CN103227864B - Method of detecting image edge and mobile terminal - Google Patents
Method of detecting image edge and mobile terminal Download PDFInfo
- Publication number
- CN103227864B CN103227864B CN201310122525.8A CN201310122525A CN103227864B CN 103227864 B CN103227864 B CN 103227864B CN 201310122525 A CN201310122525 A CN 201310122525A CN 103227864 B CN103227864 B CN 103227864B
- Authority
- CN
- China
- Prior art keywords
- point
- marginal
- noise
- target area
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Landscapes
- Image Analysis (AREA)
Abstract
The embodiment of the invention discloses a method of detecting an image edge and a mobile terminal. The method comprises the steps of obtaining a password image entered by a user, converting the password image into a bianry image, searching a coordinate of an initial point of the edge of a target area in the bianry image, calculating with an edge tracing algorithm according to the coordinate of the initial point, obtaining edge information of the target area, and verifying the password image according to the edge information, wherein the edge tracing algorithm comprises an eight neighborhood based edge tracing algorithm based. With the adoption of the method and the mobile terminal, the edge information of the password image can be extracted simply and effectively to verify the password image.
Description
Technical field
The present invention relates to electronic technology field, particularly relate to a kind of method and mobile terminal of detected image edge.
Background technology
Along with the mobile terminal function such as mobile phone, panel computer is more and more stronger, usable range is more and more wider, and the security of mobile terminal more and more comes into one's own.Utilize acquisition for mobile terminal to picture extract palm print characteristics information identifying, become a kind of mobile terminal unlocking technology, wherein, the palmprint image collected usually will position and dividing processing before extraction feature, so that obtain the palmmprint subimage of the same area, will extract the profile of palmmprint, rim detection is conventional method for this reason.
In the prior art, most palmmprint edge detection algorithm is in bianry image, utilizing the convolution mask in differentiating operator to carry out pixel each in image, convolution completes, but it is complicated to utilize differentiating operator to carry out the algorithm of convolution, and calculated amount is large, consuming time many.
Summary of the invention
The embodiment of the present invention provides a kind of method and mobile terminal of detected image edge, simply, effectively can extract the marginal information of password image, with the checking of complete paired secret image.
Embodiments provide a kind of method of detected image edge, comprising:
Obtain the password image of user's typing, and described password image is converted to bianry image;
Search for the starting point coordinate at the edge, target area in described bianry image;
According to described starting point coordinate, and adopt border following algorithm to calculate, obtain the marginal information of target area, described border following algorithm comprises the border following algorithm based on eight neighborhood;
The checking to described password image is completed according to described marginal information.
Correspondingly, the embodiment of the present invention additionally provides a kind of mobile terminal, comprising:
Obtaining processing module, for obtaining the password image of user's typing, and described password image being converted to bianry image;
Search module, for searching for the starting point coordinate at the edge, target area in described bianry image;
Computing module, for according to described starting point coordinate, and adopt border following algorithm to calculate, finally obtain the marginal information of target area, described border following algorithm comprises the border following algorithm based on eight neighborhood;
Authentication module, for completing the checking to described password image according to described marginal information.
