EP3680106A1 - Mn-detection in a printed image - Google Patents

Abstract

Method for determining printing errors in a printing process, carried out in an inkjet printing machine (7) for processing a print job, by a computer (9), print products (2) generated during the printing process being recorded and digitized using a camera system (10) , the camera image (13) generated in this way is fed to a detection algorithm on the computer (9), upon detection of printing errors (14) a message is sent to a machine control (6), which then, if necessary, ejects the printed product (2) via a waste gate, which characterized in that the detection algorithm separates color separations of the camera images (13), detects the printing errors (14) in the color separations, links images of the individual color separations to a candidate image (21), filters the candidate image (21) and finally the remaining detected printing errors ( 14) in a list and this to the machine control (9) of the printing press (7) se finds.

Description

The present invention relates to a method for checking the print quality of an inkjet printing machine using a camera and a computer.

The invention is in the technical field of digital printing.

When operating inkjet printing machines, there are specific printing errors that are specific to this type of printing machine. The most common are so-called whiteline errors, which arise when individual print nozzles of the inkjet print heads used deviate from their desired standard behavior. If this deviation exceeds certain limits, the relevant printing nozzles are generally deactivated because they disturb the printed image. However, a pressure nozzle deactivated in this way then generates a corresponding whiteline error. This is so called because it stands out most clearly in the case of a single-color printed area, because in this case the underlying printing substrate, which is usually white, emerges. If, on the other hand, a bright printing ink (e.g. opaque white) is used to print on a dark-looking background, the errors appear as so-called darkline errors. But even in multicolored image areas, where several print nozzles of different print heads print the individual color separations one above the other, the failure or deactivation of a print nozzle involved leads to corresponding color distortions in the print image to be generated. Since the printing nozzles emit ink in a line-like manner in the printing direction, the printing error generated also becomes linear, which gives rise to the term white / darkline printing error.

The reasons for the occurrence of these deviations in the operation of pressure nozzles can be of various kinds. One of the main problems here is that the ink dries out if the corresponding printhead is not used for too long and is not stored properly in the idle state. The drying ink clogs the nozzle outlet opening and thus leads to a deviating pressure point of the pressure nozzle in question or, in extreme cases, even to a complete failure. In each In this case, the pressure nozzle no longer prints exactly where the actual pressure point should be and the pressure strength also deviates from the standard values that are actually desired. In addition to dried ink, the ingress of dust particles and similar dirt can also cause whiteline errors.

Several approaches are known from the prior art for locating these whiteline errors. The most common is certainly the printing of test patterns and the detection of the whitelines via an automated recording and evaluation of these test patterns. However, this approach has the disadvantage that printing the test pattern, depending on its position and size, causes waste on the printing substrate. There are therefore methods which examine the printed image itself and then detect whiteline errors which occur from this printed image. This also has the advantage that only those whitelines or pressure nozzles causing them are detected which are really disturbing for the print image currently being generated.

The German patent application DE 2017 220361 A1 discloses such a method for the detection and compensation of failed printing nozzles in an inkjet printing machine by a computer, which is the printing of a current print image, the recording of the printed print image by an image sensor and digitization of the recorded print image by the computer, the addition of digitized color values recorded image of each column over the entire print image height and dividing the total color values by the number of pixels to obtain a column profile, subtracting an optimized column profile without unusual print nozzles from the original column profile to a difference column profile, setting a threshold for maximum values that exceed one failure of the pressure nozzle defines the application of this threshold for maximum values to the difference column profile, whereby each maximum in the resulting column profile marks a failed pressure nozzle and the compensation of the marked pressure nozzle included in the subsequent printing process as steps of the process.

However, a disadvantage of this method is that it cannot be implemented robustly in practice. The process is based on the fact that there are very little differences between one Reference image and a camera image there. In practice, however, this is not always the case. The reasons for this include, for example, incorrectly calibrated cameras, a less than ideal or outdated white balance, different types of paper or less than ideal colors in the printing unit. In addition, areas in the printed image that are occupied as monochrome as possible are used for the detection of the whitelines, which is why the method can only be used to a limited extent in printed images that do not have such areas.

From the U.S. patent US 9,944,104 B2 a whiteline inspection system is known. Here, a simple limit value comparison is proposed for the detection of the whitelines, which assumes that the motif to be checked is homogeneous at the point. In the case of an image that does not meet this condition, it is proposed that the signal be generated by subtracting a locally oriented reference image generated from prepress data. However, a difference image calculation is still necessary.

The patent application EP 3300907A1 describes, on the other hand, how a whiteline detection system can achieve an increased quality depending on the pressure situation, in particular to avoid the detection of weak and therefore uncritical whitelines, or badly compensated but invisible to the human eye as a defect be recognized. As in US 9,944,104 B2 a reference image generation step is also necessary here in order to generate reference data for locating whitelines, which one would like to do without.

It is therefore an object of the present invention to find a method for determining printing errors in a printing process of an inkjet printing press, which is more efficient and determines printing errors, in particular whiteline errors, better and more reliably than the methods known from the prior art.

The object is achieved by a method for determining printing errors in a printing process, carried out in an inkjet printing machine for processing a print job, by a computer, print products generated during the printing process being recorded and digitized with the aid of a camera system generated camera image is fed to a detection algorithm on the computer, in the event of detected printing errors, a message is sent to a machine control, which then, if necessary, ejects the printed product via a waste filter, which is characterized in that the detection algorithm separates color separations of the camera images and detects the printing errors in the color separations , Images of the individual color separations are linked to form a candidate image, the candidate image is filtered and finally the remaining detected printing errors are entered in a list and sent to the printing press. The essence of the method according to the invention is therefore to determine the printing errors directly from the camera image generated of the captured and digitized printed product. The printing errors are detected directly in the separated color separations, since the printing errors are easier to detect here than in the composite camera image. It is important, however, that the printing errors in the generated camera image can be recognized at all. For example, if the resolution of the generated camera image is too low, the information about the corresponding printing errors will be lost and the entire detection algorithm will not work. It is also important to note that the camera usually delivers RGB images, so that a separation of the individual color separations of the camera image generated naturally provides individual RGB color separations and not CMYK color separations, which correspond to the color space of the inkjet printing press used. However, this does not pose a problem for the method according to the invention, since it is primarily the exact position of the corresponding printing errors that is important, or the fact that printing errors impairing the print quality are reliably detected at all. Which color separation in the machine color space, i.e. which ink and thus which print head, is affected by the nozzle failure, can be determined by the computer using appropriate color space transformations. To improve the detection algorithm, after the detection in the color separations, the images of the individual color separations are linked again to form a common candidate image and this image is then subjected to further filtering to ensure that printing errors that actually only lead to waste are also detected accordingly. In order to reserve a later detection of the printing nozzles causing the printing errors, all columns in the candidate image which contain a detected printing error are identified.

