CN102915522A - Smart phone name card extraction system and realization method thereof - Google Patents
Smart phone name card extraction system and realization method thereof Download PDFInfo
- Publication number
- CN102915522A CN102915522A CN2012103344685A CN201210334468A CN102915522A CN 102915522 A CN102915522 A CN 102915522A CN 2012103344685 A CN2012103344685 A CN 2012103344685A CN 201210334468 A CN201210334468 A CN 201210334468A CN 102915522 A CN102915522 A CN 102915522A
- Authority
- CN
- China
- Prior art keywords
- image
- straight
- detection
- unit
- business card
- 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 69
- 238000000605 extraction Methods 0.000 title claims abstract description 40
- 238000001514 detection method Methods 0.000 claims abstract description 145
- 230000008569 process Effects 0.000 claims abstract description 36
- 238000003708 edge detection Methods 0.000 claims abstract description 33
- 230000000694 effects Effects 0.000 claims abstract description 7
- 230000002708 enhancing effect Effects 0.000 claims description 31
- 230000009466 transformation Effects 0.000 claims description 8
- 241001212149 Cathetus Species 0.000 claims description 2
- 239000000284 extract Substances 0.000 abstract description 13
- 238000005286 illumination Methods 0.000 abstract description 10
- 230000006698 induction Effects 0.000 abstract 2
- 230000008859 change Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 238000002187 spin decoupling employing ultra-broadband-inversion sequences generated via simulated annealing Methods 0.000 description 1
- 239000004575 stone Substances 0.000 description 1
Images
Landscapes
- Telephone Function (AREA)
- Character Input (AREA)
- Studio Devices (AREA)
Abstract
The invention discloses a smart phone name card extraction system and a realization method thereof. The smart phone name card extraction system comprises an image induction and enhancement module, an image detection and denoising module, a straight line detection and revision module and an image display module, wherein the image induction and enhancement module is used for converting image-text information of a name card into an image and automatically adjusting contrast ratio of the image; the image detection and denoising module is used for detecting the edges of the image with the adjusted contrast ratio through a filter and removing noises produced in the edge detection process by the filter; the straight line detection and revision module is used for detecting straight lines of the denoised image, removing the straight lines which are less than a certain threshold value of the denoised image, revising the straight lines in the image which are subjected to straight line detection and removing the straight lines which do not intersect with each other and which intersect in the angle not equal to 90 DEG; and the image display module is used for displaying image processing effects and operation interfaces. With adoption of the smart phone name card extraction system, a user using the smart phone can extract the name card accurately under the condition that the name card has small difference with a background of the smart phone or illumination is not uniform.
Description
Technical field
The business card that the present invention relates to smart mobile phone extracts and identification field, in particular business card extraction system and its implementation of a kind of smart mobile phone.
Background technology
In commercial activity, people often need to exchange visiting cards, and are very inconvenient but carry business card.Therefore people utilize present smart mobile phone function that the mode of business card with picture is stored in the smart mobile phone, so that the information of user on the inquiry business card, only need on the inquiry mobile phone canned data just passable.
In the prior art, the method for extracting the target business card has a lot, and have threshold method, Boundary extracting algorithm, SUSAN that it is main detect operator, watershed segmentation algorithm etc.Wherein, threshold method generally can be divided into two classes: global threshold and local threshold.
The global threshold method is to adopt a threshold value to divide to whole image, distributes to determine a threshold value according to histogram or the gray space of image, and the global threshold algorithm is relatively simple, and effect is relatively good when target and background gray scale difference is obvious.Poor to situation resistivities such as input picture quantizing noise or uneven illuminations especially, application is extremely restricted.Classical global threshold method algorithm comprises Otsu threshold method, iterative algorithm.
The local threshold method, that image is divided into some sub-blocks, for the selected threshold value of each piece, perhaps each pixel in the image is set a rational threshold value according to the grey scale change situation of the pixel in its field, then the processing of binaryzation is carried out in pointwise to image.For the image more complicated or noise background is arranged, be to be difficult to right area partial objectives for object and background with single global threshold, it is better at this moment using the local threshold method.Wherein typical local comparative approach has Kamel-zhao algorithm, Bernsen algorithm and Niblack algorithm etc.