The embodiment of the present invention is by acquisition for mobile terminal password image, and utilize the border following algorithm based on eight neighborhood to extract the marginal information of password image, to complete the checking to described password image, the marginal information adopting this algorithm to extract password image can make the process verified password image become more simple, quick.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, below the accompanying drawing used required in describing embodiment is briefly described, apparently, accompanying drawing in the following describes is some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
Fig. 1 is the schematic flow sheet of the method at a kind of detected image edge that the embodiment of the present invention provides;
Fig. 2 is the schematic flow sheet of the method at the another kind of detected image edge that the embodiment of the present invention provides;
Fig. 3 is the schematic flow sheet of the wherein a kind of concrete grammar to noise processed that the embodiment of the present invention provides;
Fig. 4 is the structural representation of a kind of mobile terminal that the embodiment of the present invention provides;
Fig. 5 is the structural representation of search module in Fig. 4;
Fig. 6 is the structural representation of computing module in Fig. 4;
Fig. 7 is the structural representation obtaining processing module in Fig. 4.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
Refer to Fig. 1, be the schematic flow sheet of the method at a kind of detected image edge that the embodiment of the present invention provides, comprise the following steps:
S101, obtains the password image of user's typing, and described password image is converted to bianry image;
Password image can be fingerprint or the palmmprint of user, before mobile terminal unlocks, can by the fingerprint of the camera of mobile terminal shooting user or palmmprint to obtain password image, or the fingerprint of user or palmmprint can be gathered to obtain password image by the touch-screen of mobile terminal, again binary Images Processing is carried out to the password image got, described bianry image refers to each pixel not to be black is exactly white, and its gray-scale value does not have the image of middle transition.
S102, searches for the starting point coordinate at the edge, target area in described bianry image;
Due to normally individual closed region, target area, its edge forms a closed curve, does not have specific end points, and the point on any one edge all can be used as starting point.Therefore, the detailed process of initial search point coordinate can be: from the diagonal line of described bianry image, and find the reference point in target area, again from described reference point, carry out vertical or horizontal search, until find a bit on edge, target area, and using this point as starting point.
S103, according to described starting point coordinate, and adopt border following algorithm to calculate, obtain the marginal information of target area, described border following algorithm comprises the border following algorithm based on eight neighborhood;
From the starting point that described starting point coordinate is corresponding, and adopt based on the border following algorithm of eight neighborhood to obtain the marginal information of target area, detailed process is: using starting point corresponding for described starting point coordinate as initial point, marginal point is searched in eight neighborhood points of this initial point, and when searching marginal point, the pixel value of described initial point is set to effective value, again using the described marginal point searched as initial point, repeat this step, until the coordinate of the marginal point searched is described starting point coordinate.Marginal information comprises all marginal points in target area.
S104, completes the checking to described password image according to described marginal information;
After obtaining marginal information, just can position and dividing processing password image, then to the identification of password image zooming-out characteristic sum, to complete the checking to described password image.
The embodiment of the present invention is by acquisition for mobile terminal password image, and utilize the border following algorithm based on eight neighborhood to extract the marginal information of password image, to complete the checking to described password image, the marginal information adopting this algorithm to extract password image can make the process verified password image become more simple, quick.
Refer to Fig. 2, be the schematic flow sheet of the method at the another kind of detected image edge that the embodiment of the present invention provides, comprise the following steps:
S201, obtained the password image of user's typing by camera or touch-screen, described password image comprises fingerprint or palmmprint;
Before mobile terminal unlocks, can by the fingerprint of the camera of mobile terminal shooting user or palmmprint to obtain password image, or can by the fingerprint of the touch-screen collection user of mobile terminal or palmmprint to obtain password image.
S202, is converted to bianry image by the password image got;
Described bianry image refers to each pixel not to be black is exactly white, and its gray-scale value does not have the image of middle transition.
S203, from the diagonal line of described bianry image, and finds the reference point in target area;
Due to normally individual closed region, target area, its edge forms a closed curve, does not have specific end points, and the point on any one edge all can be used as starting point.Before initial search point, first find a reference point, such as, from the upper left corner of bianry image, search for the diagonal line of the line segment of certain length along bianry image, until one of them end points of this line segment enters the target area of bianry image, then stop search, and by as a reference point for this end points, so that continue initial search point.
S204, from described reference point, carries out vertical or horizontal search, until find a bit on edge, target area, and using this point as starting point;
After searching reference point, from described reference point, carry out vertical or horizontal search, until find a bit on edge, target area, when namely carrying out vertical or horizontal search, have found the intersection point on the longitudinal axis or transverse axis and edge, target area, and using this intersection point as starting point.
