the present invention will preferably (for example carry out the 3rd yardstick to the picture that comprises described business card, Gauss's yardstick δ=2) filtering, further the filtering result of described the 3rd yardstick is carried out described straight-line detection and further detected straight line carried out to described continuity judgement, thereby the edge that obtains business card, wherein said the 3rd yardstick is less than described the second yardstick.It is pointed out that now the edge of this business card can pass through separately the 3rd yardstick, or obtain in conjunction with the second yardstick and/or the first yardstick.
Further, if still can not determine this business card edge according to the filtering of the 3rd yardstick, the present invention will proceed the filtering of the 4th yardstick etc., until determine whole business cards edge, wherein after a yardstick be less than last yardstick.
The filtering that it will be understood by those skilled in the art that above-mentioned the second yardstick, the 3rd yardstick, the 4th yardstick etc. is the first scale filter to be detected to the useful of business card edge supplement.Like this, by building filtering multiple dimensioned and that yardstick successively decreases, business card Fast Edge Detection and accurate taking into account and balance of detecting have been realized.
Step S140, finishes.
Fig. 2 is the installation drawing at the detection business card edge of the method corresponding to Fig. 1 according to an embodiment of the invention.This device 200, comprising:
Wave filter 210, for the picture that comprises described business card being carried out to the filtering of the first yardstick, to remove the noise in background;
Straight-line detection device 220, carries out straight-line detection for the filtering result to described the first yardstick;
Continuity detector 230, for the straight line detecting is carried out to continuity judgement, thereby obtains described business card edge.
As described in the embodiment of front Fig. 1, if the filtering of carrying out described the first yardstick can not obtain the edge of described business card, described wave filter 210 is further carried out the filtering of the second yardstick to the picture that comprises described business card, described straight-line detection device 220 further the filtering result of described the second yardstick is carried out to described straight-line detection and described continuity detector 230 further carries out continuity judgement to detected straight line, to obtain the edge of detected business card, wherein said the second yardstick is less than described the first yardstick.
Further, if the filtering of carrying out described the second yardstick still can not obtain the edge of described business card, described wave filter 210 is further carried out the filtering of the 3rd yardstick to the picture that comprises described business card, described straight-line detection device 220 further the filtering result of described the 3rd yardstick is carried out to described straight-line detection and described continuity detector 230 further carries out described continuity judgement to detected straight line, to obtain the edge of detected business card, wherein said the 3rd yardstick is less than described the second yardstick.
It will be appreciated by those skilled in the art that, the device of business card Fast Edge Detection has only been described with reference to Fig. 2 above simply, but the function of this device is not limited to above-mentioned content, described in Fig. 1, in method, other step also can be carried out by device corresponding in Fig. 2 accordingly.
Fig. 3 is the process flow diagram of detection business card edge method according to another embodiment of the invention.The method is similar to the method step in Fig. 1 substantially, and difference is mainly to carry out filtering, straight-line detection and continuity judgement for the different subregions of business card.The step of the method starts from S301.
Step S310, is divided into upper and lower Liang Geban district and Liang Geban district, left and right by the business card in picture;
In this step, taking the horizontal median axis of picture I as boundary, picture is divided into upper and lower Liang Geban district I
onand I
under, Liang Geban district, left and right I
leftand I
right, wherein make the upper edge of business card in upper half I
on, lower edge is in bottom half I
under.In like manner, left and right edges is respectively in Liang Geban district, left and right I
leftand I
right.It will be understood by those skilled in the art that the position of can appropriateness adjusting above-mentioned picture I is to make above-mentioned edge up and down respectively in four subgraphs in halfth district up and down, this is convenient to operation below.
Step S320, carries out respectively the filtering of the first yardstick, to remove respectively the noise in background to four subgraphs in upper and lower Liang Geban district and Liang Geban district, left and right;
Because the operation of the rim detection to each subgraph is similarly substantially, below only with upper half business card subgraph I
onbe operating as example, introduce in detail the testing process at the edge of this upper half business card subgraph.
The object of this step is image to carry out smoothly, to remove the noise in complex background.In this step, for example, to upper half business card subgraph I
oncarry out the filtering of Gauss's yardstick δ=4, after filtering, obtain result I
upper δ=4.
