DE112018000224B4 - Method and device for determining a position of a slit in a sample to be processed - Google Patents

Abstract

Method for determining a position of a slit in a sample to be processed, characterized in that the method comprises: determining (S201) recording parameters based on a received sample cooling temperature in order to prevent an impairment of an imaging result of the sample to be processed by a fog generated in its vicinity to avoid as a result of the cooling temperature of the sample to be processed being too low, the recording parameters comprising a shutter speed, an aperture number, an ISO value, an exposure value and a setting parameter of a flash lamp with regard to its switching on or off; receiving (S202) a through an image capture device, the capture parameters of which are adjusted according to the received sample cooling temperature, captured and transmitted image of the sample to be processed; filtering (S203) the image of the sample to be processed to obtain key image information of the sample to be processed; andobtaining (S204) specific position information of the slit in the sample to be processed based on a plurality of predetermined image recognition models and the key image information of the sample to be processed, each predetermined image recognition model corresponding to a feature of the slit in the sample to be processed.

Description

TECHNICAL AREA

The invention relates to the field of automation of the steel industry and in particular to a method and an apparatus for determining a position of a slot in a sample to be processed.

STATE OF THE ART

document DE 197 54 129 C1 discloses a device for detecting the change in contour of tensile specimens at different temperatures, comprising a chamber enclosing the tensile specimen, into which the tensile rods of a materials testing machine protrude, a fan for distributing a temperature control medium, a light source with a diffuser on one side of the tensile specimen, a sight tube, a Camera to record the tensile sample through the sight tube, and a light-transmitting flow deflector between the light source and the tensile sample.

document WO 2012 171 627 A1 discloses a method for determining a track property of a running tape, e.g. B. a metal strip in a rolling mill, images of the running strip are repeatedly recorded and the images are evaluated, whereby the longitudinal edge positions of the strip are determined, from which the track property is determined. An image processing device comprises an area camera for scanning a predetermined area covering at least the width of the strip and areas adjacent to each side edge over a certain length of the running strip.

With the development of economy and technology, the use of automation equipment in the steel industry is becoming more extensive. When testing the material properties of steel specimens, the specimen slots must be located and then advanced to the appropriate positions.

However, in the prior art, the cooling temperature range of the sample is wide, ranging from -193°C to 20°C. When the cooling temperature of the sample is less than or equal to -60°C, a large amount of fog will cause the image to become unclear, and the brightness will be significantly lower than at 20°C, causing imaging changes and greatly disturbing the positioning of the sample slits will result in inaccurate final positioning.

DISCLOSURE OF THE INVENTION

Thus, an object of the present invention is to provide a method and an apparatus for determining a position of a slit in a sample to be processed to solve the above problems.

In order to achieve the above objective, the technical solution of the embodiment of the present invention is as follows:

• Bestimmen von Aufnahmeparametern auf der Grundlage einer empfangenen Probenkühltemperatur, um eine Beeinträchtigung eines Bildgebungsergebnisses der zu verarbeitenden Probe durch einen in ihrer Nähe erzeugten Nebel infolge einer zu niedrigen Kühltemperatur der zu verarbeitenden Probe zu vermeiden, wobei die Aufnahmeparameter eine Verschlusszeit, eine Blendenzahl, einen ISO-Wert, einen Belichtungswert und einen Einstellparameter einer Blitzlampe hinsichtlich ihrer Ein- oder Ausschaltung umfassen,
• Empfangen eines durch eine Bilderfassungsvorrichtung, deren Aufnahmeparameter gemäß der empfangenen Probenkühltemperatur angepasst sind, erfassten und gesendeten Bildes der zu verarbeitenden Probe,
• Filtern des Bildes der zu verarbeitenden Probe, um Schlüsselbildinformationen der zu verarbeitenden Probe zu erhalten, und
• Erhalten spezifischer Positionsinformationen des Schlitzes in der zu verarbeitenden Probe basierend auf mehreren vorab festgelegten Bilderkennungsmodellen und den Schlüsselbildinformationen der zu verarbeitenden Probe, wobei jedes vorab festgelegte Bilderkennungsmodell einem Merkmal des Schlitzes in der zu verarbeitenden Probe entspricht.

