CN101331527B - Processing images of media items before validation - Google Patents

Abstract

Automatic media item validation is typically problematic in the case of media items that are damaged or marked. The present invention relates to a method of processing images of media items before automatic validation which addresses this problem. Aberrant image elements are identified, for example, using a bandpass filter. The aberrant image elements are replaced by neutral decision making data. This data is neutral with respect to a decision making process being a specified automatic media item validation process. For example, for each aberrant image element an estimated distribution is accessed for that image position across all images in a training set of images of media items. A value is selected from the estimated distribution on the basis of a significance level which is related to a significance level used by the automatic media item validation process. In this way media items which have tears, holes, marks or soiling may be successfully processed by an automatic media item validator.

Description

The image of treatment media object before checking

The cross reference of related application

The application is the part continuation application of No. 11/366,147, the U.S. Patent application submitted on March 2nd, 2006, and U.S. Patent application is for 11/366, No. 147 the part continuation application of No. 11/305,537, the U.S. Patent application submitted on Dec 16th, 2005.The application that No. 11/366,147, the application that on March 2nd, 2006 submitted to and on Dec 16th, 2005 submit to is incorporated herein by reference for 11/305, No. 537.

Technical field

The present invention relates to a kind of before checking the method and apparatus of image of treatment media object.Particularly, relate to the image of the dielectric object of processing such as bank note, passport, bond, stock, check etc., but never be limited to this.

Background technology

More and more need be with mode automatic inspection and the bank note of verifying different Currency Types and denomination simple, reliable and the saving cost.For example, this is essential in the self-service equipment (for example, self-service retail kiosk, ticket machine, the ATM (Automatic Teller Machine) that is arranged to handle deposit, self-service money changing machine etc.) that receives bank note.

In the past, the manual method of currency validation relate to the image inspection of bank note, such as transparent effect and the feel even the smell of watermark and lines alignment mark.Other known methods rely on the semi-over feature that needs half artificial inquiry.For example, use magnetic devices, UV sensor, fluorescence, infrared detector, electric capacity, bonding jumper, image model etc.Yet with regard to itself, these methods are artificial or are half artificial, and are not suitable for many application of manual intervention for a long time.For example, in self-service equipment.

To have major issue to have to be overcome in order to create the automatic currency validator.For example, there is many dissimilar currency with different security features even matrix type.The security feature that also has different brackets at different denominations usually.Therefore, need provide a kind of be used for those different Currency Types and denomination, easily and be convenient to carry out the conventional method of currency validation.

Automatic verification method in the past needs a large amount of relatively known counterfeit money samples with training classifier usually.In addition, those previous sorters are trained only to detect known counterfeit money.This is problematic, and reason is, exists for possible counterfeit money seldom or not to have available information.For example, this is problematic for the denomination or the new Currency Type of introducing of new introducing especially.

Be published in Pattern Recognition 37 (the 37th phase of pattern-recognition) (2004) 1085-1096 pages or leaves, the author is Chao He, in MarkGirolami and Gary Ross (wherein two people are present inventors), the early stage paper of exercise question for " Employing optimized combinations ofone-class classifiers for automated currency validation (adopting the optimum combination of one-class classifier for automatic banknote validation) ", (patent No. is EP1484719, US20042447169) to have described automatic banknote validation method.This relates to the image segmentation one-tenth zone of use network with whole bank note.Be independent " single class (the one-class) " sorter of each areal structure, and the little subclass of combination zone specific classification device is to provide comprehensive description (explaining term " single class " in more detail below).Cutting apart and make up by the regional specific classification device that adopts genetic algorithm to be embodied as to realize superperformance.This method needs to forge on a small quantity sample in genetic algorithm in the stage, similarly, in the time can't obtaining data falsification, this method is inapplicable.

Also need carry out automatic banknote validation in the little mode of computing cost of energy executed in real time.

Be damaged or by under the situation about making marks, the automatic currency checking is normally problematic at bank note.For example, if bank note has tear, hole, stain and/or folding angle.Bank note aging and during the wearing and tearing of bank note, take place dirty also be problematic for the automatic currency verification system.

Many problems above-mentioned also are applied to the checking such as the medium of other types such as passport, stock, bond, check.

Summary of the invention

Be damaged or the situation of the dielectric object (media items) of mark under, the checking of automated media object is normally problematic.A kind of method of before verifying automatically the image of dielectric object being handled that addresses this problem has been described.By for example using bandpass filter identification abnormal image element.Generate data with the neutrality decision-making and replace the abnormal image element.These data are neutral about generating processing as the decision-making of specifying the checking of automated media object to handle.For example, for each abnormal image element, obtain the estimation that framing spreads all in all images of the image of dielectric object training set and distribute.Based on level of signifiance selective value from the distribution of estimating, the described level of signifiance is relevant with the level of signifiance that use is handled in the checking of automated media object.By this way, automated media object validator can successfully handle have tear, the dielectric object of hole, mark or stain.

Method as described herein can be carried out by the software of the machine-readable form on storage medium.Can be with any suitable order that it will be apparent to those skilled in that and/or the step of the described method of executed in parallel.

