EP1777163A1 - Device for orienting containers - Google Patents

Abstract

Device for aligning containers (2) in relation to a geometric container characteristic comprises a first camera system having cameras (8, 9) for determining the outer and peripheral surface of the containers, a further camera system having cameras (10, 11) for aligning each container for further alignment in a region of the peripheral surface which is narrower than the geometric container characteristic and an electronic unit for further alignment based on image data or characteristic values when deviating from the theoretical position. An independent claim is also included for a labeling machine containing the above aligning device. Preferred Features: A peripheral region of each container of more than 180[deg] is determined using the first camera system.

Description

The invention relates to a device for positionally or positionally accurate alignment of containers according to the preamble of claim 1 and to a labeling machine with such a device according to the preamble of claim 23.

For containers and in particular for bottles, the typical geometrical container characteristics on its outer surface, such. B. seal surface, ornament, embossing, raised lettering, etc., it is necessary to apply the labels with high accuracy of application in relation to these container features. This means that in a labeling machine, the containers are indeed upright, but fed in a purely random orientation or orientation, these containers must first be aligned so that they each have as closely as possible with respect to their Behätermerkmale a predetermined orientation. Only then can the at least one label be applied to the respective container and then pressed against it and / or brushed.

It is known to provide for this alignment on a rotor of a labeling container receptacles, for example in the form of turntables, which are controlled by their own actuators about a vertical axis and thus also about the axis of the respective, arranged on the container receptacle rotatable. Specifically, it is also known to perform the control of the container receptacles for aligning in dependence on an image recognition or camera system, with which the respective position or orientation of at least one used for aligning typical geometric container feature as the actual value and this then stored in an electronics with there , the setpoint value representing image data or characteristic values compared and from this the necessary for the necessary position correction control of the actuator of the container receptacle is made ( EP 1 205 388 ). In one embodiment of this known device, the camera system has four cameras, which are provided consecutively along the movement path of the container receptacles in the direction of rotation of the rotor. Each camera captures each part of the circumference of the container, overlapping each 100 ° of this circumference with rotating around its container axis containers. Due to the actual image data supplied by the cameras, a rotational position correction of the container recordings and then takes place the orientation of the containers relative to their typical geometric container feature.

The object of the invention is to provide a device with which an alignment of containers with respect to at least one typical, geometric container feature with a significantly improved accuracy is possible, and in particular at a high power, i. at a plurality of processed per unit time container. To solve this problem, a device according to the patent claim 1 is formed. a labeling machine is the subject of claim 23.

In the apparatus according to the invention, the image data of a first camera system are used to pre-align the containers in such a way that they have at least approximately the required orientation after pre-aligning, in particular also with respect to their geometrical container features used for the alignment, namely at least one Accuracy as achievable with known devices. With this first camera system, the test area, i. H. the circumferential region of the respective container, where the at least one geometric container feature is located, detected over a large area.

With the image data of at least one other camera system then takes place a more accurate, possibly even the final orientation of each container. Since the container area detected by the at least one camera of the at least one further camera system is much smaller than the area to be detected by the at least one camera of the first camera system, d. H. the at least one camera of the further camera system e.g. a much smaller opening angle than the at least one camera of the first camera system, the alignment using the image data supplied by the at least one further camera system can be done very precisely in an extremely short time.

Fig. 1

in schematischer Darstellung eine Etikettiermaschine umlaufender Bauart;

Fig. 2 - 7

verschiedene Darstellungen zur Erläuterung des Algorithmus bei der Ermittlung des für die Korrektur der Orientierung notwendigen Drehwinkels ber Behälteraufnahmen.

The invention will be explained in more detail below with reference to the figures of exemplary embodiments. Show it:

Fig. 1

in a schematic representation of a labeling machine of rotating design;

Fig. 2-7

various illustrations for explaining the algorithm in the Determining the angle of rotation necessary for the correction of the orientation over container receptacles.