In a first aspect, an embodiment of the present invention provides a method for determining a position of a slit in a sample to be processed, comprising:

• Determining recording parameters on the basis of a received sample cooling temperature in order to avoid an impairment of an imaging result of the sample to be processed by a fog generated in its vicinity as a result of a cooling temperature of the sample to be processed that is too low, the recording parameters being a shutter speed, an f-number, an ISO value, an exposure value and a setting parameter of a flash lamp in terms of turning it on or off,
• Receiving an image of the sample to be processed captured and transmitted by an image capturing device whose recording parameters are adapted according to the received sample cooling temperature,
• filtering the image of the sample to be processed to obtain keyframe information of the sample to be processed, and
• obtaining specific positional information of the slit in the sample to be processed based on a plurality of predetermined image recognition models and the key frame information of the sample to be processed, each predetermined image recognition model corresponding to a feature of the slit in the sample to be processed.

• eine Aufnahmeparameterbestimmungseinheit, die zum Bestimmen von Aufnahmeparametern auf der Grundlage der empfangenen Probenkühltemperatur konfiguriert ist, um eine Beeinträchtigung eines Bildgebungsergebnisses der zu verarbeitenden Probe durch einen in ihrer Nähe erzeugten Nebel infolge einer zu niedrigen Kühltemperatur der zu verarbeitenden Probe zu vermeiden, wobei die Aufnahmeparameter eine Verschlusszeit, eine Blendenzahl, einen ISO-Wert, einen Belichtungswert und einen Einstellparamter einer Blitzlampe hinsichtlich ihrer Ein- oder Ausschaltung umfassen,
• eine Empfangseinheit zum Empfangen eines durch eine Bilderfassungsvorrichtung, deren Aufnahmeparameter gemäß der empfangenen Probenkühltemperatur angepasst sind, erfassten und gesendeten Bildes der zu verarbeitenden Probe,
• eine Filtereinheit, die konfiguriert ist, das Bild der zu verarbeitenden Probe zu filtern, um Schlüsselbildinformationen der zu verarbeitenden Probe zu erhalten, und
• eine Positionsinformationserfassungseinheit, die konfiguriert ist, um spezifische Positionsinformationen des Schlitzes in der zu verarbeitenden Probe basierend auf mehreren vorab festgelegten Bilderkennungsmodellen und den Schlüsselbildinformationen der zu verarbeitenden Probe zu erhalten, wobei jedes vorab festgelegte Bilderkennungsmodell einem Merkmal des Schlitzes in der zu verarbeitenden Probe entspricht.

In a second aspect, an embodiment of the present invention provides an apparatus for determining a position of a slit in a sample to be processed, comprising:

• a recording parameter determination unit configured to determine recording parameters based on the received sample cooling temperature in order to avoid an impairment of an imaging result of the sample to be processed by a fog generated in its vicinity as a result of a cooling temperature of the sample to be processed that is too low, the recording parameters including a shutter speed , an f-number, an ISO value, an exposure value and a setting parameter of a flash lamp with regard to turning it on or off,
• a receiving unit for receiving an image of the sample to be processed, which is captured and transmitted by an image capturing device whose recording parameters are adapted according to the received sample cooling temperature,
• a filtering unit configured to filter the image of the sample to be processed to obtain keyframe information of the sample to be processed, and
• a position information acquisition unit configured to obtain specific position information of the slit in the sample to be processed based on a plurality of predetermined image recognition models and the key frame information of the sample to be processed, each predetermined image recognition model corresponding to a feature of the slit in the sample to be processed.

The method and apparatus for determining a position of a slit in a sample to be processed, provided by the embodiment of the invention, determines the acquisition parameters according to the received sample cooling temperature and captures the image of the sample to be processed captured by an image acquisition device in the state of the acquisition parameters is collected, then filtering the image of the sample to be processed to obtain keyframe information of the sample, and lastly obtaining positional information of the slit in the sample to be processed based on a plurality of predetermined image recognition models and the keyframe information of the sample to be processed. Since different sample cooling temperatures have different effects on the recording results, there are corresponding recording parameters for each cooling temperature, so that the captured images of the sample to be processed are always in a relatively clear state. This is favorable for the subsequent background separation and determination of a position of a slit in a sample to be processed, thereby increasing not only the efficiency of obtaining the positional information of slits in the sample to be processed but also the accuracy of the positional information.

The objects, features and advantages of the invention described above are apparent from the preferred embodiments and the accompanying drawings.

