Colloidal gold detection method and device

Abstract

The invention relates to the technical field of biological detection, in particular to a colloidal gold detection method and device.The method comprises the steps that target image information of a colloidal gold detection card placed at a preset position is obtained; based on the performance of a machine to which the colloidal gold detection card belongs, extracting a color development area of the colloidal gold detection card from the target image information; determining detection line information of the colloidal gold detection card based on the color development area; and outputting a detection result of the colloidal gold detection card based on the detection line information and a preset judgment standard. According to the method, the detection line information of the colloidal gold detection card can be more accurately analyzed, so that the accuracy of a detection result can be improved.

Description

Technical Field

[0001] The present invention relates to the field of biological detection technology, and particularly to a method and device for colloidal gold detection in the field of biological detection technology. Background Art

[0002] In the fields such as biomedical research, the method of colloidal gold detection is applied to drug screening, biological interaction research and laboratory analysis. Due to its characteristics of simple operation, fast detection speed, high sensitivity, etc., this technology has broad application prospects in the field of point-of-care testing. In the related art, it is impossible to ensure that the colors photographed by the camera at different positions are consistent, and when the machine performance is low, the detection speed is slow. In the process of directly extracting the CT line by using deep learning, when the T line fades, it is easy to fail in extraction, resulting in low detection accuracy of colloidal gold. Summary of the Invention

[0003] The purpose of the present invention is to provide a method and device for colloidal gold detection, and the specific technical solutions adopted are as follows:

[0004] In a first aspect, an embodiment of the present invention provides a method for colloidal gold detection, and the method includes:

[0005] Obtaining target image information of a colloidal gold detection card placed at a preset position;

[0006] Extracting a color development area of the colloidal gold detection card from the target image information based on the performance of the machine to which the colloidal gold detection card belongs;

[0007] Determining detection line information of the colloidal gold detection card based on the color development area;

[0008] Outputting a detection result of the colloidal gold detection card based on the detection line information and a preset judgment criterion.

[0009] In a second aspect, an embodiment of the present invention provides a device for colloidal gold detection, and the device for colloidal gold detection includes:

[0010] An obtaining module, configured to obtain target image information of a colloidal gold detection card placed at a preset position;

[0011] An extracting module, configured to extract a color development area of the colloidal gold detection card from the target image information based on the performance of the machine to which the colloidal gold detection card belongs;

[0012] A determining module, configured to determine detection line information of the colloidal gold detection card based on the color development area;

[0013] An outputting module, configured to output a detection result of the colloidal gold detection card based on the detection line information and a preset judgment criterion.

[0014] In a third aspect, there is provided a computer program product, which includes: computer program code that, when running on a computer, causes the computer to execute the method in the first aspect above.

[0015] In a fourth aspect, there is provided a computer-readable storage medium storing computer program code that, when running on a computer, causes the computer to execute the method in the first aspect above.

[0016] The present invention has the following beneficial effects: First, obtain the target image information of the colloidal gold test strip placed at a preset position, and then, according to the performance of the machine to which the colloidal gold test strip belongs, extract the color development area of the colloidal gold test strip in the target image information, which can improve the accuracy of the extracted color development area. After that, determine the test line information of the colloidal gold test strip through the color development area, so as to be able to analyze the test line information of the colloidal gold test strip more accurately; finally, output the test result of the colloidal gold test strip through the test line information and a preset judgment criterion, thereby improving the accuracy of the test result. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following-described drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0018] Figure 1 It is a schematic flowchart of the implementation of a method for colloidal gold detection provided by an embodiment of the present invention;

[0019] Figure 2 It is a schematic diagram of an application scenario of a method for colloidal gold detection provided by an embodiment of the present invention;

[0020] Figure 3 It is a schematic diagram of the display interface of a machine for a method for colloidal gold detection provided by an embodiment of the present invention;

[0021] Figure 4 It is a schematic diagram of a picture marked by deep learning provided by an embodiment of the present invention;

[0022] Figure 5 It is another schematic flowchart of the implementation of a method for colloidal gold detection provided by an embodiment of the present invention;

[0023] Figure 6 It is another schematic diagram of an application scenario of a method for colloidal gold detection provided by an embodiment of the present invention;

[0024] Figure 7 It is a schematic structural diagram of a component of a colloidal gold detection device provided by an embodiment of the present invention;

[0025] Figure 8 It is a schematic structural diagram of a computer device provided by an embodiment of the present invention. Specific embodiments

[0026] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following describes in detail a colloidal gold detection method proposed according to the present invention, its specific implementation manner, structure, features and effects with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0027] Among them, in the description of the embodiments of the present invention, unless otherwise specified, " / " means "or". For example, A / B may mean A or B. The "and / or" in the text is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of the present invention, "a plurality" means two or more than two.

