Water jet path planning method and system for tilapia mossambica trimming

Abstract

The invention provides a water jet path planning method and system for tilapia mossambica trimming, and the method comprises the following steps: firstly obtaining a tilapia mossambica fillet image to be trimmed, and determining a tilapia mossambica fillet contour image; then establishing a maximum circumscribed matrix of the tilapia fillet contour image, and analyzing the tilapia fillet contour image in the maximum circumscribed matrix, so as to obtain a smooth contour edge curve of a to-be-trimmed area of the tilapia fillet; determining a trimming path of a to-be-trimmed area of the tilapia fillets under rectangular coordinates, and converting the trimming path into a trimming path of the to-be-trimmed area of the tilapia fillets under a coordinate system of a water jet trimming system; the method has the beneficial effects that through automatic processes such as image acquisition, preprocessing, edge detection and curve fitting, accurate planning of a finishing path is realized, the requirement of manual operation is reduced, and the accuracy and consistency of a finishing area are ensured, so that the finishing efficiency is greatly improved; and the problem of excessive finishing or insufficient finishing is effectively avoided.

Description

Technical Field

[0001] The invention relates to the technical field of tilapia dressing, and in particular to a water jet path planning method and system for tilapia dressing. Background Art

[0002] Tilapia fillets are highly praised in the international market for their delicate texture and unique flavor. During the trimming process of tilapia fillets, workers need to remove the dorsal fin, pelvic fin, caudal fin and other areas containing fish bones or poor flavor to ensure the taste and safety of the fillets. The dorsal fin and pelvic fin areas of the tilapia fillets obtained by filleting have more bones and hard bones remaining in them. If not handled properly, it will directly affect the eating experience of the fillets and may bring safety risks to consumers.

[0003] The existing tilapia fillet trimming relies entirely on manual labor, which has problems such as differences in trimming quality and quality control. On the one hand, the efficiency of manual trimming is relatively low, and the trimming quality is affected by the workers' experience and skill level, making it difficult to ensure consistency. On the other hand, manual trimming is relatively subjective, resulting in inconsistent quality standards, affecting the overall quality and market competitiveness of the product. Therefore, a water jet working path planning method suitable for tilapia trimming is proposed. While improving the trimming efficiency, ensuring the trimming quality and product consistency has become an urgent problem to be solved in the tilapia fillet processing industry. Summary of the invention

[0004] In view of the above-mentioned shortcomings of the prior art, the purpose of the present invention is to provide a water jet path planning method and system for tilapia trimming, which is used to solve the problems in the prior art that tilapia fillet trimming is completely dependent on manual labor and there are differences in trimming quality and quality control.

[0005] In order to achieve the above-mentioned purpose and other related purposes, the present invention provides the following technical solutions:

[0006] A water jet path planning method for tilapia trimming comprises the following steps: acquiring a tilapia fillet image to be trimmed, and obtaining a tilapia fillet edge image according to the tilapia fillet image; extracting a tilapia fillet contour image from the tilapia fillet edge image, establishing a maximum circumscribed matrix of the tilapia fillet contour image, and establishing a rectangular coordinate system according to the maximum circumscribed matrix; analyzing the tilapia fillet contour image within the maximum circumscribed matrix, and obtaining a smooth contour edge curve of a tilapia fillet region to be trimmed according to the analysis result, wherein the contour edge curve of the tilapia fillet region to be trimmed includes a dorsal fin region contour edge curve, a pelvic fin region contour edge curve, and a caudal fin region contour edge curve; determining a trimming path of the tilapia fillet region to be trimmed in rectangular coordinates according to the contour edge curve of the tilapia fillet region to be trimmed, and transforming the trimming path of the tilapia fillet region to be trimmed in rectangular coordinates into a trimming path of the tilapia fillet region to be trimmed in a water jet trimming system coordinate system.

[0007] A water jet path planning system for tilapia trimming comprises: an image acquisition and preprocessing module, used for acquiring an image of a tilapia fillet to be trimmed, and obtaining an edge image of the tilapia fillet according to the image of the tilapia fillet; a maximum circumscribed matrix establishment module, used for extracting a tilapia fillet contour image from the tilapia fillet edge image, and establishing a maximum circumscribed matrix of the tilapia fillet contour image, and establishing a rectangular coordinate system according to the maximum circumscribed matrix; a contour image analysis module, used for analyzing the tilapia fillet contour image within the maximum circumscribed matrix, and obtaining an edge image of the tilapia fillet according to the analysis result; A smooth contour edge curve of the tilapia fillet area to be trimmed is obtained, wherein the contour edge curve of the tilapia fillet area to be trimmed includes a dorsal fin area contour edge curve, a pelvic fin area contour edge curve and a caudal fin area contour edge curve; a trimming path determination module is used to determine a trimming path of the tilapia fillet area to be trimmed in rectangular coordinates according to the contour edge curve of the tilapia fillet area to be trimmed, and transform the trimming path of the tilapia fillet area to be trimmed in the rectangular coordinates into a trimming path of the tilapia fillet area to be trimmed in a water jet trimming system coordinate system.

