RussianPatents.com

Monitoring method

IPC classes for russian patent Monitoring method (RU 2282895):

G07D7/12 - Visible light, infra-red or ultra-violet radiation

G06K9/62 - Methods or arrangements for recognition using electronic means

Another patents in same IPC classes:

Protective system, in particular for valuable documents / 2282244
Protective system in case of falling light can reconstruct a pattern outside the plane of carrier in holographic way, which pattern contains concealed information. System contains surface, at least partially transparent verification element, which in case of surface contact with protective element allows reading of information stored in it.

Device for checking authenticity of bank notes / 2274900
Device has at least two groups of emitters of testing radiation, while all emitters of testing radiation in each group emit testing radiation of one frequency, which in each group is different from testing emission frequency of any one of remaining groups; set-point generator, meant for generation of periodic oscillations, each one of each serves for enabling appropriate group of test radiation emitters to provide for enabling current group only in time, when emitters of remaining groups are disabled; and receiver of reflected emission, made with possibility of receiving testing radiation with frequency of testing radiation of each group. As a result, blinking effect of protective element image can be observed on monitor screen.

Method for determining authenticity of bank notes and device for realization of said method / 2271576
Method includes measuring brightness of light streams, reflected from bank note lighted at several different angles. As portions for comparing brightness levels reflected from controlled bank note, on background of which transverse stripe is applied with reflection coefficient, exceeding background reflection coefficient, on which it was applied, aforementioned background is utilized and fragments of bank note also with level of brightness exceeding those of main background.

Device for identification of an object / 2268495
In device, due to use of acoustic-optical adjustable filter, a stream of optic emission is generated, lighting the surface of object with given values of section range, and also due to absence of necessity for mechanical movement of photo-detecting device.

Method and device for checking authenticity of sealed objects / 2268494
Method includes detection of emission, radiating from checked object in spectrum zones, which are outside visible spectrum area. To make possible reliable and comfortable for user authenticity check, emission radiated from object is detected at several portions of object in at least two selected spectrum areas with receipt of row of measured values for each of these spectrum areas, two rows of measured values are synchronized between each other and then authenticity of object is checked by comparison of two mutually synchronized rows of measured values. The most compact, comfortable simply adjustable device is characterized by at least one diaphragm between object and emission receiver, allowing setting of dimensions of checked and thus controlled portion on target object.

Visual angle-depending color-shift pigment, method of manufacturing such pigments, employment of these pigments in applications associated with protection, composition of coating containing these pigments, and detection device / 2259379
Invention aims at protecting bank notes and security papers against counterfeiting. Optically changing pigment contains interferential multilayer structure including light-transmitting dielectric layer having at least one luminescent material. Dielectric layer is selected from of rare-earth metal, bismuth, and principal group III element trifluorides; of principal group II element difluorides; mixtures thereof; organic or organometallic compounds. Luminescent material should be selected from organic or organometallic compounds containing transition or rare-earth metal ions. Above-defined structure may contain one or more semitransparent, partly reflecting layers, one or more nontransparent, fully reflecting layers, and one or more conducting layers. Pigment is prepared by a method including physical or chemical precipitation of the dielectric layer.

Luminescent compound for marking and identification of marking of document by means of this compound / 2253665
Proposed compound is prepared by mixing gadolinium oxysulfide activated by terbium and yttrium oxysulfide activated by ytterbium and erbium. Size of crystal particles of said luminophores does not exceed 1.5 mcm. Compound thus prepared is introduced into printing ink and is applied on surface to be marked by letterpress printing method in form of mark which is invisible at common lighting. Mark is visualized by infra-red light source and/or ultraviolet radiation thus causing its green glow. Document is subjected to identification for estimation of its authenticity of falsification. Marking retains preset properties for extended period of time at high temperatures, bright light and high moisture content.

Method for preventing unsanctioned access to system being protected / 2282240
Method includes determining coordinates of certain specifics of papillary pattern of user and on basis of difference of coordinates of produced image of print and one stored in database, positive or negative decision is produced about access of user to system.

Method for recognition of papillary patterns / 2279129
Method includes stage of generation of papillary pattern passport with further placement of the latter into computer memory, and stage of comparison of given papillary pattern to passport of papillary patterns, which utilization procedure for comparing two sets of values of electric parameters with arbitrary number of characteristic points, which is performed by full search of sets of characteristic parameters of all characteristic points. In process of full search of sets of coordinates and characteristic parameters, values of electric parameters are selected, matching in two sets, on basis of numbers of coincidences a signal is generated about match of compared sets of electric parameter values.

