X-ray-based nutlet damage assessment method and device under walnut shell breaking

Abstract

The invention belongs to the technical field of agricultural product processing and nondestructive testing, and provides an X-ray-based nutlet damage assessment method and device under walnut shell breaking, and the method comprises the steps: collecting an X-ray image of a walnut sample, and carrying out the preprocessing; inputting the image into a deep learning instance segmentation model to obtain segmentation masks of all walnut kernel structure blocks in the image; determining the structural feature parameters of the walnut kernels according to the segmentation masks of all the walnut kernel structural blocks in the image; constructing a linearly weighted structural damage model according to the structural feature parameters; determining a first weighting coefficient and a second weighting coefficient according to the structural characteristic parameters; and substituting the first weighting coefficient and the second weighting coefficient into a linear weighted structure damage model to determine the final damage degree of the walnut sample. According to the method, non-contact internal imaging is carried out on the kernel structure after walnut shell breaking through the X-ray imaging technology, and the problem of secondary damage caused by mechanical force application or destructive treatment in a traditional method is solved.

Description

Technical Field

[0001] This invention relates to the field of agricultural product processing and non-destructive testing technology, and in particular to a method and device for assessing kernel damage in walnuts under shell cracking based on X-rays. Background Technology

[0002] Walnuts, as a nutritious and widely valued nut, not only occupy an important position in the food industry but are also highly sought after for their unique health benefits. The structural integrity of the kernel determines not only the appearance and commercial value of the walnut but also directly affects its subsequent processing and utilization. In actual production, walnuts need to be cracked mechanically to obtain the kernel, but traditional cracking methods often result in structural damage such as cracks and fragmentation of the kernel due to improper control of external force, severely reducing product quality and economic benefits.

[0003] Current methods for detecting kernel damage mainly include classification statistics based on kernel size and quantity, coupled finite element and discrete element method simulation, and quantitative analysis of surface abrasions in kernels using image processing. Although these methods have some assessment capabilities, they generally suffer from problems such as the need to apply contact stress, the potential to cause additional structural damage, the use of single evaluation indicators that are difficult to fully reflect internal damage, and the high degree of subjectivity and unstable results. Summary of the Invention

[0004] The purpose of this invention is to at least address one of the aforementioned technical deficiencies.

[0005] Therefore, one objective of this invention is to provide a method and apparatus for assessing kernel damage in walnuts during shell cracking based on X-rays, in order to solve the problems mentioned in the background art and overcome the shortcomings of the prior art.

[0006] To achieve the above objectives, in one aspect, the present invention provides an X-ray-based method for assessing kernel damage during walnut shell cracking, comprising:

[0007] X-ray images of walnut samples were acquired and preprocessed.

[0008] The preprocessed image is input into a deep learning instance segmentation model to obtain a segmentation mask for all walnut kernel structural blocks in the image;

[0009] The structural feature parameters of the walnut kernels are determined based on the segmentation mask of all walnut kernel structural blocks in the image. The structural feature parameters include the principal structural integrity coefficient and the relative fragmentation degree.

[0010] A linearly weighted structural damage model is constructed based on the main structural integrity coefficient and the relative fragmentation degree.

[0011] The first weighting coefficient and the second weighting coefficient are determined based on the main structural integrity coefficient and the relative fragmentation.

[0012] The first and second weighting coefficients are substituted into the linearly weighted structural damage model to determine the final damage degree of the walnut sample.

[0013] Preferably, the X-ray images of the walnut sample include X-ray images of the walnut sample from two opposing viewpoints.

[0014] Preferably, the main structure integrity coefficient is as follows:

[0015]

[0016] Among them, R main Main structural integrity coefficient, A max A represents the area of ​​the largest structural region in the X-ray image of the walnut sample. total This represents the total area of ​​all regions in the X-ray image of the walnut sample.

[0017] Preferably, the relative fragmentation degree is as follows:

[0018]

[0019] Where S is the relative fragmentation degree, N is the number of structural blocks obtained by segmenting the X-ray image of the walnut sample, and N0 is the standard structural block number of the whole walnut kernel, i.e., N0 = 1.

[0020] Preferably, the linearly weighted structural damage model is as follows:

[0021] D=α(1-R main )+βS

[0022] Where D represents the X-ray image damage degree of the walnut sample, α is the first weighting coefficient, β is the second weighting coefficient, and R... main S is the structural integrity coefficient, and S is the relative fragmentation degree.