BRIEF DESCRIPTION OF THE DRAWINGS

• 1 zeigt ein Funktionsblockdiagramm eines Servers, der von einer Ausführungsform der vorliegenden Erfindung bereitgestellt wird.
• 2 zeigt ein Flussdiagramm des Verfahrens zum Bestimmen einer Position eines Schlitzes in einer zu verarbeitenden Probe, das durch eine Ausführungsform der vorliegenden Erfindung bereitgestellt wird.
• 3 zeigt ein spezielles Flussdiagramm von Schritt S203 in 2.
• 4 zeigt ein spezielles Flussdiagramm von Schritt S2031 in 3.
• 5 zeigt ein spezielles Flussdiagramm von Schritt S204 in 2.
• 6 ist ein Funktionsblockdiagramm einer Vorrichtung zum Bestimmen einer Position (und vorzugsweise Positionieren) eines Schlitzes in einer zu verarbeitenden Probe gemäß einer bevorzugten Ausführungsform der vorliegenden Erfindung.

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the embodiments are briefly introduced below. It should be understood that the following drawings only illustrate certain embodiments of the present invention and are not to be construed as limiting the scope of the invention.

• 1 Figure 12 shows a functional block diagram of a server provided by an embodiment of the present invention.
• 2 Figure 12 shows a flow chart of the method for determining a position of a slit in a sample to be processed provided by an embodiment of the present invention.
• 3 shows a specific flowchart of step S203 in 2 .
• 4 shows a specific flowchart of step S2031 in 3 .
• 5 shows a specific flowchart of step S204 in 2 .
• 6 Figure 12 is a functional block diagram of an apparatus for determining a position (and preferably positioning) of a slit in a sample to be processed in accordance with a preferred embodiment of the present invention.

References:

100

Server;

111

Storage;

112

Processor;

113

communication unit;

200

Apparatus for determining a position (and preferably positioning) of a slit in a sample to be processed;

210

recording parameter determination unit;

220

receiving unit;

230

filter unit;

240

position information acquisition unit;

250

transport unit.

EMBODIMENTS OF THE INVENTION

The technical solutions in the embodiments of the present invention are described below clearly and fully with reference to the accompanying drawings in the embodiments of the present invention ben. It is obvious that the described embodiments are only part of the embodiments of the present invention and not all embodiments. The components of the embodiments of the invention that are generally described and illustrated in the figures herein can be arranged and designed in a variety of different configurations. The following detailed description of the embodiments of the present invention, provided in the drawings, is intended to illustrate the preferred embodiments.

It should be noted that similar reference numbers and letters indicate similar elements in the following drawings, and therefore when an element is defined in one drawing it is not necessary to further define and explain it in the following drawings. In describing the present invention, the terms "first," "second," and the like are used merely to distinguish a description and should not be construed to indicate or imply relative importance.

With reference to 1 shows 1 1 is a functional block diagram of a server 100 that may be applied to an embodiment of the present invention. The server comprises a device 200 for determining a position (and preferably positioning) of a slot in a sample to be processed, a memory 111, one or more processors 112 (only one shown) and a communication unit 113. These components communicate via one or more communication buses -/signal lines with each other. The device 200 includes at least one software entity that may be stored in the form of software or firmware (firmware) in the memory 111 or solidified in an operating system (OS) of the server 100 .

The memory 111 can be used to store software programs and units, such as program instructions/units, corresponding to the software testing apparatus and the software testing method in the embodiments of the present invention. The processor 112 performs various functional applications and data processing by executing a software program and a unit of the device 200 stored in the memory 111, such as the method provided by the embodiment of the present invention. Memory 111 may be random access memory (RAM), read only memory (ROM), programmable read only memory (PROM), erasable programmable read only memory (EPROM), electric erasable programmable read only memory (EEPROM), and the like, however, is not limited to this. Access to memory 111 by processor 112 and other possible components may be under the control of the memory controller.

The communication unit 113 is configured to establish communication connection between the server 100 and other communication terminals via the network, and is used to transmit and receive data via the network.

It should be understood that the structure shown in FIG. 1 is merely illustrative, and the server 100 may also include more or fewer components than those shown in FIG 1 shown or a different configuration than those shown in 1 shown. In the 1 Components shown may be implemented in hardware, software, or a combination thereof.

First embodiment

The invention provides a method for determining a position of a slit in a sample to be processed, namely a steel sample, during an impact test on a steel sample. Let it be 2 Reference is made to FIG. 1, which is a flow chart of a method for determining a position of a slit in a sample to be processed according to an embodiment of the present invention. The procedure includes:

Step S201: Determine acquisition parameters based on the received sample cooling temperature.

If the cooling temperature of the sample is too low, for example -80°C, a large amount of fog will be generated around the sample, which will greatly affect the imaging result of the sample, so that the final imaging result will be very unclear. This not only leads to a strong disturbance of the separation of background and sample in the imaging result, but also to a deviation in the determination of the slit in the sample.

