Method for detecting poultry carcass quality and related apparatus

Abstract

The application discloses a kind of poultry carcass quality detection method and related equipment, belong to poultry detection technical field, the method includes: obtaining poultry carcass image to be detected;Poultry carcass image is input to carcass detection model, and carcass detection region is positioned and carcass feature is extracted by carcass detection model;Based on carcass feature, determine poultry carcass quality detection result;Wherein, carcass detection model is based on target detection algorithm and is constructed to obtain, target detection algorithm includes YOLO target detection algorithm, fast regional convolution algorithm and real-time target detection algorithm.The poultry carcass image obtained by the application is input to the carcass detection model trained in advance, and the carcass features in the poultry carcass image are extracted using the carcass detection model, so that the quality detection result can be determined, the poultry carcass quality detection can be automatically, efficiently and accurately completed, the human subjective influence is reduced, and the detection accuracy is improved.

Description

Technical Field

[0001] This application relates to the field of poultry testing technology, and in particular to a method and related equipment for testing the quality of poultry carcasses. Background Technology

[0002] Currently, the quality grade of poultry carcasses is crucial for achieving multi-level utilization and multi-stage value-added of poultry agricultural products.

[0003] In related technologies, the quality inspection and grading of poultry carcasses largely relies on manual inspection. However, in practical applications, it has been found that traditional quality inspection methods suffer from problems such as insufficient accuracy, low efficiency, and susceptibility to subjective human influence.

[0004] In summary, the technical problems existing in the relevant technologies need to be improved. Summary of the Invention

[0005] This application provides a method and related equipment for detecting the quality of poultry carcasses, which can achieve automated, efficient and accurate detection of poultry carcasses, reduce the influence of human subjectivity and improve the accuracy of detection.

[0006] On one hand, embodiments of this application provide a method for detecting the quality of poultry carcasses, the method comprising the following steps:

[0007] Acquire images of poultry carcasses to be inspected; The poultry carcass image is input into the carcass detection model, and the carcass detection area is located and carcass features are extracted through the carcass detection model; wherein, the carcass features include color and defect features; Based on the carcass characteristics, the results of poultry carcass quality testing are determined; The body detection model is constructed based on target detection algorithms, including YOLO target detection algorithm, fast region convolution algorithm, and real-time target detection algorithm.

[0008] Optionally, the step of inputting the poultry carcass image into the carcass detection model, locating the carcass detection region and extracting carcass features through the carcass detection model includes: The poultry carcass image is input into the carcass detection model; The carcass detection model is used to locate and identify the carcass detection area for detecting carcass color levels; Extract image data from the carcass detection area; The image data of the carcass detection area is converted to grayscale to determine the color level; The image data of the carcass detection area is used to identify epidermal damage, and the area of ​​epidermal damage is extracted as the epidermal damage feature. Joint nodes are extracted from the image data of the carcass detection area to construct bone segments, extract the skeletal centerline, and extract fracture features; The color grade, the epidermal damage characteristics, and the fracture characteristics are used as carcass features.

[0009] Optionally, acquiring the image of the poultry carcass to be detected includes: Secure the poultry carcass in the preset position; The poultry carcasses are photographed using a visible light camera, a depth camera, and an X-ray imaging system to obtain images of the poultry carcasses to be inspected.

[0010] Optionally, after acquiring images of the poultry carcass by photographing it with a visible light camera, a depth camera, and an X-ray fluoroscopy system, the method further includes: Image preprocessing was performed on poultry carcass images of different image types through color space conversion, geometric transformation, filtering and noise reduction, and morphological processing.

[0011] Optionally, determining the poultry carcass quality test results based on the carcass characteristics includes: The carcass features are input into a pre-trained classification network model to obtain the poultry carcass quality detection results corresponding to the carcass features, based on a preset classification standard.

