KR102524374B1 - Automatic classification method and system of agricultural products using image analysis model - Google Patents

Abstract

A method and system for automatic classification of agricultural products using an image analysis model are disclosed. The present invention is a method for measuring the quality grade of agricultural products based on an image taken from a camera, wherein -the first agricultural product is a pre-selected high-quality agricultural product, and the second agricultural product is a pre-selected low-quality agricultural product- Receiving a first image photographed and a second image photographed of the second agricultural product, generating a first difference image based on the first image and the second image, subjective quality of the field worker from the worker receiving an operator's masking input by selecting an image element determined to be defective from among image elements constituting the first difference image according to a criterion; Masking the difference image to generate a masked second difference image, leaving only elements that the field worker considers important in determining defects, the first image and the second image as inputs, and the second difference image Deep learning the correlation between the input and output data by the deep neural network by outputting it, calculating the size of the remaining image elements of the second difference image as a defect value, and calculating the inspection reference value through the defect value distribution of the second difference image and classifying agricultural products to be inspected based on the inspection reference value.

Description

Automatic classification method and system of agricultural products using image analysis model

The present invention relates to an automatic classification method and system for agricultural products using an image analysis model. More specifically, it relates to a method and system for learning defective parts of agricultural products through an image analysis model and using the learning results to measure the quality level of agricultural products or automatically classify them based on quality.

Agricultural products refer to animals and plants obtained from the land, and the quality of agricultural products may mean marketability including freshness and nutritional status of agricultural products.

In general, in order to sell agricultural products, experts in the field visually classify agricultural products according to size, freshness, etc., and classify quality. Due to the characteristics of agricultural products with a short distribution period, the quality grade of agricultural products and the process for this are very important. Therefore, before the agricultural products are shipped, a process of rapidly dividing quality grades is performed.

In the past, experts manually classified agricultural products, graded, etc., but the need for a technology capable of automatically performing these processes has recently emerged.

To this end, prior art KR101839548B1 proposes a device capable of detecting the maturity of agricultural products using buoyancy and sorting and classifying agricultural products according to the detection information. However, the prior art includes problems such as high cost in that a device having a complicated configuration must be provided.

Accordingly, there is a need for a method and system capable of automatically measuring the quality level of agricultural products or classifying them according to quality as well as quality level measurement by experts using only images or images using the development of image analysis model technology.

KR101839548B1 (Title of invention: agricultural product sorting device)

An object of the present invention is to provide a method and system capable of measuring quality only with images of agricultural products using a vision recognition algorithm.

In addition, an object of the present invention is to generate a difference image between a high-quality agricultural image and a low-quality agricultural product image, and to set each agricultural image and the difference image as an input value and an output value of an algorithm to automatically perform an in-depth judgment similar to an expert. It is to provide a method and system capable of measuring the quality of agricultural products using a neural network.

In addition, an object of the present invention is to provide a method and system capable of more accurately generating a difference image during vision recognition by introducing an optimized application filter and measuring the quality of agricultural products through this.

In addition, the present invention creates a clear image in any environment by generating an image through a camera including a stain-resistant lens resistant to contaminants and salt, and a method for measuring the quality of agricultural products to perform a more accurate vision recognition algorithm, and to provide the system.

In order to solve the above problems, the present invention is a method for measuring the quality grade of agricultural products based on images taken from a camera, wherein the first agricultural products are pre-selected high-quality agricultural products, and the second agricultural products are pre-selected low-quality agricultural products. agricultural products, receiving a first image of photographing the first agricultural product and a second image of photographing the second agricultural product; storing the first image and the second image; 2 Step of generating the image based on the image, selecting an image element determined to be defective among image elements constituting the first difference image according to the subjective criteria for determining good quality of the field worker, and receiving a masking input from the operator. Generating a masked second difference image in which only the elements that the field worker considers important in determining defects are left by masking the image elements other than the image element selected by the masking input from the first difference image; Deep learning the correlation between input and output data by a deep neural network by taking the first image and the second image as inputs and outputting the second difference image, the size of the remaining image elements of the second difference image as a defect value and calculating an inspection reference value through the defect value distribution of the second difference image, and measuring a quality grade of the agricultural product to be inspected based on the inspection reference value.

In addition, the generating of the first difference image may include dividing the first agricultural product in the first image into a plurality of regions, dividing the second agricultural product in the second image into a plurality of regions, and the The method may include generating the first difference image based on a plurality of regions.