This expression, software can be commodity valuable, that can separately buy and sell.This means to comprise operation or control " (dummy argument) dumb " or the software of standard software, with the function of carry out desired, therefore (therefore, software is the function of definition register in fact, even before its and its standard hardware is made up, also can be called as register).Owing to similar reason, also comprise the software of the structure of " description " or definition hardware, for example design silicon or the structure employed HDL of universal programmable chips (hardware description language) software, with the function of carry out desired.

Understand as the technician, but the preferable feature appropriate combination, and can with any characteristics combination in the many-side of the present invention.

Description of drawings

To by by way of example embodiments of the invention be described with reference to following accompanying drawing, wherein:

Fig. 1 is identification and the process flow diagram that replaces the method for the abnormal image element in the banknote image;

Fig. 2 is a process flow diagram of creating the method for the sorter that is used for banknote validation

Fig. 3 is the process flow diagram that replaces the method for the abnormal image element in the banknote image;

Fig. 4 is a synoptic diagram of creating the equipment of the sorter that is used for banknote validation;

Fig. 5 is the synoptic diagram of biil validator;

Fig. 6 is the process flow diagram of the method for checking bank note;

Fig. 7 is the synoptic diagram with self-service equipment of biil validator.

Embodiment

Below only as example, embodiments of the invention are described.The best way that applies the present invention to put into practice known to these example shown applicant is present, rather than can realize the mode that only has of the present invention.Be used for automatic banknote validation and be implemented although here this example is described and is depicted as, system described herein is described as example, rather than restriction.It will be appreciated by those skilled in the art that this example is suitable for the application in the media verify system of number of different types, described media verify system comprises passport verification system, check verification system, is used for the verification system of bond and stock, but is not limited thereto.

Use term " one-class classifier " to represent to use the sorter that forms or construct from the information of the sample of single class about only, but it is used for emerging sample dispensing is given described single class or do not distributed to described single class.These are different with the traditional binary sorter, and described traditional binary sorter is by using the information about the sample of two classes to be created, and are used to new samples is distributed in described two classes one or another.One-class classifier can be considered to define known class border on every side, thereby the sample that breaks away from described border is considered to not belong to described known class.

As mentioned above, the automatic currency checking is normally problematic under the situation of the bank note that is damaged or is labeled.For example, if bank note has tear, hole, stain and/or folding angle.Bank note aging and during the wearing and tearing of bank note, take place dirty also be problematic for automatic banknote validation system.

For example, the banknote validation system can use processing automatically, thereby the image division of bank note to be verified is become segmentation.Can form described segmentation by the additive method that uses network or independent usage space positional information.Selectively, can cut apart mapping by use and form segmentation, described cut apart mapping use with each of the set of training banknote image in the respective image element between the relevant information of correlation of pictorial element.

If the bank note that is verified be damaged or made marks, then because some information are unusual or unreliable, so this is causing problem at banknote validation automatically in handling.For example, the hole in the bank note can cause the pixel of unusual high brightness (intensity) in the image of bank note.In addition, stain on the bank note or mark can cause the pixel of unusual low-light level in the image of bank note.

Become under the situation of segmentation as the part of checking processing in the image division with bank note to be verified, a kind of selection is to ignore the segmentation that those comprise abnormal data (for example, hole, mark, folding line, tear etc.).Yet, only use small number of segments, this means that the data of vast scale are left in the basket.In addition, () important bank note zone for example, hologram, silking and watermark etc., then the degree of confidence of biil validator will descend such as security feature if the segmentation of ignoring by chance comprises.

In order to address these problems, we discern such as the abnormal image element in the image of the dielectric object of the bank note that will be verified, and replace those abnormal image elements with decision-making-neutrality (decision-neutral) data.By " decision-making-neutral-data " or " the neutral decision-making produces data ", we represent to influence the pre-data of carrying out the result of dielectric object checking processing.It can be any adequate types that described dielectric object checking is handled, and comprises particular medium object checking processing described herein, but is not limited thereto.

Fig. 1 is the outline flowchart of method of handling the image of the bank note that will be verified.

Use the image (referring to square frame 1) of below any in greater detail suitable technique being taken the bank note that to be verified.With this image normalization and/or pre-service (referring to square frame 2), for example at the particular orientation described image that aligns, and with described image zoom to specific size.This makes the variation of sensor and lighting environment to be considered.Then, introducing optional step (referring to square frame 3) uses recognizer to determine one or more in Currency Type, sequence number, denomination and the orientation of bank note.If the recognizer failure then can be attempted once more by different edges or angle with reference to banknote image.If four edges have all been attempted and all failed, then this bank note is rejected (referring to square frame 7).Otherwise, handle and continue, and unusual (referring to square frame 4) in the searching image.

Can discern unusual in any suitable manner.For example, zone that lacks in the bank note or hole cause the image-region of unusual high brightness usually.In this case, all images zone, element or the pixel on the assign thresholds can be identified as unusually.

In some Currency Types, the polymer currency is used window.This window also causes the image-region of high brightness.For these windows are not identified as unusually, when identification is unusual, can consider the knowledge relevant with size with desired location, the location of these windows.

