A strip detection method, device, medium and product

Abstract

The application discloses a strip detection method, device, medium and product, relates to the strip detection field, and the method comprises the following steps: carrying out data preprocessing on a two-dimensional electrophoresis image; the data preprocessing comprises the following steps: background removal, background removal and normalization; one-dimensional intensity projection is carried out on the preprocessed image, and one-dimensional intensity curve is generated; the one-dimensional intensity curve is used for representing the overall intensity distribution of each row of pixels in the preprocessed image; the one-dimensional intensity curve is detected peak value, and the search interval of the strip is determined; in the search interval corresponding to each strip, the center curve, the upper boundary curve and the lower boundary curve of the strip are determined by adopting a column-by-column scanning algorithm; and the strip is positioned according to the center curve, the upper boundary curve and the lower boundary curve of the strip. The application can improve the efficiency, accuracy, adaptability and operation convenience of strip detection in electrophoresis experiments.

Description

Technical Field

[0001] This application relates to the field of strip detection, and in particular to a strip detection method, equipment, medium, and product. Background Technology

[0002] In electrophoresis image analysis, band detection is a crucial foundation for molecular distribution and concentration analysis. Accurate band detection directly impacts subsequent density calculations, band correction, and the reliability of experimental results. However, existing band detection methods are only applicable to one-dimensional images, and a systematically optimized solution for band detection in two-dimensional data (especially combined with precise search of band boundary shapes) is still lacking. Furthermore, existing band detection techniques suffer from the following problems:

[0003] (1) Complex strip shape: Strips are usually irregular (such as curvature or deformation). Traditional methods often assume that the strip is rectangular, which leads to inaccurate boundary detection.

[0004] (2) Low computational efficiency: Global strip detection on two-dimensional data is computationally intensive, especially when the resolution is high or the data volume is large, resulting in low processing efficiency.

[0005] (3) Insufficient support for subsequent processing: Due to the inaccuracy of the detection results, it is difficult to provide a reliable basis for subsequent strip correction, density calculation or other analysis.

[0006] Therefore, there is an urgent need to provide an efficient and accurate strip detection method that can adapt to the irregularity of strips and provide high-precision basic data for subsequent analysis. Summary of the Invention

[0007] The purpose of this application is to provide a strip detection method, device, medium, and product that can improve the efficiency, accuracy, adaptability, and ease of operation of strip detection in electrophoresis experiments.

[0008] To achieve the above objectives, this application provides the following solution:

[0009] Firstly, this application provides a stripe detection method, the stripe detection method comprising:

[0010] The two-dimensional electrophoretic image is preprocessed; the data preprocessing includes: background removal, background removal, and normalization.

[0011] The preprocessed image is subjected to one-dimensional intensity projection to generate a one-dimensional intensity curve; the one-dimensional intensity curve is used to characterize the overall intensity distribution of each row of pixels in the preprocessed image.

[0012] The peak value of the one-dimensional intensity curve is detected to determine the search interval of the strip;

[0013] Within the search interval corresponding to each strip, the center curve, upper boundary curve, and lower boundary curve of the strip are determined by a column-by-column scanning algorithm;

[0014] Strip positioning is performed based on the center curve, upper boundary curve, and lower boundary curve of the strip.

[0015] Optionally, the data preprocessing of the two-dimensional electrophoresis image specifically includes:

[0016] Based on the two-dimensional electrophoresis image, background removal is performed using a sliding window or low-pass filtering;

[0017] Gaussian filtering or median filtering is used to smooth the image after background removal;

[0018] The smoothed image is normalized to obtain the preprocessed image.

[0019] Optionally, the step of performing one-dimensional intensity projection on the preprocessed image to generate a one-dimensional intensity curve specifically includes:

[0020] The preprocessed image is subjected to one-dimensional intensity projection along the row direction; and the intensity of each row of pixels is summed or averaged to generate a one-dimensional intensity curve.

[0021] Optionally, the step of detecting peak values ​​on the one-dimensional intensity curve and determining the search interval of the band specifically includes:

[0022] Based on the one-dimensional intensity curve, the local maximum algorithm is used to detect the peak value;

[0023] Based on the peak position, the search range of the band is determined by expanding the range upwards and downwards respectively.

[0024] Optionally, the local maximum algorithm includes: sliding window method and threshold method.

[0025] Optionally, determining the center curve, upper boundary curve, and lower boundary curve of each strip using a column-by-column scanning algorithm within the search interval corresponding to each strip specifically includes:

[0026] Within the search interval corresponding to each strip, a column-by-column scanning algorithm is used to compare the intensity values ​​of each column of pixels to determine the center point of each strip; and the center curve of the strip is generated based on the center points of all columns; the center point of the strip is the pixel with the largest intensity value.

[0027] Using the center point of each strip as a reference, a column-by-column scanning algorithm is adopted, combined with intensity threshold judgment or gradient change judgment criteria, to search for boundary points and determine the upper and lower boundary points of each column.

[0028] Connect the upper and lower boundary points of each column to determine the upper and lower boundary curves of the strip.