In addition, the generating of the first difference image based on the plurality of regions may include comparing a plurality of regions of the first agricultural product with regions corresponding to each other among a plurality of regions of the second agricultural product, 1 difference images can be created.

Also, the inspection reference value may be a median value of a boundary value between a good product and a defective product in the distribution of defect values.

The generating of the first difference image may include generating at least one corrected image by applying an image correction filter to at least one of the first image and the second image; and and generating the first difference image based on the obtained image.

In addition, in order to solve the above problems, the present invention is a camera for photographing a pre-selected high-quality first agricultural product and a pre-selected low-quality second agricultural product, and a first image of the first agricultural product and the second agricultural product A computing device for receiving a second image taken from the camera and measuring a quality grade of the agricultural product to be inspected based on the first image and the second image, wherein the computing device comprises the above-described measuring method It may include a memory for storing instructions to be executed and a processor for executing the instructions.

In addition, in order to solve the above problems, the present invention is a non-transitory computer readable medium storing instructions, and when the instructions are executed by a processor, the processor can perform the above-described method.

The present invention measures the quality of agricultural products through deep learning learning for agricultural images, but when measuring quality, the operator's subjective quality measurement criteria are directly reflected in the deep learning learning process to have the same selection performance as the manual human judgment result. have an effect

In addition, the present invention has an effect of providing a method and system capable of measuring quality only with images of agricultural products using a vision recognition algorithm.

In addition, the present invention generates a difference image between a high-quality agricultural image and a low-quality agricultural product image, and sets each agricultural image and the difference image as input values and output values of an algorithm to create a deep neural network that can automatically perform a judgment similar to an expert. It has the effect of measuring the quality of agricultural products using it.

In addition, the present invention has an effect of providing a method and system capable of more accurately generating a difference image during vision recognition by introducing an optimized application filter and measuring the quality of agricultural products through this.

In addition, the present invention creates a clear image in any environment by generating an image through a camera including a stain-resistant lens resistant to contaminants and salt, and a method for measuring the quality of agricultural products to perform a more accurate vision recognition algorithm, and It has the effect of providing the system.

Effects obtainable according to the present invention are not limited to the effects mentioned above, and other effects not mentioned can be clearly understood by those skilled in the art from the description below. will be.

1 shows a method for automatically classifying agricultural products based on images taken from a camera according to the present invention.
2 and 3 show steps of generating a first difference image according to the present invention.
4 and 5 show an embodiment of the agricultural product quality rating measurement method according to the present invention.
6 is a graph showing inspection reference values according to the present invention.
7 is a diagram showing an example of dividing an image into a plurality of regions according to the present invention.
8 is a diagram showing an example of an image correction filter according to the present invention.
9 is a diagram showing a three-dimensional HSV graph according to the present invention.
10 is a diagram illustrating an example of an HSV value of one color.
11 shows an automatic classification system for agricultural products according to the present invention.
12 is a diagram illustrating a computing device according to the present invention.
13 is a view showing a camera module included in a camera according to the present invention.
The accompanying drawings, which are included as part of the detailed description to aid understanding of the present specification, provide examples of the present specification and describe technical features of the present specification together with the detailed description.

Hereinafter, the embodiments disclosed in this specification will be described in detail with reference to the accompanying drawings, but the same or similar elements are given the same reference numerals regardless of reference numerals, and redundant description thereof will be omitted.

In addition, in describing the embodiments disclosed in this specification, if it is determined that a detailed description of a related known technology may obscure the gist of the embodiment disclosed in this specification, the detailed description thereof will be omitted.

In addition, the accompanying drawings are only for easy understanding of the embodiments disclosed in this specification, the technical idea disclosed in this specification is not limited by the accompanying drawings, and all changes included in the spirit and technical scope of the present invention , it should be understood to include equivalents or substitutes.

Terms including ordinal numbers, such as first and second, may be used to describe various components, but the components are not limited by the terms. These terms are only used for the purpose of distinguishing one component from another.

Singular expressions include plural expressions unless the context clearly dictates otherwise.

In this application, terms such as "comprise" or "have" are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other features It should be understood that the presence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded.

Hereinafter, a method for automatically classifying agricultural products using an image analysis model according to a preferred embodiment of the present specification based on the above description will be described in detail as follows.

1 shows a method for automatically classifying agricultural products based on images taken from a camera according to the present invention.

In the present invention, the first agricultural product is a pre-selected high-quality agricultural product, and the second agricultural product may mean a pre-selected low-quality agricultural product.