Stain, mark's mark, staple, folding line and other this damages cause extremely zone of opacity in banknote image.In this case, all images zone, element or the pixel with the brightness that is lower than assign thresholds can be identified as unusually.Alternatively, when identification when unusual, can consider the relevant information of expection brightness with the pictorial element of specific Currency Type and denomination.

For quick identification have on the assign thresholds or under the pictorial element of brightness, can use bandpass filter.

In case identify unusually, then can be by replacing removing unusual (referring to square frame 5) with the decision-making neutral-data.Alternatively, the ratio that is identified as unusual banknote image is checked.If this ratio on assign thresholds, if then also do not refuse this bank note in the refusal algorithm stage, is then refused this bank note (referring to square frame 7).This guarantee by amalgamation partly fuzzy counterfeit money the part genuine notes and the counterfeit money that forms is rejected.In addition, can boundary be set to the amount of the superseded abnormal data of possibility by this way.Replace 100% banknote image because handle trend decision-making-neutral-data, so may reduce the ability of forging that detects.

Then, the results modification image of bank note is sent to banknote validation system (referring to square frame 6) to be verified.

With reference to Fig. 3 the processing that forms the decision-making neutral-data is described in more detail below.

In the embodiment of particular group, preassigned banknote validation is handled and is used as describe now formed sorter.

Fig. 2 is an outline flowchart of creating the method for the sorter that is used for banknote validation.

At first, we obtain the training set (referring to the square frame 10 of Fig. 1) of the image of genuine notes.These are images of same type of the bank note of the identical Currency Type obtained and denomination.The type of image relates to how obtaining image, and this can use any way as known in the art.For example, reflected image, image, heat picture, infrared image, ultraviolet image, x light image or other image types on the transmission image, red, blue or green any passage.Image in the training set is aligned, and size is identical.As known in the prior art, if necessary, can carry out pre-service and come registration image and zoomed image.

Then, we cut apart mapping (referring to the square frame 12 of Fig. 2) by using from the information creating of training integrated images.Describedly cut apart mapping and comprise the information that about how image division is become a plurality of segmentations (segment).Described segmentation can be discontinuous, promptly given segmentation can comprise in the zones of different of image more than one sheet (patch).Preferably, but nonessential, cut apart the segmentation that mapping also comprises the specific quantity that will be used.

Mapping is cut apart in use, and we cut apart each image (referring to the square frame 14 of Fig. 2) in the training set.Then, we are from each stage extraction one or more features (referring to the square frame 16 of Fig. 2) of each training integrated images.For term " feature ", we represent any statistic or other characteristics of segmentation.For example, any other statistic in the pattern of average pixel luminance, intermediate value pixel intensity, pixel intensity, texture, histogram, Fourier transform descriptor, wavelet transformation descriptor and/or the segmentation.

Then, form sorter (referring to the square frame 18 of Fig. 2) by use characteristic information.Can use the sorter of any adequate types as be known in the art.In concrete preferred embodiment of the present invention, sorter is an one-class classifier, need be about the information of counterfeit money.Yet, also can use the sorter of the other types of binary classifier or any adequate types as be known in the art.

The method of Fig. 2 make the sorter of checking of the bank note be used for specific Currency Type and denomination can be simply, form quickly and efficiently.In order to create the sorter that is used for other Currency Types or denomination, repeat described method with the suitable training integrated images.

Before, in EP1484719 and US20042447169, (as mentioning in the background technology part) our use relates to used the cutting techniques and the genetic algorithm method of network to cut apart mapping with formation to the plane of delineation.This must use some information about counterfeit money, and when carrying out the genetic algorithm search, causes the increase that assesses the cost.

The embodiments described herein can use and form the distinct methods of cutting apart mapping, and described method does not need to use genetic algorithm or equivalent method, to search for the good mapping of cutting apart in the mapping in a large amount of possible cutting apart.This has reduced to assess the cost, and has improved performance.In addition, need be about the information of counterfeit money.

We think, in pseudo-fabrication technique, are difficult to provide the consistent quality of whole bank note to be imitated usually, and therefore, the specific region of bank note more is difficult to success than other zones and duplicates.Therefore, we recognize, do not use the mesh segmentation of strict conformance, and we can complicated dividing improves banknote validation by using more.The empirical test that we carry out the above-mentioned situation of indication is exactly this situation in fact.Cause better performance based on being segmented in the detection counterfeit money of morphological characteristic such as pattern, color and texture.Yet, in the time will being applied to train each image in the set, be difficult to use described traditional images dividing method such as the traditional images dividing method that uses edge detector.This is because each training set entry is obtained different results, and is difficult to aim at the individual features in the different training integrated images.For fear of the problem of aiming at segmentation, in a preferred embodiment, we use and are called as " time-space image decomposition ".

Provide the details of cutting apart the method for mapping about formation now.On summary, this method can be considered to specify how the plane of delineation is divided into a plurality of segmentations, and each segmentation comprises a plurality of specified pixels.As mentioned above, described segmentation can be discontinuous.For example, based on writing this instructions from the information of all images in the training set.On the contrary, use the cutting apart of strict network need be from the information of image in the training set.

For example, each cut apart mapping comprise with all images during training is gathered between the relevant information of relation of respective image element.

