DE102021117716A1 - Method, computer-readable storage medium, apparatus and system for selecting a photograph - Google Patents

Abstract

The invention relates to a method for selecting a photograph, a corresponding computer-readable storage medium and a device for carrying out the method. The method comprises the following steps:a) receiving a large number of input images;b) selecting at least one candidate image from the input images using a first selection criterion;c) specifying a template image section;d) generating at least one target image section in the at least one candidate image, the corresponds to the template image section;e) applying at least one algorithm for image processing with a first set of parameters and/or parameter values to the at least one target image section to generate processed candidate images;f) selecting at least one pre-selection image from the set of processed candidate images using a second selection criterion; g) checking whether a pre-selection recording exists that satisfies a final test criterion and if so, selecting such a pre-selection recording as the final recording, otherwise h) repeating steps e) to g), the at least e uses a preselection shot as the at least one candidate shot

Description

The invention relates to a method for selecting a photograph, a corresponding computer-readable storage medium, and a device and a system for carrying out the method.

Cameras are used for a variety of purposes in industrial production plants, particularly in the context of quality assurance. Here, photographic recordings (also referred to below as recordings) of the objects to be checked are created by cameras, with these recordings then being examined by special image processing methods. In this way, for example, the presence of plastic rivets and seals can be automatically detected in the automotive industry, weld nuts can be recognized and the alignment of body parts can be checked before welding.

It is not uncommon for black-and-white cameras (SW cameras) to be used in the above-mentioned areas of application, since they are cheaper to buy, depending on the application. In addition, black-and-white cameras offer the advantage of being able to produce recordings with a comparatively small amount of data.

In general, however, capturing a colored object in black and white, like converting a color image to grayscale, is lossy. For example, in such a process, an appropriate pair of blue and red are mapped to the same gray value, rendering these colors indistinguishable through a grayscale conversion.

For this reason, color information of a recorded object cannot be restored from a black-and-white recording without additional information. Therefore, the success of further use of a black-and-white photograph depends crucially on whether relevant information (e.g. contours) can be recognized on the black-and-white photograph.

In order to emphasize relevant areas or contours of the recorded object in a black-and-white recording or to be able to better distinguish them from one another, the object can be suitably illuminated with colored lighting sources during the recording process. For example, red areas of an object appear almost white when illuminated with a red light source in the black-and-white photograph, while blue areas appear very dark.

In addition to suitable lighting, there are a number of other parameters when taking a picture, such as the camera's detection area, focus, exposure time, etc., which determine the quality of the picture. The success of further processing steps therefore depends crucially on the selected parameter values. A suitable set of parameter values must often be determined individually for the respective application, which is also referred to as teaching a camera. Various approaches are known in the prior art for simplifying this process, in particular for the case in which the learning has to be carried out (partially) by a user.

the DE 10 2018 119 691 A1 shows a camera system for capturing codes. According to the invention, positions of contour points of the coding in relation to the edges of a search zone of the camera system are determined and analyzed. For example, if a large part of the contour points falls in a border area of the search zone of the camera system, this indicates that the search zone should be chosen differently. This can then be done manually or automatically. In this way, a higher reading security can be guaranteed.

In the DE 10 2019 113 647 A1 describes a camera system for detecting objects and/or object properties, which, in addition to the object to be detected, detects further image features and information about faulty detections. If, for example, it is established that detections of images with an increased mean gray value are often faulty, appropriate feedback can be output to the user, who can then correct the settings.

In the DE 10 2015 216 446 A1 a method for checking the completeness of a container with a plurality of objects using a 3D camera is improved in such a way that the user is supported in the selection of suitable parameters. The parameters are, in particular, threshold values for height values that determine whether a location in a container is classified as occupied or unoccupied. A central aspect of the method is to provide the user with two displays simultaneously, the first showing a two-dimensional view of the container, the second showing the detected height values with adjustable threshold values. This gives the user a better overview of the effects of the set threshold values.

the DE 10 2019 103 397 A1 shows a method of operating a camera to capture codes. Through a modular mode of operation camera, the learning phase, which is necessary for reliable detection and usually has to be carried out manually, can be carried out by the camera itself.

Proceeding from the prior art, the object of the invention is to improve the selection of photographic recordings. In particular, the method should support the selection of a suitable RGB-W lighting setting as well as parameters and parameter values of algorithms for image processing.