S205, using starting point corresponding for described starting point coordinate as initial point, marginal point is searched in eight neighborhood points of this initial point, and when searching marginal point, the pixel value of described initial point is set to effective value, again using the described marginal point searched as initial point, repeat this step, until the coordinate of the marginal point searched is described starting point coordinate;
Concrete, from the starting point searched, and adopt based on the border following algorithm of eight neighborhood to obtain the marginal information of target area, search and the computation process of edge point are specially: using starting point corresponding for described starting point coordinate as initial point, marginal point is searched in eight neighborhood points of this initial point, and when searching marginal point, the pixel value of described initial point is set to effective value, again using the described marginal point searched as initial point, repeat this step, until the coordinate of the marginal point searched is described starting point coordinate.
Such as, in bianry image by target area pixel value be a little set to 1, outside target area pixel value be a little set to 0, using starting point corresponding for starting point coordinate as initial point, and from this initial point, first aim adjoint point is searched in the direction of the clock in its eight field points, target adjoint point to be pixel value be 1 point, when determining that this target adjoint point is marginal point, the pixel value of this target adjoint point is set to 4 by 1, effective value is set to by pixel value, and using this target adjoint point as new initial point, repeat this step, until the coordinate of the marginal point searched is described starting point coordinate, now, in bianry image, the pixel value of all marginal points of target area is all replaced into 4, the pixel value of other points is constant.
S206, some pixel value being set to effective value processes, and obtains the marginal information of target area;
The marginal information of described target area is characterized by two-dimensional matrix, in two-dimensional matrix, all effective values represent the marginal point of target area, when obtaining the marginal information of target area, just the extraction to image border is completed, the border following algorithm based on eight neighborhood is taked to obtain marginal information, greatly can reduce data volume, for subsequent treatment brings very large convenience.
S207, completes the checking to described password image according to described marginal information;
After obtaining marginal information, just can position and dividing processing password image, then to the identification of password image zooming-out characteristic sum, to complete the checking to described password image.
Refer to Fig. 3, be the schematic flow sheet of the wherein a kind of concrete grammar to noise processed that the embodiment of the present invention provides, comprise the steps:
S301, judges whether there is noise in eight neighborhood points of this initial point;
Described noise is specially glitch noise, before searching for marginal point described in step S205 in eight of this initial point neighborhood points, judges whether there is noise in eight neighborhood points of this initial point.Such as, in bianry image by target area pixel value be a little set to 1, outside target area pixel value be a little set to 0, from certain initial point, and along the search of a certain bar noise, until when searching the end of this noise, a target adjoint point can cannot be searched there is noise in eight the neighborhood points determining this initial point by the point of noise end, wherein, described target adjoint point to be pixel value be 1 point.
S302, carries out Transformatin to described noise, then in eight neighborhood points of this initial point, searches for the step of marginal point described in performing;
When the step of S301 judges to there is noise, then Transformatin is carried out to noise, then perform the described step of searching for marginal point in eight neighborhood points of this initial point in S205 step.Such as, in bianry image by target area pixel value be a little set to 1, outside target area pixel value be a little set to 0, from certain initial point, and along a certain bar noise search, until when searching the end of this noise, a target adjoint point can cannot be searched there is noise in eight the neighborhood points determining this initial point by the point of noise end, wherein, described target adjoint point to be pixel value be 1 point, then by the point deletion of noise end, pixel value by this point is replaced into zero, and make search get back to its root along the end of noise, one by one by each clearing of noise, when the root of noise is got back in search, can search in eight field points of this point and will there is the point that pixel value is 1, now can perform the described step of searching for marginal point in eight neighborhood points of this initial point in S205 step.
S303, searches for the step of marginal point in eight neighborhood points of this initial point described in directly performing;
When S301 step judges there is not noise, directly perform the described step of searching for marginal point in eight neighborhood points of this initial point in S205 step.
