Method for checking optical lenses, and device for this purpose

Abstract

The invention relates to a method for operating a test system (100) for testing optical lenses (1), which are checked by means of an optical image recording device (10) in order to detect at least one defect on the lens (1) and to output same in a digitally processed test image (11), and wherein the method comprises at least the following further steps: setting up a defect detection unit (12); supplying the test image (11) from the image recording device (10) to the defect detection unit (12); identifying and classifying the defect on the lens (1) by means of the defect detection unit (12); outputting a lens image (13a) comprising the at least one identified and classified defect; setting up a lens evaluation unit (14) and supplying the lens image (13a) from the defect detection unit (12) to the lens evaluation unit (14); and evaluating the lens (1) with regard to specific quality requirements of a purchaser (A, B).

Description

[0001] Kassel, December 10, 2025

[0002] Lawyer's file SCH24176P1WO

[0003] Official file number

[0004] NN

[0005] Applicant:

[0006] Schneider GmbH & Co. KG

[0007] Biegenstraße 8

[0008] 35112 Fronhausen

[0009] Representative:

[0010] WALTHER PATENT

[0011] Walther ■ Bayer ■ Faber Heimradstraße 2 34130 Kassel, DE

[0012] METHOD FOR TESTING OPTICAL

[0013] LENSES AND DEVICE FOR THIS

[0014] The invention relates to a method for operating a testing system for testing optical lenses, which are tested by means of an optical

[0015] The image acquisition device must be checked to detect at least one defect on the lens and output it in a digitally processed test image.

[0016] STATE OF THE ART

[0017] From EP 3 531 067 A1, a device for carrying out a method for measuring optical lenses is known, which uses a first radiation source in the form of a laser and a second radiation source in the form of a screen, so that both the position of the lens in space and the refractive power distribution of the lens over its surface can be determined. The surface refractive power distribution is also referred to as a power map. In order to detect defects in the lens after the processes of determining the lens position or the first surface of the lens in space and after determining the surface refractive power distribution of the lens, the lens must generally be fed to a further station to detect the defects and to treat the lens accordingly.

[0018] For example, DE 3 943 909 A1 discloses a method for generating data about the lens that takes the defect into account, so that the lens is subsequently subjected to edge processing in which as many defects as possible are located in the edge area, which is removed when the mold body is edge-processed to form the spectacle lens.

[0019] This is achieved by identifying the position and size of any defects present in a semi-finished or finished lens after it has been provided. If corresponding edge data is recorded, a comparison can be made between this data set and the semi-finished or finished lens, each containing at least one defect. The semi-finished or finished lens is then assigned to a category. This category takes into account the type and position of the defect, so that, depending on the lens category, the edge of the semi-finished lens is designed to minimize the presence of the defect in the final lens.

[0020] WO 2019 / 238518 A2 discloses a method for material testing of optical lenses with an optical imaging system, the method comprising the following steps: at each of at least one pose of the lens in relation to the imaging system: controlling the optical imaging system to capture at least two images of the lens by means of at least one angle-variable illumination and angle-variable detection; for each of the at least one pose: processing the corresponding at least two images to generate a result image with digital contrast; and based on the at least one result image generated from the at least two images at the at least one pose: performing a material test of the lens.

[0021] The subsequently published DE 10 2024 126 710 A1 discloses a method for measuring optical lenses using a device, wherein the device comprises: a detection device arranged on a first side of the lens with respect to a plane of extension of the lens, one or more first radiation sources with which the position of the lens in space is determined, and a second radiation source with which a planar refractive power distribution of the lens over the surface is determined, wherein a planar extending, moving pattern is generated with the second or a further radiation source, which is detected through the lens by the detection device and by means of the computer unit, one or more defects on the surface of the lens are detected.The lens is detected, whereby the lens remains in an associated lens holder for determining the position of the lens in space - if necessary, determining the planar refractive power distribution of the lens over the surface and for detecting at least one defect.