According to FIG. 1, the agricultural product quality rating measurement method according to the present invention includes the steps of receiving a first image of a first agricultural product and a second image of a second agricultural product (S110), the first image and the second image Storing (S120), generating a first difference image based on the first image and the second image (S130), an image constituting the first difference image according to the subjective quality discrimination criterion of the field worker from the operator Selecting an image element determined to be defective among elements and receiving a masking input from a worker (S140), masking image elements other than the image element selected by the masking input in the first difference image so that the field worker is defective Generating a masked second difference image leaving only elements considered important in discrimination (S150), taking the first image and the second image as inputs and outputting a second difference image so that the deep neural network correlates input and output data Deep learning the relationship (S160), calculating the size of the remaining image elements of the second difference image as defect values and calculating an inspection reference value through the defect value distribution of the second difference image (S170), and It may include a step (S180) of classifying agricultural products to be inspected on the basis.

In this case, the inspection reference value may be a median value of a boundary value between a good product and a defective product in the distribution of defect values.

The first difference image may be an image in which all elements in common between the first image and the second image are excluded and only elements differing from each other are displayed. Also, the second difference image may be an image in which only specific elements are selected and displayed in the first difference image. At this time, the present invention intends to learn the algorithm through the second difference image.

In addition, the method for measuring the quality grade of aquatic products according to the present invention inputs the masking input received in step S130 to the deep learning algorithm to learn, and automatically masks the first difference image through the learned deep learning algorithm input, and through this, a second difference image may be generated. That is, the deep learning algorithm that has learned the masking input may automatically perform a process of masking the characteristic or defective part of the first difference image in FIG. 4 to be described later.

In the step of classifying the agricultural products to be inspected based on the inspection reference value (S180), the agricultural products may be classified as high quality or low quality based on the inspection reference value. That is, the method according to the present invention can measure the quality level of agricultural products based on the inspection reference value, and can classify agricultural products according to quality.

2 and 3 show steps of generating a first difference image according to the present invention.

According to Figure 2, the step of generating a first difference image according to the present invention is the step of dividing the first agricultural product in the first image into a plurality of regions (S121), dividing the second agricultural product in the second image into a plurality of regions (S122) and generating a first difference image based on a plurality of regions (S123).

At this time, the step of generating a first difference image based on the plurality of regions (S123) compares the plurality of regions of the first agricultural product with the regions corresponding to each other among the plurality of regions of the second agricultural product, and then compares the first difference image It may be a step of generating.

According to FIG. 3, generating a first difference image according to the present invention is a step of generating at least one corrected image by applying an image correction filter to at least one of the first image and the second image (S124). and generating a first difference image based on the at least one corrected image (S125).

4 and 5 show an embodiment of the automatic classification method of agricultural products according to the present invention.

According to FIG. 4 , the method for automatically classifying agricultural products according to the present invention may generate a first difference image by subtracting a second image from a first image. The first difference image may include feature elements included in the second image. In the method of automatically classifying agricultural products according to the present invention, elements judged to be defective may be selected by an operator from among characteristic elements of the first difference image through masking.

In addition, the method of automatically classifying agricultural products according to the present invention may generate a second difference image in which only elements determined to be defective selected through masking are left in the first difference image. The second difference image may refer to an image in which elements other than elements determined to be defective in the first difference image are masked and covered.

According to FIG. 5 , the deep neural network of the present invention means a system or network that builds one or more layers in one or more computers and performs a judgment based on a plurality of data. For example, a deep neural network can be implemented with a set of layers including a convolutional pooling layer, a locally connected layer, and a fully-connected layer. For example, the overall structure of the deep neural network may be a convolutional neural network (ie, convolutional neural network; CNN) structure in which a local access layer is followed by a convolutional pooling layer, and a fully connected layer is followed by a local access layer. In addition, the deep neural network may be formed, for example, in a recurrent neural network (RNN) structure in which nodes of each layer include edges pointing to the nodes and are connected recursively. The deep neural network may include various criterion (ie, the first image, the second image, and the second difference image), and a new criterion may be added by analyzing an input image. However, the structure of the deep neural network according to the embodiment of the present invention is not limited thereto, and may be formed with various structures of neural networks.

In an embodiment of the present invention, a good product sorting system including a deep neural network may be implemented in a single computer or may be implemented through a network by connecting a plurality of computers.

That is, the deep neural network of the present invention can learn the correlation between the first image and the second image and the second difference image as an output.