The embodiment of the present invention is by acquisition for mobile terminal password image, and utilize the border following algorithm based on eight neighborhood to extract the marginal information of password image, to complete the checking to described password image, the marginal information adopting this algorithm to extract password image can make the process verified password image become more simple, quick.
Refer to Fig. 4, be the structural representation of a kind of mobile terminal 1 that the embodiment of the present invention provides, described mobile terminal 1 comprises: obtain processing module 10, search module 20, computing module 30, authentication module 40.
Wherein, described acquisition processing module 10, for obtaining the password image of user's typing, and is converted to bianry image by described password image;
Password image can be fingerprint or the palmmprint of user, before mobile terminal 1 unlocks, the camera shooting fingerprint of user or palmmprint can be controlled to obtain password image by described acquisition processing module 10, or the fingerprint of touch-screen collection user or palmmprint can be controlled to obtain password image by described acquisition processing module 10, again binary Images Processing is carried out to the password image got, described bianry image refers to each pixel not to be black is exactly white, and its gray-scale value does not have the image of middle transition.
Described search module 20, for searching for the starting point coordinate at the edge, target area in described bianry image;
Due to normally individual closed region, target area, its edge forms a closed curve, does not have specific end points, and the point on any one edge all can be used as starting point.Therefore, described search module 20 from the diagonal line of described bianry image, and can find the reference point in target area, again from described reference point, carry out vertical or horizontal search, until find a bit on edge, target area, and using this point as starting point.
Described computing module 30, for according to described starting point coordinate, and adopt border following algorithm to calculate, obtain the marginal information of target area, described border following algorithm comprises the border following algorithm based on eight neighborhood;
Described computing module 30 is from starting point corresponding to described starting point coordinate, and adopt based on the border following algorithm of eight neighborhood to obtain the marginal information of target area, detailed process is: using starting point corresponding for described starting point coordinate as initial point, marginal point is searched in eight neighborhood points of this initial point, and when searching marginal point, the pixel value of described initial point is set to effective value, again using the described marginal point searched as initial point, repeat this step, until the coordinate of the marginal point searched is described starting point coordinate.Marginal information comprises all marginal points in target area.
Described authentication module 40, for completing the checking to described password image according to described marginal information;
Described authentication module 40, after obtaining marginal information, just can position and dividing processing password image, then to the identification of password image zooming-out characteristic sum, to complete the checking to described password image.
Referring to Fig. 5, is the structural representation of search module 20 in Fig. 4, and described search module 20 comprises: reference point search unit 201, starting point search unit 202.
Wherein, described reference point search unit 201, for the diagonal line from described bianry image, and finds the reference point in target area;
Due to normally individual closed region, target area, its edge forms a closed curve, does not have specific end points, and the point on any one edge all can be used as starting point.Before initial search point, first find a reference point by described reference point search unit 201, such as, described reference point search unit 201 is by the upper left corner from bianry image, search for the diagonal line of the line segment of certain length along bianry image, until one of them end points of this line segment enters the target area of bianry image, then stop search, and by as a reference point for this end points, so that continue initial search point.
Described starting point search unit 202, for from described reference point, carries out vertical or horizontal search, until find a bit on edge, target area, and using this point as starting point;
Described reference point search unit 201 is after searching reference point, by described starting point search unit 202 from described reference point, carry out vertical or horizontal search, until find a bit on edge, target area, when namely carrying out vertical or horizontal search, have found the intersection point on the longitudinal axis or transverse axis and edge, target area, and using this intersection point as starting point.
Referring to Fig. 6, is the structural representation of computing module 30 in Fig. 4, and described computing module 30 comprises: marginal point computing unit 301, marginal information acquiring unit 302, judging unit 303, noise removing unit 304, notification unit 305.