The labeling machine shown in FIG. 1 and designated generally by 1 serves for labeling containers 2, for example bottles, which are supplied to the labeling machine 1 at a container inlet 3 and leave the labeling machine 1 in a labeled outlet at a container outlet 4. The containers 2 are for example bottles made of a translucent material, e.g. made of glass, and are at their container outside with at least one typical geometric container feature such. B. sealing surface, ornament, embossing, raised lettering, etc. provided. The containers 2 are to be provided with high accuracy of application in relation to these geometric features with the labels.

The labeling machine 1 comprises u. a. the rotatable about a vertical axis of the machine in the direction of arrow A rotary table or rotor 5, which has at its periphery a plurality of container carriers or receptacles 6, which are each distributed at equal angular intervals around the vertical axis of the machine and at which for applying the Labels each a container 3 is provided with its container axis parallel to the vertical machine axis.

The containers 2 are the labeling machine 1 on the container inlet 3 via a conveyor, not shown, upright, ie oriented with its container axis in the vertical direction, but otherwise fed in any random orientation also in terms of their typical geometric container characteristics, in this purely random orientation each pass a container receptacle 6 and then aligned in an angular range W1 of the rotational movement A of the rotor 5, so that each container 3 is exactly aligned at the end of this angular range with respect to its typical geometric container characteristics, ie having a predetermined orientation. In this state, each container 2 is moved past a labeling station 7, which does not move with the rotor 5, for applying at least one label, so that it is then applied to the respective container 2 with the desired high accuracy of application with respect to the geometric container features. In the following on the labeling station 7 to the container outlet 3 angle range W2 of the rotational movement A of the rotor 5 is then carried out the usual pressing and / or brushing the labels.

For the alignment of the container 2, the container receptacles 6 are each rotatable about their own actuators about an axis parallel to the vertical machine axis, namely controlled by a multi-level image recognition system explained in more detail below with a plurality of electronic cameras 9-11 and an associated, preferably formed by a computer Evaluation and control electronics 12.

In the illustrated embodiment, the non-moving with the rotor 5 cameras 8 - 11 are each arranged radially outside the trajectory of the container receptacle 6 such that with each camera, the passing container 2 at least on the test area or on the typical geometric container features having their Container outer surface are detected. Furthermore, all cameras are 8-11 within the angular range W1 and thus in the direction of rotation A in front of the labeling station. 7

In detail, the two cameras 8 and 9, which are arranged in a following on the container inlet 3 portion of the angular range W1, a first Kammerasystem or a first stage of the image recognition system, together with a not moving with the rotor 5, a white Background or a white background mirror forming background element 13, which in the illustrated embodiment with respect to the circular path of movement of the container receptacles 6 radially inwardly and the two cameras 8 and 9 is arranged opposite, and together with a direction indicated by the arrow B1 front lighting. The two cameras 8 and 9 are arranged with their optical axes at an angle to each other such that with them a peripheral region or a settlement greater than 180 ° of the respectively moved past container 2 is detected. For this purpose, the images or image data supplied by the two cameras 8 and 9 are combined, for example, into an overall image or an overall data set which corresponds to an image of the development or of the container peripheral region of greater than 180 °.

The first stage of the image recognition system is followed by the second stage of this system formed by the single camera 10. The camera 10 is in turn associated with a background element 14 corresponding to the element 13 and forming a white background or a white background mirror, specifically in the illustrated embodiment with respect to the movement path of the container receptacle 6 radially inward. Furthermore, this second stage has a front lighting, as indicated by the arrow B2. Of course, the elements 13 and 14 of the first and second stages may also be formed by a single, continuous element. Furthermore, the front lighting for both stages can also be formed by one or more common light sources, for example luminescent screens. In principle, it is also the case that, depending on the optical properties of the containers for the foreground lighting, a respective lighting technique is selected which enables optimum detection of the container features used to align the containers. Furthermore, by a special design of the background element 13 and / or 14, for example by a partial blackening of the white background element 13 and / or 14, increased optical detection of edge profiles of the container features used for the alignment can be achieved.