This object is achieved by a computer-implemented method according to patent claim 1, a computer-readable storage medium according to patent claim 9, an image processing device according to patent claim 10 and a recording system according to patent claim 11.

1. a) Empfangen von einer Vielzahl von Eingangsaufnahmen, die ein zu erfassendes Objekt in einer Vielzahl von Beleuchtungseinstellungen angeben, wobei die Beleuchtungseinstellungen durch unterschiedliche Konfigurationen einer RGB-W-Beleuchtungseinheit und/oder durch mindestens einen Polarisationsfilter angegeben sind und ein Weißbild umfassen;
2. b) Auswählen von mindestens einer Kandidatenaufnahme aus den Eingangsaufnahmen anhand eines ersten Auswahlkriteriums;
3. c) Festlegen eines Vorlagenbildausschnitts in dem Weißbild;
4. d) Erzeugen von mindestens einem Zielbildausschnitt in der mindestens einen Kandidatenaufnahme, der zu dem Vorlagenbildausschnitt korrespondiert;
5. e) Anwenden mindestens eines Algorithmus zur Bildverarbeitung, insbesondere Konturenerkennung, Blobanalyse, Regionenanalyse, Codeanalyse oder Modell-Matching, mit einem ersten Satz von Parametern und/oder Parameterwerten auf den mindestens einen Zielbildausschnitt zur Erzeugung von verarbeiteten Kandidatenaufnahmen;
6. f) Auswählen von mindestens einer Vorauswahlaufnahme aus der Menge der verarbeiteten Kandidatenaufnahmen anhand eines zweiten Auswahlkriteriums;
7. g) Prüfen, ob eine Vorauswahlaufnahme existiert, die einem finalen Prüfkriterium genügt und wenn ja, Auswählen einer solchen Vorauswahlaufnahme als finale Aufnahme, andernfalls
8. h) Wiederholen der Schritte e) bis g), wobei die mindestens eine Vorauswahlaufnahme als die mindestens eine Kandidatenaufnahme verwendet wird und in Schritt e) ein zweiter, insbesondere von einem Benutzer vorgegebener, Satz von Parametern und/oder Parameterwerten verwendet wird.

In particular, the object is achieved by a computer-implemented method, in particular user-guided, for selecting a photograph, the method comprising the following steps:

1. a) receiving a plurality of input images indicative of an object to be captured in a plurality of illumination settings, the illumination settings being indicated by different configurations of an RGB-W illumination unit and/or by at least one polarizing filter and comprising a white image;
2. b) selecting at least one candidate recording from the input recordings based on a first selection criterion;
3. c) defining a template image section in the white image;
4. d) generating at least one target image section in the at least one candidate recording, which corresponds to the template image section;
5. e) Applying at least one algorithm for image processing, in particular contour recognition, blob analysis, region analysis, code analysis or model matching, with a first set of parameters and/or parameter values on the at least one target image section to generate processed candidate recordings;
6. f) selecting at least one pre-selection recording from the set of processed candidate recordings using a second selection criterion;
7. g) Checking whether there is a pre-selection recording that satisfies a final test criterion and, if so, selecting such a pre-selection recording as the final recording, otherwise
8. h) repeating steps e) to g), wherein the at least one preselection recording is used as the at least one candidate recording and in step e) a second set of parameters and/or parameter values, in particular specified by a user, is used.

A core idea of the method lies in the fact that at the beginning of the method there is a large number of input recordings with different lighting settings and not a single one, but potentially several of them form the basis for further method steps. This prevents an early commitment to an illumination setting that turns out to be suboptimal for later processing steps.

The input recordings include a white image, which can be understood here as a recording of the object to be recorded, in which the RGB-W lighting unit illuminates the object with white light. The white image is used to define a template image detail, with an image detail being understood in the context of this invention as the combination of any number of areas of a single recording. In particular, an image section can include several non-contiguous areas of the recording, for example non-overlapping, elliptical areas, e.g. three.

Another aspect of the method is the selection of recordings based on a first and second selection criterion and a final test criterion. The totality of these criteria means that a single final recording is finally selected from the large number of input recordings. According to the invention, several criteria are provided for this, which do not necessarily have to be identical. In this way it is allowed that different aspects for the selection of recordings can be taken into account for different processing steps of the method.