[0028] Hereinafter, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as implying or indicating relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features.

[0029] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0030] The following specifically describes the specific solution of a colloidal gold detection method provided by the present invention with reference to the accompanying drawings. Please refer to Figure 1 , which shows a schematic implementation flow diagram of a colloidal gold detection method provided by an embodiment of the present invention. The method includes:

[0031] 101. Obtain the target image information of the colloidal gold detection card placed at a preset position.

[0032] Here, the preset position may be a dedicated position of the colloidal gold detection card in the device. The target image information of the colloidal gold detection card is obtained by collecting images of the colloidal gold detection card placed in the device while ensuring that the colors captured by the camera at different positions are consistent.

[0033] In some possible implementation manners, the above step 101 may be implemented through the following steps 111 and 112 (not shown in the figure):

[0034] 111. Obtain the initial image information of the colloidal gold test strip placed at a preset position.

[0035] Here, in order to ensure the color consistency at different positions of the colloidal gold test strip during the image acquisition process, an LED square diffused light source and an industrial camera satisfying a preset dynamic range are obtained, and based on the LED square diffused light source and the industrial camera, the initial image information of the colloidal gold test strip placed at the preset position is collected. In the embodiments of the present invention, for the color consistency problem, a special light source and camera configuration design are adopted. Through precise light source illumination and high-quality image acquisition equipment, the accurate restoration of the color of the colloidal gold reaction area is ensured, and color deviation caused by factors such as light, camera angle, and environmental changes is avoided.

[0036] One of the keys to color consistency lies in the design of the light source. To ensure the color consistency of the colloidal gold reaction area at each position, an LED square diffused light source is selected (wherein, the machine lighting method of the LED square diffused light source is as Figure 2 shown). The LED square diffused light source has the characteristics of uniform illumination, stable spectral output, and high color rendering. In order to adapt to the color change of the surface of the colloidal gold test strip under different lighting conditions, an industrial camera with a high dynamic range (HDR) is selected. The HDR camera has a wider exposure range and can effectively capture the light and dark details in the image. Especially in a complex lighting environment, the camera can simultaneously retain the detail information of the highlight area and the shadow area.

[0037] 112. Perform image preprocessing on the initial image information to obtain the target image information.

[0038] Here, noise reduction processing such as filtering is performed on the initial image information, and each color channel is spliced to generate the target image information. In this way, after collecting the initial image information, by performing preprocessing on the image, the clarity of the obtained target image information can be improved, so as to facilitate subsequent colloidal gold detection through the target image information.

[0039] In some possible implementation manners, the above step 112 may be implemented through the following process:

[0040] First, perform noise reduction processing on the initial image information to obtain a denoised image;

[0041] Second, intercept the central area in the denoised image;

[0042] Next, perform linear stretching on different color channels of the central region to obtain the stretched pixel values of different color channels;

[0043] Finally, splice the stretched pixel values and the corresponding original pixel values of each color channel to generate the target image information of each color channel.

[0044] Here, after the image acquisition is completed, a series of preprocessing operations are performed on the image to further improve the image quality and enhance the features, so as to provide more reliable data support for subsequent analysis and judgment.

[0045] First, perform Gaussian smoothing processing on the image. The Gaussian smoothing operation can effectively remove the noise in the image by applying a Gaussian filter, especially reduce the detailed noise and random noise in the image, making the subsequent processing more stable and accurate. The Gaussian smoothing operation can retain the main structural information of the image while weakening the unnecessary details.