[0012] Optionally, the carcass detection model is trained based on the following steps: Acquire multiple historical poultry carcass images, and obtain the carcass feature results corresponding to the multiple historical poultry carcass images; Each of the historical poultry carcass images is used as a sample, and the carcass feature results corresponding to each of the historical poultry carcass images are used as the sample labels corresponding to the samples to construct a training dataset; The carcass detection model is pre-trained using the training dataset.

[0013] On the other hand, embodiments of this application provide a poultry carcass quality testing device, the device comprising: The image acquisition module is used to acquire images of poultry carcasses to be detected; The feature extraction module is used to input the poultry carcass image into the carcass detection model, locate the carcass detection area and extract carcass features through the carcass detection model; wherein, the carcass features include color and defect features; The quality inspection module is used to determine the quality inspection results of poultry carcasses based on the carcass characteristics; The body detection model is constructed based on target detection algorithms, including YOLO target detection algorithm, fast region convolution algorithm, and real-time target detection algorithm.

[0014] On the other hand, embodiments of this application provide an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method.

[0015] On the other hand, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0016] On the other hand, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0017] This application embodiment inputs the acquired poultry carcass image into a pre-trained carcass detection model, and uses the carcass detection model to extract carcass features from the poultry carcass image, thereby determining the quality inspection result. It can automatically, efficiently and accurately complete the quality inspection of poultry carcasses, reduce the influence of human subjectivity, and improve the detection accuracy. Attached Figure Description

[0018] Figure 1 This is a schematic diagram of the implementation environment for a poultry carcass quality testing method provided in this application embodiment; Figure 2 This is a schematic flowchart of a poultry carcass quality testing method provided in an embodiment of this application; Figure 3 This is a schematic diagram of a poultry carcass image processing and detection process provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of a poultry carcass quality testing device provided in an embodiment of this application; Figure 5 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0020] It is understood that the terms “first,” “second,” etc., used in this application may be used herein to describe various concepts, but unless otherwise stated, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the words “if,” “when,” or “in response to a determination” as used herein may be interpreted as “when…” or “when…” or “in response to a determination.”

[0021] As used in this application, the terms "at least one", "multiple", "each", "any", etc., "at least one" includes one, two or more, "multiple" includes two or more, "each" refers to each of the corresponding multiples, and "any" refers to any one of the multiples.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0023] Currently, the quality grade of poultry carcasses is crucial for achieving multi-level utilization and multi-stage value-added of poultry agricultural products.

[0024] In related technologies, the quality inspection and grading of poultry carcasses largely relies on manual inspection. However, in practical applications, it has been found that traditional quality inspection methods suffer from problems such as insufficient accuracy, low efficiency, and susceptibility to subjective human influence.

[0025] In view of this, this application provides a method and related equipment for poultry carcass quality detection. By inputting the acquired poultry carcass image into a pre-trained carcass detection model, the carcass features in the poultry carcass image are extracted using the carcass detection model, thereby determining the quality detection result. This method can automatically, efficiently, and accurately complete the poultry carcass quality detection, reduce the influence of human subjectivity, and improve the detection accuracy.

[0026] It should be noted that in all specific embodiments of this application, when processing data related to user identity or characteristics, such as user information, user behavior data, user historical data, and user location information, user permission or consent is obtained first. Furthermore, the collection, use, and processing of this data comply with relevant laws, regulations, and standards. In addition, when embodiments of this application require access to sensitive personal information of users, separate permission or consent from the user is obtained through pop-ups or redirection to confirmation pages. Only after obtaining the user's separate permission or consent is the necessary user-related data required for the proper functioning of these embodiments acquired.

[0027] The specific implementation methods of the embodiments of this application will be described in detail below with reference to the accompanying drawings. First, a method for detecting the quality of poultry carcasses provided in the embodiments of this application will be described with reference to the accompanying drawings.

[0028] Please refer to Figure 1 , Figure 1 This is a schematic diagram of the implementation environment for a poultry carcass quality testing method provided in this application embodiment. In this implementation environment, the main hardware and software components involved include a terminal processor 110 and a server 120.

