CN101967915A - Control method for safety box with palmprint recognition system - Google Patents

Abstract

The invention discloses a control method for safety box with palmprint recognition system, comprising the following steps: A1, acquiring a palmprint image, A2, pre-treating the palmprint image, A3, extracting the feature vector of the pre-treated palmprint image, and A4, matching the extracted feature vector with the palmprint feature vector of a pre-stored authorised user, sending an unlocking instruction if matched; or else, not sending the unlocking instruction if not matched; no matter matched or not, the unlocking time and user information are stored in a storage module.

Description

A kind of control method that has the safety cabinet of Palm Print Recognition System

Technical field

The present invention relates to the safety cabinet technical field, relate in particular to a kind of control method that has the safety cabinet of Palm Print Recognition System.

Background technology

People are attempting to seek a kind of more safety cabinet of " insurance " all the time, because traditional safety cabinet system opens with key and password, and key and password are the least roots of " insurance " of safety cabinet.Want to overcome these fatal drawbacks that key and password bring for the traditional insurance cabinet, in today of computer and mode identification technology develop rapidly, coming the opening safety cabinet system with human self-contained biological characteristic is a kind of method that domestic and international expert and scholars are seeking.

Biological identification technology claims the biological identification technology again, refers to that computer utilizes intrinsic physiological characteristic of human body or behavioural characteristic to carry out the technology that personal identification is identified.Biological identification technology mainly is divided into following 8 classes at present: fingerprint recognition, recognition of face, retina identification, iris identification, speech recognition, signature identification and the kinetics identification etc. of unblanking.Bio-identification has the accuracy of identification height, characteristics such as is easy to carry, can lose, can forget, can not be used or usurp, and is that one of new and high technology of development potentiality is arranged this century most.In biological identification technology commonly used, palmmprint identification is a kind of new technology that just grows up in the recent period, compares with other biological characteristic, and palmmprint has the following advantages: (1) has lifelong consistency and uniqueness; (2) location has rotational invariance and uniqueness; (3) minutia in the palmmprint and all kinds of line feature all have uniqueness and stability; (4) principal character of palmmprint is obvious, is difficult for by noise; (5) be difficult for copying; (6) owing to the resolution ratio to palmprint image can lower the requirement, the collecting device cost is lower; (7) testee's acceptable degree of palmmprint identification is higher; (8) the hardware standard degree of recognition system is also high.

But the application process of relevant palmmprint recognition technology in safety cabinet do not appear so far.

Summary of the invention

Technical problem to be solved by this invention is at the deficiencies in the prior art, and a kind of control method that has the safety cabinet of Palm Print Recognition System is provided.

The present invention adopts following technical scheme:

A kind of control method that has the safety cabinet of Palm Print Recognition System may further comprise the steps:

A1: gather palmprint image;

A2: described palmprint image is carried out preliminary treatment;

A3: the characteristic vector of extracting pretreated palmprint image;

A4: according to the authorized user palm print characteristics of characteristic vector of extracting and pre-stored to flux matched, the coupling unanimity is then sent unlock instruction, mate the inconsistent described unlock instruction that then do not send, no matter mate whether consistently, all uncaging time and user profile are stored in described memory module.

Described control method, the preliminary treatment that 2 pairs of described palmprint images of described steps A carry out comprises: the binaryzation of palmprint image, extract edge line, determine angle point, location and normalization.

Described control method, described steps A 3 adopts wavelet transformation to extract the palmprint image characteristic vector.

Described control method adopts Daubechies and Symlet orthogonal wavelet transformation to extract the palmprint image characteristic vector.

Described control method, described palmprint image characteristic extracting module are carried out 4 grades 2-d wavelet decomposition to a width of cloth palmprint image.

Palmmprint identification safety cabinet of the present invention, be to open with the self-contained biological characteristic palmmprint of human body, compare palmmprint with other biological characteristic and have lifelong consistency and uniqueness, the location has rotational invariance, the minutia of palmmprint and all kinds of line feature have stability, the principal character of palmmprint is obvious, is difficult for by noise.Compare the problem that key loss can not occur and be copied with the safety cabinet of other form; Can not occur forgetting Password and the stolen problem of password yet, safe.The nucleus equipment cost is lower, is easy to produce in enormous quantities.