According to FIG. 5 , the deep neural network according to the present invention can learn both the second difference image and the reference image as output values. The reference image may be learned as an image that can be compared with the second difference image.

6 is a graph showing inspection reference values according to the present invention.

According to FIG. 6 , defect values of the second difference image may have various distributions. For example, if the distribution of defect values of high-quality agricultural products is mostly distributed between 0 and 10 based on the defect value size and the distribution of defect values of low-quality agricultural products is mostly distributed over 90 based on the defect value size, the distribution of defect values A defect size criterion of 50, which is the median value of the boundary values of defective products, may be used as the learned inspection standard value.

That is, the automatic classification method of agricultural products according to the present invention receives the defect values of the first image and the second image, and compares the received defect values with the inspection reference value to classify the quality of the agricultural products.

7 is a diagram showing an example of dividing an image into a plurality of regions according to the present invention.

According to Figure 7, the first agricultural product and the second agricultural product according to the present invention may be the same kind of plant. In addition, the method of automatically classifying agricultural products according to the present invention may recognize each agricultural product included in the first image and/or the second image, and divide each agricultural product into a plurality of regions for recognition. To this end, the deep learning algorithm according to the present invention may be pre-learned feature vectors for the leaf area A3, the stem area A2, and the root area A1 of the corresponding agricultural product (or corresponding plant). Accordingly, the plurality of regions may include a leaf region A3 , a stem region A2 , and a root region A1 of the plant.

As described above, the method for automatically classifying agricultural products according to the present invention divides an agricultural product image into a plurality of regions and divides the image into a plurality of regions and receives defective elements from each divided region, thereby obtaining data on defective elements more effectively and obtaining a second difference image. can have an effect that is easy to create.

8 is a diagram showing an example of an image correction filter according to the present invention.

According to FIG. 8, the types and functions of filters are shown. That is, the CNN algorithm may be a learning algorithm using a plurality of layers. In addition, the CNN algorithm can automatically learn a filter that maximizes image classification accuracy, and by adding a new layer called a convolutional layer and a polling layer before the fully connected layer, after applying the filtering technique to the original image, the filtered image A classification operation can be performed on . The CNN algorithm is configured to apply a filtering technique to the original image by adding a new layer, called a convolutional layer and a pooling layer, before the fully-connected layer, and then perform a classification operation on the filtered image. can

At this time, the operation expression for the image filter using the CNN algorithm is as shown in Equation 1 below.

[Equation 1]

(step,

: 행렬로 표현된 필터링된 이미지의 i번째 행, j번째 열의 픽셀,

: pixels in the i-th row and j-th column of the filtered image expressed as a matrix,

: 필터,

: filter,

: 이미지,

: image,

: 필터의 높이 (행의 수),

: height of the filter (number of rows),

: 필터의 너비 (열의 수)이다. )

: The width of the filter (number of columns). )

Preferably, the operation expression for the image filter using the CNN algorithm is as shown in Equation 2 below.

[Equation 2]

(step,

: 행렬로 표현된 필터링된 이미지의 i번째 행, j번째 열의 픽셀,

: pixels in the i-th row and j-th column of the filtered image expressed as a matrix,

: 응용 필터

: Application filter

: 이미지,

: image,

: 응용 필터의 높이 (행의 수),

: height of application filter (number of rows),

: 응용 필터의 너비 (열의 수)이다.)

: The width (number of columns) of the application filter.)

는 아래의 수학식 3에 의하여 연산될 수 있다. A filter may be applied. In particular, in the case of aquatic products, quality can be assessed based on (1) difference in color and (2) difference in shape, so an application filter for effectively recognizing color and shape may be required. Application filters to meet these needs

Can be calculated by Equation 3 below.

[Equation 3]

: 필터,

: 계수,

: 응용 필터)(step,

: filter,

: Coefficient,

: application filter)

는 수산물의 종류에 따라 나뉘어 제1 이미지 및/또는 제2 이미지에 적용될 수 있다. 이때, 각

에 따른 필터는 도 8에 따른 엣지 인식 필터(Edge detection), 샤픈 필터(sharpen) 및 박스 블러 필터(Box blur) 중 어느 하나의 행렬일 수 있다. Preferably, the application filter according to the present invention

may be applied to the first image and/or the second image by being divided according to the type of aquatic product. At this time, each

The filter according to may be a matrix of any one of an edge detection filter according to FIG. 8, a sharpen filter, and a box blur filter.