[0008] An electronic device comprises: at least one processor; and a memory in communication with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the water jet path planning method for tilapia trimming as described above.

[0009] In one embodiment of the present invention, obtaining a tilapia fillet edge image based on a tilapia fillet image includes: preprocessing the tilapia fillet image, performing edge detection on the preprocessed tilapia fillet image, and obtaining the tilapia fillet edge image based on the edge detection result.

[0010] In one embodiment of the present invention, the tilapia fillet contour image is extracted from the tilapia fillet edge image, and the maximum circumscribed matrix of the tilapia fillet contour image is established, and a rectangular coordinate system is established according to the maximum circumscribed matrix, including: extracting the contour of the tilapia fillet in the tilapia fillet edge image, and traversing the extracted contour point set; calculating the traversed extracted contour point set, and updating the boundary of the circumscribed rectangle according to the calculation result until the maximum circumscribed matrix of the tilapia fillet contour image is obtained; taking the lower left corner of the maximum circumscribed rectangle as the origin of the coordinate system, with the X axis along the horizontal direction of the maximum circumscribed rectangle, and the Y axis along the vertical direction of the maximum circumscribed rectangle, thereby establishing a rectangular coordinate system.

[0011] In one embodiment of the present invention, the tilapia fillet contour image within the maximum circumscribed matrix is ​​analyzed, and a contour edge curve of a smooth tilapia fillet region to be trimmed is obtained according to the analysis result, including: using a trained machine learning model to identify the tilapia fillet contour image within the maximum circumscribed matrix, and obtaining contour features of the tilapia fillet region to be trimmed according to the identification result; coordinateizing the contour features of the tilapia fillet region to be trimmed, and fitting the coordinateized contour of the tilapia fillet region to be trimmed, and obtaining a smooth contour edge curve of the tilapia fillet region to be trimmed according to the fitting result.

[0012] In one embodiment of the present invention, determining a trimming path of the tilapia fillet area to be trimmed in rectangular coordinates according to the contour edge curve of the tilapia fillet area to be trimmed comprises: offsetting the contour edge curve of the tilapia fillet area to be trimmed along the axial direction, and determining the trimming path of the tilapia fillet area to be trimmed in rectangular coordinates according to the offset result, wherein the trimming path of the tilapia fillet area to be trimmed comprises a dorsal fin area trimming curve, a pelvic fin area trimming curve and a caudal fin area trimming curve.

[0013] In one embodiment of the present invention, the trimming path of the tilapia fillet area to be trimmed in rectangular coordinates is transformed into the trimming path of the tilapia fillet area to be trimmed in a water jet trimming system coordinate system, comprising: using a coordinate system transformation method to transform the trimming path of the tilapia fillet area to be trimmed in rectangular coordinates into the trimming path of the tilapia fillet area to be trimmed in the water jet trimming system coordinate system.

[0014] In one embodiment of the present invention, the coordinate system transformation method is used to transform the trimming path of the tilapia fillet to be trimmed in the rectangular coordinate into the trimming path of the tilapia fillet to be trimmed in the water jet trimming system coordinate system, including: transforming the trimming path of the tilapia fillet to be trimmed in the rectangular coordinate into the trimming path of the tilapia fillet to be trimmed in the water jet trimming system coordinate system according to the following formula: x′=e1x+e2y+t xy′=e3x+e4y+t y ; Wherein, the coordinate system of the tilapia fillet image is f(x, y), the coordinate system of the water jet trimming system is g(x′, y′), and the coordinate system transformation method is used to transform the two-dimensional coordinate system f(x, y) into the two-dimensional coordinate system is the linear transformation matrix of the two coordinate systems, is the translation vector.

[0015] In one embodiment of the present invention, after converting the trimming path of the tilapia fillet area to be trimmed in rectangular coordinates into the trimming path of the tilapia fillet area to be trimmed in the water jet trimming system coordinate system, it also includes: using the water jet trimming system to trim the tilapia fillet according to the trimming path of the tilapia fillet area to be trimmed in the water jet trimming system coordinate system.