At least one image processing algorithm for further optimization is applied to a preselection of input images, which is referred to as a set of candidate recordings and is selected according to the first selection criterion. In particular, this can be an algorithm that recognizes contours in a recording. For this purpose, image sections in the candidate recordings, called target image sections, are defined beforehand. This ensures that the algorithmic image processing is focused on the relevant areas of the image. Otherwise there is There is a risk that features outside the relevant areas, especially at the edges of the image, will affect image processing.

A further point of the invention is to carry out the image processing described repeatedly if the results of the first execution are assessed as insufficient, since, for example, relevant contours have not yet been recognized in the algorithmic image processing. To this end, steps e) to g) can be carried out repeatedly until there is a preselection recording that satisfies the final test criterion.

In a preferred embodiment, a natural number i_max can be defined so that the number of repetitions of steps e) to g) according to step h) does not exceed i_max. For example, by choosing i_max=3, it can be ensured that the method terminates after three repetitions at the latest. Since algorithmic image processing is fundamentally resource-intensive, a high number of repetitions can be undesirable in practice. An early termination after a preset number of repetitions can make it possible, for example, to adjust the final test criterion and thus start the process again.

A further embodiment can provide for the white image to be selected as the final image in the event that no preselection image that satisfies the final test criterion exists in an execution of step g). Depending on the area of application, it may be desirable for the method to always return an image, for which the white image, as a neutrally illuminated image of the object, is ideal.

• - mindestens eines der Auswahlkriterien oder das finale Prüfkriterium durch den Benutzer derart vorgegeben ist, dass wenigstens eine Aufnahme aus der Menge der jeweils wählbaren Aufnahmen ausgewählt wird, und/oder
• - der Vorlagenbildausschnitt durch den Benutzer, insbesondere mittels geometrischer Auswahlwerkzeuge und/oder durch ein Pinselwerkzeug, festgelegt wird.

In one embodiment of the method, a user can exist such that

• - at least one of the selection criteria or the final test criterion is specified by the user in such a way that at least one recording is selected from the set of recordings that can be selected in each case, and/or
• - the template image section is defined by the user, in particular by means of geometric selection tools and/or a brush tool.

This embodiment arises in particular when there is no suitable formal description for a selection criterion, the final test criterion or the selection of the template image section that a computer can evaluate, but a user can actively make this selection. In order to define a selection criterion or a final test criterion, the method preferably provides the user with an overview of all images available for selection in a lower resolution, in which he can select or deselect one or more images. The template image section can be defined in a user-friendly manner using geometric selection tools, in particular in the form of a rectangle and ellipse, and/or using a brush tool.

According to a further embodiment, at least one of the selection criteria or the final test criterion can be that at least one parameter of a recording is maximized and/or exceeds a predetermined threshold value. The parameters can in particular be an intensity difference between a brightest point and a darkest point, dynamics, contrast and/or image sharpness. This can be used as an indicator that a recording meets minimum requirements for reuse. It is also a criterion that is easy to check algorithmically.

A further embodiment can provide that at least one of the selection criteria or the final test criterion depends on an evaluation result of at least one algorithm for image analysis. The algorithm for image analysis can in particular be an algorithm for contour recognition, blob analysis, code analysis or model matching.

With contour detection, contours on object edges can be extracted, saved as reference contours and searched for in subsequent images. To evaluate how similar a section of the current image is to the reference contours, a value can be calculated that can be understood as a percentage agreement with the reference. If the value exceeds a predefined threshold, the area under consideration is evaluated as a match. An image is rated good if a predefined number of matches are found.

In a blob analysis, an image is segmented using gray value thresholds, i.e. individual objects are separated from the background. Properties, such as size, are now determined for each individual object. If all properties of an object are within specified limits, the object is rated as "good". An image is rated as "good" if a specified number of good objects are found. Optionally, the total area of all objects rated as good can also be considered as a decision criterion for the image.

Using code analysis, one- or two-dimensional codes of various types (e.g EAN13, QR code) can be searched for and read out in an image.

By means of a model matching, an entire image section can be determined as a reference and searched for in the following images. The similarity to the reference can be quantified via correlation.

In a preferred embodiment, the method can use a collection of reference images to evaluate at least one of the selection criteria or the final test criterion. Accordingly, an image is selected if at least one reference image exists, so that a distance value between the image and the reference image falls below a predetermined threshold value. Here, the distance value is measured in a suitable metric. This can be, for example, the Earth Mover's Distance (EMD) or the Euclidean distance of the gray value histograms.

