KR20220117092A - Inspection appratus and contol method thereof - Google Patents

Abstract

An inspection device is disclosed. The inspection device includes a video shooting module; and a processor. When a video that is obtained by shooting an object to be inspected through the video shooting module, the processor performs a rule-based inspection on the obtained video to obtain a video region requiring deep learning inspection among the obtained video, performs a deep learning inspection on the obtained video region, and obtains defect information on the object to be inspected based on first defect information obtained through the rule-based inspection and second defect information obtained through the deep learning inspection. An objective of the present invention is to provide the inspection device and the control method thereof for reducing an inspection time.

Description

Inspection apparatus and its control method {Inspection appratus and control method thereof}

The present invention relates to an inspection apparatus and a method for controlling the same, and more particularly, to an inspection apparatus for inspecting the appearance of an object to be inspected and a method for controlling the same.

In general, the inspection method used in the industry secures an image of the inspection object and performs defect inspection through rule-based inspection.

However, when the inspection is carried out using a general rule base, there is a problem in that the efficiency of inspection time is reduced because the criteria for judging a defect are very complicated due to various specific values of the defect.

SUMMARY OF THE INVENTION The present invention has been made in accordance with the above-mentioned necessity, and an object of the present invention is to provide an inspection apparatus and a control method thereof for reducing inspection time.

The inspection apparatus according to an embodiment of the present invention for achieving the above object, when an image obtained by photographing an object to be inspected through an image capturing module and the image capturing module, performs a rule-based inspection on the obtained image and a processor for acquiring an image region requiring deep learning inspection among the acquired images by performing the deep learning inspection, and performing a deep learning inspection on the acquired image region to acquire defect information on the inspection object.

Also, the processor may acquire defect information on the inspection object based on first defect information obtained through the rule base inspection and second defect information obtained through the deep learning inspection.

In addition, the inspection object includes a printed circuit board (PCB), and the processor inputs the obtained area into an artificial intelligence model to obtain PCB defect information corresponding to the obtained area, and the artificial intelligence model can be learned to acquire defect information based on the inspection item of the rule base inspection.

In addition, the PCB defect information may include defect information on a PCB soldering state.

In addition, the processor performs a rule-based inspection on the acquired image to perform a rule-based inspection module for obtaining a region requiring a deep learning inspection among the acquired images and a deep learning inspection on the acquired image region, It may include a deep learning inspection module for transmitting the inspection result to the rule base inspection module.

On the other hand, in the control method of the inspection apparatus according to an embodiment of the present invention, when an image of an inspection object is acquired, a rule-based inspection is performed on the acquired image, and a deep learning inspection is required among the acquired images. It may include acquiring an image region, and performing a deep learning inspection on the acquired image region to acquire defect information on the inspection object.

In addition, the obtaining of the defect information on the inspection object may include: Defect information on the inspection object based on the first defect information obtained through the rule-based inspection and the second defect information obtained through the deep learning inspection may include the step of obtaining

According to the above-described various embodiments, it is possible to improve time efficiency by shortening the inspection time by the inspection object including various features.

1 is a block diagram showing the configuration of an inspection apparatus according to an embodiment of the present invention.
2 is a diagram for explaining a method of learning an artificial intelligence model according to an embodiment.
3 is a diagram for describing a detailed configuration of a processor according to an embodiment.
4 is a flowchart illustrating a method of controlling an inspection apparatus according to an exemplary embodiment.

Hereinafter, the present disclosure will be described in detail with reference to the accompanying drawings.

Terms used in this specification will be briefly described, and the present disclosure will be described in detail.

Terms used in the embodiments of the present invention are selected as currently widely used general terms as possible while considering the functions in the present invention, which may vary depending on the intention or precedent of a person skilled in the art, the emergence of new technology, etc. . In addition, in specific cases, there are also terms arbitrarily selected by the applicant, and in this case, the meaning will be described in detail in the description of the corresponding disclosure. Therefore, the term used in the present invention should be defined based on the meaning of the term and the overall content of the present invention, rather than the name of a simple term.