[0029] Specifically, the terminal processor 110 may contain a control program for a poultry carcass quality detection method, and the server 120 serves as the backend server for this control program. The terminal processor 110 and the backend server 120 are connected. The poultry carcass quality detection method provided in this embodiment can be executed on the terminal processor 110 side.

[0030] Server 120 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0031] In addition, server 120 can also be a node server in a blockchain network.

[0032] The terminal processor 110 and the server 120 can establish a communication connection via a wireless network. This wireless network uses standard communication technologies and / or protocols. The network can be the Internet or any other network, including but not limited to a Local Area Network (LAN), Metropolitan Area Network (MAN), Wide Area Network (WAN), mobile, or any combination of wireless networks, private networks, or virtual private networks. Furthermore, these hardware and software components can use the same or different communication connection methods; this application does not impose specific limitations in this regard.

[0033] Of course, this is understandable. Figure 1 The implementation environment described in this application is only one of the optional application scenarios for the poultry carcass quality testing method provided in this embodiment. The actual application is not fixed. Figure 1 The software and hardware environment shown is not specifically limited in this application.

[0034] like Figure 2 As shown, Figure 2 This is a flowchart illustrating a method for detecting the quality of poultry carcasses provided in this application embodiment, specifically including but not limited to steps 100 to 300.

[0035] Step 100: Obtain the image of the poultry carcass to be detected.

[0036] In this embodiment of the application, the poultry carcass image can be uploaded in response to user input, or the data acquisition step of poultry carcass images can be triggered according to a preset triggering mechanism when the number of poultry carcass images to be detected in the database meets a certain threshold, and all poultry carcass images to be detected can be read from the database.

[0037] In practical applications, acquiring the image of the poultry carcass to be detected includes: Secure the poultry carcass in the preset position; The poultry carcasses are photographed using a visible light camera, a depth camera, and an X-ray imaging system to obtain images of the poultry carcasses to be inspected.

[0038] In this embodiment of the application, when acquiring images of poultry carcasses, the poultry to be inspected for carcass quality can first be fixed in a preset position. The limbs and neck of the poultry carcass can be fully extended and fixed by means of hanging, laying flat, etc., thereby improving the image quality of the poultry carcass.

[0039] Furthermore, poultry can be photographed using various cameras to obtain diverse image information. Specifically, visible light cameras can capture images of poultry carcasses, revealing skin characteristics such as carcass color, congestion, damage, and bile stains. Depth cameras can capture images of poultry carcasses, revealing characteristics such as body size and weight. X-ray imaging can also capture images of poultry carcasses, revealing characteristics such as broken bones and broken wings.

[0040] In practical applications, the same poultry carcass can be photographed multiple times from different angles, thereby effectively improving the image quality of poultry carcass images.

[0041] Therefore, this application can acquire poultry carcass images by using a variety of imaging devices, and then extract poultry carcass features from all angles to facilitate subsequent quality inspection and grading, thereby improving the accuracy of quality inspection.

[0042] Specifically, as an optional implementation, after acquiring images of the poultry carcass by photographing it with a visible light camera, a depth camera, and an X-ray fluoroscopy system, the method further includes: Image preprocessing was performed on poultry carcass images of different image types through color space conversion, geometric transformation, filtering and noise reduction, and morphological processing.

[0043] In this embodiment of the application, for visible light poultry carcass images captured by a visible light camera, the following operations can be performed sequentially: RGB to Lab color space conversion and b-channel extraction to grayscale image conversion, which enhances the chromaticity features in the visible light poultry carcass image. The following operations can also be performed sequentially: b-channel extraction and single-channel conversion to grayscale image conversion, which enhances the bruising features in the visible light poultry carcass image.