를 구하는 연산식은 아래의 수학식 4와 같다. 이때,

는 필터의 효율을 높이기 위하여 사용되는 하나의 상수로서 해석될 수 있고, 그 단위는 무시될 수 있다. Preferably,

The operation expression for obtaining is as shown in Equation 4 below. At this time,

can be interpreted as a constant used to increase the efficiency of the filter, and its unit can be ignored.

[Equation 4]

However, the diameter (diameter) of the lens of the camera used to take the image is in mm, the f-value of the lens is the aperture value (F number) of the lens, and the HSV average value is the size of the color coordinates according to the image of agricultural products through the HSV graph It may mean a value obtained by averaging values converted into values. Details of the HSV value are as follows.

9 is a diagram showing a three-dimensional HSV graph according to the present invention, and FIG. 10 is a diagram showing an example of HSV values of one color.

9 and 10, the HSV graph according to the present invention may mean a color space in which perceptual characteristics are reflected. H (Hue, 0 to 360°) may mean hue, S (Saturation, 0 to 100%) may mean saturation, and V (Value, 0 to 100%) may mean lightness. . Hue, saturation, and lightness values can be referred to as HSV values, which can be easily extracted using graphic tools such as Adobe illustrator cc 2019.

The HSV average value according to the present invention can be obtained through the HSV three-dimensional coordinates of FIG. 9 . That is, the average HSV value according to the present invention may be calculated based on the HSV value obtained through the graphic tool as shown in FIG. 10 . The distance value of the HSV coordinates measured with the origin coordinates on the HSV 3-dimensional coordinates as a reference point may constitute the above-described HSV average value. That is, the image according to the present invention includes an image of agricultural products, and the HSV color coordinates of the image of agricultural products may be distributed in a certain area. Therefore, the HSV average value according to the present invention may mean a distance value from the origin coordinates calculated based on average coordinates using the average of HSV coordinates for colors of a certain region.

However, in the case of agricultural products, there may be many differences in color for each part, so in the present invention, as shown in FIG.

[Experimental Example]

The results of analyzing the accuracy of the first difference image generated when the applied filter F' of the present invention is applied to the image generated using the CNN algorithm according to the present invention are shown in Table 1 below. At this time, the accuracy indicates the correspondence between the difference elements shown in the first difference image and the difference elements directly selected by the expert as a numerical value.

no filter applied

적용filter

apply filter

apply accuracy 49 62 84

(unit: %)

는 도 8의 샤픈 필터(sharpen)로 실험되었다. Table 1 shows, for each case, the accuracy of numerically expressing the correspondence between the difference elements of the first difference image according to the present invention and the difference elements directly selected by an expert. Table 1 summarizes the results performed based on 100 samples for a total of one agricultural product, and the accuracy is a rounded value. At this time, the general filter

was tested with the sharpen filter of FIG. 8.

를 적용하는 것이 더 높은 정확도를 나타내었다. 또한, 일반 필터

를 적용하는 것보다, 본 발명에 따른 응용 필터

를 적용하는 것이 현저히 높은 정확도를 나타내었다. As can be seen in Table 1, the case of creating a first difference image without applying a filter is more than a normal filter.

, showed higher accuracy. Also, the general filter

Rather than applying the applied filter according to the present invention

, showed significantly higher accuracy.

Hereinafter, based on the above description, an automatic classification system for agricultural products using an image analysis model according to another preferred embodiment of the present specification will be described in detail as follows.

11 shows an automatic classification system for agricultural products according to the present invention.

According to FIG. 11, the automatic sorting system for agricultural products according to the present invention may include a camera 100 and a computing device 200. The camera 100 according to the present invention may take a pre-selected high-quality first agricultural product and a pre-selected low-quality second agricultural product.

In addition, the computing device 200 according to the present invention receives a first image of photographing the first agricultural product and a second image of photographing the second agricultural product from the camera 100, and the first image and the first agricultural product. 2 Based on the image, the quality grade of agricultural products to be inspected can be measured.

The computing device 200 according to the present invention may be a subject that performs the automatic classification method of agricultural products using the image analysis model according to the above-described preferred embodiment of the present specification.

12 is a diagram illustrating a computing device according to the present invention.

According to FIG. 12 , a computing device 200 according to the present invention may include a processor 210, a memory 220, and a communication module 230.

The processor 210 may execute commands stored in the memory 220 to control other components. The processor 210 may execute instructions stored in the memory 220 .