Advantageous and therefore preferred developments of the method result from the associated subclaims and from the description with the associated drawings.

A preferred development of the method according to the invention is that the printing errors are whiteline or darkline errors caused by defective printing nozzles of the inkjet printing press. The algorithm is therefore primarily intended for the detection of the whiteline errors already described, since these printing errors in particular reduce the print quality of the printing process to such an extent that waste occurs.

A further preferred development of the method according to the invention is that the computer filters out pseudo-whiteline or darkline errors from the list of whiteline or darkline errors in a further method step, before sending it to the printing press, by using a specific test method . It is important that no false positive errors are output by the detection algorithm. In particular, thin, light lines in the print image to be generated, e.g. Barcodes are very prone to be labeled as pseudo whitelines. Therefore, the detection algorithm should check in a further procedural step by means of specific tests whether the detected white line is really a real white line, in order to rule out that wanted components of the printed image are incorrectly detected as whiteline errors and unwanted additional waste is caused.

A further preferred development of the method according to the invention is that the computer determines the causal defective pressure nozzles from the list of the remaining detected whiteline or darkline errors and, depending on this, compensates for the whiteline or darkline errors using suitable compensation methods. Although the actual aim of the method according to the invention is to precisely identify printed products in the form of printed sheets which have such quality-reducing whiteline errors that convert the printed sheet into a waste sheet, the information about the whiteline errors determined by the detection algorithm can of course be used also be used in order to determine the causal defective pressure nozzles and to have them compensated by a suitable compensation method. Finally, the compensation of the defective printing nozzles makes it possible to continue using the inkjet printing machine in question to process the current print job without having to change the print head.

A further preferred development of the method according to the invention is that the computer for the specific test method creates a reference image from prepress data of the print job, applies the detection algorithm to this reference image and thus obtains knowledge about either received candidates for pseudo whiteline or darkline errors and removes them from the list of whiteline or darkline errors or over areas in the camera image with probable pseudo-whiteline or darkline errors to which the detection algorithm is then not applied. The easiest way to detect pseudo whitelines is to use good data, e.g. the prepress data, creates a reference image and then checks whether the structure found, which was detected as a white line, is also located in this reference image. If so, it is logically a pseudo whiteline. There are two ways of dealing with the knowledge that you have found one. You can easily remove the found pseudo whiteline error from the list, which is surely the easiest procedure. However, if you want to avoid that the same pseudo-whiteline error is found again by the detection algorithm in the continuous method according to the invention, it is best to exclude the area in the camera image in which this pseudo-whiteline error has occurred from the detection according to the invention .

A further preferred development of the method according to the invention is that the computer creates the reference image in several sizes and / or resolutions, accordingly applies the detection algorithm several times to the different reference images, and summarizes and applies the knowledge gained therefrom. This procedure increases the reliability of the detection algorithm for the specific identification of whitelines as well as for the determination of pseudo whiteline errors.

A further preferred development of the method according to the invention is that the algorithm is not applied to such areas, or results from areas that are characterized by a high variation of the gray values in a limited, local environment in the reference image are excluded. Such areas as e.g. Barcodes are particularly susceptible to the detection of pseudo whiteline or darkline errors and must therefore be excluded from checking the algorithm.

A further preferred development of the method according to the invention is that the list of whiteline or darkline errors is created using column sums in the filtered candidate image by applying a limit value to the column sum determined in each case in the candidate image. Real annoying whiteline / darkline errors usually extend over a larger area of the captured camera image. To prevent that even very small, short misfires of the individual pressure nozzle lead to a detection of a printing error, although these may not be disturbing at all or are pseudo-whiteline / darkline errors, which are very short whiteline If errors are very likely, only those print columns are marked in the candidate image in which the determined print error exceeds a certain limit.

A further preferred development of the method according to the invention is that the candidate image of the individual color separations is linked by the computer using a mathematical OR operation. This type of composition of the individual color separations to the candidate image has proven to be the most suitable from a computational point of view.

A further preferred development of the method according to the invention is that the filtering of the candidate image is carried out by the computer using morphological operations. This allows, in particular, the filtering out of very short printing errors or white lines, which are usually pseudo-whitelines anyway or which do not influence the print quality of the printed product or printed sheet so strongly that a waste decision has to be made here.

A further preferred development of the method according to the invention is that the detection algorithm is used several times by the computer on the generated camera image, the method being parameterized differently in order to detect darkline or whiteline errors of different types and the results of all color separations of all applications of the process are logically linked. In addition to the multiple use of the detection algorithm on several reference images, which is an optional method step of the method according to the invention, the detection algorithm can also be applied several times to the camera image generated. In particular, this increases the accuracy of the detection algorithm when filtering out pseudo-whiteline or darkline errors, but is also positive for the hit accuracy when finding real whiteline or darkline errors.

A further preferred development of the method according to the invention is that for each of the differently parameterized applications of the method, the camera image in each pixel is previously limited to a maximum gray value. This has the advantage that bright outliers in areas of paper white that could distort the mean are filtered out.

A further preferred development of the method according to the invention is that the candidate image of a color channel is generated by dividing the image into horizontal strips, each strip being reduced to a line signal by means of a suitable averaging of each of its columns, in which then white lines or dark lines are generated a special search method is sought and each line evaluated in this way results in a line of the whiteline candidate image. This is an important feature of the method according to the invention, since the white / darkline detection by means of the detection algorithm in these strips is more efficient than if the algorithm had to work with the overall image.

A further preferred development of the method according to the invention is that the computer uses the white or darkline search method to find a dark or Whiteline at a position by evaluating a restricted neighborhood around the viewed pixel in the line signal. The classification of whether an error found is really a real whiteline or darkline error is done by evaluating the immediately adjacent pixels. This is the only way to rule out a pseudo whiteline or darkline error.

A further preferred development of the method according to the invention is that the search method first convolves the line signal with different filter cores and converts the results into logical signals by comparison with possibly different limit values, which are then converted into a white or dark line using a logical link. Candidate line signal is converted.

The invention as such and constructively and / or functionally advantageous developments of the invention are described in more detail below with reference to the accompanying drawings using at least one preferred exemplary embodiment. Corresponding elements are provided with the same reference symbols in the drawings.