[0044] Furthermore, for X-ray images of poultry carcasses used to acquire features of broken bones and wings, a normalization operation can first be performed to map the high dynamic range data to the range of 0-255. Then, edge sharpening, denoising, and contrast enhancement operations can be performed to enhance the broken wing features. For example, the Laplacian sharpening operator can be used to further highlight the bone edges and broken wing features, and non-local mean denoising can be used to avoid blurring slightly broken wing areas during the denoising process. Finally, contrast-limited adaptive histogram equalization can be used to enhance image contrast.

[0045] Therefore, this application uses image processing methods such as color space conversion, geometric transformation, filtering and noise reduction, and morphological processing to preprocess poultry carcass images of different image types and angles, thereby reducing interference and enhancing features in the images, and providing high-quality image information for subsequent image feature extraction.

[0046] Step 200: Input the poultry carcass image into the carcass detection model, locate the carcass detection region and extract carcass features through the carcass detection model; wherein, the carcass features include color and defect features; the carcass detection model is constructed based on object detection algorithms, including YOLO object detection algorithm, fast region convolution algorithm and real-time object detection algorithm.

[0047] In this embodiment, the acquired poultry carcass image is input into a carcass detection model, which locates the carcass detection area and extracts carcass features from that area. These carcass features specifically include poultry carcass color and defect features, such as bruising, damage, broken wings, broken bones, and bile stains.

[0048] Furthermore, the carcass detection model is mainly built based on object detection algorithms, which can include YOLO object detection algorithm, fast region convolution algorithm, and real-time object detection algorithm. Among them, the YOLO object detection algorithm can adopt the YOLO26 object detection algorithm, the fast region convolution algorithm can adopt the Faster R-CNN algorithm, and the real-time object detection algorithm can adopt the RT-DETRv2 algorithm. The detection model is built and trained through these object detection algorithms to obtain the carcass detection model. The carcass detection model can locate and identify targets such as color judgment areas, bruises, damage, broken wings and bones, and bile stains on poultry carcass images. It can further extract possible carcass features from the located areas. It is understood that when the poultry carcass does not have bruises, damage, or other defects, the corresponding feature extraction result is empty.

[0049] For example, the RT-DETRv2 algorithm can be used to identify target areas in visible light poultry carcass images used to determine the carcass color level, as well as features such as bruising, damage, exposed broken bones, and bile stains on the poultry carcass.

[0050] Specifically, as an optional implementation, the step of inputting the poultry carcass image into a carcass detection model, locating the carcass detection region and extracting carcass features through the carcass detection model includes: The poultry carcass image is input into the carcass detection model; The carcass detection model is used to locate and identify the carcass detection area for detecting carcass color levels; Extract image data from the carcass detection area; The image data of the carcass detection area is converted to grayscale to determine the color level; The image data of the carcass detection area is used to identify epidermal damage, and the area of ​​epidermal damage is extracted as the epidermal damage feature. Joint nodes are extracted from the image data of the carcass detection area to construct bone segments, extract the skeletal centerline, and extract fracture features; The color grade, the epidermal damage characteristics, and the fracture characteristics are used as carcass features.

[0051] In this embodiment of the application, the poultry carcass image after image preprocessing can be input into a pre-trained carcass detection model. The carcass detection model, which is built based on the target detection algorithm, locates and identifies the carcass detection area in the poultry carcass image for detecting the carcass color level, and further extracts the image data of the carcass detection area. For example, it can identify whether there are defects such as bile stains on the poultry carcass.

[0052] Furthermore, the image data of the carcass detection area is processed into grayscale to determine the color level of the poultry carcass. Specifically, a 9×9 pixel slider can be used to traverse the detected area consisting of n rows and k columns on the image. The grayscale value of the carcass detection area after grayscale processing is calculated using the following formula (1), and then the color level is determined according to the pre-set grading rules: (1) in, L Gray The grayscale value of the detected carcass region is calculated; n and k These represent the number of rows and columns, in pixels, of the detected carcass area after grayscale processing; i and j These are the indices of the sliders; x and u These are pixel coordinates; gray ( x , u ) is pixels ( x , u The grayscale value of ).