[0016] As described above, a water jet path planning method and system for tilapia dressing of the present invention have the following beneficial effects: the water jet path planning method proposed in the present invention brings significant beneficial effects on the production efficiency and quality control of the tilapia dressing process; from the perspective of production efficiency and quality control, the method realizes accurate planning of the dressing path through automated processes such as image acquisition, preprocessing, edge detection and curve fitting, reduces the need for manual operation, ensures the accuracy and consistency of the dressing area, thereby greatly improving the dressing efficiency, and effectively avoids the problem of over-dressing or under-dressing, thereby improving the appearance quality and edible value of the tilapia product; at the same time, combined with an efficient water jet dressing system, it ensures the rapidity and continuity of the dressing process, further improving the overall production rhythm. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 Shown is a flow chart of a water jet path planning method for tilapia dressing in a first embodiment of the present invention;

[0018] Figure 2 Shown is a flow chart of a water jet path planning method for tilapia dressing in a second embodiment of the present invention;

[0019] Figure 3 Shown is a schematic diagram of a water jet path planning system for tilapia dressing in a third embodiment of the present invention;

[0020] Figure 4 It is a schematic diagram of an electronic device in a fourth embodiment of the present invention;

[0021] Figure 5 Shown is a schematic diagram of an image of a tilapia fillet to be trimmed taken by a high-definition camera in the present invention;

[0022] Figure 6Shown is a schematic diagram of establishing a maximum circumscribed matrix on a tilapia fillet contour image in the present invention. DETAILED DESCRIPTION

[0023] The following describes the embodiments of the present invention through specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0024] The first embodiment of the present invention relates to a water jet path planning method for tilapia dressing, the process is as follows: Figure 1 As shown, the details are as follows:

[0025] Step 101, obtaining an image of a tilapia fillet to be trimmed, and obtaining an edge image of the tilapia fillet according to the image of the tilapia fillet.

[0026] Specifically, before obtaining the image of the tilapia fillet to be trimmed, the following steps are performed: the tilapia fillets are uniformly placed on the conveyor belt in a fixed posture before the trimming process, with the fish meat side facing upward, the fillet side facing downward, and the fish head side facing the conveying direction, and the tilapia fillets are photographed with a high-definition camera to obtain the image of the tilapia fillet to be trimmed. For details, please refer to Figure 5 ;

[0027] In addition, it should be noted that the specific steps of obtaining the edge image of the tilapia fillet according to the tilapia fillet image are as follows: first, the tilapia fillet image is preprocessed, and then the edge detection is performed on the preprocessed tilapia fillet image, and the tilapia fillet edge image is obtained according to the edge detection result; wherein, the tilapia fillet image is preprocessed, including grayscale, denoising and other operations to improve the quality of the tilapia fillet image and provide convenience for subsequent processing; the tilapia fillet color image is converted into a grayscale image, and the grayscale formula is: Grty=R*0.299+G*0.587+B*0.114, Gray represents the grayscale value, and R, G and B represent the values ​​of the red, green and blue channels in the color image respectively; the neighborhood averaging method is used to reduce the noise of the tilapia fillet image; the holistic nested edge detection (HED) algorithm is used to perform edge detection on the preprocessed tilapia fillet image to generate the tilapia fillet edge image, and the edges in the tilapia fillet edge image are represented in the form of lines.

[0028] Step 102, extracting the tilapia fillet contour image from the tilapia fillet edge image, establishing a maximum circumscribed matrix of the tilapia fillet contour image, and establishing a rectangular coordinate system according to the maximum circumscribed matrix.

[0029] Specifically, the contour of the tilapia fillet in the tilapia fillet edge image is first extracted, and the extracted contour point set is traversed; then the traversed extracted contour point set is calculated, and the boundary of the circumscribed rectangle is updated according to the calculation result, until the maximum circumscribed matrix of the tilapia fillet contour image is obtained; then the lower left corner of the maximum circumscribed rectangle is used as the origin of the coordinate system, the X-axis is along the horizontal direction of the maximum circumscribed rectangle, and the Y-axis is along the vertical direction of the maximum circumscribed rectangle, so as to establish a rectangular coordinate system.

[0030] More specifically, the contour of the tilapia fillet is extracted from the binary image using a contour extraction algorithm (such as the findContours function in OpenCV), and the extracted contour point set is traversed. For each contour point, its position relative to the current bounding rectangle is calculated; if the contour point is outside the current bounding rectangle, the boundary of the bounding rectangle is updated so that it can contain the contour point, and the above process is repeated until all contour points are traversed to obtain the final maximum bounding rectangle, thereby establishing the maximum bounding matrix of the tilapia fillet contour image; then the lower left corner of the maximum bounding rectangle is used as the origin of the coordinate system, the X axis is along the horizontal direction of the maximum bounding rectangle, and the Y axis is along the vertical direction of the maximum bounding rectangle, and a rectangular coordinate system f(x, y) is established, ensuring that each axis of the coordinate system is a unit vector, so as to perform accurate coordinate conversion and calculation. For details, please refer to Figure 6 .