[0023] Preferably, determining the first weighting coefficient and the second weighting coefficient based on the main structural integrity coefficient and the relative fragmentation includes:

[0024] Principal component analysis was used to analyze the inverse vector 1-R of the principal structural integrity coefficients. main The relative fragmentation S is standardized to extract the feature vector corresponding to the first principal component, and normalized according to its absolute value to determine the first weighting coefficient and the second weighting coefficient.

[0025] Preferably, determining the final damage degree of the walnut sample includes: calculating the damage degree of the X-ray images of the walnut sample from two relative perspectives, and taking the arithmetic mean of the damage degree of the X-ray images from the two relative perspectives as the final damage degree of the walnut sample.

[0026] On the other hand, the present invention provides an X-ray-based walnut kernel damage assessment device during shell cracking, including a frame and a control system. The upper end of the frame is provided with a squeezing and monitoring mechanism, the side of the frame is provided with an X-ray imaging mechanism, and the lower end of the frame is provided with a sample fixing and rotating mechanism. The control system is electrically connected to the squeezing and monitoring mechanism, the X-ray imaging mechanism, and the sample fixing and rotating mechanism.

[0027] Preferably, the extrusion and monitoring mechanism includes a stepping electric cylinder and a displacement sensor. The stepping electric cylinder is connected to the displacement sensor, one end of the stepping electric cylinder is connected to the upper end of the frame, and the output end of the stepping electric cylinder is connected to an extrusion plate through a force sensor.

[0028] Preferably, the sample fixing and rotating mechanism includes a stepper motor and an external toothed rotary support turntable. The output end of the stepper motor is connected to a gear, which meshes with the external toothed rotary support turntable. The external toothed rotary support turntable is provided with a flexible limiting structure.

[0029] Compared with the prior art, the advantages and beneficial effects of the present invention are as follows:

[0030] This invention utilizes X-ray imaging technology to obtain high-precision three-dimensional internal structural images of walnut kernels, providing a non-destructive and quantitative structural parameter basis for a dual-index model. Based on this imaging data, the principal structural integrity coefficient and relative fragmentation degree in the dual-index model can be accurately calculated. Principal component analysis is then used to objectively weight the features of the imaging data, forming a multi-dimensional damage assessment system. X-ray imaging not only avoids secondary mechanical damage but also serves as the data source for the scientific weighting and multi-dimensional assessment of the dual-index model. Together, they form an integrated solution for non-destructive testing and quantitative assessment, achieving visualized analysis and objective quantitative optimization of kernel damage.

[0031] The kernel damage assessment method and device proposed in this invention have a complete operation process, covering key aspects such as loading deformation control, image acquisition and processing, structure recognition, feature extraction, and damage degree output. The various structures of the device achieve synchronous scheduling and data integration through a control system, providing reliable support for subsequent data analysis. The overall device has good application potential. Attached Figure Description

[0032] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which:

[0033] Figure 1 This is a flowchart of the kernel damage assessment method of the present invention;

[0034] Figure 2This is a schematic diagram of the kernel damage assessment method according to an embodiment of the present invention;

[0035] Figure 3 This is a schematic diagram of the overall structure of the kernel damage assessment device according to an embodiment of the present invention;

[0036] Figure 4 This is a schematic diagram of the extrusion and monitoring mechanism according to an embodiment of the present invention;

[0037] Figure 5 This is a schematic diagram of the sample fixing and rotating mechanism according to an embodiment of the present invention;

[0038] Figure 6 This is a schematic diagram of the electronic device structure according to an embodiment of the present invention.