Think that the image in the training set piles up mutually and aims in same orientation.Obtain the given pixel in the banknote image plane, this pixel is considered to have " pixel intensity profile (profile) ", and described pixel intensity profile comprises the information about the pixel intensity of the specific pixel location in each training integrated images.Use any suitable cluster (clustering) algorithm, the location of pixels in the plane of delineation is clustered into segmentation, the location of pixels in described segmentation has similar or relevant pixel intensity profile.

In preferred exemplary, we use these pixel intensity profiles.Yet, be not to use the pixel intensity profile.Also can use other information from all images in the training set.For example, the mean value of the pixel intensity of the pixel of same position in the brightness profile of the piece of 4 neighbors or each the training integrated images.

The concrete preferred embodiment of the method for mapping is cut apart in the formation of describing us now in detail.This is based on the method for instructing in the following publication: Lecture Notes in ComputerScience (computer science teaching materials), 2352:747-758, Avidan in 2002, " EigenSegments:A spatio-temporal decomposition of an ensemble ofimages (peculiar segmentation: the space-time of image assemblage decomposes) " of S..

Given image assemblage (the ensemble) { I that has aimed at and be scaled to identical big or small r * c _i}=1,2, Λ, N, each image I _iCan be represented as [α with vector form by its pixel _1i, α _2i, Λ, α _Mi] ^T, wherein, α _Ji(j=1,2, Λ M) is the brightness of j pixel in i the image, M=rc is the total quantity of pixel in the image.Then can be by piling up the vectorial I of all images in (stacking) assemblage _i(using average to make zero) produces design matrix

Therefore, A=[I ₁, I ₂, Λ, I _N].Row vector [α among the A _J1, α _J2, Λ, α _JN] can be regarded as the brightness profile of the specific pixel (j) of N image.If two pixels are from the model identical zone of image, then they may have similar brightness value, and therefore have strong temporal correlation.Notice that the term here " time " does not need accurately corresponding with time shaft, but using this term " time " indicates the axle that passes different images in the assemblage.Our algorithm is attempted finding these correlativitys, and will be divided into the zone of the pixel with similar time behavior on the plane of delineation space.We measure this correlativity by the matrix between the definition brightness profile.Plain mode is to use Euclidean distance, and promptly the temporal correlation between two pixel j and the k can be represented as $d(j,k)=\sqrt{{\mathrm{\Σ}}_{i=1}^N{(a_{\mathrm{ji}}-a_{\mathrm{ki}})}^2}.$ (j, k) more little, the correlativity between two pixels is strong more for d.

In order to use the temporal correlation between the pixel spatially to decompose the plane of delineation, we carry out clustering algorithm to pixel intensity profile (row of design matrix A).This with related pixel on the generation time bunch.The most direct selection is to adopt the K mean algorithm, but can be any other clustering algorithm.As a result, the plane of delineation is divided into the plurality of segments of last related pixel of time.Then, can use this segmentation to cut apart all images in the training set as template; And the feature of extracting in can those segmentations about all images from training set is come the structural classification device.

Realize training, preferably one-class classifier in order not utilize counterfeit money.Can use the one-class classifier of any adequate types well known in the prior art.For example, based on the one-class classifier of neural network with based on the one-class classifier of adding up.

The suitable statistical method that is used for the classification of single class is based on usually from target class and extracts log-likelihood ratio maximization under the null hypothesis of the observed reading of being considered, and these methods comprise that the hypothetical target class is the D of multivariate Gaussian distribution ²Check (at Morrison, is described among the DF:MultivariateStatistical Methods (Multivariable Statistical Methods) (third edition).McGraw-Hill publishing company, New York, 1990).Under the situation of any non-Gaussian distribution, can mix (at Bishop by half parameter of using Gauss for example, CM:Neural Networks for PatternRecognition (neural network that is used for pattern-recognition) describes, the Oxford University Press, New York, 1995) or the nonparametric handkerchief once (Parzen) window (at Duda, RO, Hart, PE, Stork, describe among the DG:Pattern Classification (pattern classification) (second edition), John Wiley and Sons, INC, New York, 2001) come the density of estimating target class, and can pass through such as sample certainly (bootstrap) (at Wang, S, Woodward, WA, Gary, people such as HL: describe among the A newtest for outlier detection from a multivariate mixture distribution (the new check that exceptional value detects from Multivariate Mixed distributes), Journal of Computationaland Graphical Statistics (calculate and figure add up periodical), 6 (3): 285-299,1997) Sampling techniques obtain the distribution of the log-likelihood ratio under the null hypothesis.