Description of drawings

Fig. 1 2-d wavelet decomposing schematic representation;

The 2-d wavelet of Fig. 2 palmprint image decomposes, and wherein a is a palmmprint, and b is the wavelet decomposition figure of a palmmprint;

Fig. 3 palmmprint wavelet character vector curve map, wherein a is the palmmprint sample of palm 1,2,3, and b is the characteristic vector curve of palmmprint 1, and c is the characteristic vector curve of palmmprint 2, and d is the characteristic vector curve of palmmprint 3;

The control structure schematic diagram of Fig. 4 palmmprint safety cabinet of the present invention;

Fig. 5 is a palmprint image preprocess method schematic diagram.

The specific embodiment

Below in conjunction with the drawings and specific embodiments, the present invention is described in detail.

Embodiment 1

Present embodiment provides a kind of control structure of palmmprint safety cabinet, as shown in Figure 4, comprise palm-print image capture module 10, palmprint image pretreatment module 11, palmprint image characteristic extracting module 12, images match module 13, memory module 16 and the control module 15 of unblanking; Described palm-print image capture module 10 is used to gather user's palmprint image, described user's palmprint image carries out preliminary treatment in described palmprint image pretreatment module 11, extract the characteristic vector of pretreated palmprint image in described palmprint image characteristic extracting module 12, according to the authorized user palm print characteristics of pre-stored in characteristic vector of extracting and the memory module to flux matched, the coupling unanimity is then sent unlock instruction to the described control module of unblanking, mate the inconsistent described unlock instruction that then do not send, no matter mate whether consistently, all uncaging time and user profile are stored in described memory module;

For example, the palm-print image capture module can be used ccd video camera, by PC or DSP the image after gathering is carried out preliminary treatment, carries out characteristic vector and extracts, and then mate with the palmmprint that is stored in the memory module 16.

The palmmprint that is stored in the authorized user in the memory module 16 is set up by system in advance by the caretaker, is authorized user, and authorized user also can add at any time, revise.

The control mechanism concrete steps of the palmmprint safety cabinet of present embodiment are as follows:

A1: gather palmprint image;

A2: described palmprint image is carried out preliminary treatment; Described pretreated method is specially:

(1) binaryzation of palmprint image: the palmprint image after cutting apart is carried out binaryzation, and promptly palm portion got for 0 (deceiving), and background parts got for 1 (in vain), can obtain complete palm type, shown in Fig. 5-1.

(2) edge extracting: to the palmprint image edge extracting after the binaryzation is exactly the point of emptying palm inside.Its basic thought is: if in the image a bit for black, and its 8 neighborhood points illustrate that this point is an internal point when all being black, with this point deletion (being changed to white), otherwise, then be boundary point, write down its position.All pixels in the image are carried out this operation just can finish the extraction on palmprint image border (shown in Fig. 5-2).

(3) determine angle point: find out interested angle point A, B, C (Fig. 5-3) with the method for curve fit on the edge line of palmprint image, wherein A is the intersection point between the third finger and the little finger of toe, and B is the intersection point between forefinger and the middle finger, and C is the mid point of A, B line.

(4) location and normalization: the mid point O that the C point is moved to palmprint image, make it to overlap with the O point, O is made as the origin of coordinates (shown in Fig. 7-3) usually, with O is center rotation palmprint image, AB forwards vertical direction (vertical direction is set to the y axle) to, after mobile and rotation, employed palmprint image AB line all is positioned on the same position with vertical direction, cut out a block size at the same area place, palm center and be 128 * 128 subimage and represent whole palmprint image (as Fig. 5-4), can finish the location normalization of palmprint image.

A3: the characteristic vector of extracting pretreated palmprint image;

A4: according to the authorized user palm print characteristics of characteristic vector of extracting and pre-stored to flux matched, the coupling unanimity is then sent unlock instruction, mate the inconsistent described unlock instruction that then do not send, no matter mate whether consistently, all uncaging time and user profile are stored in described memory module.

Preferably, 2 pairs of described palmprint images of described steps A carry out binaryzation, location, normalization, filtering, micronization processes.

Preferably, described steps A 3 adopts wavelet transformation to extract the palmprint image characteristic vector.