[0039] The components include: 1. Frame; 2. Extrusion and monitoring mechanism; 201. Force sensor; 202. Stepper cylinder; 203. Displacement sensor; 204. Extrusion plate; 3. Sample fixing and rotation mechanism; 301. Stepper motor; 302. Gear; 303. Flexible limiting mechanism; 304. External gear rotary support turntable; 4. X-ray imaging mechanism; 401. X-ray emitter; 402. Flat panel detector; 5. Control system. Detailed Implementation

[0040] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0041] This invention proposes an X-ray-based method and device for assessing walnut kernel damage during shelling, belonging to the field of agricultural product processing and non-destructive testing technology. It is suitable for non-contact, quantitative analysis of walnut kernel damage during the shelling process. The method involves constructing an experimental platform to acquire high-resolution X-ray images of walnut samples under controlled shelling deformation conditions. A deep learning instance segmentation model is then used to automatically identify structural regions of the kernel. Based on the image segmentation results, morphological features such as the area and number of structural blocks are extracted. Two indicators, the principal structural integrity coefficient and the relative fragmentation degree, are constructed. Principal component analysis is introduced to determine the weights of each indicator, forming a weighted comprehensive structural damage model that enables an objective quantitative assessment of the degree of kernel damage.

[0042] like Figure 1 As shown, this embodiment provides a method for assessing kernel damage in walnuts during shell cracking based on X-rays, including:

[0043] Step S1: Acquire X-ray images of walnut samples and perform preprocessing;

[0044] Step S2: Input the preprocessed image into the deep learning instance segmentation model to obtain the segmentation mask of all walnut kernel structural blocks in the image;

[0045] Step S3: Determine the structural feature parameters of the walnut kernels based on the segmentation mask of all walnut kernel structural blocks in the image. The structural feature parameters include the principal structural integrity coefficient and the relative fragmentation degree.

[0046] Step S4: Construct a linearly weighted structural damage model based on the main structural integrity coefficient and the relative fragmentation degree;

[0047] Step S5: Determine the first weighting coefficient and the second weighting coefficient based on the main structure integrity coefficient and the relative fragmentation degree;

[0048] Step S6: Substitute the first weighting coefficient and the second weighting coefficient into the linearly weighted structural damage model to determine the final damage degree of the walnut sample.

[0049] In one implementation, step S1, acquiring an X-ray image of a walnut sample includes: fixing the walnut in a sample fixing and rotating mechanism with a flexible limiting structure, applying a preset amount of compression deformation to the walnut sample using a squeezing and monitoring mechanism, and acquiring an X-ray image of the walnut sample through an X-ray imaging mechanism.

[0050] This invention uses X-ray imaging technology to perform non-contact internal imaging of the kernel structure of a walnut after it has been cracked open, avoiding the secondary damage caused by applying mechanical force or destructive treatment in traditional methods.

[0051] In one embodiment, the walnut is fixed in the compression and monitoring mechanism of the damage assessment device with a flexible limiting structure. The compression and monitoring mechanism applies a preset amount of compression deformation to the walnut, and during the loading process, force sensors and displacement sensors simultaneously collect force response and displacement data.

[0052] In one embodiment, an X-ray imaging device is used to acquire X-ray images of a walnut sample from two relative perspectives: forward view and backward view.

[0053] In another embodiment, an X-ray imaging device is used to acquire X-ray images of the walnut sample from two relative perspectives: left and right.

[0054] As one implementation, in step S1, preprocessing the X-ray image of the walnut sample includes: adjusting the window level and window width of the X-ray image, cropping the image size to retain the complete walnut area and removing redundant background, and converting the image to PNG format.

[0055] In one embodiment, such as Figure 2As shown, the original image format was DICOM. The window level and width of the acquired image were adjusted to 120 and 200 to enhance the contrast of the kernel structure. Subsequently, the image size was cropped to retain the complete walnut area and remove redundant background. The image format was then uniformly converted to PNG to meet the input requirements of the subsequent image segmentation model.

[0056] In one embodiment, step S2, inputting the preprocessed image into a deep learning instance segmentation model to obtain segmentation masks for all walnut kernel structural blocks in the image, includes: inputting the preprocessed X-ray image into the deep learning instance segmentation model, wherein the model is a YOLOv8-seg instance segmentation model. Before use, the model is trained on a labeled dataset of walnut kernel X-ray images, which covers various structural damage conditions such as intact, slightly fragmented, moderately damaged, and highly fragmented kernels, to enhance the model's ability to identify kernel boundaries of different damage types. The model outputs segmentation masks for all kernel structural blocks in each walnut image.

[0057] This invention uses a deep learning instance segmentation model to automatically identify and extract the structure of nut images. The model training data covers a variety of damage patterns and has good generalization ability and boundary recognition accuracy. By replacing human experience judgment with deep learning-assisted image analysis, human error is significantly reduced.