Wherein, described marginal point computing unit 301, for using starting point corresponding for described starting point coordinate as initial point, marginal point is searched in eight neighborhood points of this initial point, and when searching marginal point, the pixel value of described initial point is set to effective value, then using the described marginal point searched as initial point, repeat this step, until the coordinate of the marginal point searched is described starting point coordinate;
Concrete, described marginal point computing unit 301 is from the starting point searched, and adopt based on the border following algorithm of eight neighborhood to obtain the marginal information of target area, search and the computation process of edge point are specially: described marginal point computing unit 301 using starting point corresponding for described starting point coordinate as initial point, marginal point is searched in eight neighborhood points of this initial point, and when searching marginal point, the pixel value of described initial point is set to effective value, again using the described marginal point searched as initial point, repeat this step, until the coordinate of the marginal point searched is described starting point coordinate.
Such as, in bianry image by target area pixel value be a little set to 1, outside target area pixel value be a little set to 0, described marginal point computing unit 301 using starting point corresponding for starting point coordinate as initial point, and from this initial point, first aim adjoint point is searched in the direction of the clock in its eight field points, target adjoint point to be pixel value be 1 point, when determining that this target adjoint point is marginal point, the pixel value of this target adjoint point is set to 4 by 1, effective value is set to by pixel value, and using this target adjoint point as new initial point, repeat this step, until the coordinate of the marginal point searched is described starting point coordinate, now, in bianry image, the pixel value of all marginal points of target area is all replaced into 4, the pixel value of other points is constant.
Described marginal information acquiring unit 302, processes for some pixel value being set to effective value, obtains the marginal information of target area;
The marginal information of the target area in described marginal information acquiring unit 302 is characterized by two-dimensional matrix, in two-dimensional matrix, all effective values represent the marginal point of target area, when described marginal information acquiring unit 302 obtains the marginal information of target area, just the extraction to image border is completed, the border following algorithm based on eight neighborhood is taked to obtain marginal information, greatly can reduce data volume, for subsequent treatment brings very large convenience.
Described judging unit 303, before searching for marginal point, judges whether there is noise in eight neighborhood points of this initial point for described marginal point computing unit 301 in eight neighborhood points of this initial point;
Described noise is specially glitch noise, before searching for marginal point, judges whether there is noise in eight neighborhood points of this initial point by described judging unit 303 in eight neighborhood points of described marginal point computing unit 301 at this initial point.Such as, in bianry image by target area pixel value be a little set to 1, outside target area pixel value be a little set to 0, from certain initial point, and along the search of a certain bar noise, until when searching the end of this noise, described judging unit 303 can cannot search a target adjoint point there is noise in eight the neighborhood points determining this initial point by the point of noise end, wherein, described target adjoint point to be pixel value be 1 point.
Described noise removing unit 304, if when judging to there is noise for described judging unit 303, then carry out Transformatin to described noise, reinforms described marginal point computing unit 301 and performs and describedly in eight neighborhood points of this initial point, search for marginal point;
If when described judging unit 303 judges to there is noise, then described noise removing unit 304 pairs of noises carry out Transformatin, reinform described marginal point computing unit 301 and perform and describedly in eight neighborhood points of this initial point, search for marginal point.Such as, in bianry image by target area pixel value be a little set to 1, outside target area pixel value be a little set to 0, from certain initial point, and along a certain bar noise search, until when searching the end of this noise, a target adjoint point can cannot be searched there is noise in eight the neighborhood points determining this initial point by the point of noise end by described judging unit 303, wherein, described target adjoint point to be pixel value be 1 point, then by described noise removing unit 304 by the point deletion of noise end, pixel value by this point is replaced into zero, and make search get back to its root along the end of noise, one by one by each clearing of noise, when the root of noise is got back in search, can search in eight field points of this point and will there is the point that pixel value is 1, now can notify that described marginal point computing unit 301 searches for marginal point described in performing in eight neighborhood points of this initial point.
Described notification unit 305, if when judging to there is not noise for described judging unit 303, then notifies that described marginal point computing unit 301 searches for marginal point described in performing in eight neighborhood points of this initial point.
Referring to Fig. 7, is the structural representation obtaining processing module 10 in Fig. 4, and described acquisition processing module 10 comprises: password image acquisition unit 101, binary Images Processing unit 102.