[0022] Cosmetic inspections in contact lens manufacturing are mostly carried out manually. While there are usually a set of rules regarding, for example, the number, depth, or length of permissible damage to the lenses, such as scratches, these cannot realistically be adhered to in everyday production. Moreover, this is often not the only relevant criterion, as the overall impression is frequently important. The variability in the assessments can be high due to various "intentional" factors, such as different manufacturers with varying quality standards, or the fact that the same manufacturer may offer different quality levels with different price structures, for example, for a basic and a high-end category, or for different countries supplied by the manufacturer.There are also various “unwanted” factors, for example, that a standard is difficult to define because there is no objective measure for the impression of a lens; that is, human testers are always subjective due to the real measurement conditions.

[0023] If one wants to eliminate the human factor by using a measuring machine, the difficulty still lies in providing a system that can be adapted to a poorly defined standard without major expenses.

[0024] Defect detection during quality control should be as precise as possible; technically speaking, it should be possible to determine the defect class down to the pixel level. In the context of defect detection, this means, for example, that for each pixel in the lens image, it must be clear whether it belongs to, for instance, a scratch, a speck of dust, an inclusion, or a transparent lens element. At the same time, a decision based solely on pixel-level information, and potentially including neighboring pixels, is prone to errors. Different types of defects can be distinguished not only based on pixel values ​​but also, for example, on their shape. This can be achieved by using modern segmentation models, such as those based on a so-called...UNets are based on this technology; they combine pixel-precise resolution with a large receptive field that encompasses the image area around a pixel, which can be used to determine the class of that pixel. UNets with a so-called ResNet backbone are particularly well-suited for this purpose, but other deep neural networks such as FCN, DeepLab, SegFormer, and MaskRCNN can also be used.

[0025] The difficulty for companies in assessing whether a lens is a good or bad part lies in the fact that currently no uniform standard can be defined and adhered to across shifts and production sites. In particular, it is not possible to train a new or even existing employee to comply with a specific standard, as manual assessment always involves a significant individual component.

[0026] REVELATION OF THE INVENTION

[0027] It is therefore the object of the present invention to provide a method for operating a testing system and such a testing system as can be used to determine membership in a defect class down to the pixel level, but customer-specific criteria can also be easily incorporated.

[0028] This problem is solved starting from a method for operating a testing system according to the preamble of claim 1 and outputting a testing system for testing optical lenses according to the preamble of claim 11 in conjunction with the respective characterizing features. Advantageous embodiments of the invention are specified in the dependent claims.

[0029] The invention includes the technical teaching that the method comprises at least the following further steps: setting up a defect detection device, feeding the test image from the image acquisition device to the defect detection device, detecting and classifying the defect on the lens by means of the defect detection device, outputting a lens image comprising the at least one detected and classified defect, setting up a lens evaluation device and feeding the lens image from the defect detection device to the lens evaluation device and evaluating the lens with regard to a specific quality of a customer.

[0030] The key aspect of the invention is the ability to initially have a number of lenses from a customer recorded by the lens evaluation unit of the testing system in order to train the lens evaluation unit on a customer-specific quality. Subsequently, one or more quality inspectors independently submit evaluations for the same lens. The resulting data set is used to train the lens evaluation unit, which thereby learns the average evaluation criteria of the evaluator(s) and, after training, always makes the same objective decision.

[0031] With such a trained lens evaluation algorithm, manually operating quality inspectors from various customers can subsequently be trained so that their decisions correspond as closely as possible to those of the testing system according to the learned, objective quality standard. However, the lens evaluation can also be based on lens images taken by the

[0032] The defect detection device pre-classified the data with pixel-level accuracy.

[0033] The intended outcome is that the lens evaluation, based on the specific quality of the customer, will be incorporated into the lens evaluation system, determining whether the lens is classified as good or defective. Lenses that exhibit no defects whatsoever will, of course, be examined in the same manner and subsequently classified as good.

[0034] To operate the defect detection device, a defect database can be set up in which various defects are stored. The defect detection device includes a first machine learning module that recognizes and classifies the defect in the test image based on the defects stored in the defect database. The lens image, encompassing at least one recognized and classified defect, is then output. Defects can be based on segmented pixels, the characteristics of which can define a defect. A single lens can contain multiple segmented pixel groups, meaning that a single lens can therefore exhibit multiple defects.