[0058] Under external mechanical loads, the continuity and integrity of the internal structure of a walnut are disrupted, manifesting as a significant increase in the number of structural blocks and a marked reduction in the area of ​​the main region, among other typical morphological changes. In one embodiment, step S3 involves determining the structural feature parameters of the walnut kernel based on a segmentation mask of all walnut kernel structural blocks in the image. In this step, the structural feature parameters of the kernel are extracted based on the segmentation mask image, including:

[0059] Main structural integrity coefficient:

[0060]

[0061] Among them, R main Main structural integrity coefficient, A max A represents the area of ​​the largest structural region in the X-ray image of the walnut sample. total The sum of the areas of all regions in the X-ray image of the walnut sample;

[0062] Relative fragmentation:

[0063]

[0064] Where S is the relative fragmentation degree, N is the number of structural blocks obtained by segmenting the X-ray image of the walnut sample, and N0 is the standard structural block number of the whole walnut kernel, i.e., N0 = 1.

[0065] In one embodiment, step S4 involves constructing a linearly weighted structural damage model based on the main structural integrity coefficient and the relative fragmentation degree, using the following calculation formula:

[0066] D=α(1-R main )+βS

[0067] Where D represents the X-ray image damage degree of the walnut sample, α is the first weighting coefficient, β is the second weighting coefficient, and R... main S is the structural integrity coefficient, and S is the relative fragmentation degree.

[0068] As one implementation method, in step S5, determining the first weighting coefficient and the second weighting coefficient based on the main structural integrity coefficient and the relative fragmentation includes:

[0069] Principal component analysis was used to analyze the inverse vector 1-R of the principal structural integrity coefficients. main The relative fragmentation S is standardized to extract the feature vector corresponding to the first principal component, and normalized according to its absolute value to determine the first weighting coefficient and the second weighting coefficient.

[0070] In one embodiment, to avoid redundancy amplification and main variable weakening that may be caused by empirical weighting or equal weighting, principal component analysis is used to analyze the inverse vector 1-R of the principal structural integrity coefficients. main The relative fragmentation S is standardized to extract the feature vector corresponding to the first principal component. This feature vector is then normalized based on its absolute value to determine the weighting coefficients for each index, namely the first weighting coefficient and the second weighting coefficient. Specifically:

[0071] Let x1 = 1 - R main Construct the sample feature matrix X using x2 = S as a two-dimensional feature variable:

[0072]

[0073] Where, x n1 x n2 These represent the nth sample image in the first feature (i.e., x1 = 1 - R). main The values ​​on the second feature (i.e., x2 = S).

[0074] Standardize the features of each column:

[0075]

[0076] Where, μ j σ j are the sample mean and standard deviation of the j-th feature, respectively.

[0077] Standard post-sample matrix X':

[0078]

[0079] Calculate the covariance matrix:

[0080]

[0081] Eigenvalue decomposition of the covariance matrix T yields a set of orthogonal unit eigenvectors v1 and v2 and their corresponding eigenvalues ​​λ1 and λ2, satisfying:

[0082] TV i =λ i v i , i = 1, 2; λ1 ≥ λ2;

[0083] Based on the eigenvalue decomposition results, the eigenvector v1 corresponding to the largest eigenvalue λ1 of the covariance matrix T represents the direction of maximum variation of the standardized structural variable in the sample. The eigenvector corresponding to the largest eigenvalue λ1 is obtained. in

[0084] Calculate the weighting coefficients α and β:

[0085]

[0086] This invention constructs a dual-index structural damage model, which jointly assesses the degree of kernel damage by combining the principal structural integrity coefficient and the relative fragmentation degree, and introduces principal component analysis to determine the weights, thus overcoming the problems of single evaluation dimensions and subjective weighting in previous evaluation methods.

[0087] This invention utilizes X-ray imaging technology to obtain high-precision three-dimensional internal structural images of walnut kernels, providing a non-destructive and quantitative structural parameter basis for a dual-index model. Based on this imaging data, the principal structural integrity coefficient and relative fragmentation degree in the dual-index model can be accurately calculated. Principal component analysis is then used to objectively weight the features of the imaging data, forming a multi-dimensional damage assessment system. X-ray imaging not only avoids secondary mechanical damage but also serves as the data source for the scientific weighting and multi-dimensional assessment of the dual-index model. Together, they form an integrated solution for non-destructive testing and quantitative assessment, achieving visualized analysis and objective quantitative optimization of kernel damage.