According to image in the business card since in the shooting process the even or noise of uneven illumination to cause the gray scale difference of target image and background image in the image be not clearly characteristics, Jiang Xin soil has proposed Bernsen algorithm improved algorithm, received preferably effect, but when target and background are more or less the same, because determining background dot and foreground point, cause the method to lose efficacy.
In based on edge detection algorithm, common algorithm has Roberts operator, Sobel operator, Prewitt operator, Laplace operator etc., and wherein first three plants based on the single order differential, and is rear a kind of based on second-order differential.The main cause that spatial domain can be extracted the edge is to change because often have gray-scale value to get sharply at the place, image border, also just can extract the edge of image by extracting gray-scale value points more jumpy, the difference of certainly different boundary operator values on all directions can cause the feature difference of the image border of extraction.Difference is that place, the image border gray-scale value of feeling that Second Order Differential Operator can be more responsive must change, and overcome the shortcoming of first order differential operator thick edge, but Second Order Differential Operator susceptibility also makes its antijamming capability to noise etc. greatly reduce, so before processing image with Laplace operator, all need image is carried out smoothing processing.Because such algorithm is based on differentiating operator, therefore uneven when image irradiation, the method will lose efficacy.In the business card recognition process based on mobile phone of reality, the image irradiation inequality is very common, so the method is unfavorable for cutting apart of business card.
Threshold method is a kind of effectively simple image segmentation algorithm in image segmentation algorithm, but for the image in the complex background situation is processed, threshold method is difficult to accomplish extract accurately target image, particularly when image because during uneven illumination, the method has a strong impact on the extraction of business card with complete failure, in addition, when background was close with the prospect brightness value, threshold value was difficult to accurately definite, and the method also will lose efficacy this moment.Existing based on edge detection algorithm, such as Roberts operator, Sobel operator, Prewitt operator, Laplace operator etc., all there is a common fault, namely require image irradiation even, when image irradiation is inhomogeneous, can cause some false targets to occur, in real process, because the image that smart mobile phone is taken all is shooting at close range, be generally less than 5 cun, so mobile phone and hand are cast the shade that comes and can be caused image irradiation uneven.In addition, when background and prospect are more or less the same, because threshold value is difficult to select, therefore, the method will lose efficacy too this moment.
Therefore, prior art has yet to be improved and developed.
Summary of the invention
The technical problem to be solved in the present invention is, for the defects of prior art, provides business card extraction system and its implementation of a kind of smart mobile phone.So that the user utilizes smart mobile phone, even be more or less the same at business card and its background, perhaps in the situation of uneven illumination, also can extract very accurately business card by described system.
The technical scheme that technical solution problem of the present invention adopts is as follows:
A kind of business card extraction system of smart mobile phone wherein, comprising: image sensing and enhancing module, image detection and denoising module, straight-line detection and correcting module, image display, wherein;
Described image sensing is connected with the denoising module with described image detection with the enhancing module, be used for obtaining by imageing sensor the graph text information of business card, the graph text information of described business card is converted into image, and automatically adjust the contrast of described image, the image of adjusting contrast is sent to described image detection and denoising module;
Described image detection is connected with correcting module with described straight-line detection with the denoising module, be used for to receive from described image sensing and the image that strengthens the adjustment contrast that module sends, by wave filter the image of described adjustment contrast is carried out rim detection, and remove the noise that described wave filter produces in edge detection process, and the image that will remove noise sends to described straight-line detection and correcting module;
Described straight-line detection is connected with described image display with correcting module, be used for to receive the image of the removal noise of sending from described image detection and denoising module, image to described removal noise carries out straight-line detection, and the straight line less than certain threshold value in the image of described removal noise removed, it also is used for the straight line of the image of process straight-line detection is revised, and removing non-intersect and crossing is not the straight lines of 90 degree;
Described image display is connected with correcting module with denoising module, described straight-line detection with enhancing module, described image detection with described image sensing respectively, is used for showing image processing effect and operation interface.
Described image sensing comprises with the enhancing module;
The image sensing unit is used for obtaining by imageing sensor the graph text information of business card, and the graph text information of described business card is converted into image;
Image enhancing unit is connected with described image sensing unit, is used for receiving the image of sending from described image sensing unit, and automatically adjusts the contrast of described image.