Figur 1:

ein Beispiel des Aufbaus einer Bogen-Inkjet-Druckmaschine

Figur 2:

ein Beispiel eines zur Druckinspektion verwendeten Bilderfassungssystems

Figur 3:

ein Beispiel eines erfassten Kamerabildes

Figur 4:

ein Streifen des erfassten Kamerabildes

Figur 5:

ein Streifen des erfassten Kamerabildes mit markierten Whitelines

Figur 6:

ein vergrößerter Ausschnitt mit markierten Whitelines aus dem Streifen des erfassten Kamerabildes

Figur 7

aus Bildstreifen zusammengesetztes Bild mit markierten Whiteline-Kandidaten

Figur 8:

markierte Whiteline-Bereiche in einem Kamerabild

Figur 9:

Störung des Spaltenmittelwerts durch helle Papierweiß-Bereiche oder einzelne helle Pixel

Figur 10:

der schematische Ablauf des erfindungsgemäßen Verfahrens

The drawings show:

Figure 1:

an example of the construction of a sheet inkjet printing machine

Figure 2:

an example of an image acquisition system used for print inspection

Figure 3:

an example of a captured camera image

Figure 4:

a strip of the captured camera image

Figure 5:

a strip of the captured camera image with marked whitelines

Figure 6:

an enlarged section with marked whitelines from the strip of the captured camera image

Figure 7

Image composed of image strips with marked whiteline candidates

Figure 8:

marked whiteline areas in a camera image

Figure 9:

The column mean value is disturbed by light areas of paper white or individual bright pixels

Figure 10:

the schematic sequence of the method according to the invention

The field of application of the preferred embodiment variant is an inkjet printing machine 7. An example of the basic structure of such a machine 7, consisting of feeder 1 for feeding the printing substrate 2, usually a printing sheet 2, into the printing unit 4, where it comes from the print heads 5 is printed up to the boom 3, is in Figure 1 shown. This is a sheet inkjet printing machine 7, which is controlled by a control computer 6. As already described, the operation of this printing press 7 can lead to failures of individual printing nozzles in the printing heads 5 in the printing unit 4. The result is white / dark lines, or, in the case of multi-color printing, distorted color values. An example of such a white / dark line 9 in a captured camera image 8 is shown in FIG Figure 3 shown.

1. 1. Nach dem Druck wird der bedruckte Bogen mit Hilfe eines Kamerasystems 10, welches Teil eines Inline- Bilderfassungssystems 12 sein kann, digitalisiert. Figur 2 zeigt ein Beispiel für ein solches Bilderfassungssystem 12, welches das erfindungsgemäße Verfahren einsetzt. Es besteht aus mindestens einem Bildsensor 10, üblicherweise einer Kamera 10, welche in die Inkjet-Druckmaschine 7 integriert ist. Die mindestens eine Kamera 10 nimmt die von der Druckmaschine 7 erzeugten Druckbilder 13 auf und sendet die Daten an einen Rechner 6, 9 zur Auswertung. Dieser Rechner 6, 9 kann ein eigener separater Rechner 9 sein, z.B. ein oder mehrere spezialisierte Bildverarbeitungsrechner 9, oder auch mit dem Steuerungsrechner 6 der Druckmaschine 7 identisch sein. Mindestens der Steuerungsrechner 7 der Druckmaschine 7 besitzt ein Display 11, auf welchem die Ergebnisse der Bildinspektion dem Anwender 8 angezeigt werden. Bevorzugt wird für das im Folgenden beschriebene Verfahren der Bildverarbeitungsrechner 9 eingesetzt, auf welchem dann der Bildverarbeitungsalgorithmus läuft, welcher das erfindungsgemäße Verfahren ausführt. Das so erzeugte Kamerabild 13 hat dabei eine geringere Auflösung als der Druck. Üblich ist eine Kameraauflösung von 670dpi bei einer Druckauflösung von 1200dpi. Die Auflösung und Optik muss so gewählt sein, dass White-/Darklines 14 als 1-2 Kamerapixel breite, vertikale, aufgehellte Streifen erscheinen. Ist die Auflösung zu hoch, so kann das Bild 13 zunächst mit bekannten Verfahren der Bildverarbeitung auf passende Auflösung reduziert werden, insbesondere pyramidale Bildrepräsentationen können sich hier als nützlich erweisen.
2. 2. Das Kamerabild 13 wird einem im Weiteren näher beschriebenen White-/Darkline-Detektionsalgorithmus zugeführt. Zusätzlich kann es parallel noch weiteren Auswertungen zugeführt werden.
3. 3. Werden White-/Darklines 13 vom Detektionsalgorithmus erkannt, so werden diese vom Bildverarbeitungsrechner 9 an den Steuerungsrechner 6 der Druckmaschine 7 gemeldet, welche dann, zusammen mit anderen Daten der Druckmaschine 7, eine Makulaturentscheidung trifft und den bedruckten Bogen 2 eventuell über eine Makulaturschleuse ausschleust.
4. 4. Optional können die gefundenen White-/Darklines 14 einer genaueren Auswertung unterzogen werden, um die defekte Düse zu identifizieren und diese Information zur Kompensation der defekten Düse zu nutzen.

In contrast to the methods known from the prior art, in the method according to the invention the embedding of the detection method for the white / dark lines 14 in the overall process of the printing process is different and also requires no interaction of the printer 8. The overall sequence of the method in a first, preferred embodiment variant is shown schematically in Figure 10 shown:

1. 1. After printing, the printed sheet is digitized using a camera system 10, which can be part of an inline image acquisition system 12. Figure 2 shows an example of such an image acquisition system 12 which uses the method according to the invention. It consists of at least one image sensor 10, usually a camera 10, which is integrated in the inkjet printing machine 7. The at least one camera 10 records the print images 13 generated by the printing press 7 and sends the data to a computer 6, 9 for evaluation. This computer 6, 9 can be its own separate computer 9, for example one or more specialized image processing computers 9, or it can also be identical to the control computer 6 of the printing press 7. At least the control computer 7 of the printing press 7 has a display 11 on which the results of the image inspection are shown to the user 8. For the method described below, the image processing computer 9 is preferably used, on which the image processing algorithm that executes the method according to the invention then runs. The camera image 13 generated in this way has a lower resolution than the pressure. A camera resolution of 670dpi with a print resolution of 1200dpi is common. The resolution and optics must be selected so that White- / Darklines 14 appear as vertical, lightened stripes that are 1-2 camera pixels wide. If the resolution is too high, the image 13 can first be reduced to a suitable resolution using known image processing methods; pyramidal image representations in particular can prove useful here.
2. 2. The camera image 13 is fed to a white / darkline detection algorithm described in more detail below. It can also be used for further evaluations in parallel.
3. 3. If white / dark lines 13 are detected by the detection algorithm, these are reported by the image processing computer 9 to the control computer 6 of the printing press 7, which then, together with other data from the printing press 7, makes a waste decision and possibly the printed sheet 2 via a waste lock ejected.
4. 4. Optionally, the white / dark lines 14 found can be subjected to a more precise evaluation in order to identify the defective nozzle and to use this information to compensate for the defective nozzle.