Method for recognition of papillary pattern / 2279128
Method includes generation of three passports, including an additional statistical one and determinate one. Successive execution of comparison procedures of given papillary patterns received from papillary pattern indicator with passports makes it possible to shorten total duration of recognition procedure due to taking a decision about recognition of papillary patter at early stages while satisfying recognition clarity criterions.

Method for recognition of images in optical-digital correlators / 2277257
Method for recognition of images in optical-digital correlators includes procedures for input of amplitude distributions of standard and compared objects into correlator, transformation of these distributions to synthesized phase distributions, receiving correlation between them, registration of received recognition signal and estimation of recognition result, distributions of standard and compared objects, related to arbitrary type objects, are unambiguously matched with phase random distributions Ψ_st(x,y), Ψ(x,y), synthesized from distributions of standard and compared objects and starting phase distribution Ψ_o(x,y), utilized further during recognition in optical-digital correlator instead of real objects.

Method for facsimile recognition and reproduction of printed product text / 2260208
Method includes conversion of recognized and standard images to digital form, their digital processing by determining coordinates, comparison and determining of match of recognized and standard contours. Determining of coordinates of line of characteristic contour of recognized image of symbol is performed using appropriate standard graphic image by finding value of coordinates X, Y, angle β of position of optical center of text symbols by superposition along area of printed area of digital images - in straight contrast of standard on appropriate recognized in reversed contrast.

Portable device for scientific identity identification / 2257613
Device has in case in form of small suitcase, a computer, which is compatible to operation systems meant for using programs of scientific identification. Computer is connected to display and keyboard, it can be connected to printer external relatively to case, and presumes presence of remote connection to processing center, responsible for identification. Device additionally has fingerprint reader connected to computer and digital camera connected to computer.

Identification device with protected photograph and also means and method for authentication of such an identification device / 2253148
Device has photographic image of a person and microprocessor, which has processor, memory, connected to processor and containing authentication data, and interface means, connected to said processor to organize communication with external device. Said photographic image has specially concealed information, contents of which when combined with said authentication data provides for authentication of said photographic image, and said microprocessor is made with possible realization of at least a portion of said authentication.

Method for identification of crossed symbols during recognition of hand-written text / 2251736
Method includes dividing image on areas, finding areas with hand-written symbols, using structural and sign classifiers for recognition of symbols, use of structure classifier as main recognition tool, selecting best suiting symbol of several variants.. recognition of symbol includes recognition of symbol by at least one additional sign classifier of crossed symbols, performing concurrent comparison to crossed symbol and at least one common symbol like the latter, and identification of symbol as crossed one in case of better compliance to signs of crossed symbols.

Automatic recognition of symbols on structural background by combination of models of symbols and background / 2249251
Method includes following stages: tuning, forming symbols models, recognition, recording background model together with background of read image, separating model of registered background from elementary image of background, combining for each position of symbol of model of letters and/or digits with elementary displaying of appropriate background, forming of combined models, comparison of unknown symbols to combined models, recognition of each unknown symbol as appropriate symbol, combined model of which is combined with it best in accordance to "template comparison" technology.

FIELD: method for monitoring marks, made on printed documents.

SUBSTANCE: method includes making a digital image of front side of document by determining content of one-color and multi-color components of image pixels, content of color component of each pixel is compared to range from upper to lower thresholds for appropriate pixel of acceptable unmarked document and appropriate abnormal pixel is generated, if value of pixel is outside interval between upper and lower thresholds, then presence of mark different from dirt is detected, if abnormal pixels produced as a result satisfy previously set conditions.

EFFECT: provision of possible determining of some or other forms of distortion of document.

3 cl, 6 dwg

The present invention relates to a method of monitoring instruments, in particular to the monitoring of marks made on a paper document.

In some applications there is a need for detection of marks, such as graffiti pictures or labels)made on pre-printed documents, such as important documents, including the banknotes and the like. This must be distinguished from the detection of the degree of pollution because the pollution is usually distributed according to a document mostly evenly, while the notes to which this invention relates include line, area distortion, such as ink stains, etc.

EP-A-0165734 discloses a method for comparing the incoming Bank notes with the reference pattern in such a way that take into account changes in the form of a single pixel. However, it should be noted that this applies only to the verification of documents (or objects)that were not in circulation.