Following in the direction of rotation A on the second stage (camera 10), the third stage of the image acquisition system formed by the single camera 11 is provided, namely with a backlight B3, for example, from a fluorescent screen 15 on the camera 11 not moved with the rotor 5 The backlight B3 is selected in terms of color and / or intensity as a function of the optical properties of the container 2 or the container material and / or depending on the optical properties of the filling material for optimal optical detection or adjustable.

In detail, the alignment of the container 2 with the image recognition system takes place in such a way that with the first stage or with the two local cameras 8 and 9, the respective random orientation of the passing container 2 with one receptacle per container and camera 8 and 9 respectively is detected. By subsequent comparison of the images or image data supplied by the two camera systems 8 and 9 in the electronics 12 with images or image data or typical characteristic values stored there in a data memory for the corresponding container type, the current orientation of the respective container 2 is determined in the electronics 12 , From this determines the necessary correction to achieve the required advance direction and performs the correction by appropriate control of the actuator of the respective container receptacle 6.

For each individual container 2, the position correction is carried out in the described manner by driving the container receptacle 6 in this manner, so that each container 2 is aligned at least with a positional accuracy which is the subsequent exact detection of the position of the at least one typical container feature used for the final alignment allows.

In the second stage of the image recognition system formed by the camera 10, each moved container 2 is detected in a narrower area of its typical geometric container feature. The optics of the camera 10 for this purpose, for example, designed so that the optical aperture angle of the camera 10 is smaller than the corresponding aperture angle of the cameras 8 and 9 and the region of the respective container having the typical geometric container feature is shown as full format filling. The image thus generated by each container 2 is in turn compared in the electronics 12 with a stored there for the container type or image stored for the particular type of container characteristics, then determines the necessary position correction and then by appropriate control of the actuator of the respective container receptacle. 6 causes. Due to the image area reduced to the typical container feature, the second stage of the image recognition system already achieves a very precise orientation of each container 2, in particular also with respect to the pre-alignment (with the first stage).

With the third stage formed by the camera 11, a fine adjustment or fine alignment of each container 2 takes place before it reaches the labeling station 7. As a criterion in this fine alignment, for example, at least one edge profile or at least one typical edge point is used, namely on the at least one typical container feature used for aligning and / or in the region of this container feature. The image data delivered by the camera 11 are in turn compared in the electronics 12 with image data stored there for the respective container type or with characteristic values stored there for the respective container type, so that the still necessary position correction is calculated from this comparison and the appropriate actuation of the actuator relevant container receptacle can be made.

By the above-described three-stage optical detection of the container 2 or the typical container features a very precise orientation of the labeling machine 1 is fed in arbitrary orientation or positioning Container with only four Kaneras reached before they reach the labeling station 7, so that the desired application accuracy in applying the labels with respect to the typical geometrical container characteristics with high reliability even at a very high performance for the labeling, for example, with a labeling of several tens 000 containers per hour is guaranteed.

$$\mathrm{Formel}\left(2\right):z_i=2R\begin{array}{}\end{array}\arctan \left(\frac{d\begin{array}{}\end{array}R-\sqrt{d^2{R}^2+x_i^2\left(R^2-d^2\right)}}{x\left(d+R\right)}\right)$$