Therefore, by adjusting the imaging parameters of the imaging device according to the sample cooling temperature of the sample, the imaging result of the finally obtained sample can be prevented from greatly changing due to the change in the cooling temperature.

According to the invention, the shooting parameters include, but are not limited to, shutter, aperture, ISO, EV value, setting parameters, whether the flash is on or not.

Step S202: Receiving a captured image of the sample to be processed, which is derived from an image the detection device is sent in a state of recording parameters.

It is understood that the image of the sample to be processed captured by an image capture device in the state of capture parameters is clear, easy to identify and analyze.

Step S203: filtering the image of the sample to be processed to obtain key frame information of the sample.

The background part and the sample part are included in the image of the sample to be processed. It is understood that the sample part is the image information of the sample itself, which can reflect its structure, connection relationship, and so on. The background part contains the information surrounding the sample, which can interfere with the analysis of the slit in the sample to be processed. Therefore, it is necessary to perform filter processing on the image of the sample to be processed and to filter the background portion in the image of the sample to be processed in order to obtain the image information of the key sample.

Let it be 3 Referring to which is a specific flowchart of step S203. Step S203 includes:

Sub-step S2031: Acquiring gray level histogram information of the image of the sample to be processed.

In general, the difference between the background part and the sample part is large, so the gray scale histogram information of the image of the sample to be processed can be obtained first, and the background part and the sample part are distinguished by the gray scale histogram information.

Let it be 4 Referring to which is a specific flowchart of sub-step S2031. Substep S2031 includes:

Sub-step S20311: Obtain a line of distinction between the sample and the background in the image of the sample to be processed.

It is understood that the sample has a certain shape and contour, so the distinguishing line that distinguishes the sample from the background is the contour line of the sample itself, and the distinguishing line divides the image of the sample to be processed into the sample part and the background part.

Sub-step S20312: Divide the image of the sample to be processed into a plurality of areas along the line of discrimination.

Because alcohol is usually attached to the position of the slit in the sample to be processed, the difference between the slit in the sample to be processed and the background is small, and the gray level is similar to the background, only by detecting the gray level of a specific area as the gray level histogram information of the image of the sample to be processed causes a large error in the image information of the final key sample. Therefore, the image of the sample to be processed is first divided into a plurality of areas along the line of discrimination, and by analyzing each area, the error of the image information of the key sample can be reduced.

Sub-step S20313: Obtain the gray level histogram and the gray level histogram mean value of the individual areas.

By capturing the gray level histogram and the mean gray level histogram of each region, it is convenient for the server 100 to capture the contrast of the gray level of the background part and the sample part of each region.

Sub-step S20314: Use a gray-scale histogram having the smallest mean gray-scale histogram value as gray-scale histogram information of the image of the sample to be processed.

The area with the smallest average grayscale histogram value has the lowest contrast between the sample and the background, and by using the grayscale histogram as grayscale histogram information of the image of the sample to be processed, the grayscale histogram information of the image of the sample to be processed can have the maximum recognition accuracy.

It is understood that if the server 100 can identify the sample and the background in the area with minimal contrast, it is of course also possible to identify the sample and the background in other areas, thereby distinguishing the background part of the image to be processed from the Sample part is distinguished.

Sub-step S2032: extracting background information contained in the image of the sample to be processed based on the gray level histogram information to obtain key frame information of the sample.

Step S204: Obtain specific position information of the slit in the sample to be processed based on a predetermined image recognition model and the key frame information of the sample.

In a preferred embodiment, the server 100 positions the slit in the sample to be processed using a plurality of predetermined image recognition models to avoid the interference during acquisition of the position information of the slit in the sample to be processed, resulting in inaccuracy of the final acquired position information leads. It should be noted that a variety of predefined image recognition models differ. In general, a model corresponds to a feature of the slit in the sample to be processed and achieves a better anti-interference effect. At this time, step S204 should be replaced by: obtaining specific position information of the slit in the sample to be processed based on a plurality of predetermined image recognition models and the key frame information of the sample. Let it be 5 Referring to which is a specific flowchart of step S204. Step S204 includes:

Sub-step S2041: Obtain a plurality of preliminary position information of the slits in the sample to be processed in the image information of the key sample based on each of the models.

It goes without saying that in the undisturbed state, a large number of preliminary position information items should lie within the error range.

Sub-step S2042: Integrating a plurality of provisional position information to obtain the position information.