From this sequence it becomes clear that a step-by-step processing of the camera images 13 is essential for the function of the overall system 12.

In contrast to the prior art, the previously mentioned algorithm for white / dark line detection is now only applied to the camera image 13. Figure 3 shows an example of a printing sheet 2 with captured camera images 13, one of which has a white / darkline error 14. Optionally, in a further embodiment variant, additional, downstream filtering can also be carried out using a reference image. This will be explained in more detail later in the description.

1. 1. Separiere die RGB-Farbauszüge und für jeden Farbauszug C separat:
   • 1.1. Teile das Kamerabild 13 in ca. 1-10mm hohe Streifen 15, sh. Figur 4
   • 1.2. Jeder Streifen 15 wird in Laufrichtung des Bogens 2, also in y-Richtung, gemittelt. Es ergibt sich ein Signal I_s(x) für den s-ten Streifen 15
   • 1.3. In jedem Streifen 15 werden White-/Darklines 14 separat detektiert, indem für jede x-Position ein Wahrheitswert berechnet wird:
     • 1.3.1. Als optionaler Schritt werden Pixel mit Grauwerten I_C,s(x) > G_max nicht berücksichtigt, da White-/Darklines 14 in hellen Bildbereichen nicht sichtbar werden.
     • 1.3.2. WLC(x,s) = (I_C,s (x)- I_C,s(x-1) > L) and ((I_C,s(x)- I_C,s(x+1)>L) or (I_C,s(x) - IC,s (x+2) > L)) or (I_C,s(x) - I_C,s(x-2) > L) and ((I_C,s(x) - I_C,s(x+1) > L)) Dieser Ausdruck prüft, ob eine 1 oder 2 Pixel breite White-/Darkline 14 mit einer Aufhellung um mehr als L Graustufen besteht und schließt Kanten im Bild auf effektive Weise aus. Figur 5 und 6 zeigen jeweils einen Bildstreifen 15 mit erkannten White-/Darklines 14, welche mit einer entsprechenden Markierung 16 sind. Figur 6 zeigt dabei einen vergrößerten Ausschnitt 17 aus dem Streifen 15 mit Markierung 16 und White-/Darkline 14.
   • 1.4. So ergibt sich ein schwarz-weiß-Bild WLCC (x,y), in dem alle White-/Darkline-Kandidaten 14 vermerkt sind.
2. 2. Die Bilder WLC_C(x,y) der einzelnen Farbauszüge werden ODER-Verknüpft und ergeben dann ein einziges Kandidatenbild WLC(x,y) 21, welches beispielhaft in Figur 7 dargestellt wird. Es zeigt ein aus Bildstreifen 15 zusammengesetztes Bild 21 mit markierten White-/Darkline-Kandidaten 14.
3. 3. Das Bild WLC(x,y) 21 kann nun noch mit morphologischen Operationen gefiltert werden. So erlaubt ein Erodieren mit einem Strukturelement SE der Form:
   • 010
   • 010
   sehr kurze White-/Darklines 14 auszufiltern. Die Höhe von SE kann variabel eingestellt werden und erlaubt es so eine Mindestlänge der zu detektierenden White-/Darklines 14 voreinzustellen.
4. 4. Die gleiche Auswertung, wie in den Schritten 1-3 beschrieben kann in einem weiteren Ausführungsbeispiel parallel auf ein eventuell vorhandenes Referenzbild, welches als RGB-Bild, direkt vom RIP erzeugt wird, angewendet werden. Die sich daraus ergebenden White-/Darkline-Kandidaten WLC_REF(x,y) 14 markieren Bereiche des Druckbildes, in denen falsch-positive White-/Darkline-Detektionen durch das Kundenmotiv wahrscheinlich sind. Diese Bereiche sollten aus WLC(x,y) 21 aus dem Kamerabild 13 entfernt werden. Dazu werden zunächst die Bereiche in WLC_REF(x,y) mit Hilfe einer morphologischen Dilatation ausgeweitet. Dies entspricht einer Glättung von WLC_REF(x,y). Danach wird WLC(x,y) 21 durch WLC_REF(x,y) gefiltert:
   
           WLC(x,y) ← WLC(x,y) and (not WLC_REF(x,y))
   
   
5. 5. Abschließend werden alle Spalten C_WL in WLC(x,y) 21 detektiert, die eine White-/Darkline 14 enthalten. Dies kann über einen Grenzwert minWLPerColumn an die Spaltensumme erfolgen und zwar als Kodierung: keine White-/Darkline = 0, White-/Darkline = 1 in WLC(x,y) 21, d.h. zählen der als White-/Darkline 14 markierten Einträge in WLC(x,y) 21: $$\mathit{CWL}=\left\{x|\sum _{\mathrm{y}}\mathrm{WLC}\left(x,y\right)>\mathrm{minWLPerColumn}\right\}$$
   

The detection algorithm presented here is based on the subdivision of the captured camera image 13 into horizontal strips 15, 15a, 15b. The algorithm includes the following steps:

