Light-transmitting identification device and method for mud-clamping dead shells of double-shell living products

Abstract

The invention discloses a light-transmitting identification device and a light-transmitting identification method for a mud-clamping dead shell of a double-shell living product, and the method comprises the following steps: carrying out light-transmitting identification on the double-shell living product by utilizing an identification device so as to judge the mud-clamping and / or dead shell of the double-shell living product; according to the invention, reliable quality, safety and sanitation of double-shell living products circulating in the market can be ensured; therefore, the health rights and interests of consumers can be guaranteed, and the credibility and satisfaction degree of the consumers to products can be improved.

Description

Technical Field

[0001] The invention discloses a light transmission identification device and a method for identifying dead shells of living bivalve products mixed with mud, and belongs to the technical field of aquatic product detection. Background Art

[0002] Bivalve molluscs are the most important category of edible aquatic shellfish. Their production accounts for more than 60% of the total production of farmed shellfish. The farming and management of bivalve molluscs are simple and do not require feeding. The production cost is low, and the protein in shellfish meat is easily digested and absorbed by the human body. It has long been a source of cheap animal protein supply for people. Most bivalve molluscs are often mixed with abnormal individuals such as dead shellfish, mud shellfish and shellfish with broken shells when they are harvested and circulated. These abnormal shellfish are generally difficult to identify. Once mixed, they can easily cause the death of other shellfish in the same batch, and a rancid smell will appear during cooking. In severe cases, they may even cause harm to consumers. Therefore, after the bivalve molluscs are harvested, they are required to remove the above-mentioned abnormal shellfish as much as possible before storage, processing or consumption, and store or circulate them in the market in the form of intact living shellfish. At present, there are several related methods for selecting abnormal shellfish, such as manual selection, gravity method, and percussion method. However, these methods have some shortcomings and have not been widely used so far.

[0003] The prior art discloses a mechanized method for selecting bivalve molluscs with announcement number: CN101549343A, which mainly involves vibrating the shell to close its shell, making the closed shell make a sound, and using computer sound recognition technology to identify the sound; however, the prior art identification takes a long time to learn and is prone to erroneous judgment. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention aims to provide a light-transmitting identification device and method for identifying dead shells of living bivalve products with mud, so as to solve the problem.

[0005] In order to achieve the above object, the present invention is implemented by the following technical solution: using an identification device to perform light transmission identification on a live bivalve product to determine whether the live bivalve product contains mud and / or dead shells; the identification device comprises:

[0006] A tray for laying out the live bivalve products to ensure that light can penetrate the products. The number of trays can be set according to actual needs to improve processing efficiency;

[0007] A conveyor belt is used to carry the tray and drive it to move, so as to realize the transportation of the live bivalve products;

[0008] The luminous panel, as a light source, corresponds to irradiating the live bivalve products on the tray;

[0009] A camera unit, used to capture live images of the live bivalve products on the tray after light is transmitted through them, and transmit the image data to a display screen for display;

[0010] A display screen, used for displaying the image captured by the camera unit in real time;

[0011] The processing unit is used to adjust the illumination of the light-emitting panel to meet the light transmission requirements of different types of bivalve products.

[0012] Preferably, a plurality of trays are provided, and the trays are made of light-transmitting acrylic plates.

[0013] Preferably, the light emitting panel is an LED light panel.

[0014] Preferably, the light-emitting panel is connected to a processing unit for adjusting the illumination of the light-emitting panel.

[0015] The light transmission identification method of the dead shells of the living bivalve products with mud comprises the following steps:

[0016] Step 1: Cleaning and classification: Clean the live bivalve products to remove impurities such as mud and sand attached to the surface; then classify the live bivalve products according to their types to ensure that the types of products processed in the same batch are consistent;

[0017] Step 2: Pre-processing of live bivalve products: laying the cleaned and classified live bivalve products in a single layer on a tray, ensuring that the live bivalve products do not overlap or block each other;

[0018] Step 3: Move to the imaging area, and move the tray to the imaging area formed by the light-emitting board and the camera unit through the conveyor belt. When the tray is in the imaging area, the conveyor belt automatically stops running to allow for light-transmitting photography;

[0019] Step 4: Adjust the illumination. According to the type and light transmission characteristics of the live bivalve product, adjust the illumination of the light-emitting panel through the processing unit to ensure that the light can completely penetrate the live bivalve product.