Dabei gibt R den Flaschenradius an und d den Abstand der Kamera zur Flaschenmitte.The details of an algorithm used in at least one of the stages of the image recognition system to determine the necessary correction will be explained below.
In order to be able to precisely detect the angle of rotation with an accuracy of at least one degree, the cylindrical geometry of the bottle surface must be taken into account. With known acquisition geometry (distance of the camera to the bottle, diameter of the bottle) and known geometry of the embossing pattern can be calculated on the invoice shown in the appendix for each angle of rotation of the bottle (eg in 0.5 degree increments), as the embossing pattern for an observer (= Camera) on the bottle surface is distorted. These calculated distorted imprint patterns must now be compared to the observed imprint pattern on a picked bottle. The calculated emboss pattern that best matches the observed pattern determines the angle of rotation of the bottle.
Fig. 2 shows by way of example a typical container feature, an embossing pattern 16 on a bottle in a nearly frontal view. The edge of the bottle as well as the center of the wrong one is marked with a thin vertical red line. From this frontal view, let the angle of rotation be zero degrees. Of course one defines the zero point of the rotation angle on the basis of the symmetry of the embossing pattern (thus "in the middle of the embossing pattern"). Along the horizontal test line 17, the points 17.1 - 17.7 are indicated where the embossing intersects the test line 17. These points are referred to below as imprinting points.
The variable x _i denotes the position of an embossed point in a captured image and z _{i represents} the world coordinates on the surface of the bottle. The running index i numbers the individual embossing points.
Fig. 3 shows the same embossing pattern with the bottle twisted 24 degrees to the left. The imprints are also marked in this picture. Due to the rotation of the bottle, the position and the distances of the embossing points 17.1 - 17.7 have changed in a characteristic manner. For example, has due to the perspective distortion on the cylindrical bottle body of the visible distance from two adjacent imprinting points, which have nourished the left edge of the bottle, compared to the untwisted state shortened. With even more twisting, parts of the embossing pattern would disappear behind the bottle horizon.
A geometric calculation according to FIG. 5 leads to the formulas (1) and (2). $$\mathrm{formula}\left(1\right):x_i=\frac{d\begin{array}{}\end{array}R\begin{array}{}\end{array}\sin \left(z_i/R\right)}{d-R\begin{array}{}\end{array}\cos \left(z_i/R\right)}$$

$$\mathrm{formula}\left(2\right):z_i=2R\begin{array}{}\end{array}\arctan \left(\frac{d\begin{array}{}\end{array}R-\sqrt{{\mathrm{<figure-callout\; id="2"\; label="d"\; filenames="imgf0001.png"\; state="\{\{state\}\}">d</figure-callout>}}^2{\mathrm{<figure-callout\; id="2"\; label="R"\; filenames="imgf0001.png"\; state="\{\{state\}\}">R</figure-callout>}}^2+x_{\mathrm{<figure-callout\; id="2"\; label="i"\; filenames="imgf0001.png"\; state="\{\{state\}\}">i</figure-callout>}}^2\left(R^2-d^2\right)}}{x\left(d+R\right)}\right)$$

Where R is the bottle radius and d is the distance from the camera to the center of the bottle.

With these formulas, it is possible to convert the position x _{i seen} from embossing points 17.1 - 17.7 into world coordinates z _i on the bottle surface and vice versa. In order to be able to calculate the exact distribution of embossing points 17.1 - 17.7 along a horizontal test line 17 to any angle of rotation of the bottle, the position z _{i of} all embossing points 17.1 - 17.7 on the surface of the bottle must be known at a known angle of rotation (eg at zero degrees) with respect to the symmetry axis (= Zero point) of the embossing pattern to be known. The position z _{i of} a stamping point is defined by the distance from the bottle center measured measured along the bottle surface.
In principle, the position z _{i of} the individual embossing points with respect to the center line can now be measured by applying a measuring tape to the bottle body and made available in a list to the recognition algorithm. However, the formula (2) allows to obtain this information directly from a captured image. For this purpose, the position x _{i is} determined in the image with a known rotation angle. With a known bottle radius R and known distance d to the respective camera (8, 9, 10, 11), the world coordinates z _i on the bottle surface can be determined therefrom by means of formula (2).
The learning of an embossing pattern for the recognition algorithm is thereby greatly simplified. As illustrated in FIGS. 2 and 3 by the embossing points 17. 1 - 17. 7, a user program can be executed in a computer program in which a user can mark the intersection points of the embossing pattern with a test line 17. With the help of formula (2) can then be clicked immediately Convert screen functions x _i to world coordinates z _i on the bottle surface. Thus, the user can provide the embossing pattern to the algorithm in the form of a list of embossing points 17.1-17.2.
Once the imprinting points z _{i are determined} in world coordinates for a stamping pattern, they can be converted into positions x _i seen in the opposite direction for any angle of rotation of the bottle by the formula (1). The recognition algorithm can therefore calculate the positions x _i (φ) for the given embossing pattern for all possible angles of rotation φ of the bottle. In practice, it has been proven that the detection algorithm performs this calculation for all angles of rotation φ _k with an angular distance of 0.25 degrees, ie
φ _k = 0.25 degrees * k with k = 0, ± 1, ± 2, ± 3, .... For every angle φ _k, the algorithm can and must hold the associated distribution of the observed positions x _i (φ _k ) in memory Do not recalculate them for the pattern search for the next bottle with the same embossing pattern. This can save a lot of computing time.
Next, the algorithm has to decide which distribution x _i (φ _k ) best fits the situation observed in the image. For this purpose, a method is used which assigns a score S _k to each distribution x _i (φ _k ). This score is designed to be the larger the better the observed situation fits a distribution. The largest evaluation number S _kMax , which is achieved for a given image situation, thus defines the angle of rotation φ _{kMax of} the bottle.
For the calculation of a score S _k , the brightness curve H (x) along the test line 17 is determined first (FIG. 6). x denotes the pixel position along the horizontal test profile.