An embodiment is preferred in which the method in step d) can generate the at least one target image section in the at least one candidate recording as follows: The at least one polygonal line corresponding to the template image section is transformed into at least one second polygonal line. Here, the at least one polygon that corresponds to the template image section is defined in a first coordinate system of the white image and the at least one second polygon is defined in a second coordinate system of the at least one candidate recording. The advantage of this embodiment is that the at least one candidate recording does not necessarily have to have the same dimensions as the white image.

The object is further achieved in particular by a computer-readable storage medium which contains instructions which cause at least one processor to implement a method as described above when the instructions are executed by the at least one processor.

In addition, the object is achieved in particular by an image processing device that has a computer-readable storage medium as described above and a computing unit. In this case, the computing unit is designed to execute stored instructions on the computer-readable storage medium.

• - eine Bildverarbeitungsvorrichtung wie vorstehend beschrieben,
• - eine SW-Kamera und
• - eine RGB-W-Beleuchtungseinheit.

In particular, the object is also achieved by a recording system that has the following components:

• - an image processing device as described above,
• - a SW camera and
• - a RGB-W lighting unit.

In this case, the black and white camera is designed to take pictures of an object to be captured in a multiplicity of lighting settings, the lighting settings being specified by different configurations of the RGB-W lighting unit and comprising a white image. Furthermore, the SW camera is designed to provide the recordings of the image processing device.

According to one embodiment, the components of a recording system as described above, i.e. the image processing device, the black and white camera and the RGB-W lighting unit can be installed in a single device.

In an alternative embodiment, only the image processing device and the black and white camera are built into a single device, while the RGB-W lighting unit is connected to the device as an external device.

In a further embodiment, the recording system can also have a transmission unit and a reception unit. The transmitter unit can be designed to transmit recordings to the receiver unit. The receiving unit can be designed to provide the received recordings to the image processing device. Thus, the image processing device does not have to be connected directly to the SW camera, but can be accommodated at another location, for example in a computer center.

• - eine Menge von Aufnahmen darzustellen, vorzugsweise in verringerter Bildauflösung auf mindestens einer Übersichtsseite, und die Auswahl des Benutzers von mindestens einer Aufnahme aus dieser Menge zu erfassen und/oder
• - einen Vorlagenbildausschnitt zu erfassen, den der Benutzer insbesondere mittels geometrischer Auswahlwerkzeuge und/oder durch ein Pinselwerkzeug festlegt, und/oder
• - Eingaben des Benutzers für Parameter und/oder Parameterwerte entgegenzunehmen.

A preferred embodiment can provide that a recording system as described above also has a unit for interaction with a user. The interaction unit can be designed to do this by means of input and output devices

• - Display a set of recordings, preferably in reduced image resolution on at least one overview page, and to record the user's selection of at least one recording from this set and/or
• - to capture a template image section that the user defines in particular by means of geometric selection tools and/or a brush tool, and/or
• - Receive input from the user for parameters and/or parameter values.

A recording system according to this embodiment can on the one hand offer a user an improved overview of the course of the computer-implemented method and on the other hand accept inputs from the user which the computer-implemented method uses directly or indirectly to select a recording.

A display of recordings, in particular input recordings, in reduced image resolution on an overview page can give the user an overview of the recordings available for selection. By selecting individual recordings, it is possible for the user to easily determine the first selection criterion, for example.

The user can also easily define a template image detail in a suitable graphical user interface. For this purpose, geometric selection tools and/or a brush tool are preferably present, which allow the template image section to be marked in the display of the white image. A simple geometric selection tool can create a selection area in the form of a triangle, a square, or an ellipse, for example. In order to generate polygon-shaped selection areas, a polygon tool can also be provided, with which the sections of a polygon can be defined step by step. In addition, a brush tool can be provided that creates an image detail from the total amount of all pixels that were selected with the brush tool. This is particularly advantageous if the area to be marked cannot be marked in a simple manner using a geometric selection tool.

Further embodiments of the invention result from the dependent claims.

• 1 ein beispielhaftes Aufnahmesystem;
• 2 ein Flussdiagramm eines Verfahrens;
• 3 eine grafische Benutzeroberfläche zur Bestimmung von Vorauswahlaufnahmen;
• 4 eine grafische Benutzeroberfläche zur Festlegung eines Vorlagenbildausschnitts.