[0031] Step 103, analyzing the tilapia fillet contour image within the maximum circumscribed matrix, and obtaining a smooth contour edge curve of the tilapia fillet to-be-trimmed region according to the analysis result.

[0032] Specifically, the trained machine learning model is first used to identify the contour image of the tilapia fillet inside the maximum circumscribed matrix, and the contour features of the tilapia fillet area to be trimmed are obtained according to the recognition results; then the contour features of the tilapia fillet area to be trimmed are coordinateized, and the contour of the coordinateized tilapia fillet area to be trimmed is fitted, and a smooth contour edge curve of the tilapia fillet area to be trimmed is obtained according to the fitting result;

[0033] More specifically, the tilapia fillet contour image inside the maximum circumscribed matrix is ​​analyzed, and an edge detection algorithm (such as Canny edge detection) is used to identify the edge of the tilapia fillet area. The contour of the tilapia fillet area is the tilapia fillet area to be trimmed. A machine learning model containing the tilapia fillet image is constructed, and the model is trained to use deep learning methods such as convolutional neural networks (CNN) to identify the contour features of the tilapia fillet area to be trimmed (the contour of the dorsal fin area, the contour of the pelvic fin area, and the contour of the caudal fin area). According to the previous rectangular coordinate system, the pixel coordinates [X, Y] of each point in the tilapia fillet contour image, where X is the horizontal position and Y is the vertical position, are converted into actual coordinates in the rectangular coordinate system f (x, y), and the actual coordinates are calculated using linear mapping. The conversion formula is as follows: actual coordinate x = (pixel X / image width) * actual width; actual coordinate y = (pixel Y / image height) * actual height; actual width and height refer to the actual geometric dimensions of the tilapia fillet; thereby realizing the coordinateization of the contour features of the tilapia fillet area to be trimmed;

[0034] Then, a fitting model (including straight line, circle, ellipse, polynomial curve) is selected, and a fitting equation is established for the coordinate values ​​of the contours of the area to be trimmed (the contours of the dorsal fin area, the contours of the pelvic fin area, and the contours of the caudal fin area) of the tilapia fillet using mathematical methods such as the least squares method to form a smooth dorsal fin area contour edge curve F a (x, y), x∈(a1, a2), the edge curve of the ventral fin area contour F b (x, y), x∈(b1, b2) and the edge curve F of the tail fin area contour c (x, y), y∈(c1, c2).

[0035] Step 104, determining a trimming path of the tilapia fillet region to be trimmed in rectangular coordinates according to the contour edge curve of the tilapia fillet region to be trimmed, and transforming the trimming path of the tilapia fillet region to be trimmed in rectangular coordinates into a trimming path of the tilapia fillet region to be trimmed in a water jet trimming system coordinate system.

[0036] Specifically, the specific steps of determining the trimming path of the tilapia fillet to be trimmed region in rectangular coordinates according to the contour edge curve of the tilapia fillet to be trimmed region are: offsetting the contour edge curve of the tilapia fillet to be trimmed region along the axial direction, and determining the trimming path of the tilapia fillet to be trimmed region in rectangular coordinates according to the offset result;

[0037] More specifically, the dorsal fin area needs to be trimmed along the negative direction of the y-axis by a distance a, the size of a depends on the length characteristics of the tilapia fillet, generally a = k1*L+d, where L is the length of the tilapia fillet, k1 is the proportional coefficient, d is a constant term, and generally a is 5 to 8 mm; the dorsal fin area trimming curve after the offset is F1(x, y) = F a(x, ya), x∈(a1, a2);

[0038] The trimming of the pelvic fin area needs to be offset along the positive direction of the y-axis by a distance b. The size of b depends on the length characteristics of the tilapia fillet. Generally, b = k2*L+d, where L is the length of the tilapia fillet, k2 is the proportional coefficient, and d is a constant term. Generally, b is 3 to 8 mm. The trimming curve of the pelvic fin area after the offset is F2(x, y) = F b (x, y+b), x∈(b1, b2);

[0039] The tail fin area needs to be trimmed along the negative direction of the x-axis by a distance c. The size of c depends on the length characteristics of the tilapia fillet. Generally, c=k3*L+d, where L is the length of the tilapia fillet, k3 is the proportional coefficient, and d is a constant term. Generally, c is 10-12 mm. The tail fin area trimming curve after the offset is F3(x, y)=F c (xc, y), y∈(a1, a2); so the equation of the trimming path of the tilapia fillet is: The dorsal fin area trimming curve F1(x, y) = F a (x, ya), x∈(a1, a2); ventral fin region trimming curve F2(x, y) = F b (x, y+b), x∈(b1, b2); tail fin region trimming curve F3(x, y)=F c (xc, y), y∈(a1, a2).