[0053] Therefore, using the formula (1) provided above, the grayscale average value of the body detection area consisting of n rows and k columns can be calculated block by block using a 9×9 pixel slider. Then, the average value of all sliders is averaged to obtain the overall grayscale value of the area. Then, the color level is determined according to the pre-set grading rules.

[0054] For example, a carcass is classified as Grade A when its grayscale value is greater than 80% of the maximum grayscale value (i.e., 255), Grade B when it is in the range of 75% to 80%, Grade C when it is in the range of 65% to 75%, and Grade D when it is less than 65% of the maximum grayscale value (i.e., 255).

[0055] Furthermore, the image data of the carcass detection area is used to identify epidermal damage and determine the number of wounds. For example, poultry carcass epidermal damage without bruising or injury is classified as Grade A; epidermal damage area less than 0.3 square centimeters and number of wounds less than 2 is classified as Grade B; epidermal damage area less than 1 square centimeter and number of wounds 2 to 4 is classified as Grade C; and epidermal damage area greater than 1 square centimeter or number of wounds greater than 5 is classified as Grade D.

[0056] Furthermore, the ViTPose++ pose estimation model structure can be used as the backbone network, and the SimCC pose estimation network head and ECA attention module can be introduced to detect and identify pre-processed X-ray poultry carcass images, extract joint nodes such as skull, clavicle, shoulder joint, elbow joint, wrist joint, hip joint, knee joint, intertarsal joint, and toe root joint, and construct each bone segment.

[0057] Furthermore, within the constructed bone segment region, the bone region is obtained through a segmentation network model and the skeletal centerline is extracted. The number of centerline endpoints and their spatial distribution are statistically analyzed through endpoint detection. When the endpoints are abnormal or the centerline is interrupted, the corresponding bone segment is identified as a broken bone.

[0058] For example, poultry carcasses without broken wings or bones are classified as Grade A; bones are broken but without significant displacement or exposed bone, and there is only one broken bone; bones are broken but without significant displacement or exposed bone, and there are two broken bone locations, or bones are obviously broken but without exposed bone, which is Grade C; bones are broken but without significant displacement or exposed bone, and there are three or more broken bone locations, or bones are obviously broken, the skin is damaged, and the bone is exposed, which is Grade D.

[0059] It is understood that the above-mentioned grading rules for carcass characteristics are only some optional grading rules in the poultry carcass quality detection method provided in the embodiments of this application. The actual application is not fixed to the above embodiments, and this application does not impose any specific restrictions on it.

[0060] Step 300: Based on the carcass characteristics, determine the poultry carcass quality test results.

[0061] In this embodiment of the application, the poultry carcass quality test results are determined based on the extracted carcass characteristics and their severity.

[0062] For example, determining the poultry carcass quality test results based on the carcass characteristics includes: The carcass features are input into a pre-trained classification network model to obtain the poultry carcass quality detection results corresponding to the carcass features, based on a preset classification standard.

[0063] Please refer to Figure 3 , Figure 3This is a schematic diagram of a poultry carcass image processing and detection process provided in an embodiment of this application. After acquiring poultry carcass images of different image types through various imaging devices, the poultry carcass images are preprocessed according to the image type to reduce interference and enhance features. Then, the poultry carcass images are input into the carcass detection model to locate and identify the carcass detection area for detection and extract carcass features.

[0064] Furthermore, the carcass features are input into a pre-trained classification network model to determine the severity of different carcass features, and output the poultry carcass quality test results corresponding to the carcass features according to the preset classification criteria.