Described image detection and denoising module comprise;
The Image Edge-Detection unit is connected with described image enhancing unit, be used for to receive the image of the adjustment contrast of sending from described image enhancing unit, and by wave filter the image of described adjustment contrast is carried out rim detection;
The image denoising unit is connected with described Image Edge-Detection unit, is used for receiving the image of the process rim detection of sending from described Image Edge-Detection unit, and removes the described noise that produces in edge detection process through the image of rim detection.
Described straight-line detection and correcting module comprise;
The straight-line detection unit is connected with described image denoising unit, be used for receiving the image of the removal noise of sending from described image denoising unit, and the image of described removal noise carried out straight-line detection, and will remove in the image of noise and remove less than the straight line of certain threshold value;
The straight line amending unit is connected with described straight-line detection unit, be used for receiving the image of the process straight-line detection of sending from described straight-line detection unit, and revise through the straight line in the image of straight-line detection described, getting rid of non-intersect and crossing is not 90 straight lines of spending.
Described straight-line detection unit by using Hough transformation carries out straight-line detection to the image of described removal noise.
A kind of implementation method of business card extraction system of aforesaid smart mobile phone, wherein, described implementation method specifically comprises step;
S11, smart mobile phone obtain the graph text information of business card by the image sensing unit, and the graph text information of described business card is converted into image, and described image is sent to image enhancing unit;
S12, described image enhancing unit receive described image, and automatically adjust the contrast of described image, and the image that will adjust contrast sends to the Image Edge-Detection unit;
S13, described Image Edge-Detection unit receive the image of the adjustment contrast of sending from described image enhancing unit, and by wave filter the image of described adjustment contrast are carried out rim detection, will send to through the image of rim detection the image denoising unit;
S14, described image denoising unit receive the image of the process rim detection of sending from described Image Edge-Detection unit, and remove the noise that described image through rim detection produces in edge detection process, and the image that will remove noise sends to the straight-line detection unit;
S15, described straight-line detection unit receive the image of the described removal noise of sending from described image denoising unit, and the image of described removal noise carried out straight-line detection, and the straight line less than certain threshold value in the image of described removal noise removed, and will send to through the image of straight-line detection the straight line amending unit;
S16, described straight line amending unit receive the image of sending from described straight-line detection unit, and revise through the straight line in the image of straight-line detection described, and getting rid of non-intersect and crossing is not the straight line of 90 degree.
Described step S15 cathetus detecting unit utilizes Hough transformation that the image of described removal noise is carried out straight-line detection.
Business card extraction system and its implementation of a kind of smart mobile phone provided by the present invention, described system obtains the graph text information of business card by imageing sensor, automatically adjust the contrast of image by image enhancement technique, utilize wave filter to finish the extraction of the image border of adjusting contrast, utilize Image Denoising Technology to remove the noise that produces in the process image filtering process of rim detection, it also adopts Hough transformation to finish the straight-line detection of the image of removing noise, remove simultaneously in the image non-intersect and crossing be not 90 the degree straight lines, even thereby realize in the situation of the background of complexity and uneven illumination, still can extracting accurately the purpose of business card.
Description of drawings
Fig. 1 is the preferred embodiment structure block diagram of the business card extraction system of smart mobile phone of the present invention.
Fig. 2 is the image sensing and the preferred embodiment structural representation that strengthens module of the business card extraction system of smart mobile phone of the present invention.
Fig. 3 is the image detection of business card extraction system of smart mobile phone of the present invention and the preferred embodiment structural representation of denoising module.
Fig. 4 is the straight-line detection of business card extraction system of smart mobile phone of the present invention and the preferred embodiment structural representation of correcting module.
Fig. 5 is the preferred embodiment flow chart of steps of implementation method of the business card extraction system of smart mobile phone of the present invention.
Embodiment
For making purpose of the present invention, technical scheme and advantage clearer, clear and definite, developing simultaneously referring to accompanying drawing, the present invention is described in more detail for embodiment.Should be appreciated that specific embodiment described herein only in order to explain the present invention, is not intended to limit the present invention.
See also Fig. 1, Fig. 1 is the preferred embodiment structure block diagram of the business card extraction system of a kind of smart mobile phone of the present invention.Described cell phone system comprises respectively and image sensing and the image display 101 that strengthen module 102, image detection and denoising module 103, straight-line detection and be connected with correcting module 104 connections, wherein, described image sensing is connected with correcting module 104 with denoising module 103, described straight-line detection successively with enhancing module 102, described image detection.