Wherein, described password image acquisition unit 101, for being obtained the password image of user's typing by camera or touch-screen, described password image comprises fingerprint or palmmprint;
Before mobile terminal 1 unlocks, the camera shooting fingerprint of user or palmmprint can be controlled to obtain password image by described password image acquisition unit 101, or the fingerprint of touch-screen collection user or palmmprint can be controlled to obtain password image by described password image acquisition unit 101.
Described binary Images Processing unit 102, for being converted to bianry image by the password got image;
Processing by described binary Images Processing unit 102 the described bianry image obtained refers to each pixel not to be black is exactly white, and its gray-scale value does not have the image of middle transition.
The embodiment of the present invention obtains password image by mobile terminal 1, and utilize the border following algorithm based on eight neighborhood to extract the marginal information of password image, to complete the checking to described password image, the marginal information adopting this algorithm to extract password image can make the process verified password image become more simple, quick.
Module described in the embodiment of the present invention or unit, universal integrated circuit can be passed through, such as CPU(Central Processing Unit, central processing unit), or by ASIC(Application Specific Integrated Circuit, special IC) realize.
One of ordinary skill in the art will appreciate that all or part of flow process realized in above-described embodiment method, that the hardware that can carry out instruction relevant by computer program has come, described program can be stored in a computer read/write memory medium, this program, when performing, can comprise the flow process of the embodiment as above-mentioned each side method.Wherein, described storage medium can be magnetic disc, CD, read-only store-memory body (Read-Only Memory, ROM) or random store-memory body (Random Access Memory, RAM) etc.
Above disclosedly be only present pre-ferred embodiments, certainly can not limit the interest field of the present invention with this, therefore according to the equivalent variations that the claims in the present invention are done, still belong to the scope that the present invention is contained.
Claims (8)
1. the method at detected image edge, is characterized in that, comprising:
Obtain the password image of user's typing, and described password image is converted to bianry image;
Search for the starting point coordinate at the edge, target area in described bianry image;
According to described starting point coordinate, and adopt border following algorithm to calculate, obtain the marginal information of target area, described border following algorithm comprises the border following algorithm based on eight neighborhood;
The checking to described password image is completed according to described marginal information;
Wherein, described according to described starting point coordinate, and adopt border following algorithm to calculate, the marginal information obtaining target area comprises:
Using starting point corresponding for described starting point coordinate as initial point, marginal point is searched in eight neighborhood points of this initial point, and when searching marginal point, the pixel value of described initial point is set to effective value, again using the described marginal point searched as initial point, repeat this step, until the coordinate of the marginal point searched is described starting point coordinate;
Point pixel value being set to effective value processes, and obtains the marginal information of target area;
Wherein, described in eight neighborhood points of this initial point, search for marginal point before, also comprise:
Judge whether there is noise in eight neighborhood points of this initial point;
If judge to there is noise in eight neighborhood points of this initial point, then Transformatin is carried out to described noise, then in eight neighborhood points of this initial point, search for the step of marginal point described in performing;
If judge to there is not noise in eight neighborhood points of this initial point, in eight neighborhood points of this initial point, described in directly performing, search for the step of marginal point;
Wherein, describedly Transformatin is carried out to described noise specifically comprise the point deletion of noise end, and make search get back to its root along the end of noise, with one by one by each point deletion of noise;
Wherein, describedly judge to there is noise in eight neighborhood points of this initial point, specifically comprise: in bianry image by target area pixel value be a little set to 1, outside target area pixel value be a little set to 0, from this initial point, and along a certain bar noise search, until when searching the end of this noise, a target adjoint point cannot be searched there is noise in eight the neighborhood points determining this initial point by the point of noise end, wherein, described target adjoint point to be pixel value be 1 point.