The processor 210 is a component capable of performing calculations and controlling other devices. Mainly, it may mean a central processing unit (CPU), an application processor (AP), a graphics processing unit (GPU), and the like. Also, the CPU, AP, or GPU may include one or more cores therein, and the CPU, AP, or GPU may operate using an operating voltage and a clock signal. However, while a CPU or AP consists of a few cores optimized for serial processing, a GPU may consist of thousands of smaller and more efficient cores designed for parallel processing.

The processor 210 may provide or process appropriate information or functions to a user by processing signals, data, information, etc. input or output through the components described above or by running an application program stored in the memory 220.

The memory 220 stores data supporting various functions of the server 200 . The memory 220 may store a plurality of application programs (application programs or applications) running in the server 200, data for operation of the server 200, and commands. At least some of these application programs may be downloaded from the external server 200 through wireless communication. Also, the application program may be stored in the memory 220, installed in the server 200, and driven by the processor 210 to perform the operation (or function) of the server 200.

The memory 220 may be a flash memory type, a hard disk type, a solid state disk type, a silicon disk drive type, or a multimedia card micro type. ), card-type memory (eg SD or XD memory, etc.), RAM (random access memory; RAM), SRAM (static random access memory), ROM (read-only memory; ROM), EEPROM (electrically erasable programmable read -only memory), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, and an optical disk. Also, the memory 220 may include a web storage performing a storage function on the Internet.

The communication module 230 may be a component for communicating with an external server or the camera 100 . In the case of the communication module 230, information is transmitted and received with a base station or an external server or camera 100 having a communication function through an antenna. The communication module 230 may include a modulation unit, a demodulation unit, a signal processing unit, and the like.

Wireless communication may refer to communication using a wireless communication network using a communication facility previously installed by telecommunication companies and a frequency of the communication facility. At this time, the communication module 230 is CDMA (code division multiple access), FDMA (frequency division multiple access), TDMA (time division multiple access), OFDMA (orthogonal frequency division multiple access), SC-FDMA (single carrier frequency division multiple access), and the like, as well as the communication module 230 can also be used for 3rd generation partnership project (3GPP) long term evolution (LTE). In addition, not only 5G communication currently commercialized, but also 6G communication scheduled for commercialization in the future may be used. However, the present specification may utilize a pre-installed communication network without being bound by such a wireless communication method.

In addition, as a short range communication technology, Bluetooth, BLE (Bluetooth Low Energy), Beacon, RFID (Radio Frequency Identification), NFC (Near Field Communication), infrared communication (Infrared Data Association; IrDA) ), UWB (Ultra Wideband), ZigBee, etc. may be used.

13 is a view showing a camera module included in a camera according to the present invention.

According to FIG. 13 , the camera 100 according to the present invention may include a camera module 1320. The camera module 1320 may generate a video image from an optical image. The camera module 1320 may include a housing 1324 including a through hole on a side wall, a lens 1321 installed in the through hole, and a driving unit 1323 that drives the lens 1321 . The through hole may have a size corresponding to the diameter of the lens 1321 . The lens 1321 may be inserted into the through hole.

The driving unit 1323 may be configured to control the lens 1321 to move forward or backward. The lens 1321 and the driving unit 1323 are connected in a conventionally known manner, and the lens 1321 may be controlled by the driving unit 1323 in a conventionally known manner.

In order to obtain various video images, the lens 1321 needs to be exposed to the outside of the camera module 1320 or the housing 1324 .

In particular, since the camera according to the present invention needs to be directly installed in the outer area, a lens with strong contamination resistance is required. Accordingly, the present invention proposes a coating layer for coating a lens to solve this problem.

Preferably, the lens 1321 may include an acrylic compound represented by Formula 1 below on its surface; It may be coated with a coating composition containing an organic solvent, inorganic particles and a dispersant.

[Formula 1]

here,

n and m are the same as or different from each other, each independently represent an integer of 1 to 100, and L ₁ is a biphenylene group.

When the lens 1321 is coated with the coating composition, it can exhibit excellent water repellency and stain resistance, so even if the lens 1321 installed in the external environment is exposed to a polluted environment and salt for a long time, it is possible to collect clear and clear external images. .

The inorganic particles may be selected from the group consisting of silica, alumina, and mixtures thereof. The average diameter of the inorganic particles is 70 to 100 μm, but is not limited to the above examples. After forming the coating layer 1322 on the surface of the lens 1321, the inorganic particles may improve physical strength and maintain viscosity within a certain range to increase moldability.

The organic solvent is selected from the group consisting of methyl ethyl ketone (MEK), toluene, and mixtures thereof, and preferably methyl ethyl ketone may be used, but is not limited to the above examples.