Described system comprises image sensing and strengthens module 102, its sensor of installing by smart mobile phone self obtains the graph text information of the business card of business card and business card background, and the graph text information of described business card is converted into the image that can be processed and store by smart mobile phone, described image sensing also is used for the automatically contrast of the described image of adjustment with enhancing module 102, preferably be the contrast that automatically improves described image according to the resolution of image, wherein by automatically adjusting the contrast of described image, so that adjust in the image of contrast, contrast between business card and the business card background image increases, so that the business card in the image of described adjustment contrast is clear eye-catching, promote visual effect.Described image sensing sends to described image detection and denoising module 103 with the image that enhancing module 102 will be adjusted contrast.
Described image detection and denoising module 103 receives from described image sensing and the image that strengthens the adjustment contrast that module 102 sends, and utilize wave filter that the image of described adjustment contrast is detected, especially its edge of adjusting the image of contrast is detected, detection by described wave filter, so that can isolate accurately the frame of business card through the image of Image Edge-Detection, thereby so that described business card and business card background are separated, even if because of blocking owing to staff and smart mobile phone self in shooting process, cause that background is more or less the same between the existence of uneven illumination or described business card and the described business card background, still can be good at isolating the frame of business card.Described image detection and denoising module 103 also are used for removing the noise that described wave filter produces in edge detection process, and the described image of having removed noise is sent to straight-line detection and correcting module 104.
Wherein, the method for described removal noise is; Through after the rim detection, described image detection and denoising module 103 can be isolated the frame of business card, identify the area of business card by the frame of isolating business card, described image detection and denoising module 103 are removed area less than noise spot and the pixel of described business card area, thereby have improved the sharpness of separating business card.
Described straight-line detection and correcting module 104 receives the image of the removal noise of sending from described image detection and denoising module 103, and the straight line that comprises in the image of described removal noise detects, in the process of straight-line detection, the threshold value of a default straight length in described straight-line detection and correcting module 104, the threshold value of described length are roughly quite and business card wide; When the length that detects straight line during less than described default threshold value, described straight line is removed, and because of the straight line of length less than the business card width, is not the line segment that consists of the business card frame, length is removed less than the straight line of threshold value, so that the length of the straight line in the process image of straight-line detection is all greater than described threshold value; The purpose of doing like this is, the frame of business card can be accurately isolated in the setting of passing threshold, on the basis of Image Edge-Detection, further promotes the accuracy of extracting business card, so that the business card that extracts is more accurate.
Described straight-line detection and correcting module 104 are further to revising through the straight line in the image of straight-line detection, namely utilizing described business card is rectangular characteristics, further detect the straight line that length meets the demands, disjoint straight line with to intersect be not that 90 degree or the straight lines of keeping off 90 degree are removed, thereby accuracy and the reliability of image detection have further been improved, detection by described straight-line detection and correcting module 104, extract accurately the frame of business card, and then realized the accurate extraction of whole business card.
The business card extraction system of described smart mobile phone also comprises image display 101, and the operation interface that the user provides by described image display 101 carries out the operation in the business card extraction, and can see the image processing effect of its demonstration.
Below in conjunction with Fig. 2 the image sensing of the business card extraction system of smart mobile phone of the present invention is described further with enhancing module 102, wherein, Fig. 2 is the image sensing and the preferred embodiment structural representation that strengthens module of the business card extraction system of smart mobile phone of the present invention.
As shown in Figure 2, described image sensing comprises with enhancing module 102;
Below in conjunction with Fig. 3 image detection and the denoising module 103 of the business card extraction system of smart mobile phone of the present invention are described further, wherein, Fig. 3 is the image detection of business card extraction system of smart mobile phone of the present invention and the preferred embodiment structural representation of denoising module.