Preferably, adopt Daubechies and Symlet orthogonal wavelet transformation to extract the palmprint image characteristic vector.

Preferably, described palmprint image characteristic extracting module is carried out 4 grades 2-d wavelet decomposition to a width of cloth palmprint image.

Embodiment 2

Present embodiment provides a kind of palmprint image preprocess method.

Preliminary treatment is the first step of the automatic identifying of palmmprint, and its quality directly affects the effect of palmmprint identification.Preprocess method commonly used mainly comprises the binaryzation, location (rotation and translation), normalization, filtering, refinement of palmprint image etc.

Carry out palm-print image capture with a equipment based on CCD.In order to reduce error and the distortion that causes owing to translation, rotation, distortion in the gatherer process, when gathering palmprint image, every finger of palm is opened, can extract finger edge like this, and aim at and the normalization palmprint image with it.After treatment, each palmmprint block size is 128 * 128 (shown in Fig. 2 (a)), and skew and rotation be eliminated basically, thereby helps the identification of palmprint image.

Embodiment 3

Present embodiment provides a kind of palmprint image feature extracting method---and wavelet character extracts.

Palmprint image is a kind of approximate grain periodic pattern, and wherein main line is the darkest several the thickest lines on the palm, on most of palms three main clues is arranged; Except main line, also have a lot of pleat lines on the palm, in general these lines are thinner, shallow than main line, and very irregular.The streakline direction of zones of different and spatial frequency are being represented the feature of palmprint image inherence in the palmprint image.Characteristics at palmprint image, the method experiment that we extract through various features, find because wavelet transformation has the function of multichannel, multiresolution, therefore with a kind of feature of extracting palmprint image based on method of wavelet, and then discern and not only saved the pretreated time of image, and the robustness of identification is also higher.

Wavelet transformation theory is further developing of Fourier analysis theories, is the needs of people for the profound understanding of characteristics of signals.Wavelet transformation provides an adjustable T/F window, flexible result be exactly we can be under different resolution ratio decomposed signal, the result of translation is exactly that we can organize signal to this as window, observes the part of oneself being concerned about.

Definition: if function Ψ (x) satisfies the small echo condition that allows,

$C_{\mathrm{\&psi;}}={\&Integral;}_{-\&infin;}^{\&infin;}({\left|\widehat{\mathrm{\&psi;}}\left(\mathrm{\&omega;}\right)\right|}^2/\mathrm{\&omega;})\mathrm{d\&omega;}<\&infin;$

Ψ (x) is called and can allows small echo (integration small echo, basic small echo) so.Wherein

It is the Fourier transform of Ψ (t).

The wavelet function system that is generated by basic small echo can be expressed as:

${\mathrm{\&psi;}}_{b,a}\left(t\right)={\left|\frac{1}{a}\right|}^{\frac{1}{2}}\mathrm{\&psi;}\left(\frac{t-b}{a}\right)$

Then the wavelet transformation of function f (x) is defined as

$\left(W_{\mathrm{\&psi;}}f\right)(b,a)={\left|a\right|}^{-1/2}{\&Integral;}_{-\&infin;}^{\&infin;}f\left(t\right)\stackrel{\&OverBar;}{\mathrm{\&psi;}}\left(\frac{t-b}{a}\right)\mathrm{dt}$

The center and the window width of wavelet function Ψ (t) time window provide with t* and Δ Ψ respectively, frequency window respectively by ω * and Provide, set

${\mathrm{\&psi;}}_{b,a}\left(t\right)={\left|\frac{1}{a}\right|}^{\frac{1}{2}}\mathrm{\&psi;}\left(\frac{t-b}{a}\right)$

Then the time window of small echo is [b+at ^*-a Δ _Ψ, b+at ^*+ a Δ _Ψ], the width of time window is the 2a Δ _Ψ, frequency window is

The width of frequency window is

This shows that for the HFS of detection signal, time window can narrow down, frequency window can broaden; For the low frequency part of detection signal, time window can broaden, and frequency window can narrow down.Therefore, by wavelet transformation well reflected signal the time-the frequency local characteristics.Signal fastened at this function do decomposition, just obtained the definition of continuous wavelet transform.