[0065] For example, a CNN classification network model can be selected, and the preset classification criteria can be determined as follows: when the color is grade C or above, and there is no bruising, damage, broken wings or bones, or bile stains, the poultry carcass quality test result is grade A; when the color is grade C or above, and the severity of bruising, damage, broken wings or bones is AAB or ABB, and there is no bile stains, or when the color is grade D, and the grade of bruising, damage, broken wings or bones is AAA or AAB, and there is no bile stains, the poultry carcass quality test result is grade B; when... The quality of poultry carcasses is grade C if the color is grade C or above, and the grades of bruising, damage, broken wings and bones are AAC, ABC, BBB or BBC and there is no bile staining; or if the color is grade D, and the grades of bruising, damage, broken wings and bones are AAC or ABC and there is no bile staining. The quality of poultry carcasses is grade C if the grades of bruising, damage, broken wings and bones are ACC, BCC or CCC, or if there is grade D in bruising, damage, broken wings and bones, or if there is bile staining.

[0066] It is understood that the above-mentioned preset classification criteria are only some optional classification criteria in the poultry carcass quality detection method provided in the embodiments of this application. The actual application is not fixed to the above embodiments, and this application does not impose specific restrictions on it.

[0067] Therefore, compared with the existing grading methods that rely on manual visual inspection, have inconsistent standards, and are inefficient, this invention, by inputting poultry carcass images into a carcass detection model, enables the automatic identification and quantitative grading of key defects such as carcass color, bruising / damage, broken wings and bones, and bile stains, and outputs objective and consistent grading results. This can effectively improve detection efficiency and consistency, reduce manual labor and human error, and lower quality risks.

[0068] Specifically, as an optional implementation, the carcass detection model is trained based on the following steps: Acquire multiple historical poultry carcass images, and obtain the carcass feature results corresponding to the multiple historical poultry carcass images; Each of the historical poultry carcass images is used as a sample, and the carcass feature results corresponding to each of the historical poultry carcass images are used as the sample labels corresponding to the samples to construct a training dataset; The carcass detection model is pre-trained using the training dataset.

[0069] In this embodiment, multiple historical poultry carcass images and their corresponding carcass feature results can be obtained during the historical poultry carcass quality detection process. Then, a training sample is constructed by using any historical poultry carcass image as a sample and its corresponding carcass feature result as the sample label. Multiple training samples are acquired to build a training dataset, which is then input into the carcass detection model. The model parameters are adjusted based on each output result of the carcass detection model, ultimately completing the pre-training process of the carcass detection model.

[0070] The pre-training process of the carcass detection model can be considered complete after reaching a pre-set number of pre-training iterations; or it can be considered complete when the training output of the carcass detection model converges.

[0071] In practical applications, after constructing the training dataset, it can be further divided into a training set, a validation set, and a test set. The training set accounts for 60% of the training dataset, the validation set accounts for 20%, and the test set accounts for 20%. The training set is used for model training, and the validation and test sets are used for model validation.

[0072] For example, when constructing a training dataset, images of chicken carcasses of different breeds can be collected and filtered to ensure the quality of the dataset. The acquired images can be processed by adding noise, blurring, translating, rotating, cropping, etc., to expand the number of training datasets.

[0073] Please see Figure 4 , Figure 4 This is a schematic diagram of a poultry carcass quality testing device provided in an embodiment of this application. This application also provides a poultry carcass quality testing device that can implement the above-mentioned poultry carcass quality testing method. The device includes: Image acquisition module 410 is used to acquire images of poultry carcasses to be detected; The feature extraction module 420 is used to input the poultry carcass image into the carcass detection model, locate the carcass detection area and extract carcass features through the carcass detection model; wherein, the carcass features include color and defect features; The quality inspection module 430 is used to determine the quality inspection results of poultry carcasses based on the carcass characteristics. The body detection model is constructed based on target detection algorithms, including YOLO target detection algorithm, fast region convolution algorithm, and real-time target detection algorithm.

[0074] It is understood that the content of the above method embodiments is applicable to the present device embodiments. The specific functions implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0075] Please see Figure 5 , Figure 5 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application. The electronic device includes: The processor 501 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 502 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 502 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 502 and is called and executed by the processor 501 using the methods described in the embodiments of this application. The input / output interface 503 is used to implement information input and output; The communication interface 504 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 505 transmits information between various components of the device (e.g., processor 501, memory 502, input / output interface 503, and communication interface 504); The processor 501, memory 502, input / output interface 503, and communication interface 504 are connected to each other within the device via bus 505.