Step S330, carries out straight-line detection to the filtering result of described the first yardstick;
For upper half business card subgraph I
on, this step is to I
upper δ=4carry out straight-line detection.According to a preferred embodiment of the invention, specifically detection method can be carried out as follows:
First, to I
upper δ=4carry out self-adaption binaryzation, as follows:
Wherein, t is threshold value.
Secondly, the binary map obtaining after binaryzation is for example carried out to fast discrete hough straight-line detection, owing to only detecting coboundary, therefore can only need the straight line of detection level direction, in most cases, straight line that even can detection level direction ± 20 °.And each point that converts ρ θ space for hough maintains a dynamic point set space and stores I
upper δ =4, binarythe point of middle correspondence.
Step S340, carries out continuity judgement to the straight line detecting, thereby obtains respectively four edges of described business card.
For upper half business card subgraph I
on, this step is carried out described continuity judgement for the straight line that upper half business card subgraph is detected, thereby obtains the coboundary of this business card that is arranged in upper half business card subgraph, completes the detection of this subgraph.
This continuity judgement is for getting rid of the interference that word ideal lines is capable, and the ideal lines that line detection algorithm detects at literal line, owing to not being real continuous, therefore will be filtered in this step.For straight line ρ
iθ
i, and I corresponding to this straight line
upper δ=4, binarythe point set in space is P
i=(x
i, y
i), i=1,2 ..., N, and method for detecting continuity can carry out as follows:
X′＝sort(X)，X＝{x
i|i＝1，2，....N}
If X ' meets following formula, meet continuity:
| x '
i-x '
i-i|≤g, i=2,3 ..., N, wherein g is threshold value, for example, g=3 can be set.
As previously mentioned, the present invention preferably adopts the filtering of the first yardstick (for example Gauss's yardstick δ=4), if but to upper half business card subgraph I
onthe filtering of described δ=4 of carrying out, can not obtain the coboundary that described subgraph is corresponding, for example can further carry out the filtering of the second yardstick (for example Gauss's yardstick δ=3) to this subgraph, further the filtering result of described the second yardstick is carried out described straight-line detection and further detected straight line carried out to continuity judgement, wherein known described the second yardstick is less than described the first yardstick.It is pointed out that now the detection of this coboundary can be passed through separately this second yardstick, or obtain in conjunction with the first yardstick.
Further, if to the filtering of upper described δ=3 of carrying out of described upper half business card subgraph I, can not obtain the coboundary that described subgraph is corresponding, further carry out the filtering of the 3rd yardstick (for example Gauss's yardstick δ=2) to this subgraph, further the filtering result of described the 3rd yardstick is carried out described straight-line detection and further detected straight line carried out to described continuity judgement, wherein known described the 3rd yardstick is less than described the second yardstick.It is pointed out that now the detection of this coboundary can be passed through separately the 3rd yardstick, or obtain in conjunction with the second yardstick and/or the first yardstick
Further, if still can not determine the coboundary of this subgraph according to the filtering of the 3rd yardstick, the present invention will proceed the filtering of the 4th yardstick (such as Gauss's yardstick δ=1) etc., until determine each edge of whole business cards, wherein a known rear yardstick is less than last yardstick.
The filtering that it will be understood by those skilled in the art that above-mentioned the second yardstick, the 3rd yardstick, the 4th yardstick etc. is the first scale filter to be detected to the useful of business card subgraph corresponding edge supplement.Like this, by building multiple dimensioned filtering of successively decreasing, business card Fast Edge Detection and accurate taking into account and balance of detecting have been realized.
Step S350, finishes.
The advantage of this embodiment is the multiple dimensioned straight-line detection of business card subregion proposing according to the present invention, and by judging that linearism filters the interference that word ideal lines is capable, in computing velocity than generic linear detection method fast one to two order of magnitude, the accuracy of business card rim detection reaches 99% substantially.
Fig. 4 is the installation drawing at the detection business card edge of the method corresponding to Fig. 3 according to another embodiment of the invention.This device 400, comprising:
Subgraph dispenser 410, for being divided into the business card of picture in upper and lower Liang Geban district and Liang Geban district, left and right;
Wave filter 420, for four subgraphs in upper and lower Liang Geban district and Liang Geban district, left and right being carried out respectively to the filtering of the first yardstick, to remove respectively the noise in background;
Straight-line detection device 430, carries out straight-line detection for the filtering result to described the first yardstick; And
Continuity detector 440, for the straight line detecting is carried out to continuity judgement, thereby obtains respectively four edges of described business card.