[0040] In addition, the specific steps of transforming the trimming path of the tilapia fillet to be trimmed area under rectangular coordinates into the trimming path of the tilapia fillet to be trimmed area under the water jet trimming system coordinate system are: transforming the trimming path of the tilapia fillet to be trimmed area under rectangular coordinates into the trimming path of the tilapia fillet to be trimmed area under the water jet trimming system coordinate system by using a coordinate system transformation method;

[0041] Furthermore, the water jet trimming system mainly includes a three-axis motion mechanism and a water jet. During the trimming process, the water jet path is the working path of the water jet. The coordinate system of the water jet trimming system is g(x′, y′), and the coordinate system of the original tilapia fillet image is f(x, y). The coordinate system transformation method is used to transform the two-dimensional coordinate system f(x, y) into the two-dimensional coordinate system g(x′, y′): x′=e1x+e2y+t x ;y′=e3x+e4y+t y ,in, is the linear transformation matrix of the two coordinate systems (for rotation and scaling transformations, they are cosθ, -sinθ, sinθ, cosθ, or a combination of scaling factors), is the translation vector;

[0042] The original tilapia fillet trimming curve function in the f(x, y) coordinate system is converted into a function in the g(x′, y′) coordinate system. The function F(x, y) in the tilapia fillet coordinate system f(x, y) corresponds to the function G(x′, y′) in the g(x′, y′) coordinate system. The equation of the corresponding trimming path in the water jet trimming system coordinate system is: dorsal fin area trimming curve G1(x′, y)=G a (x′, x′-a), x′∈(a′1, a′2); the ventral fin region trimming curve G2(x′, y′)=Gb(x′, y′+b), x′∈(b′1, b′2); the tail region trimming curve G3(x′, y′)=G c (x′-c′, y′), y′∈(a′1, a′2); a′, b′ and c are all offsets corresponding to the coordinate system g(x′, y′).

[0043] In practical applications, the specific steps of the water jet path planning method are as follows: Step 1, obtain the trajectory curve of tilapia fillet:

[0044] (1) Image acquisition: A high-definition camera with a resolution of 4000x3000 pixels was used to capture an image of a tilapia fillet placed in a fixed posture, with the fish meat side facing upward, the fillet side facing downward, and the fish head side facing the conveying direction;

[0045] (2) Preprocessing: The captured color image is converted into a grayscale image. The grayscale value is calculated using the formula: Gray = R*0.299+G*0.587+B*0.114. The grayscale image is denoised using the 3×3 neighborhood average method.

[0046] (3) Edge detection and extraction: The HED algorithm is used to perform edge detection on the preprocessed image to generate the edge image of the tilapia fillet. Then, the findContours function of OpenCV is used to extract the contour of the tilapia fillet from the binary edge image.

[0047] (4) Coordinate system establishment and coordinate conversion: Based on the extracted contour, the maximum circumscribed rectangle of the tilapia fillet is determined, and the coordinates of its lower left corner are (1000, 1500). Therefore, a rectangular coordinate system f(x, y) is established, with the origin at (1000, 1500), the X axis along the horizontal direction, and the Y axis along the vertical direction. The pixel coordinates of each point in the contour image are converted to the actual coordinates in the coordinate system f(x, y). The actual width of the tilapia fillet is 300 mm and the height is 200 mm. The conversion formula is: x = (pixel X-1000) / 4*300 / 3000y = (pixel Y-1500) / 3*200 / 2000; then, the edge curves F of the dorsal fin, pelvic fin, and caudal fin regions are obtained through curve fitting. a (x, y), F b (x, y), Fc (x, y).

[0048] Step 2: Establish the trimming area curve of tilapia fillet: The length of tilapia fillet is 250mm. According to the empirical formula, the trimming offset of dorsal fin area is calculated as a=7mm, the trimming offset of pelvic fin area is calculated as b=5mm, and the trimming offset of caudal fin area is calculated as c=11mm. Therefore, the trimming curves after offset are: F1(x, y)=F a (x, y-0.007*300); F2 (x, y) = F b (x, y+0.005*200); F3(x, y)=F c (x-0.011*300,y).

[0049] Step 3: Convert to water jet path: There is a 45-degree rotation between the coordinate system g(x′, y′) of the water jet trimming system and f(x, y), and there is a translation vector (50, 30), so the transformation matrix is: The translation vector is: t x =50,t y =30; using the coordinate system transformation formula, the trimming curve in the f(x, y) coordinate system is converted into a function in the g(x′, y′) coordinate system. Taking the dorsal fin area as an example, the trimming path equation after conversion is: G1(x′, y′)=G a (0.707x′-0.707y′+50-0.007*300*0.707+0.007*200*0.707,0.707x′+0.707y′+30-0.007*300*(-0.707)+0.007*200*0.707); G here a (x′, y′) is the converted function form, not a simple linear transformation, because the original function F a (x, y) may be nonlinear; in practical applications, it is necessary to a (x, y) is interpolated or fitted to obtain the corresponding function G in the g(x′, y′) coordinate system a (x′, y); similarly, the trimming path equations G2(x′, y) and G3(x′, y′) of the ventral fin and caudal fin regions can be obtained; the numerical values ​​and formulas in the above examples can be accurately calculated and calibrated according to the specific tilapia fillet size, image resolution, water jet system parameters, etc.