[0035] The detected and classified defect in the lens image is then stored as information within the lens image, particularly pixel-accurately, using the first machine learning module. This information preferably includes a summary of the defect details regarding the type, location, intensity, number, and / or size (e.g., length, width, and / or area). This summary of defect information can then be transferred to the lens evaluation unit along with the lens image.

[0036] Furthermore, a decision database can be set up in which evaluations of the lenses according to specific quality criteria of the customer are stored, in particular the customer who uses the testing system with its specific quality criteria for the evaluation of the lenses, wherein the lens evaluation device can have a second machine learning module with which the digitally processed at least one defect in the lens image is evaluated based on the specific quality criteria represented in the decision database and a decision is issued as to whether the lens is to be evaluated as a good part or as a bad part.

[0037] It is possible to configure the system so that one or more defect detection units are centrally located, for example, at the testing system manufacturer, while multiple lens evaluation units are set up by the customer, thus multiple and / or decentralized, and each unit is assigned its own customer-specific decision database. Of course, it is also possible to set up all units and databases decentrally, and data maintenance, updates, and / or provision can be carried out via data exchange, for example, via a cloud system. It is also conceivable to manage only the defect database for the defect detection unit at the manufacturer's end, either through manufacturer-side storage and online data provision via data transmission, or through customer-side storage and manufacturer-side data maintenance via online data provision.

[0038] A further advantage is that the first and / or second machine learning module can each be trained using artificial intelligence and / or neural networks. This allows the machine learning modules to be trained in conjunction with the defect database or the decision database, respectively, to output the lens image or the decision as to whether the lens is a good or a defective part. Based on the decision of the second machine learning module as to whether the lens is a good or a defective part, human, i.e., manually operating, quality inspectors can be trained to make the most accurate decision possible.

[0039] If a machine learning module is used for defect detection, it must be trained, for example, in the case of a deep neural network, to recognize defects. For this purpose, the machine learning module is presented with test images, from which it calculates a lens image containing defects. This calculated lens image is then compared with an expected lens image, which was manually created to match the original test image, by defining a comparison function between the expected and calculated lens images. The machine learning module is characterized by the fact that it performs mathematical operations that depend on parameters to arrive at a decision. Training, therefore, means that these parameters are adjusted so that the calculated and expected lens images become more similar to each other.The machine learning module becomes better at recognizing and classifying the correct defects, which is usually formulated mathematically in such a way that this corresponds to a minimum of the comparison function.

[0040] The decision-making process includes at least one step: using the lens defects as input, to generate an evaluation of the lens. If a machine learning module is used for this purpose, it usually needs to be trained. This requires data pairs consisting of defects on a lens and expected evaluations based on these defects. A mathematical comparison function can then be defined between the calculated decision and the expected decision. The minimum of this function corresponds to an optimal match between the machine learning module's evaluation and the expected decisions. This comparison function can be used in a mathematical procedure to adjust the parameters of the machine learning module to approximate a minimum of the comparison function.

[0041] The problem preceding the invention is further solved by a testing system for testing optical lenses, comprising an optical image acquisition device for detecting at least one defect (see page 11 - segmentation) on the lens and for outputting a digitally processed test image, wherein, according to the invention, a defect detection device is provided with which the at least one defect on the lens can be detected and classified based on the test image, so that a lens image can be output by the defect detection device which includes at least one classified defect, and wherein, furthermore, a lens evaluation device is provided with which, based on the lens image, an evaluation of the lens can be carried out based on a specific quality of a customer.

[0042] Although separating the system into a defect detection unit and a lens evaluation unit offers the advantage of modularity—requiring only the replacement of the defect detection unit to introduce new defect types or correct errors in defect detection, and only the replacement of the lens evaluation unit to adapt to individual customer quality criteria—implementing both steps in a single unit would also be possible. In this case, greater modularity would be traded for more efficient computation and a simpler design.

[0043] In particular, the testing system is designed so that the defect detection unit is assigned a defect database and the lens evaluation unit a decision database. Since the defect database can be used across multiple customers, it typically contains significantly more images (at least several thousand) than the customer-specific decision databases (typically around 100 to 1000 records each). Both databases can also be updated, i.e., further enriched, during operation.