[0020] Step 5: Photograph and observe, and adjust the illumination of the light-emitting board according to the type of the live bivalve product, so that the light emitted by the light-emitting board can completely penetrate the live bivalve product;

[0021] Step 6: Sorting and rejection: For live bivalve products with mud or dead shells, take them out of the tray and sort them.

[0022] Preferably, in step 3, the conveyor belt is braked through the control of the processing unit.

[0023] Preferably, in step 6, the sorting process can be completed manually or achieved through automated sorting equipment.

[0024] Beneficial Effects

[0025] The present invention uses an identification device to perform light transmission identification on live bivalve products, and the present invention can accurately identify live bivalve products with mud and / or dead shells; compared with traditional manual selection, gravity method, tapping method and other methods, this identification method has higher identification accuracy and efficiency, and can effectively reduce misjudgment and missed judgment. By accurately identifying and eliminating live bivalve products with mud and / or dead shells, the present invention can ensure that the quality of live bivalve products circulating on the market is reliable, safe and hygienic. This helps to protect the health rights and interests of consumers and enhance consumers' trust and satisfaction with products. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0027] Figure 1 It is a structural schematic diagram of the identification device of the present invention; DETAILED DESCRIPTION

[0028] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the present invention is further explained below in conjunction with specific implementation methods.

[0029] See also Figure 1 The present invention provides a technical solution of a light-transmitting identification device for identifying live bivalve products with mud and dead shells: the identification device is used to perform light-transmitting identification on live bivalve products to determine whether the live bivalve products contain mud and / or dead shells; the identification device comprises:

[0030] The tray 1 is used to lay out the live bivalve products flatly to ensure that light can penetrate the products; the number of trays 1 can be set to multiple according to actual needs to improve processing efficiency. The tray 1 is preferably made of a light-transmitting acrylic board; this prevents the tray 1 from reflecting light and affecting the subsequent manual or external existing sorting equipment operations.

[0031] The conveyor belt 2 is used to carry the tray 1 and drive it to move, so as to realize the transportation of the living bivalve products; the conveyor belt 2 can be braked by controlling the conveyor belt 2, preferably, by relying on the processing unit 7 for control.

[0032] The light-emitting board 3, as a light source, corresponds to irradiating the living bivalve products on the tray 1; the light-emitting board 3 is an LED light board with sufficient illumination to ensure that the light can completely penetrate the living bivalve products; the light-emitting board 3 is connected to the processing unit 7, which is used to adjust the illumination of the light-emitting board 3 to meet the light transmission requirements of different types of bivalve products.

[0033] The camera unit 5 is used to capture the live image of the bivalve live products on the tray 1 after light is transmitted through them, and transmit the image data to the display screen 6 for display.

[0034] The display screen 6 is used to display the image captured by the camera unit 5 in real time.

[0035] The processing unit 7 is used to adjust the illumination of the light-emitting panel 3 and control the operation and braking of the conveyor belt 2.

[0036] The identification method comprises the following steps:

[0037] Step 1: Cleaning and classification: Clean the live bivalve products to remove impurities such as mud and sand attached to the surface; then classify the live bivalve products according to their types to ensure that the types of products processed in the same batch are consistent;

[0038] Step 2: Pre-processing the live bivalve products, laying the cleaned and classified live bivalve products in a single layer on the tray 1, ensuring that the live bivalve products do not overlap or block each other;

[0039] Step 3: Move to the imaging area 4, and move the tray 1 to the imaging area 4 formed by the light-emitting panel 3 and the camera unit 5 through the conveyor belt 2. When the tray 1 is in the imaging area 4, the conveyor belt 2 automatically stops running to allow for light-transmitting photography;

[0040] Step 4: Adjust the illumination, according to the type and light transmission characteristics of the bivalve live product, adjust the illumination of the light-emitting panel 3 through the processing unit 7 to ensure that the light can completely penetrate the bivalve live product;

[0041] Step 5: photograph and observe, and adjust the illumination of the light-emitting board 3 according to the type of live bivalve products, so that the light emitted by the light-emitting board 3 completely passes through the live bivalve products;

[0042] Step 6: Sorting and rejection: For the live bivalve products with mud or dead shells, they are taken out from the tray 1 and sorted.