[0050] The second embodiment of the present invention relates to a water jet path planning method for tilapia trimming. The second embodiment is a detailed discussion of the first embodiment as a whole. The main detailed discussion is: in the second embodiment of the present invention, an embodiment is clarified, and this embodiment discusses the specific process of trimming tilapia fillets using a water jet trimming system according to the trimming path of the tilapia fillet to be trimmed area in the water jet trimming system coordinate system.

[0051] For this implementation, please refer to Figure 2 , including the following steps, are described as follows:

[0052] Steps 201 to 204 are similar to steps 101 to 104 in the first embodiment, and are not described in detail herein.

[0053] Step 205 , using a water jet trimming system to trim the tilapia fillet according to a trimming path of the tilapia fillet trimming area in a coordinate system of the water jet trimming system.

[0054] In practical applications, the working parameters and process of the tilapia fillet water jet finishing system are as follows: Working parameters of the water jet finishing system: working pressure 300-350 bar, high-pressure nozzle aperture 0.15-0.20 mm, the movement speed of the water jet in the water jet is controlled at 10-20 cm / s, and the vertical distance between the water jet nozzle and the surface of the tilapia fillet is controlled at 10-15 mm;

[0055] Workflow: The water jet system is provided with a three-axis motion mechanism, a feeding and conveying system, a water knife, etc. The feeding and conveying system is provided with a mesh conveyor belt (the movement speed of the conveyor belt is adjustable), which is located below the three-axis motion mechanism. The three-axis motion mechanism includes X, Y, and Z axes, and a water knife is installed on the Z axis. The three-axis motion mechanism controls the spatial (X, Y, Z) coordinates of the water knife to realize arbitrary movement of the water knife; the feeding and conveying system is provided with a mesh conveyor belt, and the feeding side and the discharging side of the feeding and conveying system are respectively provided with laser grating sensors for sensing the tilapia fillet entering or leaving the trimming area of ​​the water knife; the three-axis motion mechanism is provided with a zero position or an initial working position, the zero position is a fixed coordinate (pre-set), and the initial working position is determined by the trimming path equation of each tilapia fillet to be trimmed;

[0056] After the tilapia fillet is placed in a fixed posture at the front end to complete the acquisition of the trajectory curve, the establishment of the trimming area curve and the conversion into the equation of the water jet path, the equation parameters of the water jet path are transmitted to the trimming intelligent control system, and the trimming intelligent control system executes the control of the water jet system. When the laser grating sensor recognizes that the tilapia fillet has entered the water jet trimming area, the feeding and conveying system uses a timing control method to transport the tilapia fillet to the fixed trimming area, and keeps the feeding and conveying system in a static state. The water jet starts from the initial working position, and the water jet completes the trimming of the tilapia fillet according to the trimming path equation of the tilapia fillet. After the execution is completed, the feeding and conveying system is started again to send the tilapia fillet out of the trimming area (the rear-end laser grating sensor determines whether it has left the trimming area), and after completion, wait for the next tilapia fillet to enter; in the non-trimming working state, the water jet is in a stopped state and does not discharge water.

[0057] The third embodiment of the present invention relates to a water jet path planning system for tilapia dressing, see Figure 3 ,include:

[0058] An image acquisition and preprocessing module is used to acquire an image of a tilapia fillet to be trimmed, and obtain an edge image of the tilapia fillet according to the image of the tilapia fillet;

[0059] A maximum circumscribed matrix establishment module is used to extract a tilapia fillet contour image from a tilapia fillet edge image, establish a maximum circumscribed matrix of the tilapia fillet contour image, and establish a rectangular coordinate system according to the maximum circumscribed matrix;

[0060] A contour image analysis module is used to analyze the contour image of the tilapia fillet within the maximum circumscribed matrix, and obtain a contour edge curve of the smooth tilapia fillet area to be trimmed according to the analysis result, wherein the contour edge curve of the tilapia fillet area to be trimmed includes a dorsal fin area contour edge curve, a pelvic fin area contour edge curve, and a caudal fin area contour edge curve;

[0061] The trimming path determination module is used to determine the trimming path of the tilapia fillet to be trimmed area in rectangular coordinates according to the contour edge curve of the tilapia fillet to be trimmed area, and transform the trimming path of the tilapia fillet to be trimmed area in rectangular coordinates into the trimming path of the tilapia fillet to be trimmed area in the coordinate system of the water jet trimming system.