As the dispersing agent, a polyester-based dispersing agent may be used, and specifically, TEGO-Disperse 670 (manufacturer : EVONIK) can be used, but it is not limited to the above examples, and all dispersants obvious to those skilled in the art can be used without limitation.

The coating composition may further include a stabilizer as other additives, and the stabilizer may include a UV absorber, an antioxidant, and the like, but is not limited to the above examples and may be used without limitation.

The coating composition for forming the coating layer 1322 may more specifically include an acrylic compound represented by Chemical Formula 1; organic solvents, inorganic particles and dispersants.

The coating composition may include 40 to 60 parts by weight of the acrylic compound represented by Formula 1, 20 to 40 parts by weight of inorganic particles, and 5 to 15 parts by weight of a dispersant, based on 100 parts by weight of the organic solvent. In the case of the above range, a synergistic effect is expressed to the extent that the water repellency effect due to the interaction of each component is of critical significance, and when it is out of the above range, the synergistic effect is rapidly reduced or almost nonexistent.

More preferably, the viscosity of the coating composition is 1500 to 1800 cP, and when the viscosity is less than 1500 cP, when applied to the surface of the lens 1321, there is a problem that it is not easy to form the coating layer 1322 because it flows down, and the coating composition exceeds 1800 cP. In this case, there is a problem in that it is not easy to form a uniform coating layer 1322.

[Preparation Example 1: Preparation of coating layer]

1. Preparation of coating composition

A coating composition was prepared by mixing methyl ethyl ketone with an acrylic compound represented by Formula 1, inorganic particles, and a dispersant:

[Formula 1]

here,

n and m are the same as or different from each other, each independently represent an integer of 1 to 100, and L ₁ is a biphenylene group.

A more specific composition of the antistatic composition is shown in Table 2 below.

TX1 TX2 TX3 TX4 TX5 organic solvent 100 100 100 100 100 acrylic compound 30 40 50 60 70 inorganic particles 10 20 30 40 50 dispersant One 5 10 15 20

(unit weight parts)

2. Preparation of coating layer

A coating layer 1322 was formed by applying the coating composition of DX1 to DX5 on one surface of the lens 1321 and then curing the coating composition.

[Experimental example]

1. Evaluation of surface appearance

Due to the difference in viscosity of the coating composition, after the coating layer 1322 was prepared, a sensory evaluation was performed on whether a uniform surface was formed. Evaluation was conducted on whether or not a uniform coating layer 1322 was formed, and the evaluation was conducted according to the following criteria.

○: uniform coating layer formation

×: Formation of non-uniform coating layer

TX1 TX2 TX3 TX4 TX5 sensory evaluation Х ○ ○ ○ Х

When forming the coating layer 1322, if the viscosity is less than a certain amount, flow occurs on the surface of the lens 1321, and it is difficult to form a uniform coating layer 1322 after the curing process in many cases. Accordingly, a problem of lowering the production yield may occur. In addition, even when the viscosity is too high, it is difficult to uniformly apply the composition, and it is impossible to form a uniform coating layer 1322.

2. Measurement of water repellency angle

After forming the coating layer 1322 on the surface of the lens 1321, the results of measuring the water repellency angle are shown in Table 4 below.

Advancing contact angle (") Static contact angle (“) receding contact angle (“) TX1 117.1±2.9 112.1±4.1 < 10 TX2 132.4±1.5 131.5±2.7 141.7±3.4 TX3 138.9±3.0 138.9±2.7 139.8±3.7 TX4 136.9±2.0 135.6±2.6 140.4±3.4 TX5 116.9±0.7 115.4±3.0 < 10

As shown in Table 4, after the coating layer 1322 was formed using the coating compositions of TX1 to TX5, the result of measuring the contact angle was confirmed. TX1 and TX5 measured receding contact angles less than 10 degrees. That is, it was confirmed that a phenomenon in which water droplets are pinned occurs when the coating composition is out of the optimal range for preparing the coating composition. On the other hand, it was confirmed that the pinning phenomenon did not occur in TX2 to 4, indicating that excellent waterproofing effect could be exhibited.

3. Fouling resistance evaluation

A lens 1321 having a coating layer 1322 according to the above embodiment formed outside the facility was attached to a model camera, and exposed to an external (outdoor) environment for 4 days. As the comparative example (Con), the same lens 1321 without the coating layer 1322 was used, and the model camera was attached to the same position in each example.