[0046] Then, roughly intercept the central region of the image. Since the reaction area of the colloidal gold test strip is usually located in the center or a specific area of the image, in order to reduce the processing complexity and improve the efficiency, the central region in the image is intercepted. This operation reduces the interference of background information by locating the key area in the image and retains the most useful part, helping to extract key information.

[0047] Next, perform linear stretching on the color channels of the image. The red, green, and blue (RGB) color channels of the image are linearly stretched separately. Specifically, first find the minimum and maximum values of each color channel, and then transform the pixel values of each channel according to the following formula:

[0048] New pixel value = (Original pixel value - Minimum value) / (Maximum value - Minimum value) × 255

[0049] This process maps the pixel values of each color channel to the range of 0 to 255, ensuring that the brightness ranges of different color channels are consistent, thereby enhancing the contrast and detailed information of the image.

[0050] Then, use the linearly stretched red channel, the original green channel, and the original blue channel to form a new image. Then, use the original red channel, the stretched green channel, and the original blue channel to form another image. Finally, use the original red channel, the original green channel, and the stretched blue channel to form the third piece of target image information. In this way, a total of three pieces of processed target image information will be obtained for subsequent analysis respectively.

[0051] The composition of each piece of target image information is different, which can highlight the characteristics of different color channels. The purpose of doing this is to analyze the image more carefully and help distinguish and identify the color changes in the colloidal gold reaction area in the subsequent steps. In this way, based on different color channels, the quality of the image can be further optimized, and the accuracy and reliability of image analysis can be improved.

[0052] 102. Extract the color development area of the colloidal gold test strip from the target image information based on the performance of the machine to which the colloidal gold test strip belongs.

[0053] Here, the machine to which the colloidal gold test strip belongs is as Figure 3 shown, where Figure 3 the detection interface of the machine is shown. The performance of the machine to which the colloidal gold test strip belongs is the detection accuracy of the machine used to detect colloidal gold. The higher the detection accuracy, the higher the performance of the machine, and the lower the detection accuracy, the lower the performance of the machine.

[0054] In some possible implementation manners, when the performance of the machine is low, it can be implemented through the following steps 121 to 126 (not shown in the figure):

[0055] 121. When the performance of the machine to which the colloidal gold test strip belongs meets the first performance, perform edge processing on the target image information of each color channel to obtain the edge texture image of each color channel.

[0056] Here, use the Canny algorithm in the vision library openCV to process the three processed images and the original image obtained, and obtain four edge texture images.

[0057] 122. Merge the edge texture images of each color channel to obtain the target texture image.

[0058] Here, take the union of the four edge texture images to obtain the final target texture image.

[0059] 123. Perform image dilation processing on the target texture image to obtain the initial dilated image.

[0060] Here, since the colloidal gold color development area is mostly rectangular, use convolution kernels with heights and widths of (8, 4) and (5, 5) to perform image dilation processing on the final texture image to obtain the initial dilated image.

[0061] 124. Adjust the pixel values of the initial dilated image to obtain the adjusted image.

[0062] Here, set the edge 20 pixel values of the dilated image to 0, and then use flood filling on the image starting from the (0, 0) pixel point to obtain the adjusted image.

[0063] 125. Perform image inversion and image dilation on the adjusted image to obtain the target dilated image.

[0064] Here, perform binary inversion on the processed image, and then use a convolutional kernel with a height and width of (5, 5) to perform image dilation on the image, and use a convolutional kernel with a height and width of (10, 1) to perform image erosion on the image to obtain the target dilated image.

[0065] 126. Perform contour screening on the target dilated image to obtain the color display area.

[0066] Here, use the findContours algorithm in the traditional vision library openCV to find all the contours, and screen the contours that meet the aspect ratio and size as the color display area of the colloidal gold test strip. In this way, in the case of low machine performance, by performing edge processing on the obtained target image information, the color display area can be accurately extracted.

[0067] In some possible implementation manners, if the performance of the machine to which the colloidal gold test strip belongs is relatively high, the color display area can be extracted from the target image information through deep learning, which can be achieved through the following process:

[0068] First, when the performance of the machine to which the colloidal gold test strip belongs meets the second performance, use a convolutional layer and an attention mechanism to extract the image features of the target image information.

[0069] Among them, the second performance is higher than the first performance.