[0062] It is not difficult to find that this embodiment is a system embodiment corresponding to the first embodiment, and this embodiment can be implemented in conjunction with the first embodiment. The relevant technical details mentioned in the first embodiment are still valid in this embodiment, and in order to reduce repetition, they are not repeated here. Accordingly, the relevant technical details mentioned in this embodiment can also be applied in the first embodiment.

[0063] It is worth mentioning that all modules involved in this embodiment are logic modules. In practical applications, a logic unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. In addition, in order to highlight the innovative part of the present invention, this embodiment does not introduce units that are not closely related to solving the technical problem proposed by the present invention, but this does not mean that there are no other units in this embodiment.

[0064] A fourth embodiment of the present invention relates to an electronic device, see Figure 4 ,include:

[0065] At least one processor; and a memory in communication with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the water jet path planning method for tilapia trimming as described above.

[0066] Among them, the memory and the processor are connected in a bus manner, and the bus may include any number of interconnected buses and bridges, and the bus connects various circuits of one or more processors and memories together. The bus can also connect various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be one element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices on a transmission medium. The data processed by the processor is transmitted on a wireless medium via an antenna, and further, the antenna also receives data and transmits the data to the processor.

[0067] The processor is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. Memory can be used to store data used by the processor when performing operations.

[0068] A fifth embodiment of the present invention relates to a computer-readable storage medium storing a computer program, which implements the above method embodiment when executed by a processor.

[0069] That is, those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor to execute all or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0070] In summary, the water jet path planning method proposed in the present invention brings significant beneficial effects on the production efficiency and quality control of the tilapia dressing process; from the perspective of production efficiency and quality control, the method realizes accurate planning of the dressing path through automated processes such as image acquisition, preprocessing, edge detection and curve fitting, reduces the need for manual operation, ensures the accuracy and consistency of the dressing area, thereby greatly improving the dressing efficiency, and effectively avoids the problem of over-dressing or under-dressing, thereby improving the appearance quality and edible value of tilapia products; at the same time, combined with an efficient water jet dressing system, the rapidity and continuity of the dressing process are ensured, further improving the overall production rhythm; in addition, the application of intelligent control systems and laser grating sensors also enhances the stability and reliability of the dressing process, ensuring the stable output of product quality.

[0071] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. All equivalent modifications or changes made by those skilled in the art without departing from the spirit and technical ideas disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. A water jet path planning method for tilapia dressing, characterized in that: The following steps are involved: Acquire a tilapia fillet image to be trimmed, and obtain a tilapia fillet edge image according to the tilapia fillet image; Extracting a tilapia fillet contour image from the tilapia fillet edge image, establishing a maximum circumscribed matrix of the tilapia fillet contour image, and establishing a rectangular coordinate system according to the maximum circumscribed matrix; Analyze the tilapia fillet contour image within the maximum circumscribed matrix, and obtain a contour edge curve of a smooth tilapia fillet region to be trimmed according to the analysis result, wherein the contour edge curve of the tilapia fillet region to be trimmed includes a dorsal fin region contour edge curve, a pelvic fin region contour edge curve, and a caudal fin region contour edge curve; The trimming path of the tilapia fillet to be trimmed in rectangular coordinates is determined according to the contour edge curve of the tilapia fillet to be trimmed in the rectangular coordinates, and the trimming path of the tilapia fillet to be trimmed in the rectangular coordinates is transformed into the trimming path of the tilapia fillet to be trimmed in the coordinate system of the water jet trimming system.

2. A water jet path planning method for tilapia dressing according to claim 1, characterized in that: The step of obtaining the tilapia fillet edge image according to the tilapia fillet image comprises: The tilapia fillet image is preprocessed, and edge detection is performed on the preprocessed tilapia fillet image, and a tilapia fillet edge image is obtained according to the edge detection result.

3. A water jet path planning method for tilapia dressing according to claim 1, characterized in that: The method of extracting a tilapia fillet contour image from a tilapia fillet edge image, establishing a maximum circumscribed matrix of the tilapia fillet contour image, and establishing a rectangular coordinate system according to the maximum circumscribed matrix comprises: Extracting the contour of the tilapia fillet in the tilapia fillet edge image, and traversing the extracted contour point set; Calculating the contour point set extracted by traversal, and updating the boundary of the circumscribed rectangle according to the calculation result, until the maximum circumscribed matrix of the tilapia fillet contour image is obtained; The lower left corner of the maximum circumscribed rectangle is used as the origin of the coordinate system, the X axis is along the horizontal direction of the maximum circumscribed rectangle, and the Y axis is along the vertical direction of the maximum circumscribed rectangle, so as to establish a rectangular coordinate system.