[0044] Machine learning modules enable automated learning and comprise systems that recognize patterns and rules from datasets, either through guided or self-learning methods. In machine learning, pattern recognition is achieved through statistical procedures based on a training dataset. This contrasts with classical programming, where fixed algorithms and rules are defined. These must then be precisely and completely defined and known to the developer, which can be very difficult for many applications.

[0045] Neural networks can form a machine learning model consisting of multiple interconnected artificial neurons. Each neuron processes input values ​​and outputs a value that is influenced by adjustable parameters. By layering multiple levels of neurons, deep neural networks are created, where the output of one neuron serves as the input for subsequent neurons. This allows the network to learn complex patterns.

[0046] The machine learning modules can also utilize so-called "convolutional neural networks," or CNNs for short. These networks are a special type of neural network that is particularly well-suited for processing image data and spatial information. CNNs are designed to recognize patterns and features in local image areas, making these systems especially effective for image and object recognition. The unique feature of a CNN lies in its "convolutional layers," which use filters—also called kernels—to "scan" small areas of the input image. These filters extract features such as edges, shapes, and textures, which are used as fundamental information for subsequent layers. By applying these layers multiple times, the network is enabled to recognize increasingly complex patterns as the learning process progresses.

[0047] In image processing, segmentation refers to the division of images into segments, which can be achieved by the defect detection system within the lens image. In the context of defect detection, this means that for each input image, a cropped and / or scaled output image is provided, in which each pixel is marked with its predefined class. For example, in the context of defect detection, this means that for each pixel in the lens image, it is determined whether it belongs to, for instance, a scratch, a dust particle, an inclusion, or a transparent lens element. Such a task can be handled, for example, by a deep neural network, resulting in a segmentation model.

[0048] Finally, there are so-called UNets; these refer to a specific architecture, i.e., the structure and / or organization of the individual layers of a neural network, which can be used for segmentation tasks and can also be part of machine learning modules. In the first part, the resolution of the input image is gradually reduced, as with most CNNs, to enable the recognition of increasingly complex image structures. However, in the second part of the network, these structures are gradually enlarged again and combined with the less complex, but higher-resolution structures from the first part to represent the complex structures precisely and at high resolution. This structure schematically resembles an LI shape. UNets represent one way to build segmentation systems with a neural network and, alongside other architectures, are a modern "standard" model for this field.There is still considerable variation in the exact structure within the individual levels and cross-connections of the UNet.

[0049] PREFERRED EXAMPLE OF THE INVENTION

[0050] Further measures improving the invention are described in more detail below, together with a description of a preferred embodiment of the invention, with reference to the figures. The figures show:

[0051] Figure 1 shows a schematic representation of the image acquisition device, the defect detection device and the lens evaluation device.

[0052] Figure 2 shows a schematic representation of the structure of the defect detection device and

[0053] Figure 3 shows a schematic representation of the structure of the lens evaluation device.

[0054] Figure 1 schematically shows the structure of the inspection system 100 with the features of the present invention. The essential structural structure of the inspection system 100 comprises an image acquisition device 10, a defect detection device 12, and a lens evaluation device 14. The image acquisition device 10 can detect defects on the lens 1 and convert them into at least one digitally processed test image. Image acquisition devices 10 generally include a camera 21 with which an image can be captured, which is generated by means of a screen 22 and captured through the lens 1. The image acquisition device 10 has further functions as disclosed in WO 2023 041659 A1.

[0055] The image acquisition device 10 thus enables the provision of images that are such that various defects can be detected and distinguished within them. If several stripe patterns are recorded with the camera 21, which were generated by means of the screen 22, they can then be processed to create several output images, which are referred to here as test images 11 and which serve as input images in the next step.