If the filtering of described the first yardstick that arbitrary subgraph of described four subgraphs is carried out, can not obtain edge corresponding to described arbitrary subgraph, described wave filter 420 is further carried out the filtering of the second yardstick to this arbitrary subgraph, described straight-line detection device 430 further the filtering result of described the second yardstick is carried out to described straight-line detection and described continuity detector 440 further carries out continuity judgement to detected straight line, and wherein said the second yardstick is less than described the first yardstick.
If the filtering of described the second yardstick that arbitrary subgraph of described four subgraphs is carried out, can not obtain edge corresponding to described arbitrary subgraph, described wave filter 420 is further carried out the filtering of the 3rd yardstick to described arbitrary subgraph, described straight-line detection device 430 further the filtering result of described the 3rd yardstick is carried out to described straight-line detection and described continuity detector 440 further carries out described continuity judgement to detected straight line, and wherein said the 3rd yardstick is less than described the second yardstick.
It will be appreciated by those skilled in the art that, the device of business card Fast Edge Detection has only been described with reference to Fig. 4 above simply, but the function of this device is not limited to above-mentioned content, described in Fig. 3, in method, other step also can be carried out by device corresponding in Fig. 4 accordingly.
Fig. 5 A and Fig. 5 B are the effect schematic diagram of carrying out front and back, detection business card of the present invention edge.Wherein, Fig. 5 A represents the to be detected picture that comprises business card.Fig. 5 B represents this picture to carry out business card rim detection and the length breadth ratio of business card has been realized to the schematic diagram of proofreading and correct.
Provided instructions of the present invention for the object illustrating and describe, but it is not intended to be exhaustive or be limited to the invention of disclosed form.It may occur to persons skilled in the art that a lot of amendments and variant.It will be appreciated by those skilled in the art that the method and apparatus in embodiment of the present invention can be with software, hardware, firmware or its combination realization.
Therefore; embodiment is for principle of the present invention, practical application being described better and making the other staff in those skilled in the art can understand following content and select and describe;; do not departing under the prerequisite of spirit of the present invention, all modifications of making and replacement all will fall in the protection domain of the present invention of claims definition.
Claims (18)
1. a method that detects business card edge, comprising:
The picture that comprises business card is carried out to the filtering of the first yardstick, to remove the noise in background;
Filtering result to described the first yardstick is carried out straight-line detection;
The straight line detecting is carried out to continuity judgement, thereby obtain the edge of described business card.
2. method according to claim 1, also comprises:
If the filtering of carrying out described the first yardstick can not obtain the edge of described business card, further the picture that comprises described business card is carried out the filtering of the second yardstick, further the filtering result of described the second yardstick is carried out described straight-line detection and further detected straight line carried out to continuity judgement, wherein said the second yardstick is less than described the first yardstick.
3. method according to claim 2, also comprises:
If the filtering of carrying out described the second yardstick still can not obtain the edge of described business card, further the picture that comprises described business card is carried out the filtering of the 3rd yardstick, further the filtering result of described the 3rd yardstick is carried out described straight-line detection and further detected straight line carried out to described continuity judgement, wherein said the 3rd yardstick is less than described the second yardstick.
4. according to the method described in claim 1-3 any one, wherein, described filtering comprises gaussian filtering.
5. according to the method described in claim 1-3 any one, wherein, described straight-line detection comprises fast discrete hough straight-line detection.
6. according to the method described in claim 1-3 any one, wherein, described continuity judgement comprises the absolute value of the distance between two points of arbitrary neighborhood that judge in the point set space that detected straight line is corresponding.
7. a method that detects business card edge, comprising:
Business card in picture is divided into upper and lower Liang Geban district and Liang Geban district, left and right;
Four subgraphs in upper and lower Liang Geban district and Liang Geban district, left and right are carried out respectively to the filtering of the first yardstick, to remove respectively the noise in background;
Filtering result to described the first yardstick is carried out straight-line detection; And
The straight line detecting is carried out to continuity judgement, thereby obtain respectively four edges of described business card.