[0043] In other embodiments, the processing unit is further configured to: determine the type of the living bivalve product according to an image recognition model, and then automatically adjust to an optimal illumination for output according to the type of the living bivalve product.

[0044] The construction of the image recognition model includes:

[0045] S11, obtaining a plurality of images of live bivalve products;

[0046] S12, labeling the bivalve live product images according to their corresponding species names, and then performing big data training;

[0047] S13, outputting an image recognition model based on the live bivalve product. It can be understood that by identifying the product type through the image recognition model, and then automatically adjusting and outputting the optimal illumination, the work efficiency can be further improved and the error of manual operation can be reduced.

[0048] Example 1

[0049] The live bivalve product is selected from the Bafi clam. Based on the biological characteristics of shellfish, after the shellfish dies, it fails to spit out the mud and sand, and the mud and sand have poor light transmittance, so there will be obvious color difference with other parts of the Bafi clam.

[0050]

[0051] Based on the experimental data in Table 1, the overall light transmittance of the preferred Bafi clams measured by an existing light transmittance tester under an illumination of 6000LX is over 80%; at a light transmittance of 80%, humans can easily distinguish which Bafi clams contain sand.

[0052] The identification method comprises the following steps:

[0053] Step 1: Cleaning and sorting: Clean the clams to remove impurities such as mud and sand attached to the surface;

[0054] Step 2: Pre-treat the clams by laying the cleaned and sorted clams in a single layer on the tray 1, ensuring that the clams do not overlap or block each other;

[0055] Step 3: Move to the imaging area 4, and move the tray 1 to the imaging area 4 formed by the light-emitting panel 3 and the camera unit 5 through the conveyor belt 2. When the tray 1 is in the imaging area 4, the conveyor belt 2 automatically stops running to allow for light-transmitting photography;

[0056] Step 4: Adjust the illumination. According to the type and light transmission characteristics of the clams, adjust the illumination of the light-emitting panel 3 to 6000LX through the processing unit 7 to ensure that the light can completely pass through the clams.

[0057] Step 5: shooting and observing, adjusting the illumination of the light-emitting panel 3 according to the buffalo clam, so that the light emitted by the light-emitting panel 3 completely passes through the buffalo clam product, and transmitting the live image to the display screen 6 through the camera unit 5;

[0058] Step 6: Sorting and rejection: For the clams with mud or dead shells, they are taken out from the tray 1 manually according to the image shown on the display screen 6 and sorted.

[0059] Example 2

[0060] The difference from Example 1 is that the live bivalve product is selected from clams;

[0061]

[0062] Based on the experimental data in Table 2, under an illumination of 50,000 LX, the overall light transmittance of the clam reaches more than 80%.

[0063] Example 3

[0064] The difference from Example 1 is that the live bivalve product is selected from clams;

[0065]

[0066] Based on the experimental data in Table 3, under an illumination of 117,000 LX, the overall light transmittance of the clam reaches more than 80%.

[0067] Example 4

[0068] The difference from Example 1 is that the live bivalve product is selected from American clams;

[0069]

[0070]

[0071] Based on the experimental data in Table 4, under an illumination of 200,000 LX, the overall light transmittance of the American clam reaches more than 80%.

[0072] The camera unit, display screen, processing unit, and transmission belt light mentioned in this patent are all existing conventional components and can be purchased directly on the market, so their circuit connection structure will not be described in detail in this specification.

[0073] In other embodiments, based on step 6, the processing unit is further used to: determine the type of the living bivalve product according to an image recognition model, and then automatically adjust to an optimal illumination for output according to the type of the living bivalve product.

[0074] The construction of the image recognition model includes:

[0075] S11, obtaining a plurality of images of live bivalve products;

[0076] S12, labeling the bivalve live product images according to their corresponding species names (mainly based on the patterns and colors of the bivalve live products), and then performing big data training;

[0077] S13, outputting an image recognition model based on the live bivalve product. It can be understood that by identifying the product type through the image recognition model, and then automatically adjusting and outputting the optimal illumination, the work efficiency can be further improved and the error of manual operation can be reduced.