In the present invention, a "module" or "unit" performs at least one function or operation, and may be implemented as hardware or software, or a combination of hardware and software. In addition, a plurality of “modules” or a plurality of “units” are integrated into at least one module and implemented with at least one processor (not shown) except for “modules” or “units” that need to be implemented with specific hardware. can be

1 is a block diagram showing the configuration of an inspection apparatus according to an embodiment of the present invention.

Referring to FIG. 1 , an examination apparatus 100 includes an image capturing module 110 and a processor 120 .

The image capturing module 110 may be implemented with various types of cameras, and may capture the appearance of an inspection object (or a measurement object). The image capturing module 110 is activated according to a preset event and captures the appearance of the object to be inspected. For example, the image capturing module 110 may be activated as a user command or a preset program is executed.

According to an example, the inspection object may be implemented as a printed circuit board (PCB). For example, a board that composes an electronic circuit by fixing electronic components such as resistors, capacitors, inductors, and integrated circuits (ICs) to the surface of a printed wiring board and connecting them with copper wires. can mean

The processor 120 is electrically connected to the image capturing module 110 to control the overall operation of the examination apparatus 100 . The processor 120 may include one or a plurality of processors. According to an example, the processor 120 may perform the operation of the test apparatus 100 according to various embodiments of the present disclosure by executing at least one instruction stored in a memory (not shown).

According to an embodiment, the processor 120 may include a digital signal processor (DSP), a microprocessor (microprocessor), a graphics processing unit (GPU), an artificial intelligence (AI) processor, a neural network (NPU) for processing a digital image signal. Processing Unit), TCON (Time controller), but is not limited thereto, Central processing unit (CPU), MCU (Micro Controller Unit), MPU (micro processing unit), controller (controller), application processor (application processor (AP)), communication processor (communication processor (CP)), may include one or more of an ARM processor, or may be defined by the term. may be implemented as a system on chip (SoC), large scale integration (LSI), or an application specific integrated circuit (ASIC) or field programmable gate array (FPGA) with a built-in processing algorithm.

In addition, the processor 120 for executing the artificial intelligence model according to an embodiment is a general-purpose processor such as a CPU, an AP, a digital signal processor (DSP), etc., a graphics-only processor such as a GPU, a VPU (Vision Processing Unit), or an NPU and It can be implemented through a combination of the same artificial intelligence-only processor and software. The processor 120 may control to process input data according to a predefined operation rule or an artificial intelligence model stored in a memory (not shown). Alternatively, when the processor 120 is a dedicated processor (or an artificial intelligence-only processor), it may be designed with a hardware structure specialized for processing a specific artificial intelligence model. For example, hardware specialized for processing a specific artificial intelligence model may be designed as a hardware chip such as an ASIC or FPGA. When the processor 120 is implemented as a dedicated processor, it may be implemented to include a memory for implementing an embodiment of the present invention or a memory processing function for using an external memory.

According to an embodiment, when an image of the appearance of the inspection object is acquired through the image capturing module 110 , the processor 120 performs a rule-based inspection on the acquired image and requires a deep learning inspection among the acquired images. At least one image region is acquired (or extracted). Here, the inspection object may include a printed circuit board (PCB) as described above. Since the rule-based inspection is a conventional technique used for PCB defect inspection, a detailed description thereof will be omitted.

For example, the processor 120 performs a rule-based inspection on the acquired image and then acquires an image region in which defect information, such as whether there is a defect, a defect type, and a defect level, is not clearly detected as an image region requiring a deep learning inspection. However, the present invention is not limited thereto.

Subsequently, the processor 120 may acquire defect information on the inspection object by performing a deep learning inspection on the at least one acquired image region.

Specifically, the processor 120 may obtain PCB defect information corresponding to the obtained area by inputting the obtained area into the artificial intelligence model. In particular, the PCB defect information may include defect information on a PCB soldering state. Here, the PCB defect information may include at least one of whether there is a defect, a defect type, and a defect level.