[0056] In the following step, the defect on lens 1 is detected and classified using the defect detection device 12. For this purpose, a defect database 15 is set up in which different defects are stored, wherein the defect detection device 12 has a first machine learning module 16, with which the defect in the test image 11 is detected and classified based on the defects stored in the defect database 15 and with which the lens image 13a comprising the at least one detected and classified defect is output as an accompanying data set.In other words, the at least one detected and classified defect in the lens image 13a is stored as information in the lens image 13a, particularly pixel-accurately, by means of the first machine learning module 16. A summary of the defect information regarding the type, location, intensity, number, and / or size (e.g., length, width, and / or area) of the defect can be generated, and the lens image and / or a summary of the defect information 13b is transferred to the lens evaluation unit 14. In a further step, the lens image and / or the summary of the defect information 13b is transferred from the defect detection unit 12 to the lens evaluation unit 14, where the lens 1 is evaluated with respect to a specific quality level by a customer, which can be customer A or customer B and can define different specific quality criteria and their standards.Thus, at least one or exactly one defect detection device 12 can be set up centrally, while several lens evaluation devices 14 can be set up decentrally and / or multiple times, to which customer-specific decision databases 17 are assigned.

[0057] The lens evaluation device 14 bases its decisions on a decision database 17, in which defects detected on lenses 1 and their evaluation according to the respective specific quality criterion 18 of the customer currently being trained (generally, that of customer A or B) are stored for customer-specific evaluation. The lens evaluation device 14 has a second machine learning module 19, which evaluates the digitally processed at least one defect in the lens image and / or in the summary of defect information 13b based on the specific quality criterion 18 represented in the decision database 17 and outputs a decision as to whether the lens 1 is a good part 1a or a defective part 1b. Different quality criteria 18 can be customer-specifically defined by customer A or B, e.g., by means of...Several hundred lens-specific decision databases 17 are created, which form the basis for evaluation by a specific machine learning module 19 per specific quality criterion.

[0058] Although the image acquisition unit 10, the defect detection unit 12, and the lens evaluation unit 14 are referred to here as separate components, they are generally implemented in a single physical machine and are only separated in the software implementation. This separation is not strictly necessary, however. For example, the first machine learning module 16 could also be designed to process the camera images to create the inspection image 11 and / or perform the tasks of the second machine learning module 19. In particular, depending on the architecture of the machine learning modules, separate training and subsequent integration of the modules is easily achievable.

[0059] The defect database 15 and the decision database 17 are generally only needed during model training when using machine learning / AI. In production use, usually only the rules or parameters learned by the model based on these databases 15 and 17 are used.

[0060] Figure 2 shows a schematic representation of the structure of the defect database 15, as well as the training of the machine learning module 16 of the defect detection device 12. Several image acquisition devices 10 are shown as examples, each of which transmits test images to the defect detection device 12, for instance, from a number of different production sites. The defect detection device 12 and / or at least the defect database 15 with the defects stored therein can, for example, be located and / or hosted at the manufacturer of the inspection system 100. The defect database 15 is thus created for subsequent training, initially with the test images 11 from many lens images, without detecting defects or making final decisions. This database is supplemented by annotating the collected images, whereby all existing defects / anomalies are drawn into each test image 11 and sorted into categories.From this, data pairs are generated from stored test images 15a and expected lens images 15c.

[0061] The defect detection device 12 has a first machine learning module 16, which detects and classifies the defect in the test image 11 based on the defects stored in the defect database 15. The defect detection process, which involves training generalized rules about the manifestations of defects to continuously improve the function of the first machine learning module 16, is described below.

[0062] The stored test images 15a are presented as input to the neural network of the first machine learning module 16. This module generates a calculated lens image 15b, which is compared with the expected lens image 15c from the defect database 15. The training of the machine learning module 16 is then formulated as a mathematical optimization problem. This involves calculating an initial comparison function V1 between the expected lens image 15c and the calculated lens image 15b. This function is minimized when the calculated result of the model from the dataset in the defect database 15 exactly matches the expected result, the expected lens image 15c. The variables of this function are all parameters in the model, which are then minimized using an algorithm across all images in the defect database 15.

[0063] Ideally, the machine learning module 16 "learns" generalized rules about the appearance of defects, instead of just comparing them with already known defects.