[0070] Second, use a residual efficient layer aggregation network to scale the image features to obtain the adjusted features;

[0071] Finally, based on the adjusted features, identify the color display area in the target image information.

[0072] Here, for machines with stronger performance, use deep learning methods to process. Based on YOLOv11, innovate the architecture to improve the calculation efficiency and detection accuracy, including the following steps:

[0073] 1. Collect data: Collect an image dataset containing the color display area of the colloidal gold test strip, and label the color display area in the image to generate training and test sets.

[0074] Among them, after labeling the color display area in the image, the obtained labeled image is as Figure 4 shown, that is, the image labeled by deep learning.

[0075] 2. Design the network architecture: This architecture includes multiple core modules. First is the basic convolutional layer for feature extraction, and then the Area Attention module is introduced to enhance the understanding of the global context. The Area Attention module significantly reduces the computational complexity through simple partitioning operations while maintaining a large receptive field, thus effectively improving the detection accuracy. Extract CT line features: Use the trained CNN to extract the features of the CT line.

[0076] 3. Introduce the Residual-Efficient Layer Aggregation Network (R-ELAN): The R-ELAN is adopted. This innovative design optimizes the feature aggregation process. R-ELAN combines residual connections and an efficient layer aggregation strategy. By introducing a scaling factor, it ensures the stability during the training process and improves the optimization efficiency of large-scale models.

[0077] 4. Optimize the FlashAttention model: The FlashAttention model is combined to solve the memory access bottleneck problem in the attention mechanism, thus improving the inference speed of the model. FlashAttention enables it to achieve fast inference at a relatively low computational cost while maintaining high accuracy.

[0078] 5. Model training: Use the standard object detection training process to train the network with the labeled data.

[0079] 6. Evaluation optimization: Use the cross-validation method to evaluate the performance of the model.

[0080] 103. Based on the color development area, determine the detection line information of the colloidal gold test strip.

[0081] Here, the detection line information is used to characterize the position of the CT line of the colloidal gold test strip. By performing operations such as expanding and denoising the color development area, analyzing the positions of the peaks and valleys, the position of the CT line of the colloidal gold test strip is obtained, that is, the detection line information is obtained. In some possible implementation manners, the above step 103 can be achieved through Figure 5 the steps shown as follows:

[0082] 501. Expand the color development area to obtain the expanded area.

[0083] Here, sort the intercepted areas to ensure that the subsequent results can be output from left to right. Perform Gaussian filtering on the original image and process the intercepted color development areas from left to right in sequence. First, perform interpolation on the color development area to expand it to twice its original size, that is, the expanded area is obtained.

[0084] 502. Perform color gamut conversion on the expanded area to obtain the converted area.

[0085] Here, the BGR color gamut in the expanded area is converted to the Lab color gamut to obtain the converted area.

[0086] 503, perform filtering processing on the red channel in the converted area to obtain a filtered curve.

[0087] Here, considering that the colloidal gold CT line shows red and green colors, the a channel is taken for subsequent processing. Perform linear stretching on the a channel, calculate the sum of pixel values of each row in the a channel, convert the two-dimensional image into a one-dimensional curve; use average filtering to smooth the one-dimensional curve to obtain a filtered curve.

[0088] 504, perform peak searching on the filtered curve to obtain peak values.

[0089] Here, perform peak searching on the filtered curve to find the peaks and valleys therein, and filter out the low peaks (the larger the value obtained by subtracting the valley from the peak, the higher the peak).

[0090] 505, based on the peak values, determine the detection line information of the colloidal gold test strip.

[0091] Here, select the two highest peaks as the positions of the CT lines, that is, obtain the detection line information. Among them, use the quantitative analysis method to extract the CT lines of the colloidal gold test strip, and the obtained detection line information is as Figure 6 shown, and different data points in Figure 6 represent the positions of the extracted CT lines.

[0092] 104, based on the detection line information and a preset judgment criterion, output the detection result of the colloidal gold test strip.

[0093] Here, the preset judgment criterion can be a user-defined judgment criterion, that is, the correlation coefficient (R value) set by the user.