Here, the artificial intelligence model may be trained to acquire defect information by classifying an image region based on inspection items of the rule-based inspection.

According to an example, the artificial intelligence model is a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN), a Restricted Boltzmann Machine (RBM), a Deep Belief Network (DBN), a Bidirectional Recurrent Deep Neural Network (BRDNN), or a deep Q-network ( Deep Q-Networks), but is not limited thereto.

According to an embodiment, the processor 120 may acquire defect information on the inspection object based on the first defect information obtained through the rule base inspection and the second defect information obtained through the deep learning inspection.

2 is a diagram for explaining a method of learning an artificial intelligence model according to an embodiment.

According to an embodiment, the artificial intelligence model may be learned based on a pair of input training data and output training data, or may be learned based on input training data. Here, the learning of the artificial intelligence model means that the basic artificial intelligence model (for example, an artificial intelligence model including an arbitrary random parameter) is learned using a plurality of training data by a learning algorithm, and thus a desired characteristic (or, It means that a predefined action rule or artificial intelligence model set to perform the purpose) is created. Such learning may be performed through the test apparatus 100 , but is not limited thereto, and may be performed through a separate server and/or system. Examples of the learning algorithm include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning. However, this is an example of supervised learning, and it is possible to train an artificial intelligence model based on unsupervised learning that trains an artificial intelligence model by inputting only input data without using recommended administrative information as output data. to be.

For example, as shown in FIG. 2 , the examination apparatus 100 may store an image region for learning in a DB and train the artificial intelligence model 210 based on the corresponding information. For example, the image region and defect information corresponding to the image region may be learned by using each input/output training data pair. In particular, the artificial intelligence model 210 may use an image region corresponding to each inspection item of the rule base inspection as input data, and may use defect information corresponding to the image region as output data.

However, this is an example of supervised learning, and it goes without saying that an artificial intelligence model can be trained based on unsupervised learning in which an artificial intelligence model is trained by inputting only input data without using defect information as output data. .

3 is a diagram for describing a detailed configuration of a processor according to an embodiment.

Referring to FIG. 3 , the processor 120 may include a rule base inspection module 121 and a deep learning inspection module 122 . Here, each module can be implemented in the form of at least one of software, hardware, or a combination thereof.

The rule base inspection module 121 may acquire a region requiring a deep learning inspection from among images obtained by performing a rule base inspection on an image obtained by photographing an inspection object. Here, the inspection object may be a PCB exterior.

The deep learning inspection module 122 may perform a deep learning inspection on the image region acquired through the rule base inspection module 121 and transmit the inspection result to the rule base inspection module 121 . In this case, the rule base inspection module 121 may acquire defect information on the inspection object based on the first defect information obtained through the rule base inspection and the second defect information received from the deep learning inspection module 122 . have.

4 is a flowchart illustrating a method of controlling an inspection apparatus according to an exemplary embodiment.

According to the control method of the inspection apparatus shown in FIG. 4 , when an image of an inspection object is acquired ( S410 ), a rule-based inspection is performed on the acquired image, and an image region requiring a deep learning inspection is selected from among the acquired images. can be obtained (S420).

Subsequently, a deep learning inspection may be performed on the obtained image region to acquire defect information on the inspection object ( S430 ).

In addition, in step S430 of obtaining the defect information on the inspection object, the defect information on the inspection object is obtained based on the first defect information obtained through the rule base inspection and the second defect information obtained through the deep learning inspection. can

Here, the inspection object may include a printed circuit board (PCB). In this case, in step S430 of obtaining defect information on the inspection object, the obtained area may be input to the artificial intelligence model to obtain PCB defect information corresponding to the obtained area. Here, the artificial intelligence model may be trained to acquire defect information based on the inspection items of the rule-based inspection.

In addition, the PCB defect information may include defect information on a PCB soldering state.

According to the above-described various embodiments, it is possible to improve time efficiency by shortening the inspection time by the inspection object including various features.