[0064] Finally, Figure 3 shows a schematic representation of the training process for the lens evaluation device 14. First, for example, several hundred lenses, the lens array 1.1, are received by the testing system 100. From the defect detection device 12 of the testing system 100, a lens image and / or the summary of the defect information 13b with the detected and classified data is transferred to a decision database 17 for each data point. The decision database 17 is composed of at least one of the specific quality criteria 18, determined by the several hundred lenses. The respective lens 1 is then forwarded from the testing system 100 to human inspectors for evaluation. Their evaluation of the lens is recorded via an input interface 20 and, assigned to the defects detected by the testing system, stored in the decision database 17.The resulting data pairs are then given to the lens evaluation unit 14 for training.

[0065] The goal of training the second machine learning module 19 is to map the specific quality criteria 18. Data pairs consisting of defects in a lens 1 and the expected rating of lens 1 are extracted from the defect database 15. The defects are provided to the second machine learning module 19 as input information, which calculates a decision. A second mathematical comparison function V2 is defined between the calculated decision (i.e., whether it is a good part 1a or a defective part 1b) and the expected rating 24. The minimum of this function corresponds to an optimal agreement between the second machine learning module 19 and the expected decisions. The parameters of the second machine learning module 19 are the variables of the function. These are iteratively optimized during training to minimize the comparison function V2.

[0066] The invention is not limited in its implementation to the preferred embodiment described above. Rather, a number of variants are conceivable, which utilize the solution presented even in fundamentally different designs. All features and / or advantages arising from the claims, the description, or the drawings, including design details or spatial arrangements, can be essential to the invention, both individually and in various combinations.

[0067] Reference symbol list:

[0068] Lens

[0069] 1a Good part

[0070] 1 b Bad part

[0071] 1.1 Lentil group

[0072] 10 Image capture device

[0073] II Test image

[0074] 12 Defect detection device

[0075] 13a Lens image

[0076] 13b Lens image and / or summary of defect information

[0077] 14 Lens evaluation device

[0078] 15 Defect database

[0079] 15a Stored test image (from the database)

[0080] 15b calculated lens image

[0081] 15c expected lens image (from the database)

[0082] 16 first machine learning module

[0083] 17 Decision database

[0084] 18 specific quality criteria

[0085] 19 second machine learning module

[0086] 20 Input interface

[0087] 21 camera

[0088] 22-inch screen

[0089] 24 expected ratings

[0090] 100 examination system

[0091] A customer

[0092] B Customer

[0093] V1 first comparison function

[0094] V2 second comparison function

Claims

Claims:

1. Method for operating a test system (100) for testing optical lenses (1) which are tested by means of an optical image acquisition device (10) in order to detect at least one defect on the lens (1) and output it in a digitally processed test image (11), wherein the method comprises at least the following further steps: - Setting up a fault detection device (12), - Feeding the test image (11 ) from the image acquisition device (10) to the defect detection device (12), - Detecting and classifying the defect on the lens (1 ) using the defect detection device (12), - Output of a lens image (13a) comprising at least one detected and classified defect, - Setting up a lens evaluation device (14) and feeding the lens image (13a) from the defect detection device (12) to the lens evaluation device (14) and - Evaluating the lens (1) with respect to a specific quality of a customer (A, B).

2. Method for operating a testing system (100) according to claim 1, characterized in that the evaluation of the lens (1) with regard to the specific quality of the customer (A, B) by means of the lens evaluation device (14) is converted into the result of whether the lens (1 ) is recognized as a good part (1a) or as a bad part (1 b).

3. Method for operating a testing system (100) according to claim 1 or 2, characterized in that a defect database (15) is set up in which different defects are stored, wherein the defect detection device (12) has a first machine learning module (16) that performs a segmentation, wherein the defect in the test image (11) is recognized and classified based on the defects stored in the defect database (15) and with which the lens image (13a) comprising the at least one recognized and classified defect is output.

4. Method for operating a testing system (100) according to claim 3, characterized in that the detected and classified defect in the lens image (13a) is stored as information in the lens image (13a) by means of the first machine learning module (16), in particular pixel-accurately, preferably comprising a summary of the defect information about the type, location, intensity, number and / or size such as length and / or width and / or area of ​​the defect, wherein the summary of the defect information is transferred to the lens evaluation device (14) along with the lens image (13b).