[0094] In some possible implementation manners, if a first marker line is recognized in the detection line information, obtain the first pixel value of the second marker line and the second pixel value of the first marker line in the detection line information; here, the first marker line is the C line and the second marker line is the T line. If the C line is recognized, then calculate the R value, the RGB values of the C line, and the RGB values of the T line. Then, based on the first pixel value and the second pixel value, determine the correlation coefficient between the first marker line and the second marker line; and based on the correlation coefficient and the preset judgment criterion, determine and output the detection result of the colloidal gold test strip. Here, divide the RGB values of the T line by the RGB values of the C line respectively, then multiply by the proportions of the three RGB channels of the C line respectively, and finally add them up to obtain the result R. Judge positive or negative according to the R value set by the user, and output the result on the software interface as shown in Figure 3 shown.

[0095] In an embodiment of the present invention, first, target image information of a colloidal gold test strip placed at a preset position is obtained. Then, according to the performance of the machine to which the colloidal gold test strip belongs, the color development area of the colloidal gold test strip is extracted from the target image information, which can improve the accuracy of the extracted color development area. After that, based on the color development area, the test line information of the colloidal gold test strip is determined, so as to more accurately analyze the test line information of the colloidal gold test strip. Finally, based on the test line information and a preset judgment criterion, the test result of the colloidal gold test strip is output, thereby improving the accuracy of the test result.

[0096] An embodiment of the present invention provides a device for colloidal gold detection. Please refer to Figure 7 , which shows a schematic structural diagram of the composition of a device for colloidal gold detection provided by an embodiment of the present invention. The device 700 includes:

[0097] An acquisition module 701, configured to acquire target image information of a colloidal gold test strip placed at a preset position;

[0098] An extraction module 702, configured to extract the color development area of the colloidal gold test strip from the target image information based on the performance of the machine to which the colloidal gold test strip belongs;

[0099] A determination module 703, configured to determine the test line information of the colloidal gold test strip based on the color development area;

[0100] An output module 704, configured to output the test result of the colloidal gold test strip based on the test line information and a preset judgment criterion.

[0101] In some possible implementation manners, the output module 704 is further configured to determine the pixel value of the test line in the target image information based on the test line information; and determine and output the test result of the colloidal gold test strip based on the pixel value of the test line and the preset judgment representation.

[0102] In some possible implementation manners, the acquisition module 701 is further configured to acquire initial image information of a colloidal gold test strip placed at a preset position; and perform image preprocessing on the initial image information to obtain the target image information.

[0103] In some possible implementation manners, the acquisition module 701 is further configured to acquire an LED square diffused light source and an industrial camera satisfying a preset dynamic range; and collect the initial image information of the colloidal gold test strip placed at a preset position based on the LED square diffused light source and the industrial camera.

[0104] In some possible implementation manners, the obtaining module 701 is further configured to perform noise reduction processing on the initial image information to obtain a denoised image; intercept a central region in the denoised image; perform linear stretching on different color channels of the central region to obtain stretched pixel values of different color channels; and splice the stretched pixel values of each color channel and the corresponding original pixel values to generate target image information of each color channel.

[0105] In some possible implementation manners, the extraction module 702 is further configured to, when the performance of the machine to which the colloidal gold test strip belongs meets the first performance, perform edge processing on the target image information of each color channel to obtain edge texture images of each color channel; merge the edge texture images of each color channel to obtain a target texture image; perform image dilation processing on the target texture image to obtain an initial dilated image; perform pixel value adjustment on the initial dilated image to obtain an adjusted image; perform image inversion and image dilation processing on the adjusted image to obtain the target dilated image; and perform contour screening on the target dilated image to obtain the color development region.

[0106] In some possible implementation manners, the extraction module 702 is further configured to, when the performance of the machine to which the colloidal gold test strip belongs meets the second performance, extract image features of the target image information by using a convolutional layer and an attention mechanism; where the second performance is higher than the first performance; scale the image features by using a residual efficient layer aggregation network to obtain adjusted features; and identify the color development region in the target image information based on the adjusted features.

[0107] In some possible implementation manners, the determining module 703 is further configured to expand the color development region to obtain an expanded region; perform color gamut conversion on the expanded region to obtain a converted region; perform filtering processing on the red channel in the converted region to obtain a filtered curve; perform peak seeking processing on the filtered curve to obtain a peak value; and determine the detection line information of the colloidal gold test strip based on the peak value.