1. 1. Separate the RGB color separations and for each color separation C separately:
   • 1.1. Divide the camera image 13 into strips 1-10mm high, sh. Figure 4
   • 1.2. Each strip 15 is averaged in the running direction of the sheet 2, that is to say in the y direction. A signal I _s (x) results for the s th stripe 15
   • 1.3. White / dark lines 14 are detected separately in each strip 15 by calculating a truth value for each x position:
     • 1.3.1. As an optional step, pixels with gray values I _{C, s} (x) > G _{max are} not taken into account, since white / dark lines 14 are not visible in bright image areas.
     • 1.3.2. WLC ( x, s ) = (I _{C, s} (x) - I _{C, s} (x-1)> L) and (( I _{C, s} (x) - I _{C, s} (x + 1) > L ) or (I _{C, s} (x) - IC, s (x + 2)> L)) or (I _{C, s} (x) - I _{C, s} (x-2) > L) and (( I _{C , s} (x) - I _{C, s} (x + 1)> L )) This printout checks whether there is a 1 or 2 pixel wide white / dark line 14 with a brightening by more than L gray levels and opens up edges in the image effective way. Figures 5 and 6 each show an image strip 15 with recognized white / dark lines 14, which are with a corresponding marking 16. Figure 6 shows an enlarged detail 17 from the strip 15 with marking 16 and white / dark line 14.
   • 1.4. The result is a black and white image WLCC (x, y), where all white- / Darkline candidates 14 are noted.
2. 2. The images WLC _C ( x, y ) of the individual color separations are OR-linked and then result in a single candidate image WLC (x, y) 21, which is shown as an example in Figure 7 is pictured. It shows an image 21 composed of image strips 15 with marked white / darkline candidates 14.
3. 3. The image WLC ( x, y ) 21 can now be filtered using morphological operations. Eroding with a structural element SE thus allows the form:
   • 010
   • 010
   filter out very short white / dark lines 14. The height of SE can be set variably and thus allows a minimum length of the white / dark lines 14 to be detected to be preset.
4. 4. In a further exemplary embodiment, the same evaluation as described in steps 1-3 can be applied in parallel to a possibly existing reference image, which is generated as an RGB image directly from the RIP. The resulting white / darkline candidates WLC _REF ( x, y ) 14 mark areas of the printed image in which false positive white / darkline detections by the customer motif are likely. These areas should be removed from the WLC ( x, y ) 21 from the camera image 13. For this purpose, the areas in WLC _REF ( x, y ) are first expanded using a morphological dilation. This corresponds to a smoothing of WLC _REF ( x, y ). Then WLC ( x, y ) 21 is filtered by WLC _REF ( x, y ):
   
   WLC ( x, y ) ← WLC ( x, y ) and (not WLC _REF ( x, y ))
   
   
5. 5. Finally, all columns C _WL in WLC ( x, y ) 21 are detected that contain a white / dark line 14. This can be done via a limit value minWLPerColumn to the column sum and as coding: no white / dark line = 0, white / dark line = 1 in WLC ( x, y ) 21, i.e. count the entries marked as white / dark line 14 in WLC ( x, y ) 21: $$\mathit{CWL}=\left\{x|\sum _{\mathrm{y}}\mathrm{WLC}\left(x,y\right)>\mathrm{minWLPerColumn}\right\}$$
   

• So können die nachgelagerten Filter variiert werden.
• Die Anzahl der der White-/Darkline-Kandidaten 14 muss eine Mindestanzahl pro Spalte erreichen um als White-/Darkline 14 gemeldet zu werden
• Für den Helligkeitswert der Pixel wird ein Maximalwert definiert, damit sehr helle Pixel nicht den Mittelwert verfälschen. Denn eine White-/Darkline 14 hat keine sehr hellen Pixel in einem 670 dpi Kamerabild 13. D.h. alle Grauwerte im Bild > 50 werden auf 50 begrenzt;
• Es wird geprüft. ob an den relevanten Stellen im Referenzbild starke Strukturen vorhanden sind, die schon im Referenzbild zu einer White-/Darkline-ähnlichen Struktur führen und deshalb im Kamerabild 13 ausgeblendet werden müssen. Dafür muss das Referenzbild nicht in der vollen Auflösung vorliegen, da nur eine grobe Abschätzung benötigt wird ob der Teilbereich des Referenzbildes strukturiert oder homogen ist; sh. Schritt 4.
• Das oben beschriebene Verfahren kann zur schritthaltenden Anwendung auf einer Grafikkarte (GPU) als Rechenbeschleuniger implementiert werden.
• Der beschriebene Detektionsalgorithmus kann als Teilkomponente des Bilderfassungssystems 12, welches die Bildinspektion durchführt, implementiert werden. Aus dem WLC(x,y)-Bild 21 können dann noch Daten für einen Report an den Bediener 8, bzw. Kunden abgeleitet werden, indem zusammenhängende Flächen (Blobs) im Bild 13 erkannt werden und in einem Übersichtsbild für den Bediener/-in 8 einer späteren Auswertung markiert werden. Figur 8 zeigt ein Beispiel für ein Kamerabild 13 mit markierten White-/Darkline-Bereichen 20 als Teil eines solchen Reports.

The method according to the invention can also be adapted in further preferred embodiments:

• The downstream filters can be varied in this way.
• The number of white / darkline candidates 14 must reach a minimum number per column in order to be reported as white / darkline 14
• A maximum value is defined for the brightness value of the pixels so that very bright pixels do not falsify the mean value. This is because a white / dark line 14 has no very bright pixels in a 670 dpi camera image 13. That is, all gray values in the image> 50 are limited to 50;
• It is checked. whether there are strong structures at the relevant points in the reference image that already lead to a white / darkline-like structure in the reference image and must therefore be hidden in the camera image 13. The reference image does not have to be in full resolution for this, since only a rough estimate is required as to whether the partial area of the reference image is structured or homogeneous; sh. Step 4.
• The method described above can be implemented for step-by-step application on a graphics card (GPU) as a computing accelerator.
• The detection algorithm described can be implemented as a subcomponent of the image acquisition system 12 which carries out the image inspection. Data can then be derived from the WLC ( x, y ) image 21 for a report to the operator 8 or customer by recognizing coherent areas (blobs) in the image 13 and in an overview image for the operator 8 to be marked for later evaluation. Figure 8 shows an example of a camera image 13 with marked white / darkline areas 20 as part of such a report.

However, a reference image is usually required in these further preferred embodiments, which, in addition to the disadvantages already mentioned, affects the processing speed. However, the use of a reference image can further improve the quality of the method by avoiding false / positively detected white / dark lines 14.

The method according to the invention thus has many advantages over the prior art. In the case of large color deviations between the target image and camera image 13, for example in the case of an incorrectly calibrated workflow with regard to cameras 10, white balance, paper type, short white / dark lines 14, they are often lost in the image / signal noise. This disadvantage is eliminated with the method according to the invention. Also has to come from Methods known in the art, the reference image can be transported in full resolution to the computer 9, for example with 670 dpi. This is only possible with the currently available technical means at high costs. Since the algorithm presented here manages without a reference image or at least without a high-resolution reference image, these costs can be saved. Finally, a reference image is fundamentally not necessary for the detection, even if it can be used to avoid false-positive white / darkline detections through structures contained in the customer motif. In particular for the detection of white / darkline candidates 14, there is no longer any need to compare the reference and camera images 13 directly.