Meanwhile, the above-described methods according to various embodiments of the present invention may be implemented in the form of an application that can be installed in an existing inspection apparatus.

In addition, the above-described methods according to various embodiments of the present disclosure may be implemented only by software upgrade or hardware upgrade of an existing inspection apparatus.

In addition, the various embodiments of the present invention described above may be performed through an embedded server provided in the test apparatus or at least one external server of the test apparatus.

Meanwhile, according to an embodiment of the present invention, the various embodiments described above may be implemented as software including instructions stored in a machine-readable storage media readable by a machine (eg, a computer). The device is a device capable of calling a stored instruction from a storage medium and operating according to the called instruction, and may include a test apparatus according to the disclosed embodiments. When the instruction is executed by the processor, the processor directly , or other components under the control of the processor to perform a function corresponding to the instruction. The instruction may include code generated or executed by a compiler or interpreter. The machine-readable storage medium includes: It may be provided in the form of a non-transitory storage medium, where 'non-transitory storage medium' means a tangible device and does not contain a signal (eg, electromagnetic wave). However, this term does not distinguish between a case in which data is semi-permanently stored in a storage medium and a case in which data is temporarily stored, for example, a 'non-transitory storage medium' may include a buffer in which data is temporarily stored.

In addition, each of the components (eg, a module or a program) according to the above-described various embodiments may be composed of a single or a plurality of entities, and some sub-components of the aforementioned sub-components may be omitted, or other sub-components may be omitted. Components may be further included in various embodiments. Alternatively or additionally, some components (eg, a module or a program) may be integrated into a single entity to perform the same or similar functions performed by each corresponding component prior to integration. According to various embodiments, operations performed by a module, program, or other component may be sequentially, parallelly, repetitively or heuristically executed, or at least some operations may be executed in a different order, omitted, or other operations may be added. can

In the above, preferred embodiments of the present invention have been illustrated and described, but the present invention is not limited to the specific embodiments described above, and is commonly used in the technical field pertaining to the present disclosure without departing from the gist of the present invention as claimed in the claims. Various modifications are possible by those having the knowledge of, of course, and these modifications should not be individually understood from the technical spirit or perspective of the present invention.

100: inspection device 110: image capturing module
120: processor

Claims (7)

video recording module; and
When an image of an object to be inspected is acquired through the image capturing module, a rule-based inspection is performed on the acquired image to obtain an image region requiring a deep learning inspection among the acquired images,
Inspection apparatus comprising a; processor to obtain defect information on the inspection object by performing a deep learning inspection on the obtained image region. According to claim 1,
The processor is
An inspection apparatus for acquiring defect information on the inspection object based on first defect information obtained through the rule-based inspection and second defect information obtained through the deep learning inspection. According to claim 1,
The test object is
including a printed circuit board (PCB),
The processor is
Input the obtained area into an artificial intelligence model to obtain PCB defect information corresponding to the obtained area,
The artificial intelligence model is
An inspection apparatus learned to acquire defect information based on an inspection item of the rule-based inspection. 4. The method of claim 3,
The PCB defect information is,
Inspection device containing defect information about the PCB soldering condition. According to claim 1,
The processor is
a rule-based inspection module for performing a rule-based inspection on the acquired image to acquire a region requiring a deep learning inspection from among the acquired images; and
A deep learning inspection module that performs a deep learning inspection on the obtained image region and transmits the inspection result to the rule base inspection module; inspection apparatus comprising a. In the control method of the inspection device,
acquiring an image region requiring a deep learning test from among the acquired images by performing a rule-based inspection on the acquired image when an image obtained by photographing the inspection object; and
A control method comprising a; performing a deep learning inspection on the obtained image region to obtain defect information on the inspection object. 7. The method of claim 6,
The step of obtaining defect information on the inspection object includes:
Acquiring defect information on the inspection object based on the first defect information obtained through the rule base inspection and the second defect information obtained through the deep learning inspection; Control method comprising a.

Images