After that, the degree of contamination and corrosion of the lens 1321 before and after the experiment was evaluated as related, and for objective comparison, the result was compared with a comparative example in which the coating layer 1322 was not formed, and the result was evaluated by an index of 1 to 10, and the following Table 5 shows. In the index below, the lower the number, the better the stain resistance.

Con TX1 TX2 TX3 TX4 TX5 stain resistance 10 7 3 3 3 8

(Unit: index)

Referring to Table 5, in the case of forming the coating layer 1322 on the lens 1321, even if the lens 1321 is exposed to the outside while installing the camera in the external environment, high contamination resistance is easily analyzed for a long period of time. It can be seen that image data can be collected. In particular, in the case of TX2 to TX4, it can be confirmed that the contamination resistance by the coating layer 1322 is very excellent.

The above-described present invention can be modeled as a computer readable code on a medium on which a program is recorded. The computer-readable medium includes all types of recording devices in which data readable by a computer system is stored. Examples of computer-readable media include Hard Disk Drive (HDD), Solid State Disk (SSD), Silicon Disk Drive (SDD), ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc. , and also includes those modeled in the form of carrier waves (eg, transmission over the Internet). Accordingly, the above detailed description should not be construed as limiting in all respects and should be considered illustrative. The scope of this specification should be determined by reasonable interpretation of the appended claims, and all changes within the equivalent scope of this specification are included in the scope of this specification.

Any or other embodiments of the present invention described above are not mutually exclusive or distinct. Certain or other embodiments of the present invention described above may be used in combination or combination of respective configurations or functions.

The above detailed description should not be construed as limiting in all respects and should be considered illustrative. The scope of the present invention should be determined by reasonable interpretation of the appended claims, and all changes within the equivalent scope of the present invention are included in the scope of the present invention.

100: camera
200: computing device

Claims (7)

As a method of performing classification according to the quality of agricultural products based on images taken from a camera, - first agricultural products are agricultural products of pre-selected good products, and second agricultural products are agricultural products of pre-selected defective products, -
Receiving a first image of photographing the first agricultural product and a second image of photographing the second agricultural product;
storing the first image and the second image;
generating a first difference image based on the first image and the second image;
receiving an operator's masking input by selecting an image element determined to be defective from among image elements constituting the first difference image according to subjective good product discrimination criteria of the operator;
Generating a masked second difference image in which only elements that a field worker considers important in determining a defect are left by masking remaining image elements other than the image element selected by the masking input from the first difference image;
Deep learning a correlation between input and output data by a second deep neural network by using the first image and the second image as inputs and outputting the second difference image;
calculating a size of a remaining image element of the second difference image as a defect value and calculating an inspection reference value through a defect value distribution of the second difference image; and
Classifying agricultural products to be inspected based on the inspection reference value; Including,
Generating the first difference image,
Dividing the first agricultural product in the first image into a plurality of regions;
Dividing the second agricultural product in the second image into a plurality of regions; and
generating the first difference image based on the plurality of areas; and
Generating the first difference image based on the plurality of regions,
Comparing a plurality of regions of the first agricultural product with regions corresponding to each other among a plurality of regions of the second agricultural product to generate the first difference image;
Generating the first difference image,
generating at least one corrected image by applying an image correction filter according to Equation 2 below to at least one of the first image and the second image; and
Generating the first difference image based on the at least one corrected image;
Automatic classification method of agricultural products using image analysis model.
[Equation 2]

(step,

: pixels in the i-th row and j-th column of the filtered image expressed as a matrix,

: As an applied filter, Equation 3 below is applied.

: image,

: height of application filter (number of rows),

: The width (number of columns) of the application filter.)
[Equation 3]

(step,

: filter,

: Coefficient,

: application filter) delete delete According to claim 1,
The inspection reference value is a median value of a boundary value between a good product and a defective product in the distribution of defect values.
Automatic classification method of agricultural products using image analysis model. delete A camera for photographing the first agricultural products of pre-selected good products and the second agricultural products of pre-selected defective products; and
Computing for receiving a first image of the first agricultural product and a second image of the second agricultural product from the camera, and measuring a quality grade of the agricultural product to be inspected based on the first image and the second image. Including; device;
The computing device,
a memory storing instructions for performing the method of claim 1 or claim 4; and
A processor that performs the command; that includes,
Automatic classification system of agricultural products using image analysis model. A non-transitory computer readable medium storing instructions,
The instructions, when executed by a processor, cause the processor to perform the method of claim 1 or 4.

Images