1. 1. Das Kamerabild 13 wird in seinen Grauwerten/Farbkanalwerten komprimiert. Die Kompression wird so ausgeführt, dass Helligkeitswerte oberhalb einer Schwelle S_max auf den Schwellwert S_max begrenzt werden. Dies unterdrückt effektiv alle Strukturen im Bild 13, die heller als S_max sind. Damit werden in diesem Schritt White-/Darklines 14 in dunklen Flächen in homogenen und inhomogenen Bereichen sehr gut gefunden. Die Kompression wird vor dem ersten Schritt des vorherigen Ausführungsbeispiels ausgeführt.
2. 2. Auch hier wird das Kamerabild 13 in seinen Grauwerten, bzw. Farbkanalwerten auf komprimiert. Die Kompression wird hier jedoch so ausgeführt, dass Helligkeitswerte oberhalb einer Schwelle K_max (K_max > S_max) auf den Schwellwert K_max begrenzt werden. Die Kompression wird vor dem dritten Schritt des vorherigen Ausführungsbeispiels ausgeführt. Zusätzlich wird die lokale Homogenität des Bildes 13 berechnet, indem bei der Mittelung im zweiten Schritt des vorherigen Ausführungsbeispiels zum Mittelwert noch die Standardabweichung des Spaltensegments berechnet wird. Nur White-/Darklines 14 in relativ homogenen Flächen, d.h. bei einer Standardabweichung < σ_max, werden in die Kandidatenliste aufgenommen. Diese Filterung kann im dritten Schritt des vorherigen Ausführungsbeispiels erfolgen. In diesem Ansatz werden White-/Darklines 14 in hellen, homogenen Flächen sehr gut gefunden. White-/Darklines 14 in hellen inhomogenen Bereichen sind für das menschliche Auge ohnehin nur schwer zu sehen und werden deshalb nicht berücksichtigt.

There is also a further, particularly preferred exemplary embodiment of the method according to the invention, which further improves the method. The following two-stage algorithm based on the previous embodiment is proposed:
In stage one, a targeted search is made for white / darkline candidates 14:
For this purpose, the algorithm presented in the previous exemplary embodiments is called up several times with different parameters. The results of the runs of the algorithm are then logically linked. In addition, the algorithm is further improved in its processes. This is done as follows:
The algorithm is applied several times to the camera image 13 of the sheet 2. In the different applications, the parameters are adjusted as follows:

1. 1. The camera image 13 is compressed in its gray values / color channel values. The compression is carried out in such a way that brightness values above a threshold S _{max are} limited to the threshold value S _max . This effectively suppresses all structures in Figure 13 that are lighter than S _max . In this step, white / dark lines 14 are found very well in dark areas in homogeneous and inhomogeneous areas. The compression is carried out before the first step of the previous exemplary embodiment.
2. 2. Here, too, the camera image 13 is compressed in its gray values or color channel values. However, the compression is carried out here in such a way that brightness values above a threshold K _max (K _max > S _max ) are limited to the threshold value K _max . The compression is carried out before the third step of the previous exemplary embodiment. In addition, the local homogeneity of the image 13 is calculated by calculating the standard deviation of the column segment during the averaging in the second step of the previous exemplary embodiment. Only white / dark lines 14 in relatively homogeneous areas, ie with a standard deviation <σ _max , are included in the candidate list. This filtering can take place in the third step of the previous exemplary embodiment. In this approach, white / dark lines 14 are found very well in bright, homogeneous areas. White- / Darklines 14 in bright inhomogeneous areas are difficult to see anyway and are therefore not taken into account.

Both results are linked with a logical OR and combined into a white / darkline candidate list. More complex links with further information are also conceivable as an option.

• Median statt Mittelwert; Vorteil ist hier, dass das Verfahren sehr robust auf Ausreißer reagiert
• Mittelwert nur über Pixel, die einen maximalen Helligkeitswert Gmax,mean nicht überschreiten. Vorteil ist hier das Ausfiltern von hellen Ausreißern oder Papierweiß-Bereichen, die den Mittelwert verfälschen können. Dies ist beispielhaft in Figur 9 dargestellt. Gut ist hier die Störung des Spaltenmittelwerts im oberen und unteren Teil von Figur 9 durch helle Papierweiß-Bereich oder einzelne helle Pixel zu erkennen. Ein Problem stellt hier allerdings das Auftreten von Pseudo-White-/Darklines 14b, sowie ein mangelnder Kontrast des erfassten Druckbildes 13 dar.

In the second step of the previous exemplary embodiment, in addition to simple averaging, various averaging methods can be applied to a generated image signal that have advantageous properties. For example:

• Median instead of mean; The advantage here is that the process reacts very robustly to outliers
• Average only over pixels that do not exceed a maximum brightness value Gmax, mean. The advantage here is filtering out bright outliers or areas of paper white that can distort the mean value. This is exemplified in Figure 9 shown. The disturbance of the column mean in the upper and lower part of is good here Figure 9 recognizable by bright paper white area or single bright pixels. However, a problem here is the occurrence of pseudo white / dark lines 14b and a lack of contrast in the captured print image 13.

In the middle part, the printed image 13 captured by the camera 10 is shown with a white / darkline error 14. A stripe with text 15a and a stripe at the image edge 15b are cut out from this print image 13, from which image signals 18, 19 are then respectively generated. In the image signal 18 of the strip with text 15a one can clearly see the mentioned effect of the white / darkline error 14 in the signal in the form of a corresponding peak 14a in the signal 18. In addition, a peak of a pseudo white / darkline error 14b is shown, which results from the text representation. It can be clearly seen that a distinction in the image signal 18 between the real peak of a white / darkline error 14a and the peak 14b of a pseudo white / darkline error 14b is difficult to distinguish, since the minimum detection height 19 of both peaks 14a, 14b is exceeded. In the lower part, two image signals 18a, 18b are shown for the case of the generated signal for the image edge. Here the minimum detection height 19 is exceeded only in the signal with improved contrast 18a and the white / darkline 14 is reliably detected. In the second signal with low contrast 18b, the minimum detection height 19 is not exceeded and the white / dark line 14 is accordingly not recognized.