[0088] As one implementation method, in step S6, determining the final damage degree of the walnut sample includes: calculating the damage degree of the X-ray images of the walnut sample from two relative perspectives, and taking the arithmetic mean of the damage degree of the X-ray images from the two relative perspectives as the final damage degree of the walnut sample.

[0089] In one embodiment, the damage degree D of the walnut sample is calculated from two different perspective images before and after the image.front and D back The arithmetic mean of these values ​​is taken as the final damage level of the walnut sample.

[0090]

[0091] like Figure 3 As shown, this embodiment provides an X-ray-based walnut kernel damage assessment device for walnut shelling, suitable for performing the above-mentioned X-ray-based walnut kernel damage assessment method. It includes: a frame 1 and a control system 5. The upper end of the frame 1 is provided with a compression and monitoring mechanism 2, the side of the frame 1 is provided with an X-ray imaging mechanism 305, and the lower end of the frame 1 is provided with a sample fixing and rotation mechanism 3. The control system 5 is electrically connected to the compression and monitoring mechanism 2, the X-ray imaging mechanism 305, and the sample fixing and rotation mechanism 3.

[0092] Furthermore, such as Figure 4 As shown, the extrusion and monitoring mechanism 2 includes a stepping electric cylinder 202 and a displacement sensor 203. The stepping electric cylinder 202 is connected to the displacement sensor 203. One end of the stepping electric cylinder 202 is connected to the upper end of the frame 1. The output end of the stepping electric cylinder 202 is connected to the extrusion plate 204 through a force sensor 201.

[0093] The frame 1 is used to support the entire evaluation device. The extrusion and sensing monitoring device is fixed at the middle of the upper end of the frame 1, including a force sensor 201, a stepper cylinder 202 and a displacement sensor 203. The stepper cylinder 202 is used to apply axial extrusion to the walnut sample at a set speed. The force sensor 201 and the displacement sensor 203 are used to monitor the extrusion force on the sample and the deformation displacement generated during the loading process, respectively.

[0094] Furthermore, such as Figure 5 As shown, the sample fixing and rotating mechanism 3 includes a stepper motor 301 and an external tooth rotary support turntable 304. The output end of the stepper motor 301 is connected to a gear 302, which meshes with the external tooth rotary support turntable 304. The external tooth rotary support turntable 304 is provided with a flexible limiting structure.

[0095] The sample fixing and rotation device is located at the bottom center of the frame 1, including a stepper motor 301, a gear 302, a flexible limiting mechanism 303, and an external gear rotary support turntable 304. The stepper motor 301 is connected to the external gear rotary support turntable 304 through the gear 302 to achieve precise rotation control of the sample. The flexible limiting mechanism 303 is located above the turntable and has a through-hole groove that matches the shape of a walnut. It is used to provide flexible constraint on the sample without affecting X-ray transmission, preventing the walnut shell from falling off and accumulating during the squeezing process, and avoiding fragments from obscuring or interfering with the imaging area.

[0096] As one implementation method, the flexible limiting structure is made of EPE foam, with the foam pores slightly larger than the size of a walnut. EPE foam has good flexibility and low stiffness, which can effectively avoid causing additional mechanical interference to the walnut. The density of EPE foam is much lower than that of a walnut, and its absorption of X-rays is extremely weak. In actual imaging, it does not form obvious obstruction or artifacts of the internal structure of the walnut, and has no impact on the imaging quality.

[0097] like Figure 3 As shown, the X-ray imaging mechanism 305 includes an X-ray emitter 401 and a flat panel detector 402, which are respectively disposed at both ends of the frame 1 and arranged opposite each other, for acquiring images of the internal structure of walnut samples. The X-ray emitter 401 emits X-ray signals that can penetrate the walnut shell and kernel, and the flat panel detector 402 receives the X-rays after they have passed through the sample and generates a high-resolution image, realizing non-contact imaging of the kernel structure.

[0098] The control system 5 is used to coordinate and control the operation of each part, including setting loading parameters, controlling the rotation angle, and synchronously triggering X-ray acquisition. At the same time, it receives feedback data from the force sensor 201 and the displacement sensor 203 in real time, realizing automated control and data synchronization management of the entire kernel damage assessment process.