5. Method for operating a testing system (100) according to one of the preceding claims, characterized in that a decision database (17) is set up in which the evaluations of the lenses (1) according to specific quality criteria (18) of the customer (A, B) are stored, wherein the lens evaluation device (14) has a second machine learning module (19) with which the digitally processed at least one defect in the lens image (13a or 13b) is determined based on the data in the The decision database (17) is evaluated based on the stored expected assessments and a decision is issued as to whether the lens (1) is a good part (1a) or a bad part (1b).

6. Method for operating a test system (100) according to one of the preceding claims, characterized in that at least one or exactly one defect detection device (12) is set up centrally, wherein several lens evaluation devices (14) are set up decentrally and / or multiple times, to which customer-specific decision databases (17) are assigned.

7. Method for operating a testing system (100) according to one of the preceding claims, characterized in that the first machine learning module (16) and / or the second machine learning module (19) are each equipped with artificial intelligence and / or with neural networks, such that the machine learning modules (16, 19) interact with the The defect database (15) or the decision database (17) are trained to output the lens image (13) or the decision as to whether the lens (1) is a good part (1a) or a bad part (1b).

8. Method for operating a testing system (100) according to one of the preceding claims, characterized in that human quality inspectors are trained based on the decision of the second machine learning module (19) as to whether the lens (1) is a good part (1a) or a bad part (1b).

9. Method for operating a test system (100) according to one of the preceding claims, characterized in that the training of the defect detection by means of the defect detection device (12) is carried out with a comparison between the expected lens image (15c) and a calculated lens image (15b) from the first machine learning module (16), in which a first comparison function (V1) between the expected lens image (15c) and the calculated lens image (15b) is calculated.

10. Method for operating a testing system (100) according to one of the preceding claims, characterized in that the training of the decision-making process using the lens evaluation device (14) comprises at least the step of forming data pairs from the defects in the lens image (13a or 13b) and the expected evaluation (24) of the lens (1), wherein the defects are supplied to the second machine learning module (19) as input information, which calculates a decision, and / or wherein a mathematical comparison function (V2) is defined between the calculated decision and the expected decision, the minimum of which corresponds to an optimal agreement of the second machine learning module (19) with the expected decisions.

11. Testing system (100) for testing optical lenses (1), comprising an optical image acquisition device (10) for detecting at least one defect on the lens (1) and for outputting a digitally processed test image (11), characterized in that that a defect detection device (12) is provided which performs a segmentation by which the at least one defect on the lens (1) is detectable and classifiable based on the test image (11), so that a lens image (13a or 13b) can be output by the defect detection device (12) which includes at least one classified defect, and / or (furthermore) a lens evaluation device (14) is provided with which, based on the lens image (13a or 13b), an evaluation of the lens (1) can be carried out on the basis of a specific quality of a customer (A, B).

12. Testing system (100) for testing optical lenses (1) according to claim 11, characterized in that a defect database (15) is assigned to the defect detection device (12) and a decision database (17) is assigned to the lens evaluation device (14), wherein the defect database (15) has 5 to 100 times and / or 10 to 50 times the number of data records as the number of data records of the decision database (17).

13. Testing system (100) for testing optical lenses (1) according to claim 11 or 12, characterized in that the defect detection device (12) has a first machine learning module (16) and / or the lens evaluation device (14) has a second machine learning module (19), wherein one or both machine learning modules (16) are designed with artificial intelligence and / or with neural networks.

14. Testing system (100) for testing optical lenses (1) according to any one of claims 11 to 13, characterized in that an input interface (20) is provided via which data on the lenses (1) with the specific quality criteria (18) of the customer (A, B) can be entered and / or via which a human quality inspector can make an input to the lens evaluation device (14).

15. Testing system (100) for testing optical lenses (1) according to any one of claims 11 to 14, characterized in that the defect detection device (12) is designed such that it wholly or partially fulfills the tasks of the image acquisition device (10) and / or the lens evaluation device (14).

Images