1. 1. Es werden zwei Schwellen verwendet, je nachdem ob eine 1-Pixel-breite, oder eine 2-Pixel-breite White-/Darkline 14 detektiert werden soll. Je nach Kamerauflösung kann es zudem auch sinnvoll sein, auch 3-, 4-, ... N-Pixel breite White-/Darklines 14 zu finden. Es müssen dann entsprechend mehr Schwellen angewendet werden. Der Detektions-Ausdruck aus dem dritten Schritt lautet dann mit den zwei Schwellen L1 und L2: $$\mathrm{WLC}\left(\mathit{x},\mathit{s}\right)=\left(\left({\mathit{I}}_{\mathit{C},\mathit{s}}\left(\mathit{x}\right)-{\mathit{I}}_{\mathit{C},\mathit{s}}\left(\mathit{x}-\mathit{1}\right)>\mathit{<figure-callout\; id="1"\; label="L"\; filenames="imgf0002.png,imgf0006.png"\; state="\{\{state\}\}">L</figure-callout>}\mathit{1}\right)\mathrm{and}\left({\mathit{I}}_{\mathit{C},\mathit{s}}\left(\mathit{x}\right)-{\mathit{I}}_{\mathit{C},\mathit{s}}\left(\mathit{x}+\mathit{1}\right)>\mathit{<figure-callout\; id="1"\; label="L"\; filenames="imgf0002.png,imgf0006.png"\; state="\{\{state\}\}">L</figure-callout>}\mathit{1}\right)\right)\mathrm{or}\left(\left({\mathit{I}}_{\mathit{C},\mathit{s}}\left(\mathit{x}\right)-{\mathit{I}}_{\mathit{C},\mathit{s}}\left(\mathit{x}-\mathit{1}\right)>\mathit{<figure-callout\; id="2"\; label="L"\; filenames="imgf0001.png,imgf0003.png"\; state="\{\{state\}\}">L</figure-callout>}\mathit{2}\right)\mathrm{and}\left({\mathit{I}}_{\mathit{C},\mathit{s}}\left(\mathit{x}\right)-{\mathit{I}}_{\mathit{C},\mathit{s}}\left(\mathit{x}+\mathit{2}\right)>\mathit{<figure-callout\; id="2"\; label="L"\; filenames="imgf0001.png,imgf0003.png"\; state="\{\{state\}\}">L</figure-callout>}\mathit{2}\right)\right)\mathrm{or}\left(\left({\mathit{I}}_{\mathit{C},\mathit{s}}\left(\mathit{x}\right)-{\mathit{I}}_{\mathit{C},\mathit{s}}\left(\mathit{x}-\mathit{2}\right)>\mathit{<figure-callout\; id="2"\; label="L"\; filenames="imgf0001.png,imgf0003.png"\; state="\{\{state\}\}">L</figure-callout>}\mathit{2}\right)\mathrm{and}\left({\mathit{I}}_{\mathit{C},\mathit{s}}\left(\mathit{x}\right)-{\mathit{I}}_{\mathit{C},\mathit{s}}\left(\mathit{x}+\mathit{1}\right)>\mathit{<figure-callout\; id="2"\; label="L"\; filenames="imgf0001.png,imgf0003.png"\; state="\{\{state\}\}">L</figure-callout>}\mathit{2}\right)\right)$$
   
2. 2. Die Schwelle kann von der lokalen Umgebung jedes Pixel x abhängig gemacht werden, sodass für White-/Darklines 14 in hellen Bildbereichen höhere Schwellen angewendet werden, als in Bildbereichen mit niedriger Helligkeit. Als Maß für die lokale Helligkeit können die Grauwerte in einer engen Umgebung um die Position x unter Ausschluss einer evtl. vorhandenen White-/Darkline 14 gemittelt werden. Alternativ kann ein gleitender Medianfilter auf I_C,s(x) angewendet werden.

In the third step of the previous exemplary embodiment, white / dark lines 14 are detected via a threshold L. Two further improvements are also found for this threshold in this further exemplary embodiment:

1. 1. Two thresholds are used, depending on whether a 1-pixel-wide or a 2-pixel-wide white / dark line 14 is to be detected. Depending on the camera resolution, it can also make sense to find 3, 4, ... N-pixel wide white / dark lines 14. Then more thresholds have to be applied accordingly. The detection expression from the third step is then with the two thresholds L1 and L2: $$\mathrm{WLC}\left(\mathit{x},\mathit{s}\right)=\left(\left({\mathit{I.}}_{\mathit{C.},\mathit{s}}\left(\mathit{x}\right)-{\mathit{I.}}_{\mathit{C.},\mathit{s}}\left(\mathit{x}-\mathit{1}\right)>\mathit{<figure-callout\; id="1"\; label="L"\; filenames="imgf0002.png,imgf0006.png"\; state="\{\{state\}\}">L</figure-callout>}\mathit{1}\right)\mathrm{and}\left({\mathit{I.}}_{\mathit{C.},\mathit{s}}\left(\mathit{x}\right)-{\mathit{I.}}_{\mathit{C.},\mathit{s}}\left(\mathit{x}+\mathit{1}\right)>\mathit{<figure-callout\; id="1"\; label="L"\; filenames="imgf0002.png,imgf0006.png"\; state="\{\{state\}\}">L</figure-callout>}\mathit{1}\right)\right)\mathrm{or}\left(\left({\mathit{I.}}_{\mathit{C.},\mathit{s}}\left(\mathit{x}\right)-{\mathit{I.}}_{\mathit{C.},\mathit{s}}\left(\mathit{x}-\mathit{1}\right)>\mathit{L}\mathit{2nd}\right)\mathrm{and}\left({\mathit{I.}}_{\mathit{C.},\mathit{s}}\left(\mathit{x}\right)-{\mathit{I.}}_{\mathit{C.},\mathit{s}}\left(\mathit{x}+\mathit{2nd}\right)>\mathit{L}\mathit{2nd}\right)\right)\mathrm{or}\left(\left({\mathit{I.}}_{\mathit{C.},\mathit{s}}\left(\mathit{x}\right)-{\mathit{I.}}_{\mathit{C.},\mathit{s}}\left(\mathit{x}-\mathit{2nd}\right)>\mathit{L}\mathit{2nd}\right)\mathrm{and}\left({\mathit{I.}}_{\mathit{C.},\mathit{s}}\left(\mathit{x}\right)-{\mathit{I.}}_{\mathit{C.},\mathit{s}}\left(\mathit{x}+\mathit{1}\right)>\mathit{L}\mathit{2nd}\right)\right)$$
   
2. 2. The threshold can be made dependent on the local environment of each pixel x, so that higher thresholds are used for white / darklines 14 in bright image areas than in image areas with low brightness. As a measure of the local brightness, the gray values can be averaged in a narrow environment around the position x to the exclusion of any white / dark line 14 that may be present. Alternatively, a moving median filter can be applied to I _{C, s} (x).