[0076] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0077] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0078] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0079] It is understood that the content of the above method embodiments is applicable to the embodiments of this program product. The specific functions implemented by the embodiments of this program product are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0080] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0081] This application provides a method and related equipment for detecting the quality of poultry carcasses. By inputting the acquired poultry carcass image into a pre-trained carcass detection model, the carcass detection model extracts the carcass features from the poultry carcass image, thereby determining the quality detection result. This method can automatically, efficiently, and accurately complete the detection of poultry carcass quality, reduce the influence of human subjectivity, and improve the detection accuracy.

[0082] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0083] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0084] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0085] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0086] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0087] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0088] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0089] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0090] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0091] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0092] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for detecting the quality of poultry carcasses, characterized in that, The method includes the following steps: Acquire images of poultry carcasses to be inspected; The poultry carcass image is input into the carcass detection model, and the carcass detection area is located and carcass features are extracted through the carcass detection model; wherein, the carcass features include color and defect features; Based on the carcass characteristics, the results of poultry carcass quality testing are determined; The body detection model is constructed based on target detection algorithms, including YOLO target detection algorithm, fast region convolution algorithm, and real-time target detection algorithm.

2. The method according to claim 1, characterized in that, The step of inputting the poultry carcass image into the carcass detection model, locating the carcass detection region and extracting carcass features through the carcass detection model includes: The poultry carcass image is input into the carcass detection model; The carcass detection model is used to locate and identify the carcass detection area for detecting carcass color levels; Extract image data from the carcass detection area; The image data of the carcass detection area is converted to grayscale to determine the color level; The image data of the carcass detection area is used to identify epidermal damage, and the area of ​​epidermal damage is extracted as the epidermal damage feature. Joint nodes are extracted from the image data of the carcass detection area to construct bone segments, extract the skeletal centerline, and extract fracture features; The color grade, the epidermal damage characteristics, and the fracture characteristics are used as carcass features.

3. The method according to claim 1, characterized in that, The acquisition of the poultry carcass image to be detected includes: Secure the poultry carcass in the preset position; The poultry carcasses are photographed using a visible light camera, a depth camera, and an X-ray imaging system to obtain images of the poultry carcasses to be inspected.

4. The method according to claim 3, characterized in that, After acquiring images of the poultry carcass to be inspected by photographing it with a visible light camera, a depth camera, and an X-ray fluoroscopy system, the process further includes: Image preprocessing was performed on poultry carcass images of different image types through color space conversion, geometric transformation, filtering and noise reduction, and morphological processing.

5. The method according to claim 1, characterized in that, The determination of poultry carcass quality test results based on the carcass characteristics includes: The carcass features are input into a pre-trained classification network model to obtain the poultry carcass quality detection results corresponding to the carcass features, based on a preset classification standard.

6. The method according to claim 1, characterized in that, The carcass detection model was trained based on the following steps: Acquire multiple historical poultry carcass images, and obtain the carcass feature results corresponding to the multiple historical poultry carcass images; Each of the historical poultry carcass images is used as a sample, and the carcass feature results corresponding to each of the historical poultry carcass images are used as the sample labels corresponding to the samples to construct a training dataset; The carcass detection model is pre-trained using the training dataset.

7. A poultry carcass quality testing device, characterized in that, The device includes: The image acquisition module is used to acquire images of the poultry carcasses to be detected; The feature extraction module is used to input the poultry carcass image into the carcass detection model, locate the carcass detection area and extract carcass features through the carcass detection model; wherein, the carcass features include color and defect features; The quality inspection module is used to determine the quality inspection results of poultry carcasses based on the carcass characteristics. The body detection model is constructed based on target detection algorithms, including YOLO target detection algorithm, fast region convolution algorithm, and real-time target detection algorithm.

8. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 6.

Images