As shown in Figure 3, image detection and denoising module 103 comprise;
Image Edge-Detection unit 301 is connected with described image enhancing unit 202, be used for to receive the image of the adjustment contrast of sending from described image enhancing unit 202, and by wave filter the image of described adjustment contrast is carried out rim detection, rim detection by described wave filter, so that can be good at distinguishing through business card and the business card background in the image of rim detection, namely can extract business card from its background, this kind mode can be applicable to the situation that business card and business card background image are more or less the same; Its implementation is by described wave filter the image of described adjustment contrast to be carried out rim detection,, so that can being extracted, the edge of business card and then can extract described business card by the business card extraction system of described smart mobile phone by described wave filter; And adopt described method can improve the robustness of the business card extraction system performance of smart mobile phone, so that the user is using described system to carry out in the process that business card extracts the security that has improved operation system of smart phone;
Image denoising unit 302 is connected 302 and connects with described Image Edge-Detection unit, be used for receiving the image of the process rim detection of sending from described Image Edge-Detection unit 301, because of the processing of described image through rim detection by described Image Edge-Detection unit 301, can extract the frame of business card, the shared area of business card during 302 discriminations of described image denoising unit are published picture and looked like, and by area is removed less than noise spot and the pixel of business card area occupied, and then remove described noise through producing in the image filtering process of rim detection, thereby clear accurately by the business card that described image denoising unit 302 extracts, be convenient to user's identification; Wherein said noise refers in incomplete situation of imaging system, transmission medium and recording unit etc. at described smart mobile phone, and described business card and business card background image form, tend to be subject in the transmission log process pollution of multiple noise at it.In addition, some link of processing at image also can be introduced noise in result images when the object of input also is not so good as anticipation.These noises often show as isolated pixel point or a noise spot that causes stronger visual effect on image, the generation of described noise has reduced the sharpness of business card imaging greatly.Noise and image are uncorrelated and occur with useless message form, thereby upset the observable information of image.For data image signal, noise shows as either large or small extreme value, these extreme values act on the true gray-scale value of image pixel by plus-minus, cause bright, dim spot interference to image, greatly reduced picture quality, affect image restoration, cut apart, the carrying out of the follow-up work such as feature extraction, figure identification, thereby be unfavorable for that smart mobile phone is for the further processing of described image.And can protect well shape, the size of business card image target to reach specific how much and topological structure feature by the noise on the described business card of described image denoising unit 302 removals, and eliminated the impact of its noise existence on described image straight-line detection by the image of described image denoising unit 302.
Below in conjunction with Fig. 4 straight-line detection and the correcting module 104 of the business card extraction system of smart mobile phone of the present invention are described further, wherein, Fig. 4 is the straight-line detection of business card extraction system of smart mobile phone of the present invention and the preferred embodiment structural representation of correcting module.
As shown in Figure 4, straight-line detection and correcting module 104 comprise;
Straight-line detection unit 401 is connected with described image denoising unit 302, be used for receiving the image of the removal noise of sending from described image denoising unit 302, and the image of described removal noise carried out straight-line detection, the principle of wherein said straight-line detection is that described straight-line detection unit 401 adopts Hough transformation to carry out the straight line in the described removal noise image is detected, by described Hough transformation so that described straight-line detection unit 401 detects the straight line in the image of described removal noise, and preseting the threshold value of a straight length, general described Threshold is the width of general business card; And then will remove less than the straight line of described threshold value in the image, thereby detect satisfactory business card frame, on the basis of Image Edge-Detection unit 301 rim detection, further improve the accuracy of extracting business card; The image that described straight-line detection unit 401 will be removed less than certain threshold value straight line sends to straight line amending unit 402;
Straight line amending unit 402 is connected with described straight-line detection unit 401; Be used for receiving the image of the process straight-line detection of sending from described straight-line detection unit, and revise through the straight line in the image of straight-line detection described, getting rid of non-intersect and crossing is not 90 degree or the straight line of keeping off 90 degree; Its principle is, the design that utilizes business card is rectangular characteristics, straight line in the image is revised, get rid of the straight line that can not consist of rectangular shaped rim, be non-intersect and be not 90 the degree or keep off 90 the degree straight lines, thereby the accurate position of positioning name, further process by 402 pairs of described images through straight-line detection of straight line amending unit, so that business card can extract from the business card background accurately, even if the background of business card and business card are more or less the same, perhaps in the process of taking, in the situation of uneven illumination, still can realize accurately extracting the purpose of business card, solve the defective of prior art.
The method that the present invention also provides a kind of business card to extract elaborates to described method below in conjunction with Fig. 5, and wherein Fig. 5 is the preferred embodiment flow chart of steps of implementation method of the business card extraction system of smart mobile phone of the present invention.