The invention is described below using exemplary embodiments which are explained in more detail using the figures. Here show:

• 1 an exemplary recording system;
• 2 a flowchart of a method;
• 3 a graphical user interface for determining preselection shots;
• 4 a graphical user interface for specifying a template image section.

In the following description, the same reference numerals are used for the same parts and parts with the same effect.

1 shows a recording system 70 according to the invention. In this exemplary embodiment, the recording system 70 is used to produce a photographic recording of an object 30 for subsequent production control.

In the figure, object 30 is a cuboid component with five screws attached one below the other, the correct positioning of which is to be checked in production control.

For the purpose described, a black and white camera 10 is aimed at the object 30 whose surface is illuminated by an RGB-W lighting unit 20 . In order to avoid unwanted reflections in the photographic recording, the B&W camera 10 is additionally equipped with three polarization filters 11.

The RGB-W lighting unit 20 permits a large number of different lighting settings by switching the individual colored light sources on and off. In addition, further variations result from the different settings of the polarization filters 11 . In this way, the B&W camera 10 can create a large number of input recordings E1, . . . En and a white image E0 that show the object 30 in different lighting settings.

Further components of the recording system 70 are an image processing device having a computer-readable storage medium 71 that contains instructions for executing a method according to the invention, and a computing unit 72 that executes the method according to the instructions stored on the storage medium 71 .

It should be noted that the representation in 1 schematically shows the components of a recording system according to the invention. Multiple components can be combined into a single device that performs the functions of all components. In particular, according to the embodiments described above, the black and white camera 10, the storage medium 71 and the computing unit 72 can be installed in one device, while the RGB-W lighting unit 20 is optionally connected internally in said device or externally to it.

In 2 a flowchart is shown that shows the sequence of a method 50 according to the invention.

First, in step 51, input recordings E1,...,En and a white image E0 are received.

In step 52, a subset of the input recordings E1, . . . , En, which are referred to as candidate recordings K1, . The first selection criterion can consist, for example, in checking algorithmically whether the input recordings E1, . . . En have a sufficiently high contrast.

In step 53, a template image section A0 is defined in the white image E0. In particular, this can be automated using algorithms for area detection or manually using suitable marking tools. In this way, for example, the object 30 to be detected can be separated from its background or a relevant area of the object 30 can be selected.

The template image section A0 serves as the basis for the following step 54. Here, target image sections A1,...,Am are generated in the candidate recordings K1,...,Km, which correspond to the template image section A0. In a simple case, the candidate recordings K1,...,Km have the same dimensions as the white image E0, so that the formal description of the template image section A0, for example as a polygon, can be used directly to define the target image sections A1,...,Am . However, it can also happen that at least one candidate recording K1,...,Km has a different dimension than the white image E0. In such a case, a suitable transformation of the template image section A0, which is defined in a first coordinate system of the white image E0, into the at least one target image section A1,...,Am, which is defined in at least a second coordinate system of the at least one differently dimensioned candidate recording K1, is required. ...,Km is defined.

In step 55, algorithms for image processing are applied to the target image sections A1, . . . , Am. For example, a first algorithm can detect edges using the Sobel operator. A second algorithm can enhance the detected edges in the recording with a line width that is a parameter value of the second algorithm. In the first execution of the step, the line width can be assigned a default value, for example 3pt. Finally, the manipulated target image sections are combined with the respective complementary, unchanged target image sections to form processed candidate recordings K'1, . . . , K'm. By using the image processing algorithms, the contours running in the target image sections appear intensified.

In step 56, preselection recordings V1,...,Vk are selected from the set of processed candidate recordings K'1,...,K'm using a second selection criterion.

Finally, in step 57, the pre-selection recordings V1,...,Vk are evaluated using a final selection criterion. In principle, the same or similar aspects as in the case of the first and second selection criteria come into consideration as the final selection criterion, for example a sufficient development of contours. If at least one pre-selection recording V1,...,Vk meets the final test criterion, the method selects this recording as the final recording F.