Can be that the support vector data field is described (SVDD) (at Tax to single class adoptable additive method of classifying, DMJ, Duin, describe among the RPW:Support vector domain description (description of support vector territory), Pattern Recognition Letters (pattern-recognition wall bulletin), 20 (11-12): 1191-1199,1999), also have known " supporting to estimate (supportestimation) " (at Hayton, P, Scholkopf, B, Tarrassenko, L, Anuzis, describe among the P:Support Vector Novelty Detection Applied to Jet Engine VibrationSpectra (support vector that is applied to the jet engine vibrational spectra newly detects), Advances in Neural Information Processing Systems (the neural network information handling system is entered rank), 13, eds Leen, Todd K and Dietterich, Thomas G and Tresp, Volker, MIT Press, 946-952,2001) and extreme value theory (EVT) (at Roberts, .IEE Proceedings on Vision, Image ﹠amp are described among the SJ:Novelty detection using extreme value statistics (using the new detection of statistics of extremes); Signal Processing (about the IEE minutes of vision, image and signal Processing), 146 (3): 124-129,1999).In SVDD, estimate the DATA DISTRIBUTION of support, EVT estimates the distribution of extreme value simultaneously.To this application-specific, use a large amount of genuine notes samples, therefore, in this case, can obtain the reliable estimation that target class distributes.Accordingly, in a preferred embodiment, we select clearly to estimate single class sorting technique of Density Distribution, although this is dispensable.In a preferred embodiment, we use the D based on parameter ²Single class sorting technique of check.

In a preferred embodiment, the statistic test of hypothesis that is used for our one-class classifier is described in detail as follows:

Suppose that N is independent, equally distributed p dimensional vector sample (characteristic set of each bank note) x ₁, Λ, x _N∈ C has the basis density function p (x| θ) about parameter θ.To new some x _N+1Provide following test of hypothesis, so that H ₀: x _N+1∈ C, and $H_1:x_{N+1}\∉C,$ Wherein, C represents that null hypothesis is genuine zone, and defines C by p (x| θ).Suppose that distribution under the alternative hypothesis is uniformly, the normal state log-likelihood ratio of so invalid and alternative hypothesis

$\mathrm{\λ}=\frac{\underset{\mathrm{\θ}\∈\mathrm{\Θ}}{\sup }{L}_0\left(\mathrm{\θ}\right)}{\underset{\mathrm{\θ}\∈\mathrm{\Θ}}{\sup }{L}_1\left(\mathrm{\θ}\right)}=\frac{\underset{\mathrm{\θ}}{\sup }{\mathrm{\Π}}_{n=1}^{N+1}p\left(x_n\right|\mathrm{\θ})}{\underset{\mathrm{\θ}}{\sup }{\mathrm{\Π}}_{n=1}^N\left(x_n\right|\mathrm{\θ})}---\left(1\right)$

The test statistics that can be used as null hypothesis.In the preferred embodiment, we can use the test statistics of log-likelihood ratio as the checking of the bank note that is used for up-to-date appearance.

1) have the proper vector of multivariate gaussian density: the proper vector of supposing to describe the indivedual points in the sample is multivariate Gauss, whether the every bit from the check assessment sample that above likelihood ratio (1) occurs shares COMMON MEAN ((is being described among the Morrison, DF:Multivariate StatisticalMethods (Multivariable Statistical Methods) (third edition).McGraw-Hill publishing company, New York, 1990)).Suppose that N is independent, equally distributed p dimensional vector sample x1, Λ, x _NFrom the multivariate normal distribution with average μ and covariance C, its sample estimation is With The option table at random of sample is shown x ₀, relevant square Ma Shi (Mahalanobis) distance

${\mathrm{<figure-callout\; id="2"\; label="D"\; filenames="S2006800475165E00011.png"\; state="\{\{state\}\}">D</figure-callout>}}^2={(x_0-{\widehat{\mathrm{\&mu;}}}_N)}^T{\hat{C}}_N^{-1}(x_0-{\widehat{\mathrm{\&mu;}}}_N)---\left(2\right)$

Can be expressed as being distributed as the center F with p and N-p-1 degree of freedom distributes

$F=\frac{(N-p-1){\mathrm{ND}}^2}{p{(N-1)}^2-\mathrm{Np}{D}^2}---\left(3\right)$

Then, if

F＞F _{α；p，N-p-1} (4)

Common population mean vector x then ₀With residue x _iNull hypothesis will be rejected, wherein, F _{α; P, N-P-1}Be to have degree of freedom (p, last α 100% point that F N-p-1) distributes.

Hypothesis is selected x now ₀As having maximum D ²The observation vector of statistic.From size is the maximum D of the random sample of N ²Complex distribution.Yet, can obtain the conservative approximate value of percent 100 α on this critical value by Bao Falongni (Bonferroni) inequality.Therefore, if

$F>F_{\frac{\mathrm{\&alpha;}}{N};p,N-p-1}---\left(5\right)$

Then we can conclude x ₀It is exceptional value.

In fact, equation (4) and equation (5) all can be used for the exceptional value detection.