At first enter step 501, smart mobile phone obtain business card by the image sensing unit graph text information, and the graph text information of described business card is converted into image, and described image is sent to image enhancing unit;
Wherein, the concrete ins and outs that realize of step 501, step 502 preferred embodiment of asking for an interview Fig. 2.
Wherein the concrete ins and outs of step 503, step 504 realization please see the preferred embodiment of Fig. 3 for details.
Further, straight-line detection unit by using Hough transformation carries out straight-line detection to described image.
Wherein the concrete ins and outs of the realization of step 505, step 506 please see the preferred embodiment of Fig. 4 for details.
The method of extracting by described business card so that the user is by smart mobile phone, even if in the situation that business card background and business card be more or less the same be not easy to distinguish and in shooting process uneven illumination also can realize extracting accurately business card.
What need were clear and definite is, business card extraction system and its implementation by a kind of smart mobile phone of the present invention not only can be applied in the mode of extracting business card by smart mobile phone, also can be applicable on the application platforms such as palm PC, ipad, notebook, for extracting business card under complex background, the user provides technical support by system and method for the present invention, and in the process of extracting business card, solved the drawback of the pixel that uneven illumination produces in shooting process in the prior art.
Should be understood that, application of the present invention is not limited to above-mentioned giving an example, and for those of ordinary skills, can be improved according to the above description or conversion, and all these improvement and conversion all should belong to the protection domain of claims of the present invention.
Claims (7)
1. the business card extraction system of a smart mobile phone is characterized in that, comprising: image sensing and enhancing module, image detection and denoising module, straight-line detection and correcting module, image display, wherein;
Described image sensing is connected with the denoising module with described image detection with the enhancing module, be used for obtaining by imageing sensor the graph text information of business card, the graph text information of described business card is converted into image, and automatically adjust the contrast of described image, the image of adjusting contrast is sent to described image detection and denoising module;
Described image detection is connected with correcting module with described straight-line detection with the denoising module, be used for to receive from described image sensing and the image that strengthens the adjustment contrast that module sends, by wave filter the image of described adjustment contrast is carried out rim detection, and remove the noise that described wave filter produces in edge detection process, and the image that will remove noise sends to described straight-line detection and correcting module;
Described straight-line detection is connected with described image display with correcting module, be used for to receive the image of the removal noise of sending from described image detection and denoising module, image to described removal noise carries out straight-line detection, and the straight line less than certain threshold value in the image of described removal noise removed, it also is used for the straight line of the image of process straight-line detection is revised, and removing non-intersect and crossing is not the straight lines of 90 degree;
Described image display is connected with correcting module with denoising module, described straight-line detection with enhancing module, described image detection with described image sensing respectively, is used for showing image processing effect and operation interface.
2. the business card extraction system of smart mobile phone according to claim 1 is characterized in that, described image sensing comprises with the enhancing module;
The image sensing unit is used for obtaining by imageing sensor the graph text information of business card, and the graph text information of described business card is converted into image;
Image enhancing unit is connected with described image sensing unit, is used for receiving the image of sending from described image sensing unit, and automatically adjusts the contrast of described image.
3. the business card extraction system of smart mobile phone according to claim 2 is characterized in that, described image detection and denoising module comprise;
The Image Edge-Detection unit is connected with described image enhancing unit, be used for to receive the image of the adjustment contrast of sending from described image enhancing unit, and by wave filter the image of described adjustment contrast is carried out rim detection;
The image denoising unit is connected with described Image Edge-Detection unit, is used for receiving the image of the process rim detection of sending from described Image Edge-Detection unit, and removes the described noise that produces in edge detection process through the image of rim detection.
4. the business card extraction system of smart mobile phone according to claim 3 is characterized in that, described straight-line detection and correcting module comprise;
The straight-line detection unit is connected with described image denoising unit, be used for receiving the image of the removal noise of sending from described image denoising unit, and the image of described removal noise carried out straight-line detection, and will remove in the image of noise and remove less than the straight line of certain threshold value;
The straight line amending unit is connected with described straight-line detection unit, be used for receiving the image of the process straight-line detection of sending from described straight-line detection unit, and revise through the straight line in the image of straight-line detection described, getting rid of non-intersect and crossing is not 90 straight lines of spending.