2. the method for claim 1, is characterized in that, the starting point coordinate at the edge, target area in the described bianry image of described search, comprising:
From the diagonal line of described bianry image, and find the reference point in target area;
From described reference point, carry out vertical or horizontal search, until find a bit on edge, target area, and using this point as starting point.
3. method as claimed in claim 2, it is characterized in that, the marginal information of described target area is characterized by two-dimensional matrix, and in two-dimensional matrix, all effective values represent the marginal point of target area.
4. method as claimed in claim 3, is characterized in that, the password image of described acquisition user typing, and described password image is converted to bianry image, comprising:
Obtained the password image of user's typing by camera or touch-screen, described password image comprises fingerprint or palmmprint;
The password image got is converted to bianry image.
5. a mobile terminal, is characterized in that, comprising:
Obtaining processing module, for obtaining the password image of user's typing, and described password image being converted to bianry image;
Search module, for searching for the starting point coordinate at the edge, target area in described bianry image;
Computing module, for according to described starting point coordinate, and adopt border following algorithm to calculate, obtain the marginal information of target area, described border following algorithm comprises the border following algorithm based on eight neighborhood;
Authentication module, for completing the checking to described password image according to described marginal information;
Wherein, described computing module comprises:
Marginal point computing unit, for using starting point corresponding for described starting point coordinate as initial point, marginal point is searched in eight neighborhood points of this initial point, and when searching marginal point, the pixel value of described initial point is set to effective value, again using the described marginal point searched as initial point, repeat this step, until the coordinate of the marginal point searched is described starting point coordinate;
Marginal information acquiring unit, processes for some pixel value being set to effective value, obtains the marginal information of target area;
Wherein, described computing module also comprises:
Judging unit, before searching for marginal point, judges whether there is noise in eight neighborhood points of this initial point for described marginal point computing unit in eight neighborhood points of this initial point;
Noise removing unit, if when judging to there is noise for described judging unit, then carry out Transformatin to described noise, reinforms described in the execution of described marginal point computing unit and search for marginal point in eight neighborhood point of this initial point;
Notification unit, if when judging there is not noise for described judging unit, then notifies that described marginal point computing unit searches for marginal point described in performing in eight neighborhood points of this initial point;
Wherein, described noise removing unit specifically for the point deletion by noise end, and makes search get back to its root along the end of noise, with one by one by each point deletion of noise;
Wherein, described judging unit, specifically in bianry image by target area pixel value be a little set to 1, outside target area pixel value be a little set to 0, from this initial point, and along the search of a certain bar noise, until when searching the end of this noise, a target adjoint point cannot be searched there is noise in eight the neighborhood points determining this initial point by the point of noise end, wherein, described target adjoint point to be pixel value be 1 point.
6. mobile terminal as claimed in claim 5, it is characterized in that, described search module comprises:
Reference point search unit, for the diagonal line from described bianry image, and finds the reference point in target area;
Starting point search unit, for from described reference point, carries out vertical or horizontal search, until find a bit on edge, target area, and using this point as starting point.
7. mobile terminal as claimed in claim 6, it is characterized in that, the marginal information of the target area in described computing module is characterized by two-dimensional matrix, and in two-dimensional matrix, all effective values represent the marginal point of target area.