Otherwise, steps 55 to 57 are executed again. In this case, however, the preselection recordings V1,...,Vk determined last are used as candidate recordings K1,...,Km. In addition, a second set of parameters and/or parameter values is used. If, for example, there is no pre-selection recording K1,...,Km with sufficient definition of contours according to the final test criterion in the first run, an obvious adjustment of the parameter values would be to increase the intensity of the edge enhancement of the corresponding algorithm from step 55. This can have the effect that the corresponding recording in the second execution of step 57 satisfies the final test criterion and is selected as the final recording F.

In 3 1 shows an embodiment of a graphical user interface 80 for selecting candidate recordings K1,...,Km from the input recordings E1,...,En. The user interface 80 shows the four input recordings E1, E2, E3, E4 on an overview page, each with an image resolution that takes up slightly less than a quarter of the screen area. The user can use the buttons 83 to go to the previous or next overview page, on which the remaining input recordings can be seen. In the user interface 80, each of the input recordings E1, E2, E3, E4 contains a selection symbol 81, 82 at the upper left edge of the screen. The user can use this to include the respective input recording in the set of candidate recordings K1,...,Km or remove it from this.

In the exemplary embodiment shown, the input recordings E1, E2, E3, E4 show the object 30, with the contours of the object 30 being pronounced to different extents. The contours in E1 are only weakly defined, in E2 and E3 they are moderately strong. The entrance recording E4, on the other hand, shows such strong contours that a detailed representation in intermediate areas is no longer given.

From the in 3 In the illustrated input recordings E1, E2, E3, E4, the user has decided in this case to select the input recordings E2 and E3, while E1 and E4 are deselected. The set of candidate recordings therefore includes at least E2 and E3, but not E1 and E4. The selected input recordings E2, E3 are each identified by a filled-in selection symbol 82, the other input recordings E1, E4 by an unfilled selection symbol 81.

4 shows an exemplary embodiment of a graphical user interface 90 for marking the template image section A0 in the white image E0. At the upper right edge of the user interface 90 there is a toolbar 91 which provides the user with various selection tools: a triangle tool 92, a rectangle tool 93, an ellipse tool 94, a polygon tool 95 and a brush tool 96.

In addition, is 4 It can be seen that the user uses the polygon tool 95 to define a loop to enclose the top screw head of the object 30 (the loop being shown in FIG 4 is not closed yet).

At this point it should be pointed out that all parts described above are individually - even without additional features described in the respective context, even if these have not been explicitly identified as optional features in the respective context, e.g. B. by using: in particular, preferably, for example, e.g. B., if necessary, round brackets, etc. - and in combination or any sub-combination are to be regarded as independent configurations or developments of the invention, as defined in particular in the introduction to the description and the claims. Deviations from this are possible. Specifically, it should be noted that the word in particular or round brackets do not denote any characteristics that are mandatory in the respective context.

reference list

10

SW camera

11

polarizing filter

20

RGB-W lighting unit

30

object

50

procedure

51

Receiving input recordings

52

Selecting Candidate Recordings

53

Specify a template image section

54

Defining target image sections

55

Applying image processing algorithms

56

Choosing preset shots

57

test step

70

recording system

71

storage medium

72

unit of account

80

User interface for selecting candidate shots

81

Selection icon (empty)

82

Selection icon (filled)

83

Page change buttons

90

User interface for marking the template image section

91

toolbar

92

triangle tool

93

rectangle tool

94

ellipse tool

95

polygon tool

96

brush tool

A0

Template image cutout

A1,...,Am

target image section

E0

white screen

E1,..,En

entrance shots

f

final recording

K1,...,Km

candidate recordings

K'1,..., K'm

processed candidate recordings

V1,..., Vk

pre-selection shots

QUOTES INCLUDED IN DESCRIPTION

This list of documents cited by the applicant was generated automatically and is included solely for the better information of the reader. The list is not part of the German patent or utility model application. The DPMA assumes no liability for any errors or omissions.