Present embodiment adopts wavelet transformation to extract the palmprint image feature, and the two-dimentional biorthogonal wavelet that the palmprint image after original location and the normalization is carried out the J rank decomposes, and every grade decomposition as shown in Figure 1.

As shown in Figure 2, a width of cloth palmprint image is carried out 4 grades 2-d wavelet decomposition.In the decomposition result of Fig. 2: the 1st in the upper right corner is cH ₁, the 1st in the lower right corner is cD ₁, the 1st in the lower left corner is cV ₁, other and the like.So far, obtained 3J+1 width of cloth subimage.These two kinds of information of streakline direction in the palmprint image and spatial frequency can be extracted the 3J width of cloth subimage { cH after the wavelet decomposition well _k, cV _k, cD _kIn go.Each width of cloth subimage is asked normalized 2 norms, thereby obtain the characteristic vector that length is 3J

$\left\{{[{f_k}^H,{f_k}^V,{f_k}^D]}_{k=1,...,J}\right\},$

Wherein

K=1 ..., J

The length of trying to achieve is that the characteristic vector of 3J can be understood as palmprint image in the different proportion factor (2 ^k) under the condition and different directions (H, V, D) the general Energy distribution on.Get 3 different palms, each palm has been gathered 12 image patterns, has certain displacement and angle difference between sample, and Fig. 3 is in 12 samples of each palm.To these 36 samples, try to achieve 3 length and be 12 characteristic vector, and the characteristic vector of 12 palmmprint samples of same palm is depicted as curve map in a width of cloth figure, as shown in Figure 3.As can be seen from Figure 3, characteristic vector exists evident difference (different palm) and enough stability (the different samples of identical palm).

Used palmprint image database one has the palmmprint of 20 different palms, and each palm has 12 samples, comes to 240 palmprint images.Palmprint image is that size is 256 grades of gray level images of 128 * 128 pixels, is collected by the palm-print image capture module.Test under different small echos and decomposed class (J) condition, what the discovery effect was best is Daubechies and Symlet orthogonal wavelet, and decomposed class is preferably 4 grades.

Embodiment 4

Present embodiment provides project testing, in the project testing, has finished the learning training of 5 people, 50 width of cloth (everyone 10 width of cloth) palmprint images, importing 200 images then discerns, everyone 20 width of cloth of 5 people in the storehouse, stranger's palmprint image 100 width of cloth of picked at random, recognition result sees Table 1.

Table 1 test result

By table 1 as seen, the orthogonal wavelet that adopts in the project has all obtained very high classification accuracy rate.When the sample of misclassification is analyzed, find that these samples all are because palm and collector excessive extrusion when gathering, cause streakline too to be out of shape or become close, thereby changed the direction and the spatial frequency feature of palmmprint streakline.

Test result shows that the recognizer of wavelet transformation is very effective.Simultaneously, the no key safety cabinet system that the present invention proposes if further commercialization, can be used as the renewal product of current safety cabinet system fully.

Should be understood that, 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 (5)

1. a control method that has the safety cabinet of Palm Print Recognition System is characterized in that, may further comprise the steps:

A1: gather palmprint image;

A2: described palmprint image is carried out preliminary treatment;

A3: the characteristic vector of extracting pretreated palmprint image;

A4: according to the authorized user palm print characteristics of characteristic vector of extracting and pre-stored to flux matched, the coupling unanimity is then sent unlock instruction, mate the inconsistent described unlock instruction that then do not send, no matter mate whether consistently, all uncaging time and user profile are stored in described memory module.

2. according to claim 1 control method, it is characterized in that the preliminary treatment that 2 pairs of described palmprint images of described steps A carry out comprises: the binaryzation of palmprint image, extract edge line, determine angle point, location and normalization.

3. control method according to claim 1 is characterized in that, described steps A 3 adopts wavelet transformation to extract the palmprint image characteristic vector.

4. control method according to claim 3 is characterized in that, adopts Daubechies and Symlet orthogonal wavelet transformation to extract the palmprint image characteristic vector.

5. according to claim 3 or 4 described control methods, it is characterized in that described palmprint image characteristic extracting module is carried out 4 grades 2-d wavelet decomposition to a width of cloth palmprint image.

Images