8. method according to claim 7, also comprises:
If the filtering of described the first yardstick that the arbitrary subgraph in described four subgraphs is carried out, can not obtain edge corresponding to described arbitrary subgraph, further carry out the filtering of the second yardstick to this arbitrary subgraph, further the filtering result of described the second yardstick is carried out described straight-line detection and further detected straight line carried out to described continuity judgement, wherein said the second yardstick is less than described the first yardstick.
9. method according to claim 8, also comprises:
If the filtering of described the second yardstick that the arbitrary subgraph in described four subgraphs is carried out, can not obtain edge corresponding to described arbitrary subgraph, further carry out the filtering of the 3rd yardstick to this arbitrary subgraph, further the filtering result of described the 3rd yardstick is carried out described straight-line detection and further detected straight line carried out to described continuity judgement, wherein said the 3rd yardstick is less than described the second yardstick.
10. a device that detects business card edge, comprising:
Wave filter, for the picture that comprises described business card being carried out to the filtering of the first yardstick, to remove the noise in background;
Straight-line detection device, carries out straight-line detection for the filtering result to described the first yardstick;
Continuity detector, for the straight line detecting is carried out to continuity judgement, thereby obtains described business card edge.
11. devices according to claim 10, also comprise:
If the filtering of carrying out described the first yardstick can not obtain the edge of described business card, described wave filter is further carried out the filtering of the second yardstick to the picture that comprises described business card, described straight-line detection device further the filtering result of described the second yardstick is carried out to described straight-line detection and described continuity detector further carries out described continuity judgement to detected straight line, and wherein said the second yardstick is less than described the first yardstick.
12. devices according to claim 11, also comprise:
If the filtering of carrying out described the second yardstick still can not obtain the edge of described business card, described wave filter is further carried out the filtering of the 3rd yardstick to the picture that comprises described business card, described straight-line detection device further the filtering result of described the 3rd yardstick is carried out to described straight-line detection and described continuity detector further carries out described continuity judgement to detected straight line, and wherein said the 3rd yardstick is less than described the second yardstick.
13. according to the device described in claim 10-12 any one, and wherein, described filtering comprises gaussian filtering.
14. according to the device described in claim 10-12 any one, and wherein, described straight-line detection comprises fast discrete hough straight-line detection.
15. according to the device described in claim 10-12 any one, and wherein, described continuity judgement comprises the absolute value of the distance between two points of arbitrary neighborhood that judge in the point set space that detected straight line is corresponding.
16. 1 kinds are detected the device at business card edge, comprising:
Subgraph dispenser, for being divided into the business card of picture in upper and lower Liang Geban district and Liang Geban district, left and right;
Wave filter, for four subgraphs in upper and lower Liang Geban district and Liang Geban district, left and right being carried out respectively to the filtering of the first yardstick, to remove respectively the noise in background;
Straight-line detection device, carries out straight-line detection for the filtering result to described the first yardstick; And
Continuity detector, for the straight line detecting is carried out to continuity judgement, thereby obtains respectively four edges of described business card.
17. devices according to claim 16, also comprise:
If the filtering of described the first yardstick that arbitrary subgraph of described four subgraphs is carried out, can not obtain edge corresponding to described arbitrary subgraph, described wave filter is further carried out the filtering of the second yardstick to this arbitrary subgraph, described straight-line detection device further the filtering result of described the second yardstick is carried out to described straight-line detection and described continuity detector further carries out continuity judgement to detected straight line, and wherein said the second yardstick is less than described the first yardstick.