[0099] The specific implementation process of the kernel damage assessment device of the present invention is as follows:

[0100] The walnut sample to be tested is first placed within a flexible limiting mechanism 303 fixed on an external toothed rotary support turntable 304. The flexible limiting mechanism 303 provides flexible constraint and employs a through-hole groove structure to prevent the sample shell from detaching and accumulating during the compression process, which could lead to image blurring or imaging interference. The walnut sample is fixed with the suture line facing the imaging direction.

[0101] After the control system 5 is activated, the stepper cylinder 202 applies axial compressive force to the walnut sample at a set speed, applying a single compressive deformation along the axial direction perpendicular to the suture line, simulating the stress-deformation process under actual shell-breaking conditions. During loading, the force sensor 201 collects the pressure signal on the walnut in real time, and the displacement sensor 203 simultaneously collects and records the loading displacement. The sampling data from the two sensors are simultaneously collected and uploaded by the control system 5 to form a complete force response record.

[0102] After the set compression amount is completed, the X-ray imaging mechanism 305 is synchronously triggered under the unified scheduling of the control system 5. The X-ray emitter 401 emits a ray signal, which penetrates the walnut shell and kernel structure and is received by the flat panel detector 402 to generate a high-resolution image. The resulting image is a cross-sectional view of the internal structure of the kernel.

[0103] The control system 5 drives the stepper motor 301 to control the external gear rotary support turntable 304 to precisely rotate the walnut sample by 180° as preset, and then performs another X-ray image acquisition. This process can achieve kernel imaging from two typical perspectives, front and back or left and right. After acquiring the X-ray image of the walnut sample, the kernel damage assessment method of this invention is used to quantitatively assess the walnut kernel.

[0104] It is understood that after the kernel damage assessment device acquires the X-ray image of the walnut sample, the kernel damage assessment method of the present invention can be executed through the control system of the device to quantitatively assess the walnut kernels. Alternatively, the kernel damage assessment method of the present invention can be executed through other computers or electronic devices to quantitatively assess the walnut kernels.

[0105] The kernel damage assessment method and device proposed in this invention have a complete operation process, covering key aspects such as loading deformation control, image acquisition and processing, structure recognition, feature extraction, and damage degree output. The various structures of the device achieve synchronous scheduling and data integration through a control system, providing reliable support for subsequent data analysis. The overall device has good application potential.

[0106] To address the aforementioned technical problems, this invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps of the X-ray-based walnut kernel damage assessment method described above.

[0107] like Figure 6 As shown, the computer / electronic device includes memory, processor, and network interface interconnected via a system bus. It should be noted that the figure only shows a computer device with components such as memory, processor, network interface, and operating system; however, it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented alternatively. Those skilled in the art will understand that the computer / electronic device described here is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0108] Computers / electronic devices can be desktop computers, laptops, PDAs, and cloud servers, among other computing devices. They can interact with users through keyboards, mice, remote controls, touchpads, or voice-activated devices.

[0109] There may be one or more memories, and at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory may be an internal storage unit of a computer device, such as the hard disk or RAM of the computer device. In other embodiments, the memory may also be an external storage device of the computer device, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the computer device. Of course, the memory may include both internal storage units and external storage devices of the computer device. In this embodiment, the memory is typically used to store the operating system and various application software installed on the computer device, such as the program code of a method for assessing kernel damage in walnuts based on X-ray cracking. In addition, the memory may also be used to temporarily store various types of data that have been output or will be output.

[0110] In some embodiments, the processor may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip. The processor is typically used to control the overall operation of a computer device. In this embodiment, the processor is used to run program code stored in memory or process data, such as running program code for a method of assessing kernel damage in walnuts based on X-ray cracking.

[0111] Network interfaces may include wireless network interfaces and / or wired network interfaces, which are typically used to establish communication connections between computer devices and other electronic devices.

[0112] The present invention also provides another embodiment, namely, providing a readable storage medium on which a computer program is stored, which, when executed by a processor, implements the steps of the above-described method for assessing kernel damage in walnuts based on X-ray cracking.