US-A-6012565 describes the classification of documents, but has no relation to the detection of the marks on the documents.

WO-A-00/26861 has to do with the recognition of banknotes and also considers the contamination is detected. However, as mentioned above, the detectors contamination is not able to detect the mark, such as graffiti.

According to the present invention a method of monitoring marks, made by the x on printed documents includes obtaining a digital representation of the front side of the document by determining the content of monochrome or multi-color component pixel representation; comparing the content of the color component of each pixel represent the range from the upper to the lower threshold for the corresponding pixel of an acceptable document without notice or generation of the respective anomalous pixel, if the pixel value is outside the range; and determining whether marking, if the resulting anomalous pixels satisfy predetermined conditions.

The invention allows the detection of the mark, such as graffiti, and allows you to determine the level of graffiti. This provides the user the ability to be more (or less) resistant to specific forms of distortion.

Usually for each pixel is determined by a single color component or the value of the grey levels, but in more complex examples can be obtained represent color components of each pixel.

The upper and lower thresholds can be obtained in various ways. For example, can be tested by the one or more documents, without notice and determined the average value for each pixel. These average values can then be modified by adding an appropriate number or multiplying by on the walking number to obtain the upper and lower thresholds. Alternatively, can be analyzed a set of documents without notes, used and unused, and the stored record, at least of the least brightest and most colourful values for each pixel, which can then be used to determine the lower and upper thresholds.

In a preferred approach, the captured image representative sample set of banknotes in circulation, and they must not contain misrepresentations. In this set are the darkest pixels in each position, x, and y are used to determine the lower bounding image (level). A similar method using the brightest pixels is used to obtain the upper limiting image (level).

These stored values can then be further modified using multiplicative or additive factors to obtain the final upper and lower thresholds before they are compared with the input pixel values.

After the anomalous pixels are identified, the method tries to determine whether satisfied or not one or more pre-defined conditions. Such predefined conditions may be chosen from:

(a) the total number of abnormal pixels is greater than the "total" (total) in the exhaust gas;

b) the total number of abnormal pixels in the overlay, with the ratio of perimeter to area greater than the first predetermined parameter is greater than the threshold "sprawl" (rare);

C) the total number of abnormal pixels in the overlay, with the ratio of perimeter to area is less than the second predefined parameter is greater than the threshold of "compact";

g) the total number of abnormal pixels within a certain distance from another of the abnormal pixel is greater than the threshold of "sgruppirovannoe".

Usually defined each of these conditions, and the presence of more than one indicates a positive result, thus pointing to the presence in the document of a particular type of graffiti or other markings. The user can then decide whether the level of markup is valid for, in the case of banknotes, the banknotes were sent to re-treatment, or invalid, and in this case, the banknote should be withdrawn from circulation.

Although views are visible under normal lighting, they may include, instead of or together with this view, visible with the invisible in normal lighting conditions, such as ultraviolet or infrared.

The invention is applicable to a wide range of processes,including sorting, account distribution, checking and recirculation of the documents. It can be used for processing a variety of documents, including documents protected and valuable documents, such as banknotes.

The invention can be implemented using conventional hardware for pattern recognition and is particularly suitable for use in the system of De La Rue Vision™.

Next will be described an example method according to the present invention with reference to the accompanying drawings, where

figure 1 is a block diagram of a method;

figa-2C illustrate the image of the banknote is of good quality, the image of the banknote, with each pixel having its maximum value, and the image of the banknote, with each pixel having its minimum value, respectively

figa and 3B illustrate examples of the compact arrangement of the pixels and the distributed arrangement of the pixels, respectively.

Figure 1 shows the image 1 of the banknote under test and the corresponding reference image 2 is the same banknote, which should be stored in the memory. In many cases, it is still more than one reference image, for example, corresponding to the same note with different orientation, and also banknotes of various denominations. In order to be able to implement the pic is b, you must first establish a relation between the test image 1 and the reference image 2. After the analyzed image 1 digitized, it can be achieved in various ways, and, for example, is typically accomplished by comparing the position of the known features of printing two images. This is achieved through education one-dimensional "projections" of the average intensities of the pixels in the columns/rows in the directions of the long and short sides of the banknote (phases 3, 4). Then determined by the degree of their correlation with the corresponding projections of the reference image while sequentially changing the position relative to the original. The position at which the maximum level of correlation is considered correct. The measurement result of this positional shift is added to the sample image 1 when compared with the limiting images at subsequent stages.