For example, when there is a large disturbance, the server 100 can reject the position information with the larger error in the plurality of preliminary position information and determine the true position information of the slit in the sample to be processed from the remaining preliminary position information.

In a preferred embodiment, the specific position information is image coordinates.

Step S205: Transmitting the position information to an impact robot.

By transmitting the position information to the impact robot, the impact robot can know the position of the sample in real time, and the impact robot can carry out the impact test.

Second embodiment

Let it be 6 referenced. 6 Figure 200 is a functional block diagram of an apparatus 200 for determining a position (and preferably positioning) of a slit in a sample to be processed in accordance with a preferred embodiment of the present invention. It should be noted that the basic principle and technical effects of the device 200 provided in this embodiment are the same as in the above embodiment. For a brief description of what is not mentioned in the embodiment part, the corresponding content in the above embodiment can be referred to. The device 200 comprises a recording parameter determination unit 210, a receiving unit 220, a filter unit 230, a position information acquisition unit 240 and a transport unit 250.

The acquisition parameter determination unit 210 is configured to determine acquisition parameters based on the received sample cooling temperature.

In a preferred embodiment, it can be understood that the recording parameter determination unit 210 can be used to carry out step S201.

The reception unit 220 is configured to receive an image of a sample to be processed collected by an image acquisition device in a state of the acquisition parameters.

In a preferred embodiment, it can be understood that the receiving unit 220 can be used to perform step S202.

The filter unit 230 is configured to filter the image of the sample to be processed to obtain key frame information of the sample.

In particular, the filter unit 230 is configured to acquire gray level histogram information of a background of the image of the sample to be processed.

The filter unit 230 is configured to obtain a line of distinction between the sample and the background in the image of the sample to be processed, the filter unit 230 is further configured divide the image of the sample to be processed into a plurality of regions along the line of distinction, the filtering unit 230 is further configured to obtain the grayscale histogram and the grayscale histogram mean of each region, and the filtering unit 230 is further configured to obtain a grayscale histogram having the smallest grayscale histogram mean as the grayscale histogram information of the image of the sample to be processed.

The filter unit 230 is further configured to extract background information contained in the image of the sample to be processed based on the gray level histogram information to obtain key frame information of the sample.

In a preferred embodiment, it can be understood that the filter unit 230 can be used to perform step S203, sub-step S2031, sub-step S2032, sub-step S20311, sub-step S20312, sub-step S20313 and sub-step S20314.

The position information acquisition unit 240 is configured to obtain position information of the slit in the sample to be processed based on the predetermined image recognition model and the key frame information of the sample.

In a preferred embodiment, the position information acquisition unit 240 is further configured to obtain specific position information of the slit in the sample to be processed based on a plurality of predetermined image recognition models and the key frame information of the sample.

In a preferred embodiment, it can be understood that the position information acquisition unit 240 can be used to perform step S204, sub-step S2041 and sub-step S2042.

The transport unit 250 serves to transmit position information to an impact robot.

In a preferred embodiment, it can be understood that the transport unit 250 can be used to perform step S205.

In summary, the method and apparatus for determining a position of a slit in a sample to be processed, provided by the embodiment of the invention, determines the acquisition parameters according to the received sample cooling temperature and captures the image of the sample to be processed captured by an image capturing device in the state of Acquisition parameters is collected, then filtering the image of the sample to be processed to obtain keyframe information of the sample, and finally positional information of the slit in the sample to be processed based on a plurality of predetermined image recognition models and the keyframe information of the sample. Since different sample cooling temperatures have different effects on the recording results, there are corresponding recording parameters for each cooling temperature, so that the captured images of the sample to be processed are always in a relatively clear state. This is favorable for the subsequent background separation and determination of a position of the slit in the sample to be processed, thereby increasing not only the efficiency of obtaining the positional information of slits in the sample to be processed but also the accuracy of the positional information.

It should be noted that in this context relational terms such as first and second etc. are only used to distinguish one entity or operation from another entity or operation and does not necessarily require such actual relationship or ordering between those entities or operations or implied. The terms "including", "comprising" or any other variant thereof are intended to encompass a non-exclusive inclusion such that a process, method, article or device comprising a plurality of elements includes not only those elements but others as well includes elements not explicitly listed or inherent in such process, method, article or apparatus. Without further limitation, an element defined by the phrase "comprising..." does not preclude the presence of additional equivalent elements in the process, method, article, or device that comprise the element.