Patent Literature Cited

• DE 102018119691 A1 [0008]
• DE 102019113647 A1 [0009]
• DE 102015216446 A1 [0010]
• DE 102019103397 A1 [0011]

Claims (15)

Computer-implemented method, in particular user-guided, for selecting a photograph (F), the method comprising the following steps: a) receiving a plurality of input recordings (E1,...,En) which indicate an object (30) to be detected in a plurality of lighting settings, the lighting settings being provided by different configurations of an RGB-W lighting unit (20) and/or or are indicated by at least one polarization filter (11) and comprise a white image (E0); b) selecting at least one candidate recording (K1,...,Km) from the input recordings (E1,...,En) using a first selection criterion; c) defining a template image section (A0) in the white image (E0); d) generating at least one target image section (A1,...,Am) in the at least one candidate recording (K1,...,Km), which corresponds to the template image section (A0); e) Applying at least one algorithm for image processing, in particular for contour detection, blob analysis, region analysis, code analysis or model matching, with a first set of parameters and/or parameter values on the at least one target image section (A1,...,Am) to generate processed candidate records (K'1,...,K'm); f) selecting at least one pre-selection recording (V1,...,Vk) from the set of processed candidate recordings (K'1,...,K'm) using a second selection criterion; g) Checking whether a pre-selection recording (V1,...,Vk) exists that satisfies a final test criterion and if so, selecting such a pre-selection recording (V1,...,Vk) as the final recording (F), otherwise h) repeating steps e) to g), wherein the at least one pre-selection recording (V1,...,Vk) is used as the at least one candidate recording (K1,...,Km) and in step e) a second, in particular a user-specified set of parameters and/or parameter values is used. procedure after claim 1 , wherein the number of repetitions of steps e) to g) according to step h) does not exceed a predetermined value. Method according to one of the preceding claims, wherein in the event that in an execution of step g) there is no pre-selection recording (V1,...,Vk) that satisfies the final test criterion, the white image (E0) as the final recording (F) is selected. Method according to any one of the preceding claims, wherein - at least one of the selection criteria or the final test criterion is specified by a user in such a way that at least one recording is selected from the set of recordings that can be selected in each case, and/or - The template image section (A0) is defined by a user, in particular by means of geometric selection tools and/or a brush tool. Method according to one of the preceding claims, wherein at least one of the selection criteria or the final test criterion is that at least one parameter of a recording, in particular an intensity difference between a brightest and a darkest point, dynamics, contrast and/or image sharpness, is maximized and/or or exceeds a predetermined threshold. Method according to one of the preceding claims, wherein at least one of the selection criteria or the final test criterion depends on an evaluation result of at least one algorithm for image analysis, in particular contour recognition, blob analysis, region analysis, code analysis and/or model matching. Method according to one of the preceding claims, wherein a recording is selected according to at least one of the selection criteria or the final test criterion if at least one reference image exists in a collection of reference images, so that a distance value between the recording and the reference image in a metric falls below a predetermined threshold value. Method according to one of the preceding claims, wherein in step d) the at least one target image section (A1, ..., Am) in the at least one candidate recording (K1, ..., Km) is generated in that the at least one polygonal course, the corresponds to the template image detail (A0) and is defined in a first coordinate system of the white image (E0), is transformed into at least one second polygonal course, which is defined in a second coordinate system of the at least one candidate image (K1,...,Km). A computer-readable storage medium containing instructions that cause at least one processor to implement the method of any preceding claim when the instructions are executed by the at least one processor. Image processing apparatus, comprising: - a computer-readable storage medium (71). claim 9 and - a computing unit (72) which is designed to execute instructions stored on the computer-readable storage medium. Recording system (70), comprising: - an image processing device according to claim 10 , - a black and white camera (10) and - an RGB-W lighting unit (20), wherein the black and white camera (10) is designed to take pictures of an object (30) to be detected in a multiplicity of lighting settings, wherein the lighting settings are indicated by different configurations of the RGB-W lighting unit (20) and comprise a white image (E0), and is further adapted to provide the images to the image processing device. system after claim 11 , wherein the image processing device, the SW camera (10) and the RGB-W lighting unit (20) are installed in a single device. system after claim 11 wherein the image processing device and the black and white camera (10) are built into a single device, and the RGB-W lighting unit (20) is an external device connected to the device. system according to one of the Claims 11 until 13 , further comprising: - a transmitting unit and - a receiving unit, wherein - the transmitting unit is designed to transmit the recordings made to the receiving unit and - the receiving unit is designed to provide the received recordings to the processing unit. system according to one of the Claims 11 until 14 , further comprising an interaction unit which is designed to use input and output devices - to display a set of recordings (E1,...,En), preferably in reduced image resolution on at least one overview page, and the selection of a user from at least one recording from this set and/or - to capture a template image section (A0) which a user specifies in particular by means of geometric selection tools and/or a brush tool, and/or - to receive input from a user for parameters and/or parameter values.

Images