For each reference image 2, the system stores the corresponding lower bounding the image 5 and the upper bounding the image 6. They are shown in more detail in figs and 2B, respectively, together with the image of the banknote, good quality, relevant reference image 2 shown in figa.

The contents of each pixel of the upper bounding image 6 obtained by the obsledovanie a large number of genuine banknotes and write the most brilliant value for each pixel in the group of notes. Similarly, the lower bounding the image 5 is obtained by recording the least bright or lowest values in the group for each pixel.

Then the version of the analyzed image 7 with the adjusted position is compared, pixel by pixel, with the lower and upper limiting images 5, 6. If the amplitude of a pixel with position (x₁,₁on the examined image is larger than the amplitude of the corresponding pixel position (x₁,₁upper bounding the image, then the pixel is classified as an abnormal pixel, which leads to the installation of a pixel with position (x₁,₁in the abnormal image 10. The same test is applied to the analyzed image and the lower bounding the image, i.e. if the amplitude of the analyzed pixel image is smaller than the amplitude of the pixel of the lower bounding the image, then set the abnormal pixel.

The result of this process is the generation of abnormal images 10, where you can see that the mark 11 on the analyzed image 1 identified. However, in order to produce a detection mark, an additional analysis of the anomalous image 10. This process is viewed and categoryseries each anomalous pixel. The method, therefore, ska the range of the anomalous image pixel by pixel. When there is abnormal pixel is incremented "total" count of pixels graffiti (step 12).

At step 14, visible group of anomalous pixels using test 8-way links to determine their area and perimeter, i.e. the investigated anomalous pixel (Central pixel grid 3×3) directly borders with other abnormal pixel (one or more external pixels in the same lattice 3×3). This allows the pixels in such groups as "distributed" or "compact" based on the ratio of perimeter to area of the group. Figa illustrates a typical example of a group of pixels classified as compact (the ratio perimeter/area = 0,35), and figv illustrates an example of a group of pixels classified as distributed (the ratio perimeter/area = 1,04). This classification is obtained by giving information about the area and the perimeter of the Comparators 15, 16, where the ratio is compared with the parameter in this case is 0.6. You do not want the settings were the same. Depending on the results of these comparisons are incremented or counter compactness or counter distribution.

After determining (step 13) the distance between the anomalous pixel and other anomalous pixel, this distance is compared with a threshold close to e is up 19, and, if the distance is less than the threshold proximity, counter sgruppirovannoe is incremented (step 20).

To obtain the final results, the number of samples defined on the stages 17, 18, 20, then compared with the corresponding thresholds for stages 21-23, respectively, together with the result of comparison of the "total" counter with a threshold (step 24).

These results can then be saved and/or displayed and/or used by the device performing the analysis to determine how to proceed with the bill. For example, Bank notes, which show unacceptable levels of graffiti, may be sent to the station of rejection or to call a stop device.

The threshold is exceeded by the counter "compactness" indicates the presence of spots or other "solid" (solid) distortion; the threshold is exceeded by the counter "distribution" indicates the presence of inscriptions or drawings; and the threshold is exceeded by the counter "sgruppirovannoe" indicates an ordered distortion, such as banking ink stamp.

Of course, the invention may be implemented as software, hardware and firmware, which should be obvious to a person skilled in this technical field.

1. Method of monitoring the marks made on the printed document is Oh, including obtaining a digital representation of the front side of the document by determining the contents of a single color or multi-color component pixel representation, comparing the color component of each pixel with the range varying between the upper and lower thresholds, obtained by analysis of printed documents that are not annotated with information about the least brightest and most colourful values for each pixel and determine their average values for use in determining the lower and upper thresholds, respectively, the generation of the corresponding anomalous pixel, if the value is outside the interval between the upper and lower thresholds, the presence of marks other than dirt, if the resulting anomalous pixels satisfy predefined conditions, selected one or more:

(a) the total number of abnormal pixels is greater than a specified number of total values of the received pixels

b) the total number of abnormal pixels in the overlay, with the ratio of perimeter to area notes, greater than the first predefined parameter distributed anomalous pixels

C) the total number of abnormal pixels in the overlay, with the ratio of perimeter to area of the mark, more than a predefined pairs is Tr a compact anomalous pixels.

2. The method according to claim 1, in which the digital representation of the front side of the document corresponds mind that the front side when the visible light.

3. The method according to claim 1 or 2, wherein the document is a protected document or valuable document such as a banknote.