[0113] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0114] It will be readily understood by those skilled in the art that this invention includes any combination of the inventive description and specific embodiments outlined in the foregoing specification, as well as the various parts shown in the accompanying drawings. Due to space limitations and for the sake of brevity, not all of these combinations have been described in detail. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

[0115] Although embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention without departing from the principles and spirit of the invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for assessing kernel damage in walnuts during shell cracking based on X-rays, characterized in that, include: X-ray images of walnut samples were acquired and preprocessed. The preprocessed image is input into a deep learning instance segmentation model to obtain a segmentation mask for all walnut kernel structural blocks in the image; The structural feature parameters of the walnut kernels are determined based on the segmentation mask of all walnut kernel structural blocks in the image. The structural feature parameters include the principal structural integrity coefficient and the relative fragmentation degree. A linearly weighted structural damage model is constructed based on the main structural integrity coefficient and the relative fragmentation degree. The first weighting coefficient and the second weighting coefficient are determined based on the main structural integrity coefficient and the relative fragmentation. The first and second weighting coefficients are substituted into the linearly weighted structural damage model to determine the final damage degree of the walnut sample.

2. The method for assessing kernel damage in walnuts during shell cracking based on X-rays as described in claim 1, characterized in that, The X-ray images of the walnut sample include X-ray images of the walnut sample from two opposing viewpoints.

3. The method for assessing kernel damage in walnuts during shell cracking based on X-rays as described in claim 1, characterized in that, The main structure integrity coefficient is as follows: Among them, R main Main structural integrity coefficient, A max A represents the area of ​​the largest structural region in the X-ray image of the walnut sample. total This represents the total area of ​​all regions in the X-ray image of the walnut sample.

4. The method for assessing kernel damage in walnuts during shell cracking based on X-rays as described in claim 1, characterized in that, The relative fragmentation is as follows: Where S is the relative fragmentation degree, N is the number of structural blocks obtained by segmenting the X-ray image of the walnut sample, and N0 is the standard structural block number of the whole walnut kernel, i.e., N0 = 1.

5. The method for assessing kernel damage in walnuts during shell cracking based on X-rays as described in claim 1, characterized in that, The linearly weighted structural damage model is as follows: D=α(1-R main )+βS Where D represents the X-ray image damage degree of the walnut sample, α is the first weighting coefficient, β is the second weighting coefficient, and R... main S is the structural integrity coefficient, and S is the relative fragmentation degree.

6. The method for assessing kernel damage in walnuts during shell cracking based on X-rays as described in claim 1, characterized in that, Determining the first weighting coefficient and the second weighting coefficient based on the main structural integrity coefficient and the relative fragmentation includes: Principal component analysis was used to analyze the inverse vector 1-R of the principal structural integrity coefficients. main The relative fragmentation S is standardized to extract the feature vector corresponding to the first principal component, and normalized according to its absolute value to determine the first weighting coefficient and the second weighting coefficient.

7. The method for assessing kernel damage in walnuts during shell cracking based on X-rays as described in claim 2, characterized in that, Determining the final damage degree of a walnut sample involves: calculating the damage degree of X-ray images of the walnut sample from two relative perspectives, and taking the arithmetic mean of the damage degree of the X-ray images from the two relative perspectives as the final damage degree of the walnut sample.

8. A device for assessing kernel damage during walnut shell cracking based on X-rays, characterized in that, The device includes a frame and a control system. The upper end of the frame is provided with a compression and monitoring mechanism, the side of the frame is provided with an X-ray imaging mechanism, and the lower end of the frame is provided with a sample fixing and rotating mechanism. The control system is electrically connected to the compression and monitoring mechanism, the X-ray imaging mechanism, and the sample fixing and rotating mechanism.

9. The X-ray-based walnut kernel damage assessment device under shell cracking as described in claim 8, characterized in that, The extrusion and monitoring mechanism includes a stepping electric cylinder and a displacement sensor. The stepping electric cylinder is connected to the displacement sensor. One end of the stepping electric cylinder is connected to the upper end of the frame. The output end of the stepping electric cylinder is connected to an extrusion plate through a force sensor.

10. The X-ray-based walnut kernel damage assessment device as described in claim 8, characterized in that, The sample fixing and rotating mechanism includes a stepper motor and an external toothed rotary support turntable. The output end of the stepper motor is connected to a gear, which meshes with the external toothed rotary support turntable. The external toothed rotary support turntable is provided with a flexible limiting structure.

Images