• Berechnung des Luminanz-Kanals aus dem Lab-Farbraum
• Berechnung des Helligkeitswertes oder Sättigungswertes aus dem HSB-Farbraum
• Mittelung der geeignet gewichteten RGB-Farbkanäle, auf das menschliche Auge angepasst

As a further advantageous improvement of the previous exemplary embodiment, the algorithm cannot be applied to an RGB image 13, but rather the RGB image 13 is previously converted into a grayscale image which has the best possible contrast for white / dark lines 14. Suitable transformation operations for this are:

• Calculation of the luminance channel from the Lab color space
• Calculation of the brightness value or saturation value from the HSB color space
• Averaging of suitably weighted RGB color channels, adapted to the human eye

In stage 2, pseudo white / dark lines 14b are now filtered out of the white / dark line candidates 14 determined in stage one by using one or more filters. There are the following improvements over the previous embodiment:
By using a column filter on the white / darkline candidate list, all white / darkline candidates 14 who do not have at least the number N _{col, min} more white / darkline candidates 14 in one and the same image column become the white / Darkline candidate list removed. The idea behind this filter is to rule out very short or occasional false detections. Because in most realistic print motifs, a white / dark line 14 will affect several areas of a column, while false detections only occur locally.

The filter described in step four in the previous exemplary embodiment with the aid of the reference image is also carried out here with all the modifications described above. As an improvement, the size of the reference image is adjusted beforehand. It can also make sense to process the reference image several times in different resolutions and to summarize the results of these stages before filtering. This simulates the loss of quality on the "perfect" reference image by the camera system 10 and thus allows different structures to be detected effectively which can lead to white / darkline-like structures in the camera image 13.

The further, particularly preferred exemplary embodiment has the additional advantage over the previous exemplary embodiment that it has a higher recognition performance of white / dark lines 14 with a simultaneously lower number of pseudo white / dark lines 14 b. However, a reference image evaluation is necessary for this, the additional processing steps of which can lead to longer computing times of the computer 6, 9 used. The decision as to which preferred exemplary embodiment should be used should therefore be made on the basis of the requirements of the specific application. Print jobs in which the white / dark line detection is time or performance critical should rather use the first exemplary embodiment presented, while print jobs in their print images are particularly important for a thorough detection of white / dark lines 14 and / or for which an increased There is a risk of the occurrence of pseudo white / dark lines 14b, rather should resort to the second exemplary embodiment presented.

Reference list

1

Investors

2nd

Printing substrate

3rd

boom

4th

Inkjet printing unit

5

Inkjet print head

6

Control computer of the inkjet printing machine

7

Inkjet printing machine

8th

user

9

Image processing computer

10th

Image sensor / camera

11

Display

12th

Imaging system

13

captured print image

14

Whiteline / Darkline printing errors

14a

Peak of a whiteline / dark line in the generated image signal

14b

Peak of a pseudo whiteline / dark line in the generated image signal

15

Stripe of the captured print image

15a

Stripe of a captured print image with text content

15b

Stripe of a captured print image at the edge of the image

16

recognized and marked white / dark lines

17th

Enlarged section of the strip of the captured print image

18th

generated image signal from the strip of the captured print image with text content

18a

generated image signal from the strip of the captured print image at the edge of the image

18b

generated image signal from the strip of the captured print image at the edge of the image

19th

Minimum detection height of a white / dark line in the generated image signal

20

marked white / darkline areas #

21

Candidate image composed of strips

Claims (15)

Method for determining printing errors in a printing process, carried out in an inkjet printing machine (7) for processing a print job, by a computer (9), print products (2) generated during the printing process being recorded and digitized using a camera system (10) the camera image (13) generated in this way is fed to a detection algorithm on the computer (9), when printing errors (14) are detected, a message is sent to a machine control system (6) which then, if appropriate, ejects the printed product (2) via a waste paper switch,
characterized,
that the detection algorithm separates color separations of the camera images (13), detects the printing errors (14) in the color separations, links images of the individual color separations to a candidate image (21), filters the candidate image (21) and finally filters the remaining detected printing errors (14) into one Enter the list and send it to the machine control (9) of the printing press (7). Method according to claim 1,
characterized,
that the printing errors (14) are whiteline or darkline errors (14) caused by defective printing nozzles of the inkjet printing machine (7). Method according to claim 2,
characterized,
that the computer (9) in a further process step, before sending it to the machine control (9) printing press (7), from the list of whiteline or darkline errors (14) by using a specific test method pseudo-whiteline or darkline Filtered out error (14b). Method according to one of claims 2 to 3,
characterized,
that the computer (9) determines the causal defective pressure nozzles from the list of the remaining detected whiteline or darkline errors (14) and, depending on this, compensates for the whiteline or darkline errors (14) using suitable compensation methods. Method according to claim 4,
characterized,
that the computer (9) creates a reference image for the specific test procedure from prepress data of the print job, applies the detection algorithm to this reference image and thus gains knowledge about either received candidates for pseudo whiteline or darkline errors (14b) and this from the list removed from whiteline or darkline errors (14) or over areas in the camera image (13) with probable pseudo-whiteline or darkline errors (14b), to which the detection algorithm is then not applied. Method according to claim 5,
characterized,
that the computer (9) creates the reference image in several sizes and / or resolutions, accordingly applies the detection algorithm several times to the different reference images and summarizes and applies the knowledge gained from this. Method according to claim 6,
characterized,
that the algorithm is not applied to such areas, or that results from areas that are characterized by a high variation of the gray values in a limited, local environment in the reference image are excluded. Method according to one of the preceding claims,
characterized,
that creating the list of white line or dark line defects (14) is carried out by the computer (9) via column sums in the filtered candidate image (21) by applying a limit value to the respectively determined column sum in the candidate image (21). Method according to one of the preceding claims,
characterized,
that the candidate image (21) of the individual color separations is linked by the computer (9) by means of a mathematical OR operation. Method according to one of the preceding claims,
characterized,
that the filtering of the candidate image (21) is carried out by the computer (9) by means of morphological operations. Method according to one of the preceding claims,
characterized,
that the detection algorithm is repeatedly applied by the computer (9) to the generated camera image (13), the method being parameterized differently in order to detect darkline or whiteline errors (14) of different types and the results of all color separations of all applications of the method logically linked. A method according to claim 11,
characterized,
that for each of the differently parameterized applications of the method, the generated camera image (13) is previously limited to a maximum gray value in each pixel. Method according to one of the preceding claims,
characterized,
that the candidate image (21) of a color channel is generated by dividing the camera image (13) into horizontal strips (15), each strip (15) being reduced to an image signal (18) by a suitable averaging of each of its columns in which then white or dark lines (14) are searched for by a special search method and each line evaluated in this way results in a line of the whiteline candidate image (21). A method according to claim 13,
characterized,
that the white or dark line search method recognizes a dark or white line (14) at a position by viewing a restricted neighborhood around the viewed pixel in the image signal (18). A method according to claim 14,
characterized,
that the search method first convolves the image signal (18) with different filter cores and converts the results into logical signals by comparison with possibly different limit values, which is then converted into a white or darkline candidate image signal with the aid of a logical link.

Images