Bereiche, in denen sich keine Prägungspunkte befinden, weisen dann sehr kleine Werte H_Sub(x) auf, wohingegen an einem Prägungspunkt hohe Werte zu finden sind. Durch Wahl eines geeigneten Schwellwertes können auf diese Weise die Orte b_i der Prägungspunkte in dem gegeben Bild identifiziert werden.
Die Bewertungszahl S_k für eine Verteilung der gesehenen Positionen x_i(φ_k) wird dann auf folgende Weise berechnet:
Es wird das Punktepaar b_i und x_j mit dem kleinsten Abstand gesucht. Wenn dieser Abstand kleiner als eine vorgegebene maximale Distanz d ist, dann wird das gefundene Punktepaar als passend gewertet, d.h. es wird angenommen, dass die im Bild gefundene Position des Prägungspunktes b_i mit einer Position des Prägungsmusters zu der Flaschenverdrehung φ_k passt. In diesem Fall wird zur Bewertungszahl S_k ein Bonusbeitrag addiert. Da die Prägungsmuster verschiedener Flaschen nie alle ganz exakt gleich sind, die Flaschengeometrie sowie die Flaschenposition zur Kamera bei der Bildaufnahme Schwankungen unterworfen ist, kann man nie von einer exakten Übereinstimmung eines Punktespaars b_i und x_j ausgehen. Deshalb wird über die maximale Distanz d verlangt, dass die Punkte hinreichend nahe beisammen liegen müssen. Wurde ein Punktepaar auf diese Weise gefunden, dann werden diese als bereits zugeordnet in einer internen Liste des Algorithmus markiert. Für den verbleibenden Rest der Punkte wird dann der Vorgang solange wiederholt, bis alle möglichen Punkte entweder zugeordnet worden sind oder bis alle Punkte als nicht zuordenbar erkannt wurden (d.h. es wurde für einen Punkt bi kein Modelpunkt x_j gefunden, der hinreichend nahe liegt).
Wenn für Modellpunkte x_j keine entsprechenden Punkte bi gefunden wurden, dann werden hierfür Malusbeiträge von der Bewertungszahl S_k abgezogen.
Die Figur 7 zeigt für das in der Figur 3 gezeigte Beispiel die Abhängigkeit der Bewertungszahl S_k in Abhängigkeit vom Winkel. Man erkennt, dass es ein scharfes Maximum bei ca. -24 Grad gibt, d.h. das gesehene Punktemuster b_j am besten dem Punktemuster x_j bei einem Flaschendrehwinkel von -24 Grad entspricht.In such a brightness profile, embossing points are noticeable by significant fluctuations in brightness on a length scale which corresponds to the approximate width of an imprinting point. However, these brightness fluctuations are also superimposed on other brightness fluctuations, which however all take place on a significantly larger length scale and can thus be separated from the brightness fluctuations caused by embossing points in the following manner: From the brightness profile H (x), a brightness profile H _Ave (x) is calculated is smoothed on a length scale, which is well above the width of an imprinting point. This smoothed brightness profile H _Ave (x) is subtracted from the original brightness profile H (x) and considers only the amounts of the differences, ie $${\mathrm{H}}_{\mathrm{Sub}}\left(\mathrm{x}\right)=\left|\mathrm{H}\left(\mathrm{x}\right)-{\mathrm{H}}_{\mathrm{Ave}}\left(\mathrm{x}\right)\right|$$