As additional data x _N+1But the time spent, in the check of the new samples that designs the part that does not form crude sampling, we can use the increment of following average and covariance to estimate, i.e. average

${\widehat{\mathrm{\&mu;}}}_{N+1}=\frac{1}{N+1}\{N{\widehat{\mathrm{\&mu;}}}_N+x_{N+1}\}---\left(6\right)$

And covariance

${\hat{C}}_{N+1}=\frac{N}{N+1}{\hat{C}}_N+\frac{N}{{(N+1)}^2}(x_{N+1}-{\widehat{\mathrm{\&mu;}}}_N){(x_{N+1}-{\widehat{\mathrm{\&mu;}}}_N)}^T.---\left(7\right)$

By using expression formula (5) and (6) and matrix inversion theorem, the equation (2) that is used for N sampling reference set and N+1 check point becomes

${\mathrm{<figure-callout\; id="2"\; label="D"\; filenames="S2006800475165E00011.png"\; state="\{\{state\}\}">D</figure-callout>}}^2={\mathrm{\&sigma;}}_{N+1}^T{\hat{C}}_{N+1}^{-1}{\mathrm{\&sigma;}}_{N+1}---\left(8\right)$

Wherein,

${\mathrm{\&sigma;}}_{N+1}=(x_{N+1}-{\widehat{\mathrm{\&mu;}}}_{N+1})=\frac{N}{N+1}(x_{N+1}-{\widehat{\mathrm{\&mu;}}}_N)|---\left(9\right)$

${\hat{C}}_{N+1}^{-1}=\frac{N+1}{N}({\hat{C}}_N^{-1}-\frac{{\hat{C}}_N^{-1}(x_{N+1}-{\widehat{\mathrm{\&mu;}}}_N){(x_{N+1}-{\widehat{\mathrm{\&mu;}}}_N)}^T{\hat{C}}_N^{-1}}{N+1+{(x_{N+1}-{\widehat{\mathrm{\&mu;}}}_N)}^T{\hat{C}}_N^{-1}(x_{N+1}-{\widehat{\mathrm{\&mu;}}}_N)})---\left(10\right)$

Pass through D _{N+1, N} ²Represent

Then

${\mathrm{<figure-callout\; id="2"\; label="D"\; filenames="S2006800475165E00011.png"\; state="\{\{state\}\}">D</figure-callout>}}^2=\frac{{\mathrm{ND}}_{N+1,N}^2}{N+1+D_{N+1,N}^2}---\left(11\right)$

So, can be according to the average of common estimation

And covariance

Estimation and the normal distribution of hypothesis check new some x _N+1Although find that the hypothesis of multivariate Gauss feature vector is that suitable practicality is selected to many application, the hypothesis of multivariate Gauss feature vector is false in fact usually.In the part below, we abandon this hypothesis, and consider any density.

2) has the proper vector of any density: by (for example using any half suitable parameter well known in the prior art, gauss hybrid models) or nonparametric (for example, handkerchief is the window method once) density estimation method, can be from the finite data sample that from any density p (x), extracts

The acquisition probability density is estimated

Then, in calculating log-likelihood ratio (1), can adopt this density.Different with the situation of multivariate Gaussian distribution, under null hypothesis, there is not the analysis distribution of test statistics (λ).So, in order to obtain this distribution, can adopt the other non-analysis ineffective distribution of numeral under the density that abstracting method obtains to estimate, so, various critical values set up can distributing from the experience that obtains

As if as can be seen, at ultimate value N → ∞, than can be by with the estimation of getting off

$\mathrm{\&lambda;}=\frac{\underset{\mathrm{\&theta;}\&Element;\mathrm{\&Theta;}}{\sup }{L}_0\left(\mathrm{\&theta;}\right)}{\underset{\mathrm{\&theta;}\&Element;\mathrm{\&Theta;}}{\sup }{L}_1\left(\mathrm{\&theta;}\right)}\&RightArrow;\hat{p}(x_{N+1};{\widehat{\mathrm{\&theta;}}}_N)---\left(12\right)$

Wherein,

Be illustrated in the x under the model of estimating by original N sample _N+1Probability density.

Gather the parameter of sampling in vain and using its estimation Density Distribution at the B that produces N sample from reference data set

Afterwards, can be by selecting N+1 sample at random and calculating

Obtain the test statistics that B duplicates from sampling

Right by mode with ascending order

Ordering can limit critical value α, thus if λ≤λ _α, then refuse null hypothesis, wherein λ in the level of signifiance of expectation _αBe

J minimum value, and α=j/ (B+1).

Preferably, be different segments, repeat to form the method for sorter, and use the image of the bank note of the known true and false to test.Then, selection provides the quantity of the segmentation of optimum performance, and uses the sorter of the segmentation of described quantity to be used.We find that although can use the segmentation of any suitable quantity, the optimal number of segmentation approximately is from 2 to 15.

As mentioned above, particular problem relate to identification and the image of the bank note that replaces being verified in the abnormal image element.Fig. 3 is with decision-making. neutral-data replaces the process flow diagram of the processing of abnormal image element.For each pictorial element (square frame 300), for example pixel, pixel groups are obtained the distribution (square frame 301) of framing.Described distribution is the estimation distribution that described framing is spreaded all over all images of gathering in the training of image.As mentioned above, the training of image set can be a plurality of images of genuine notes.For example, described distribution can be the brightness profile of the piece of pixel intensity profile or four pixel location, or as above-mentioned similar.Preferably, described distribution is identical with employed distribution during the processing of cutting apart mapping that is formed for biil validator as mentioned above.Because estimated described distribution,, and ask when having saved so this has reduced to assess the cost.