[0108] In some possible implementation manners, the output module 704 is further configured to, if a first marker line is identified in the detection line information, obtain a first pixel value of a second marker line and a second pixel value of the first marker line in the detection line information; determine a correlation coefficient between the first marker line and the second marker line based on the first pixel value and the second pixel value; and determine and output the detection result of the colloidal gold test strip based on the correlation coefficient and the preset judgment criterion.

[0109] Optionally, the transmission medium may be a wired link (such as but not limited to, coaxial cable, optical fiber, and Digital Subscriber Line (DSL), etc.) or a wireless link (such as but not limited to, Wireless Fidelity (WIFI), Bluetooth, and mobile device network, etc.). It should be noted that: For the device provided in the above embodiment, only the division of the above-mentioned functional modules is used for illustration. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, the method embodiments provided in the above embodiments belong to the same concept. For the specific implementation process, please refer to the method embodiments, which will not be elaborated here.

[0110] Figure 8 is a schematic structural diagram of a computer device provided by an embodiment of the present invention. Exemplarily, as Figure 8 shown, the computer device 800 includes: a memory 801, a processor 802, and a computer program 803 stored in the memory 801 and running on the processor 802. When the processor 802 executes the computer program 803, the computer device can execute any one of the colloidal gold detection methods described above.

[0111] In addition, an embodiment of the present invention also protects a system, which may include a memory and a processor. Among them, an executable program code is stored in the memory, and the processor is used to call and execute the executable program code to execute a colloidal gold detection method provided by an embodiment of the present invention. In this embodiment, the system can be divided into functional modules according to the above method examples. For example, it can correspond to each functional module, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is illustrative, only a logical function division, and there may be other division methods in actual implementation. It should be noted that all relevant contents of each step involved in the above method embodiments can be cited in the function description of the corresponding functional module, which will not be elaborated here.

[0112] It should be understood that the device provided in this embodiment is used to execute the above method for colloidal gold detection, so the same effects as those of the above implementation method can be achieved. In the case of adopting an integrated unit, the device may include a processing module and a storage module. Among them, when the device is applied to a device, the processing module can be used to control and manage the actions of the device. The storage module can be used to support the device to execute mutual program codes, etc. Among them, the processing module can be a processor or a controller, which can implement or execute various exemplary logic blocks, modules and circuits described in combination with the disclosure of the present invention. The processor can also be a combination that realizes computing functions, such as including a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc. The storage module can be a memory.

[0113] In addition, the device provided in the embodiment of the present invention can specifically be a chip, a component or a module. The chip may include a connected processor and a memory; among them, the memory is used to store instructions. When the processor calls and executes the instructions, the chip can execute the method for colloidal gold detection provided in the above embodiment. This embodiment also provides a computer-readable storage medium, in which computer program codes are stored. When the computer program codes run on a computer, the computer is enabled to execute the above relevant method steps to implement the method for colloidal gold detection provided in the above embodiment.

[0114] This embodiment also provides a computer program product. When the computer program product runs on a computer, it causes the computer to execute the above-related steps to implement a method for colloidal gold detection provided in the above embodiment. Among them, the device, computer-readable storage medium, computer program product, or chip provided in this embodiment are all used to execute the corresponding method provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method provided above, and will not be elaborated here. Through the description of the above embodiments, those skilled in the art can understand that for the convenience and simplicity of description, only the above-mentioned division of each functional module is used as an example. In practical applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In the embodiments provided by the present invention, it should be understood that the disclosed device and method can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of modules or units is only a logical functional division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection can be through some interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical, mechanical, or other form.

[0115] It should be noted that the above sequence of the embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the figures do not necessarily require the particular order or continuous order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous. Each embodiment in this specification is described in a progressive manner, and the same or similar parts among the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. The above content is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention.

Claims

1. A method for colloidal gold detection, characterized in that The method for colloidal gold detection includes: Obtaining target image information of a colloidal gold test strip placed at a preset position; Extracting the color development area of the colloidal gold test strip from the target image information based on the performance of the machine to which the colloidal gold test strip belongs; Determining the test line information of the colloidal gold test strip based on the color development area; Outputting the test result of the colloidal gold test strip based on the test line information and a preset judgment criterion.