Areas in which there are no embossing points then have very small values _Hsub (x), whereas at an embossing point high values are to be found. By choosing a suitable threshold value, the locations b _{i of} the imprinting points in the given image can be identified in this way.
The score S _k for a distribution of the viewed positions x _i (φ _k ) is then calculated as follows:
We search for the pair of points b _i and x _j with the smallest distance. If this distance is smaller than a predetermined maximum distance d, then the pair of points found is judged to be suitable, ie it is assumed that the position of the embossing point b _i found in the image matches a position of the embossing pattern to the bottle twist φ _k . In this case, a bonus contribution is added to the rating number S _k . Since the embossing patterns of different bottles are never quite exactly the same, the bottle geometry and the bottle position to the camera are subject to fluctuations during image acquisition, one can never assume an exact match of a pair of points b _i and x _j . Therefore, the maximum distance d requires that the points be sufficiently close together. If a pair of points has been found in this way, they are marked as already assigned in an internal list of the algorithm. For the remainder of the points, the process is then repeated until all possible points have either been assigned or until all points have been identified as unassignable (ie no model point x _{j has been} found sufficiently close for a point bi).
If no corresponding points bi were found for model points x _j , then penalty contributions are deducted from the evaluation number S _k .
FIG. 7 shows, for the example shown in FIG. 3, the dependence of the evaluation number S _k as a function of the angle. It is evident that there is a sharp peak at approximately -24 degrees, ie the seen points pattern best x _j corresponds to the _j b dot pattern with a bottle rotation angle of -24 degrees.

The invention has been described above by means of an embodiment. It is understood that numerous changes and modifications are possible without thereby departing from the inventive idea underlying the invention. Thus, it was previously assumed that the first stage of the image recognition system two cameras 8 and 9 and the second or third stage each have only one camera 10 and 11 respectively. Of course, the number of cameras in these stages may also be chosen differently, but it is necessary, but at least advisable, for the first-stage camera system to detect as large a peripheral area as possible of the container 2 passed by.

In the illustrated embodiment, the cameras 8, 9, 10 and 11 are each designed and / or driven in such a way that they are each created an image or an image data set of each container 2 passed and then the pre-alignment (in the first stage) on the basis of this image data set. , the pre-adjustment (in the second stage) and the fine adjustment (in the third stage) by comparison with the respective image data.

LIST OF REFERENCE NUMBERS

1

labeling

2

Container or bottle

3

container inlet

4

container outlet

5

Rotor or turntable

6

container receptacle

7

labeling

8, 9, 10, 11

electronic camera

12

Evaluation and control electronics

13, 14

Background element or background mirror

15

Backlight element, for example, luminescent screen

16

Embossing pattern or container feature

17

test line

17.1 - 17.7

Cutting or embossing point

A

Direction of rotation of the rotor 5

B1, B2, B3

lighting

W1, W2

Angular range of the rotational movement of the rotor 5

Claims (23)