Then, based on the level of signifiance (also being called as degree of confidence) selective value from the distribution of obtaining (square frame 302).The described level of signifiance is relevant with the level of signifiance of the sorter that uses in biil validator.For example, the described level of signifiance is identical with the level of signifiance that sorter uses.Because the level of signifiance is relevant with the level of signifiance of sorter, so obtain decision-making-neutral-data by selective value by this way.Then, the value (referring to square frame 303) that replaces abnormal image element place with selected value.By using decision-making-neutral-data by this way, we guarantee the classification results of the remainder indication biil validator of bank note.This is better than classic method, and for described classic method, disappearance or insecure data mean on the genuine notes, will suffer false acceptance rate for avoiding many False Rejects.By this way, we need not to revise the processing of core banknote validation and just can successfully solve damage, shabby, that tear is arranged or that part is faded bank note.The just pre-service of required banknote image.In addition, this is implemented under the situation of false acceptance rate not being traded off.

Fig. 4 is a synoptic diagram of creating the equipment 20 of the sorter 22 that is used for banknote validation.It comprises:

Import 21, be configured to visit the training set of banknote image;

Processor 23 is configured to use training set image creation to cut apart mapping;

Dispenser 24 is configured to use cut apart to shine upon and cuts apart each training integrated images;

Feature extractor 25 is configured to extract one or more features from each segmentation of each training integrated images; And

Classification forms device 26, is configured to use characteristic information and forms sorter; Wherein, configuration processor is to cut apart mapping based on creating from the information of all images in the training set.For example, by using above-described picture breakdown when empty.

Fig. 5 is the synoptic diagram of biil validator 31.It comprises:

Import, be configured to receive at least one image 30 of the bank note that to be verified;

Cut apart mapping 32;

Processor 36 is configured to unusual in the recognition image;

Amending image device 37 is configured to by generating the unusual image that forms modification that the data replacement identifies with neutral decision-making, and the described data that generate data as the neutrality decision-making are relevant with sorter 35;

Another processor 33 (can be integrated with processor 36) is configured to use cut apart and shines upon the image of cutting apart bank note;

Feature extractor 34 is configured to extract one or more features from each segmentation of banknote image;

Sorter 35 is configured to bank note is categorized as effective or invalid based on the feature of extracting; Wherein, cut apart the relevant information of relation that mapping comprises the respective image element between all images in the training set with the image of bank note.Note, needn't be separate for the device of Fig. 5, these devices can be integrated.

Fig. 6 is the process flow diagram of the method for checking bank note.Described method comprises:

Visit is with at least one image (square frame 40) of the bank note that is verified;

Identification abnormal image element (square frame 41);

Replace abnormal image element (square frame 42) with the decision-making neutral-data;

Mapping (square frame 43) is cut apart in visit;

The image (square frame 44) that bank note is cut apart in mapping is cut apart in use;

From each segmentation of banknote image, extract feature (square frame 45);

Use sorter bank note to be categorized as effective or invalid (square frame 46) based on the feature of being extracted;

Wherein, cut apart mapping be based on the training image of bank note set in each image-related information form.Can be with any suitable order well known in the prior art or the step of these methods of combination execution.Cut apart mapping can imply comprise with training set in each image-related information, this is cut apart mapping because can form based on described information.Yet the information that implies in cutting apart mapping can be the simple files with pixel address tabulation, and it will be included in each segmentation.

Fig. 7 is the synoptic diagram with self-service equipment 51 of biil validator 53.It comprises:

Be used to accept the device 50 of bank note;

Be used to obtain the imaging device 52 of the digital picture of bank note;

Be used for the processor 54 that decision-making-neutral-data replaces abnormal image; And

Aforesaid biil validator 53.

Can carry out method described herein to image or other performances of bank note, described image/performance is any adequate types.For example, image or aforesaid other images on redness, blueness and the green channel.

Can be only form and cut apart based on the image of a type (such as red channel).Selectively, can form based on the image of all types (such as red, blueness and green channel) and cut apart mapping.Also can form a plurality of mappings of cutting apart, cut apart mapping being combined to form of every kind of image or multiple image type is a kind of.For example, can there be three to cut apart mapping, cut apart mapping for one and be used for the red channel image, cut apart mapping for one and be used for the blue channel image, cut apart mapping for one and be used for the green channel image.In this case, during the checking of single bank note, use the suitable mapping/sorter of cutting apart according to the type of selected image.Therefore, can revise each method in the said method by using dissimilar images and cutting apart mapping/sorter accordingly.

The same with imaging device, the device that is used to accept bank note is any adequate types well known in the prior art.Can use any feature selecting algorithm well known in the prior art to select one or more features in extracting characterization step, to use.In addition, except that characteristic information discussed here, also can form sorter based on the customizing messages relevant with the special denomination of bank note or Currency Type.For example, with the information in the zone of significantly enriching, shape or the spatial frequency in given Currency Type and denomination in data aspect the color.

For the technician is obvious, under the situation of not losing effect, can expand or change given any scope or device value here.

Should be appreciated that only provided the above description of preferred embodiment as example, those skilled in the art can carry out various modifications.

Claims (23)

1. the method for the image of a treatment media object comprises:

(i) unusual in the image of the described dielectric object of identification;

(ii), generate the data of data and generate processing relevant as the decision-making that preassigned dielectric object checking is handled as the neutrality decision-making by generating the unusual image that forms modification that the data replacement identifies with neutral decision-making.