2. The method for colloidal gold detection according to claim 1, wherein, The obtaining of the target image information of the colloidal gold test strip placed at the preset position includes: Obtaining initial image information of the colloidal gold test strip placed at the preset position; Performing image preprocessing on the initial image information to obtain the target image information.

3. The method for colloidal gold detection according to claim 2, characterized in that, The obtaining of the initial image information of the colloidal gold test strip placed at the preset position includes: Obtaining an LED square diffused light source and an industrial camera that meets a preset dynamic range; Collecting the initial image information of the colloidal gold test strip placed at the preset position based on the LED square diffused light source and the industrial camera.

4. A method for colloidal gold detection according to claim 2, wherein The performing of image preprocessing on the initial image information to obtain the target image information includes: Performing noise reduction processing on the initial image information to obtain a denoised image; Cropping the central area in the denoised image; Performing linear stretching on different color channels of the central area to obtain stretched pixel values of different color channels; Stitching the stretched pixel values of each color channel and the corresponding original pixel values to generate the target image information of each color channel.

5. A method for colloidal gold detection according to claim 1, characterized in that, The extracting of the color development area of the colloidal gold test strip from the target image information based on the performance of the machine to which the colloidal gold test strip belongs includes: When the performance of the machine to which the colloidal gold test strip belongs meets the first performance, performing edge processing on the target image information of each color channel to obtain edge texture images of each color channel; Merging the edge texture images of each color channel to obtain a target texture image; Performing image dilation processing on the target texture image to obtain an initial dilated image; Adjusting the pixel values of the initial dilated image to obtain an adjusted image; Performing image inversion and image dilation processing on the adjusted image to obtain the target dilated image; Performing contour screening on the target dilated image to obtain the color development area.

6. A method for colloidal gold detection according to claim 1, wherein, The extracting of the color development area of the colloidal gold test strip from the target image information based on the performance of the machine to which the colloidal gold test strip belongs includes: When the performance of the machine to which the colloidal gold test strip belongs meets the second performance, extracting the image features of the target image information by using a convolutional layer and an attention mechanism; where the second performance is higher than the first performance; Scaling the image features by using a residual efficient layer aggregation network to obtain adjusted features; Identifying the color development area in the target image information based on the adjusted features.

7. A method for colloidal gold detection according to claim 1, characterized in that, The determining of the test line information of the colloidal gold test strip based on the color development area includes: Expanding the color development area to obtain an expanded area; Performing color gamut conversion on the expanded area to obtain a converted area; Performing filtering processing on the red channel in the converted area to obtain a filtered curve; Perform peak searching on the filtered curve to obtain the peak value; Based on the peak value, determine the test line information of the colloidal gold test strip.

8. A method for colloidal gold detection according to claim 1, characterized in that, Based on the test line information and a preset judgment criterion, output the test result of the colloidal gold test strip, including: Based on the test line information, determine the pixel value of the test line in the target image information; Based on the pixel value of the test line and the preset judgment representation, determine and output the test result of the colloidal gold test strip.

9. A method for colloidal gold detection according to claim 8, characterized in that, Based on the pixel value of the test line and the preset judgment representation, determine and output the test result of the colloidal gold test strip, including: If a first marker line is identified in the test line information, obtain the first pixel value of the second marker line and the second pixel value of the first marker line in the test line information; Based on the first pixel value and the second pixel value, determine the correlation coefficient between the first marker line and the second marker line; Based on the correlation coefficient and the preset judgment criterion, determine and output the test result of the colloidal gold test strip.

10. A device for colloidal gold detection, characterized in that, The device for colloidal gold detection includes: An acquisition module for acquiring the target image information of a colloidal gold test strip placed at a preset position; An extraction module for extracting the color development area of the colloidal gold test strip from the target image information based on the performance of the machine to which the colloidal gold test strip belongs; A determination module for determining the test line information of the colloidal gold test strip based on the color development area; An output module for outputting the test result of the colloidal gold test strip based on the test line information and a preset judgment criterion.

Images