4. A water jet path planning method for tilapia dressing according to claim 1, characterized in that: The tilapia fillet contour image within the maximum circumscribed matrix is ​​analyzed, and a contour edge curve of a smooth tilapia fillet area to be trimmed is obtained according to the analysis result, including: Using the trained machine learning model to identify the tilapia fillet contour image within the maximum circumscribed matrix, and obtaining the contour features of the tilapia fillet area to be trimmed according to the recognition result; The contour features of the tilapia fillet region to be trimmed are coordinateized, and the contour of the coordinateized tilapia fillet region to be trimmed is fitted, and a smooth contour edge curve of the tilapia fillet region to be trimmed is obtained according to the fitting result.

5. A water jet path planning method for tilapia dressing according to claim 1, characterized in that: The method of determining a trimming path of the tilapia fillet to be trimmed region in rectangular coordinates according to the contour edge curve of the tilapia fillet to be trimmed region comprises: The contour edge curve of the area to be trimmed of the tilapia fillet is offset along the axial direction, and a trimming path of the area to be trimmed of the tilapia fillet in rectangular coordinates is determined according to the offset result, wherein the trimming path of the area to be trimmed of the tilapia fillet includes a trimming curve of a dorsal fin area, a trimming curve of a pelvic fin area, and a trimming curve of a caudal fin area.

6. A water jet path planning method for tilapia dressing according to claim 1, characterized in that: The method of transforming the trimming path of the tilapia fillet to-be-trimmed region in rectangular coordinates into the trimming path of the tilapia fillet to-be-trimmed region in the coordinate system of the water jet trimming system comprises: The coordinate system transformation method is used to transform the trimming path of the tilapia fillet to-be-trimmed area in the rectangular coordinates into the trimming path of the tilapia fillet to-be-trimmed area in the water jet trimming system coordinate system.

7. A water jet path planning method for tilapia dressing according to claim 6, characterized in that: The method of using a coordinate system transformation method to transform the trimming path of the tilapia fillet to be trimmed region under the rectangular coordinates into the trimming path of the tilapia fillet to be trimmed region under the water jet trimming system coordinate system comprises: The trimming path of the tilapia fillet to be trimmed area under the rectangular coordinates is transformed into the trimming path of the tilapia fillet to be trimmed area under the water jet trimming system coordinate system according to the following formula: x′=e1x+e2y+t x ; y′=e3x+e4y+t y ; The coordinate system of the tilapia fillet image is f(x, y), the coordinate system of the water jet trimming system is g(x′, y′), and the two-dimensional coordinate system f(x, y) is transformed into the two-dimensional coordinate system g(x′, y′) by using the coordinate system transformation method. is the linear transformation matrix of the two coordinate systems, is the translation vector.

8. A water jet path planning method for tilapia dressing according to claim 1, characterized in that: After the trimming path of the tilapia fillet to be trimmed in rectangular coordinates is transformed into the trimming path of the tilapia fillet to be trimmed in the coordinate system of the water jet trimming system, the method further includes: The water jet trimming system is used to trim the tilapia fillet according to a trimming path of the tilapia fillet to-be-trimmed region in the coordinate system of the water jet trimming system.

9. A water jet path planning system for tilapia dressing, characterized in that: include: An image acquisition and preprocessing module, used for acquiring an image of a tilapia fillet to be trimmed, and obtaining an edge image of the tilapia fillet according to the image of the tilapia fillet; A maximum circumscribed matrix establishing module is used for extracting a tilapia fillet contour image from the tilapia fillet edge image, establishing a maximum circumscribed matrix of the tilapia fillet contour image, and establishing a rectangular coordinate system according to the maximum circumscribed matrix; A contour image analysis module is used to analyze the contour image of the tilapia fillet within the maximum circumscribed matrix, and obtain a contour edge curve of a smooth tilapia fillet area to be trimmed according to the analysis result, wherein the contour edge curve of the tilapia fillet area to be trimmed includes a dorsal fin area contour edge curve, a pelvic fin area contour edge curve, and a caudal fin area contour edge curve; The trimming path determination module is used to determine the trimming path of the tilapia fillet to be trimmed area in rectangular coordinates according to the contour edge curve of the tilapia fillet to be trimmed area, and transform the trimming path of the tilapia fillet to be trimmed area in the rectangular coordinates into the trimming path of the tilapia fillet to be trimmed area in the coordinate system of the water jet trimming system.

10. An electronic device, characterized in that: include: at least one processor; as well as, A memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor so that the at least one processor can execute the water jet path planning method for tilapia trimming as described in any one of claims 1 to 8.

Images