2. the unusual step in the described image of the method for claim 1, wherein described identification comprises the application bandpass filter.

3. the method for claim 1, wherein, described method comprises: for each abnormal image element, distribute by obtaining the estimation that framing spreads all in all images of the training set of the image of dielectric object, and from described estimation distributes selective value, obtains described neutral decision-making generation data.

4. method as claimed in claim 3, wherein, described value is selected from described estimation distributes based on the level of signifiance, and the described level of signifiance is the level of signifiance that described preassigned dielectric object checking is handled.

5. method as claimed in claim 3, wherein, the training of the image of described dielectric object set includes only the image of true dielectric object.

6. method as claimed in claim 3, wherein, described distribution is based on that the pixel intensity profile estimates.

7. the method for claim 1, wherein described preassigned dielectric object checking is handled and is comprised the use one-class classifier.

8. the method for claim 1 further comprises: the image of described modification is offered described preassigned dielectric object checking processing as input.

9. the method for claim 1, wherein comprise situation damage, shabby, that tear is arranged or the dielectric object that part is faded unusually in the image of described dielectric object.

10. the equipment of the image of a treatment media object, described equipment comprises:

(i) processor is configured to discern unusual in the image of described dielectric object;

(ii) the amending image device is configured to generate the data of data and generate processing as the decision-making that preassigned dielectric object checking is handled relevant by generating the unusual image that forms modification that the data replacement identifies with neutral decision-making as the neutrality decision-making.

11. equipment as claimed in claim 10, wherein, described processor comprises the unusual bandpass filter that is used for discerning described image.

12. equipment as claimed in claim 10, wherein, described amending image device is arranged to: for each abnormal image element, distribute by obtaining the estimation that framing spreads all in all images of the training set of the image of dielectric object, and from described estimation distributes selective value, obtains described neutral decision-making generation data.

13. equipment as claimed in claim 12, wherein, described amending image device is arranged to: select described value based on the level of signifiance from described estimation distributes, the described level of signifiance is the level of signifiance that described preassigned dielectric object checking is handled.

14. equipment as claimed in claim 12, wherein, described amending image device is arranged to based on the pixel intensity profile estimates described distribution.

15. equipment as claimed in claim 12, wherein, described configuration image modifier is arranged to: estimate described distribution from the image training set of the image that includes only true dielectric object.

16. equipment as claimed in claim 10 comprises biil validator, and wherein, described configuration image modifier is arranged to: the image of described modification is input to described dielectric object validator.

17. equipment as claimed in claim 16, wherein, described dielectric object validator comprises one-class classifier.

18. equipment as claimed in claim 10, wherein, comprising unusually in the image of described dielectric object be damage, shabby, situation tear or the dielectric object that part is faded is arranged.

19. a dielectric object validator comprises:

(i) import, be configured to receive at least one image of the dielectric object that to be verified;

(ii) processor is configured to discern unusual in the image of described dielectric object;

(iii) the amending image device is configured to by generating the unusual image that forms modification that the data replacement identifies with neutral decision-making, and the data that generate data as the neutrality decision-making are relevant with the sorter of described dielectric object validator;

(iv) cut apart mapping;

(v) processor is configured to use the described image that described dielectric object is cut apart in mapping of cutting apart;

(vi) feature extractor is configured to extract one or more features from each segmentation of the image of described dielectric object;

(vii) sorter is configured to based on the feature of extracting described dielectric object be classified

Wherein, described cut apart mapping comprise with the set of the training image of dielectric object in the relevant information of relation of respective image element between all images.

20. dielectric object validator as claimed in claim 19, wherein, described amending image device is arranged to: for each abnormal image element, distribute by obtaining the estimation that framing spreads all in all images of the training set of the image of dielectric object, and from described estimation distributes selective value, obtains described neutral decision-making generation data.

21. dielectric object validator as claimed in claim 19, wherein, comprising unusually in the image of described dielectric object be damage, shabby, situation tear or the dielectric object that part is faded is arranged.

22. a self-service equipment comprises:

(i) be used to accept the device of dielectric object;

(ii) be used to obtain the imaging device of the digital picture of described dielectric object; And

(iii) dielectric object validator comprises:

(i) import, be configured to receive at least one image of the dielectric object that to be verified;

(ii) processor is configured to discern unusual in the image of described dielectric object;

(iii) the amending image device is configured to by generating the unusual image that forms modification that the data replacement identifies with neutral decision-making, and the data that generate data as the neutrality decision-making are relevant with the sorter of dielectric object checking;

(iv) cut apart mapping;

(v) processor is configured to use the described image that described dielectric object is cut apart in mapping of cutting apart;

(vi) feature extractor is configured to extract one or more features from each segmentation of the image of described dielectric object;

(vii) sorter is configured to based on the feature of extracting described dielectric object be classified;

Wherein, described cut apart mapping comprise with the set of the training image of dielectric object in the relevant information of relation of respective image element between all images.

23. equipment as claimed in claim 22, wherein, comprising unusually in the image of described dielectric object be damage, shabby, situation tear or the dielectric object that part is faded is arranged.

Images