Device for aligning containers (2) with respect to at least one geometric container feature (16) in a desired position or orientation, with a conveyor (5) with container receptacles (6) for receiving a respective container, and along one of the conveyor ( 5) formed transport path angeorneten cameras (8, 9, 10) of an image recognition system, which by comparing the of the cameras (8, 9, 10, 11) delivered actual image data with in an evaluation and control electronics (12) stored target Image data or characteristics causes alignment of the container (3), characterized
that forming a first stage of the image recognition system first camera system takes an advance direction of the container (3) and the at least one camera (8, 9) of said first camera system having outer or peripheral surface of the container detected in the typical geometric container feature (16) over a large area in that at least one further camera system following in the transport direction for further alignment with its at least one camera (10, 11) detects the respective container (2) guided past for further alignment in a narrower area of the peripheral surface having the at least one typical geometric container feature (16) , And that the electronics due to further stored image data or characteristics in existing deviations from the target position on the actuator of the respective container receptacle (6) causes a further alignment. Apparatus according to claim 1, characterized in that in the transport direction (A) of the carrier (5) following the first stage of the image recognition forming first camera system following at least a second, a second stage of the image recognition system forming camera system and a third, a third stage of the image recognition system forming camera system with at least one camera (10, 11) is provided. Apparatus according to claim 1 or 2, characterized in that with the first camera system or the at least one camera (8, 9) of this system, a peripheral region of the respective container (2) of greater than 180 ° is detected. Device according to one of the preceding claims, characterized in that the first camera system comprises at least two cameras (8, 9) which are arranged with their camera axes at an angle relative to each other. Apparatus according to claim 4, characterized in that the images or image data supplied by the at least two cameras (8, 9) of the first camera system in the electronics (12) are combined to form an overall image. Device according to one of the preceding claims, characterized in that at least one camera system has at least two cameras (8, 9). Device according to one of the preceding claims, characterized in that the at least one further camera system, in particular the second and third camera system each have only one camera (10, 11). Device according to one of the preceding claims, characterized in that the camera systems or their cameras for generating individual images of the past-moving containers (3) are formed. Device according to one of the preceding claims, characterized in that the cameras (8, 9, 10, 11) of the camera systems are designed and / or controlled such that they only generate one image from the respectively guided container (2). Device according to one of the preceding claims, characterized in that at least one camera system, preferably the first camera system with a front lighting (B1, B2) is formed. Device according to one of the preceding claims, characterized in that at least one camera system, for example the at least one further camera system or the third camera system for the production of images or image data is formed by translucency. Device according to one of the preceding claims, characterized in that at least one camera system with a backlight is executed. Device according to one of the preceding claims, characterized in that the foreground or background illumination in color and / or intensity is adjustable. Device according to one of the preceding claims, characterized in that the feed dog is a rotor (5) which can be driven circumferentially about a vertical machine axis. Device according to one of the preceding claims, characterized in that each container receptacle (6) has its own actuator. Device according to one of the preceding claims, characterized in that the container receptacles (6) are turntable. Device according to one of the preceding claims, characterized in that the electronics (12) the distance, the at least two reference points (17.1 to 17.7) of the typical container feature (16) of the respective container (2) in the at least one camera (8, 9, 10, 11) compared with stored for the container type characteristics. Apparatus according to claim 17, characterized in that the electronics consist of a spacing pattern of a plurality of distances between reference points (17.1 - 17.7) of the typical container feature (16) of the respective container (2) in the at least one camera (8, 9, 10, 11 ) compared with at least one stored for the container type spacing pattern. Apparatus according to claim 17 or 18, characterized in that the electronics (12) the distance or the spacing pattern of the reference points (17.1 - 17.7) in the of the at least one camera (8, 9, 10, 11) supplied image data for the Container type stored distances or distance patterns compares, determines the distance with the best match in the image data distance or the best match with the distance pattern in the image data distance pattern and from this the necessary correction determined for the orientation of the container (2). Device according to one of the preceding claims, characterized in that it is part of a labeling machine (1) with a container inlet (3) for the container to be labeled (2), with a container outlet (4) for the labeled container (2) and at least one on one of the conveyor (5) between the container inlet (3) and the container outlet (4) formed transport path provided labeling station (7), and
in that the first camera system and the at least one further camera system are provided on the transport path between the container inlet (3) and the at least one labeling station (7). Apparatus according to claim 20, characterized in that the feed dog is a rotor (5) revolving around a vertical machine axis and having a plurality of container receptacles (6). Device according to one of the preceding claims, characterized in that each container receptacle for aligning the receptacle (3) provided on this receptacle is rotatable by an actuator driven by the electronics. Labeling machine with a device for aligning containers (2) with respect to at least one geometric container feature (16) in a desired position or orientation, characterized in that the device is designed according to one of the preceding claims.

Images