The above description is only the preferred embodiment of the present invention. It should be noted that similar reference numbers and letters indicate similar elements in the following drawings, and therefore when an element is defined in one drawing it is not necessary to further define and explain it in the following drawings.

Claims (8)

Method for determining a position of a slit in a sample to be processed, characterized in that the method comprises: determining (S201) acquisition parameters on the basis of a received sample cooling temperature in order to avoid impairment of an imaging result of the sample to be processed by fog generated in its vicinity as a result of too low a cooling temperature of the sample to be processed, wherein the shooting parameters include a shutter speed, an f-number, an ISO value, an exposure value and a setting parameter of a flash lamp with regard to turning it on or off; receiving (S202) an image of the sample to be processed captured and transmitted by an image capturing device whose capturing parameters are adjusted according to the received sample cooling temperature; filtering (S203) the image of the sample to be processed to obtain key frame information of the sample to be processed; and obtaining (S204) specific position information of the slit in the sample to be processed based on a plurality of predetermined image recognition models and the key frame information of the sample to be processed, each predetermined image recognition model corresponding to a feature of the slit in the sample to be processed. procedure after claim 1 , characterized in that the step of filtering (S203) the image of the sample to be processed to obtain key frame information of the sample to be processed comprises: obtaining (S2031) gray level histogram information of the image of the sample to be processed; extracting (S2032) background information contained in the image of the sample to be processed based on the gray scale histogram information to obtain the key frame information of the sample to be processed. procedure after claim 2 , characterized in that the step of obtaining (S2031) the gray level histogram information of the image of the sample to be processed comprises: obtaining (S20311) a line of distinction between the sample to be processed and the background in the image of the sample to be processed; dividing (S20312) the image of the sample to be processed into a plurality of areas along the discrimination line; determining (S20313) the gray level histogram and the average gray level histogram of each area; and using (S20314) a gray scale histogram having the smallest average gray scale histogram value as gray scale histogram information of the image of the sample to be processed. Method according to one of the preceding claims, characterized in that the step of obtaining (S204) specific position information of the slit in the sample to be processed based on the plurality of predetermined image recognition models and the key frame information of the sample to be processed comprises: detecting (S2041) a plurality of preliminary position information of the slit in the sample to be processed in the key frame information of the sample to be processed based on each of the plurality of predetermined image recognition models; and integrating (S2042) the plurality of provisional position information to obtain the specific position information. Apparatus (200) for determining a position of a slit in a sample to be processed, characterized in that the apparatus (200) comprises: an acquisition parameter determination unit (210) configured to determine acquisition parameters based on the received sample cooling temperature to avoid impairment to avoid an imaging result of the sample to be processed by a fog generated in its vicinity due to a too low cooling temperature of the sample to be processed, the recording parameters being a shutter speed, an aperture number, an ISO value, an exposure value and a setting parameter of a flash lamp in terms of their or include elimination; a receiving unit (220) for receiving an image of the sample to be processed captured and transmitted by an image capturing device whose capturing parameters are adjusted according to the received sample cooling temperature; a filter unit (230) configured to filter the image of the sample to be processed to obtain key frame information of the sample to be processed; and a position information acquisition unit (240) configured to obtain specific position information of the slit in the sample to be processed based on a plurality of predetermined image recognition models and the key frame information of the sample to be processed, each predetermined image recognition model being associated with a feature of the slit in the sample to be processed sample corresponds. Device (200) according to claim 5 , characterized in that the filter unit (230) is further configured to obtain grayscale histogram information from the background of the image of the sample to be processed, and that the filter unit (230) is further configured to obtain background information contained in the image of the sample to be processed, based on to extract the gray level histogram information to obtain the key frame information of the sample to be processed. Device (200) according to claim 6 , characterized in that the filter unit (230) is further configured to obtain a line of distinction between the sample to be processed and the background in the image of the sample to be processed, that the filter unit (230) is further configured to convert the image of the sample to be processed into dividing a plurality of areas along the distinction line, that the filter unit (230) is further configured to determine the average gray level histogram of the individual areas, and that the filter unit (230) is further configured to use the smallest average gray level histogram as gray level histogram information of the background. Device (200) according to one of Claims 5 until 7 , characterized in that the position information acquisition unit (240) is further configured to acquire a plurality of preliminary position information of the slit in the sample to be processed in the key frame information of the sample to be processed based on each of the plurality of predetermined image recognition models, and that the position information acquisition unit (240 ) is further configured to integrate the plurality of preliminary position information to obtain the specific position information.

Images