5. the business card extraction system of smart mobile phone according to claim 4 is characterized in that, described straight-line detection unit by using Hough transformation carries out straight-line detection to the image of described removal noise.
6. the implementation method such as the business card extraction system of the described smart mobile phone of claim 1 to 5 any one is characterized in that, described implementation method specifically comprises step;
S11, smart mobile phone obtain the graph text information of business card by the image sensing unit, and the graph text information of described business card is converted into image, and described image is sent to image enhancing unit;
S12, described image enhancing unit receive described image, and automatically adjust the contrast of described image, and the image that will adjust contrast sends to the Image Edge-Detection unit;
S13, described Image Edge-Detection unit receive the image of the adjustment contrast of sending from described image enhancing unit, and by wave filter the image of described adjustment contrast are carried out rim detection, will send to through the image of rim detection the image denoising unit;
S14, described image denoising unit receive the image of the process rim detection of sending from described Image Edge-Detection unit, and remove the noise that described image through rim detection produces in edge detection process, and the image that will remove noise sends to the straight-line detection unit;
S15, described straight-line detection unit receive the image of the described removal noise of sending from described image denoising unit, and the image of described removal noise carried out straight-line detection, and the straight line less than certain threshold value in the image of described removal noise removed, and will send to through the image of straight-line detection the straight line amending unit;
S16, described straight line amending unit receive the image of sending from described straight-line detection unit, and revise through the straight line in the image of straight-line detection described, and getting rid of non-intersect and crossing is not the straight line of 90 degree.
7. the implementation method of the business card extraction system of smart mobile phone according to claim 6 is characterized in that, described step S15 cathetus detecting unit utilizes Hough transformation that the image of described removal noise is carried out straight-line detection.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012103344685A CN102915522A (en) | 2012-09-12 | 2012-09-12 | Smart phone name card extraction system and realization method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012103344685A CN102915522A (en) | 2012-09-12 | 2012-09-12 | Smart phone name card extraction system and realization method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102915522A true CN102915522A (en) | 2013-02-06 |
Family
ID=47613877
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012103344685A Pending CN102915522A (en) | 2012-09-12 | 2012-09-12 | Smart phone name card extraction system and realization method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102915522A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103886554A (en) * | 2014-03-12 | 2014-06-25 | 王好贤 | Positioning method for automatically recognizing codes in system |
| CN104077767A (en) * | 2013-03-29 | 2014-10-01 | 北京千橡网景科技发展有限公司 | Method and device for detecting edge of business card |
| CN105260997A (en) * | 2015-09-22 | 2016-01-20 | 北京好运到信息科技有限公司 | Method for automatically obtaining target image |
| CN105868759A (en) * | 2015-01-22 | 2016-08-17 | 阿里巴巴集团控股有限公司 | Method and apparatus for segmenting image characters |
| CN104063868B (en) * | 2014-06-30 | 2017-05-10 | 中国科学院自动化研究所 | Polygonal work piece detecting and positioning method |
| CN113486786A (en) * | 2021-07-05 | 2021-10-08 | 江苏鼎峰信息技术有限公司 | Automatic operation correcting system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101359403A (en) * | 2008-07-28 | 2009-02-04 | 上海同盛工程建设配套管理有限公司 | Method for extracting contour outline of buildings from satellite imagery |
| CN101383005A (en) * | 2007-09-06 | 2009-03-11 | 上海遥薇实业有限公司 | Method for separating passenger target image and background by auxiliary regular veins |
| CN101436254A (en) * | 2007-11-14 | 2009-05-20 | 佳能株式会社 | Image processing method and image processing equipment |
| CN101894373A (en) * | 2010-08-19 | 2010-11-24 | 潘海朗 | Adopt the Weather fax image forward line extracting method of boundary rectangle |
| CN102147857A (en) * | 2011-03-22 | 2011-08-10 | 黄晓华 | Image processing method for detecting similar round by using improved hough transformation |