[0078] In other embodiments, the construction of the image recognition model further includes:

[0079] S14, obtaining a plurality of photos of the same type of live bivalve products under optimal illumination;

[0080] S15, labeling the plurality of photos of the same type of live bivalve products under the optimal illumination according to the corresponding three names of "mud", "dead shell" and "normal", and then performing big data training.

[0081] It can be understood that by using an image recognition model to identify photos of live bivalve products of the same type under optimal illumination, and then determining their positions in the pictures, automatic sorting can ultimately be achieved through automated equipment.

[0082] By introducing the image recognition model, the identification device can automatically identify the type of live bivalve products and automatically adjust the illumination of the light-emitting panel to the optimal level according to the type. This function not only reduces the tedious process of manual adjustment of illumination, but also improves the accuracy of illumination adjustment, thereby ensuring the effect of light-transmitting photography.

[0083] The images of live bivalve products taken under optimal illumination have more obvious differences in light transmittance, which is conducive to subsequent sorting work.

[0084] The image recognition model can not only identify product types and illumination requirements, but can also further identify live bivalve products with mud or dead shells. This function provides the basis for automated sorting.

[0085] By combining the image recognition model with existing automated sorting equipment, the existing automated sorting equipment can automatically sort out problematic products from pallets based on the images identified by the image recognition model, greatly improving sorting efficiency and accuracy, thereby replacing manual sorting.

[0086] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic features of the present invention. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the attached claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any figure mark in the claims should not be regarded as limiting the claims involved.

[0087] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. A light-transmitting identification device for bivalve live products with mud and dead shells, characterized in that: The identification device is used to perform light transmission identification on the live bivalve products to determine whether the live bivalve products contain mud and / or dead shells; the identification device comprises: A tray for laying out the live bivalve products to ensure that light can penetrate the products. The number of trays can be set according to actual needs to improve processing efficiency; A conveyor belt is used to carry the tray and drive it to move, so as to realize the transportation of the live bivalve products; The luminous panel, as a light source, corresponds to irradiating the live bivalve products on the tray; A camera unit, used to capture live images of the live bivalve products on the tray after light is transmitted through them, and transmit the image data to a display screen for display; A display screen, used for displaying the image captured by the camera unit in real time; The processing unit is used to adjust the illumination of the light-emitting panel to meet the light transmission requirements of different types of bivalve products.

2. The light-transmitting identification device for bivalve live products with mud and dead shells according to claim 1, characterized in that: A plurality of trays are provided, and the trays are made of light-transmitting acrylic plates.

3. The light-transmitting identification device for bivalve live products with mud and dead shells according to claim 1, characterized in that: The light emitting panel is an LED light panel.

4. The light-transmitting identification device for bivalve live products with mud and dead shells according to claim 4, characterized in that: The light-emitting panel is connected to the processing unit to adjust the illumination of the light-emitting panel.

5. A method for identifying bivalve live products with mud and dead shells through light transmission, characterized in that: The following steps are involved: Step 1: Cleaning and sorting: cleaning the live bivalve products to remove impurities such as mud and sand attached to the surface; Then, they are classified according to the types of live bivalve products to ensure that the types of products processed in the same batch are consistent; Step 2: Pre-processing of live bivalve products: laying the cleaned and classified live bivalve products in a single layer on a tray, ensuring that the live bivalve products do not overlap or block each other; Step 3: Move to the imaging area, and move the tray to the imaging area formed by the light-emitting board and the camera unit through the conveyor belt. When the tray is in the imaging area, the conveyor belt automatically stops running to allow for light-transmitting photography; Step 4: Adjust the illumination. According to the type and light transmission characteristics of the live bivalve product, adjust the illumination of the light-emitting panel through the processing unit to ensure that the light can completely penetrate the live bivalve product. Step 5: Photograph and observe, and adjust the illumination of the light-emitting board according to the type of the live bivalve product, so that the light emitted by the light-emitting board can completely penetrate the live bivalve product; Step 6: Sorting and rejection: For live bivalve products with mud or dead shells, take them out of the tray and sort them.

6. The light transmission identification method of bivalve live products with mud and dead shells according to claim 5, characterized in that: In step 3, the conveyor belt is braked through the control of the processing unit.

7. The light transmission identification method of bivalve live products with mud and dead shells according to claim 5, characterized in that: In step 6, the sorting process can be completed manually or achieved through automated sorting equipment.

Images