8. mobile terminal as claimed in claim 7, it is characterized in that, described acquisition processing module comprises:
Password image acquisition unit, for being obtained the password image of user's typing by camera or touch-screen, described password image comprises fingerprint or palmmprint;
Binary Images Processing unit, for being converted to bianry image by the password got image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310122525.8A CN103227864B (en) | 2013-04-10 | 2013-04-10 | Method of detecting image edge and mobile terminal |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310122525.8A CN103227864B (en) | 2013-04-10 | 2013-04-10 | Method of detecting image edge and mobile terminal |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103227864A CN103227864A (en) | 2013-07-31 |
CN103227864B true CN103227864B (en) | 2014-12-31 |
Family
ID=48838116
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310122525.8A Expired - Fee Related CN103227864B (en) | 2013-04-10 | 2013-04-10 | Method of detecting image edge and mobile terminal |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103227864B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106934812A (en) * | 2015-12-25 | 2017-07-07 | 北京展讯高科通信技术有限公司 | Image-signal processor and its image-signal processing method |
CN110659343B (en) * | 2019-09-23 | 2023-08-11 | 创新先进技术有限公司 | Geofence data extraction method, device and equipment |
CN110910401A (en) * | 2019-10-31 | 2020-03-24 | 五邑大学 | Semi-automatic image segmentation data annotation method, electronic device and storage medium |
CN116228634B (en) * | 2022-12-07 | 2023-12-22 | 辉羲智能科技(上海)有限公司 | Distance transformation calculation method, application, terminal and medium for image detection |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101493883B (en) * | 2008-01-21 | 2012-12-12 | 宏达国际电子股份有限公司 | Method for unlocking locked operational equipment and operational equipment |
CN101393607B (en) * | 2008-09-03 | 2010-12-15 | 崔志明 | Method for implementing cerebrovascular image recognition by using fast boundary tracking |
CN102739856A (en) * | 2012-05-31 | 2012-10-17 | 西安电子科技大学 | Mobile phone unlocking system and method based on palm image information |
-
2013
- 2013-04-10 CN CN201310122525.8A patent/CN103227864B/en not_active Expired - Fee Related
Also Published As
Publication number | Publication date |
---|---|
CN103227864A (en) | 2013-07-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10643055B2 (en) | Fingerprint recognition method and system capable of improving fingerprint recognition rate | |
US9934420B2 (en) | Fingerprint information processing method and apparatus for speed improvement of fingerprint registration and authentication | |
KR101909971B1 (en) | Fingerprint identification method and fingerprint identification device | |
US9785819B1 (en) | Systems and methods for biometric image alignment | |
JP6361942B2 (en) | Electronic device including minimal sensing region and fingerprint information processing method thereof | |
US10496863B2 (en) | Systems and methods for image alignment | |
WO2016127736A1 (en) | Computing method for area of fingerprint overlapping area and electronic apparatus | |
CN104809452A (en) | Fingerprint identification method | |
CN104809453A (en) | Authentication method based on fingerprints | |
JP2007094862A (en) | Information generation device, information generation method, information generation program and machine-readable recording medium | |
CN104809464A (en) | Fingerprint information processing method | |
TWI437501B (en) | Identity verification apparatus and method thereof based on biometric features | |
CN103227864B (en) | Method of detecting image edge and mobile terminal | |
US10127681B2 (en) | Systems and methods for point-based image alignment | |
CN107087075B (en) | Prompting method based on screen fingerprint identification and mobile terminal | |
US20180349670A1 (en) | Biometric information process device, biometric information process method, computer-readable non-transitory medium and distance detection device | |
CN106940802B (en) | Method and apparatus for authentication using biometric information | |
US20070292005A1 (en) | Method and apparatus for adaptive hierarchical processing of print images | |
KR20160146081A (en) | Method for pre-processing image comprising biological inforamtion | |
KR20180108628A (en) | Method and fingerprint detection system for analyzing biometrics of user | |
KR102558736B1 (en) | Method and apparatus for recognizing finger print | |
JP2015026283A (en) | Image processing apparatus, image processing method, and program | |
CN110490020B (en) | Bar code identification method and device, computer equipment and storage medium | |
CN104598894A (en) | Fingerprint sensing device, product with fingerprint sensing function and fingerprint sensing method thereof | |
KR102452511B1 (en) | Method and apparatus for detection element image in drawings |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
PP01 | Preservation of patent right | ||
PP01 | Preservation of patent right |
Effective date of registration: 20180428 Granted publication date: 20141231 |
|
PD01 | Discharge of preservation of patent | ||
PD01 | Discharge of preservation of patent |
Date of cancellation: 20210428 Granted publication date: 20141231 |
|
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20141231 Termination date: 20180410 |