| 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 |
| CN102521594A (en) * | 2011-12-06 | 2012-06-27 | 康佳集团股份有限公司 | Method for accurately extracting object and system thereof |
-
2012
- 2012-09-12 CN CN2012103344685A patent/CN102915522A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101383005A (en) * | 2007-09-06 | 2009-03-11 | 上海遥薇实业有限公司 | Method for separating passenger target image and background by auxiliary regular veins |
| CN101436254A (en) * | 2007-11-14 | 2009-05-20 | 佳能株式会社 | Image processing method and image processing equipment |
| CN101359403A (en) * | 2008-07-28 | 2009-02-04 | 上海同盛工程建设配套管理有限公司 | Method for extracting contour outline of buildings from satellite imagery |
| CN101894373A (en) * | 2010-08-19 | 2010-11-24 | 潘海朗 | Adopt the Weather fax image forward line extracting method of boundary rectangle |
| CN102147857A (en) * | 2011-03-22 | 2011-08-10 | 黄晓华 | Image processing method for detecting similar round by using improved hough transformation |
| 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 |
| CN102521594A (en) * | 2011-12-06 | 2012-06-27 | 康佳集团股份有限公司 | Method for accurately extracting object and system thereof |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104077767A (en) * | 2013-03-29 | 2014-10-01 | 北京千橡网景科技发展有限公司 | Method and device for detecting edge of business card |
| CN103886554A (en) * | 2014-03-12 | 2014-06-25 | 王好贤 | Positioning method for automatically recognizing codes in system |
| CN103886554B (en) * | 2014-03-12 | 2016-08-31 | 哈尔滨工业大学（威海） | Code location method in automatic recognition system |
| CN104063868B (en) * | 2014-06-30 | 2017-05-10 | 中国科学院自动化研究所 | Polygonal work piece detecting and positioning method |
| CN105868759A (en) * | 2015-01-22 | 2016-08-17 | 阿里巴巴集团控股有限公司 | Method and apparatus for segmenting image characters |
| CN105868759B (en) * | 2015-01-22 | 2019-11-05 | 阿里巴巴集团控股有限公司 | The method and device of segmented image character |
| CN105260997A (en) * | 2015-09-22 | 2016-01-20 | 北京好运到信息科技有限公司 | Method for automatically obtaining target image |
| CN113486786A (en) * | 2021-07-05 | 2021-10-08 | 江苏鼎峰信息技术有限公司 | Automatic operation correcting system |
| CN113486786B (en) * | 2021-07-05 | 2024-04-09 | 江苏鼎峰信息技术有限公司 | An automatic homework correction system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20250005922A1 (en) | Real-time glare detection inside a dynamic region of an image | |
| CN110033471B (en) | Frame line detection method based on connected domain analysis and morphological operation | |
| CN105869113B (en) | Method and device for generating panoramic images | |
| US9679354B2 (en) | Duplicate check image resolution | |
| CN102915522A (en) | Smart phone name card extraction system and realization method thereof | |
| CN110648330B (en) | Defect detection method for camera glass | |
| CN114298985B (en) | Defect detection method, device, equipment and storage medium | |
| CN106599783B (en) | Video occlusion detection method and device | |
| CN110136069B (en) | Text image correction method and device and electronic equipment | |
| CN117456371B (en) | A method, device, equipment and medium for detecting hot spots in strings | |
| CN111539980B (en) | Multi-target tracking method based on visible light | |
| CN103034856A (en) | Method and device for locating text area in image | |
| CN105139391B (en) | A kind of haze weather traffic image edge detection method | |
| WO2024016632A1 (en) | Bright spot location method, bright spot location apparatus, electronic device and storage medium | |
| WO2014184372A1 (en) | Image capture using client device | |
| Kumar et al. | Comparative analysis for edge detection techniques | |
| Wu et al. | Image haze removal: status, challenges and prospects | |
| CN114596210A (en) | Noise estimation method, apparatus, terminal device, and computer-readable storage medium | |
| US20150112853A1 (en) | Online loan application using image capture at a client device | |
| Rani et al. | Escalating the resolution of an urban aerial image via novel shadow amputation algorithm | |
| CN111178118B (en) | Image acquisition and processing method, device and computer-readable storage medium | |
| CN105303363A (en) | Data processing method and data processing system | |
| CN108090425B (en) | Lane line detection method, device and terminal | |
| CN115641279A (en) | A Method of Edge Detection in High Noise Image | |
| CN112329572B (en) | Rapid static living body detection method and device based on frame and flash point |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate 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: 20130206 |