18. devices according to claim 17, also comprise:
If the filtering of described the second yardstick that arbitrary subgraph of described four subgraphs is carried out, can not obtain edge corresponding to described arbitrary subgraph, described wave filter is further carried out the filtering of the 3rd yardstick to described arbitrary subgraph, described straight-line detection device further the filtering result of described the 3rd yardstick is carried out to described straight-line detection and described continuity detector further carries out described continuity judgement to detected straight line, and wherein said the 3rd yardstick is less than described the second yardstick.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310117732.4A CN104077767A (en) | 2013-03-29 | 2013-03-29 | Method and device for detecting edge of business card |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310117732.4A CN104077767A (en) | 2013-03-29 | 2013-03-29 | Method and device for detecting edge of business card |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104077767A true CN104077767A (en) | 2014-10-01 |
Family
ID=51599009
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310117732.4A Pending CN104077767A (en) | 2013-03-29 | 2013-03-29 | Method and device for detecting edge of business card |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104077767A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107248148A (en) * | 2017-06-14 | 2017-10-13 | 上海晔芯电子科技有限公司 | Image denoising method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6826311B2 (en) * | 2001-01-04 | 2004-11-30 | Microsoft Corporation | Hough transform supporting methods and arrangements |
| CN101976114A (en) * | 2010-09-29 | 2011-02-16 | 长安大学 | System and method for realizing information interaction between computer and pen and paper based on camera |
| CN102521569A (en) * | 2011-11-30 | 2012-06-27 | 康佳集团股份有限公司 | Method and system for identifying identity card by using smart phone and mobile phone |
| CN102915522A (en) * | 2012-09-12 | 2013-02-06 | 康佳集团股份有限公司 | Smart phone name card extraction system and realization method thereof |
| CN102930265A (en) * | 2012-09-19 | 2013-02-13 | 广州市中崎商业机器有限公司 | Method and device for scanning multiple identity cards |
-
2013
- 2013-03-29 CN CN201310117732.4A patent/CN104077767A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6826311B2 (en) * | 2001-01-04 | 2004-11-30 | Microsoft Corporation | Hough transform supporting methods and arrangements |
| CN101976114A (en) * | 2010-09-29 | 2011-02-16 | 长安大学 | System and method for realizing information interaction between computer and pen and paper based on camera |
| CN102521569A (en) * | 2011-11-30 | 2012-06-27 | 康佳集团股份有限公司 | Method and system for identifying identity card by using smart phone and mobile phone |
| CN102915522A (en) * | 2012-09-12 | 2013-02-06 | 康佳集团股份有限公司 | Smart phone name card extraction system and realization method thereof |
| CN102930265A (en) * | 2012-09-19 | 2013-02-13 | 广州市中崎商业机器有限公司 | Method and device for scanning multiple identity cards |
Non-Patent Citations (1)
| Title |
|---|
| 华顺刚 等: "一种改进的Hough变换算法及图象特征点提取", 《中国图象图形学报》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107248148A (en) * | 2017-06-14 | 2017-10-13 | 上海晔芯电子科技有限公司 | Image denoising method and system |
| CN107248148B (en) * | 2017-06-14 | 2023-08-25 | 思特威(上海)电子科技股份有限公司 | Image noise reduction method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105868758B (en) | method and device for detecting text area in image and electronic equipment | |
| CN101615252B (en) | Method for extracting text information from adaptive images | |
| US9311533B2 (en) | Device and method for detecting the presence of a logo in a picture | |
| WO2018018788A1 (en) | Image recognition-based meter reading apparatus and method thereof | |
| CN104376318B (en) | Underscore and form line in removing file and picture while retaining and intersecting stroke | |
| CN111382704B (en) | Vehicle line pressing violation judging method and device based on deep learning and storage medium | |
| CN104636706A (en) | Complicated background bar code image automatic partitioning method based on gradient direction consistency | |
| CN105405142A (en) | Edge defect detection method and system for glass panel | |
| CN108108731B (en) | Text detection method and device based on synthetic data | |
| CN103632159B (en) | Method and system for training classifier and detecting text area in image | |
| US10169673B2 (en) | Region-of-interest detection apparatus, region-of-interest detection method, and recording medium | |
| CN110598566A (en) | Image processing method, device, terminal and computer readable storage medium | |
| CN109948521B (en) | Image deviation rectifying method and device, equipment and storage medium | |
| CN103034848A (en) | Identification method of form type | |
| CN109344824B (en) | Text line region detection method, device, medium and electronic equipment | |
| CN104794479A (en) | Method for detecting text in natural scene picture based on local width change of strokes | |
| CN108960221B (en) | Bank card identification method and device based on image | |
| US20120320433A1 (en) | Image processing method, image processing device and scanner | |
| CN103488966A (en) | Intelligent mobile phone capable of identifying real-name ticket information | |
| CN115240197A (en) | Image quality evaluation method, image quality evaluation device, electronic apparatus, scanning pen, and storage medium | |
| CN103914829A (en) | Method for detecting edge of noisy image | |
| Jipeng et al. | Skew correction for Chinese character using Hough transform | |
| CN114419006A (en) | Method and system for removing watermark of gray level video characters changing along with background | |
| Boiangiu et al. | Handwritten documents text line segmentation based on information energy | |
| CN104077767A (en) | Method and device for detecting edge of business card |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20141001 |