[0029] Secondly, this application provides a strip detection device, the strip detection device comprising:

[0030] The data preprocessing module is used to preprocess the two-dimensional electrophoresis images; the data preprocessing includes: background removal, background removal, and normalization;

[0031] The one-dimensional intensity curve generation module is used to perform one-dimensional intensity projection on the preprocessed image to generate a one-dimensional intensity curve; the one-dimensional intensity curve is used to characterize the overall intensity distribution of each row of pixels in the preprocessed image.

[0032] The search interval determination module is used to detect peak values ​​on a one-dimensional intensity curve and determine the search interval of the band.

[0033] The boundary and center determination module is used to determine the center curve, upper boundary curve, and lower boundary curve of each strip within the search interval corresponding to each strip using a column-by-column scanning algorithm;

[0034] The strip positioning module is used to position the strip based on its center curve, upper boundary curve, and lower boundary curve.

[0035] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the strip detection method described above.

[0036] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the strip detection method described above.

[0037] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the strip detection method described above.

[0038] According to the specific embodiments provided in this application, this application has the following technical effects:

[0039] This application provides a method, apparatus, medium, and product for strip detection. By preprocessing two-dimensional electrophoresis images to remove background noise and reduce the impact of uneven illumination, the image quality and strip signal discernibility are effectively improved. Furthermore, smoothing and normalization operations are used to further optimize image contrast and strip features, making them more prominent in subsequent detection. The characteristics of different experimental images are fully considered to ensure good adaptability of the preprocessing results. A one-dimensional intensity projection is performed on the preprocessed image to generate a one-dimensional intensity curve. Peak values ​​are detected on the one-dimensional intensity curve to determine the search interval for stripes. By extracting the intensity distribution curve of the image, the approximate location of the stripes is quickly located, and regions that may contain stripes are marked. Subsequently, the search interval of the strip is generated based on the intensity change, which efficiently narrows the detection range and provides a clear positioning basis for subsequent accurate calculations, reducing unnecessary computation and significantly improving the detection speed. This method is more efficient than the traditional pixel-by-pixel scanning method. Within the search interval corresponding to each strip, a column-by-column scanning algorithm is used to determine the center curve, upper boundary curve, and lower boundary curve of the strip. This enables the accurate extraction of the center curve and upper and lower boundaries of the strip, adapting to complex strip shapes such as bending and tilting, while avoiding misjudgment problems caused by boundary blurring or noise interference. This application combines one-dimensional fast detection with two-dimensional accurate detection methods to achieve efficient and accurate automated detection of strips. It can adapt to the feature analysis of strips with complex shapes such as bending and tilting, significantly improving the efficiency and reliability of experimental data processing. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 This is a schematic flowchart of a strip detection method in one embodiment of this application. Detailed Implementation

[0042] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0043] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0044] In one exemplary embodiment, such as Figure 1 As shown, a stripe detection method is provided, which includes the following steps S101 to S105. Wherein:

[0045] S101, perform data preprocessing on the two-dimensional electrophoresis image; the data preprocessing includes: background removal, background removal and normalization;

[0046] S101 specifically includes:

[0047] S11. Based on the two-dimensional electrophoresis image, a sliding window or low-pass filter is used to calculate and remove the background signal of the image, making the intensity of the strips more prominent.

[0048] S12 uses Gaussian filtering or median filtering to smooth the image after background removal, eliminating noise points while preserving the main structural features of the stripes.

[0049] S13, normalize the smoothed image to obtain the preprocessed image, reducing the impact of intensity differences in the image on subsequent detection.

[0050] By removing background noise, reducing uneven illumination, and normalizing the image, the image quality and stripe signal are made more prominent. At the same time, it has been optimized for different experimental image characteristics, and can adapt to various experimental conditions and sample types.

[0051] S102, Perform one-dimensional intensity projection on the preprocessed image to generate a one-dimensional intensity curve; the one-dimensional intensity curve is used to characterize the overall intensity distribution of each row of pixels in the preprocessed image.

[0052] As a specific implementation, the preprocessed image is subjected to one-dimensional intensity projection along the row direction; and the intensity of each row of pixels is summed or averaged to generate a one-dimensional intensity curve, with the striped region corresponding to the significant peak in the curve.

[0053] S103, detect the peak value of the one-dimensional intensity curve to determine the search range of the strip;

[0054] S103 specifically includes:

[0055] S31, based on the one-dimensional intensity curve, the local maximum algorithm is used to detect the peak value; the local maximum algorithm includes: sliding window method and threshold method.

[0056] Among them, the sliding window method finds the point with the highest intensity within the window as the peak value. The threshold method sets an intensity threshold and only retains peaks that exceed the threshold.

[0057] S32, based on the peak position, expand upwards and downwards by a set range (e.g., 5-10 rows each) to determine the search interval of the strip; the search interval covers the possible upper and lower boundaries of the strip, ensuring the integrity of the strip while reducing unnecessary calculations;

[0058] The above S102 and S103 use a one-dimensional fast detection method to determine the approximate location of the stripe in the image (approximate center row and its search range), thus narrowing the search area for subsequent precise detection.

[0059] S104: Within the search interval corresponding to each strip, a column-by-column scanning algorithm is used to determine the center curve, upper boundary curve, and lower boundary curve of the strip; based on S103, the specific position and boundary of each strip are accurately detected to solve problems such as strip bending and width variation.

[0060] S104 specifically includes:

[0061] S41, within the search interval corresponding to each strip, the intensity values ​​of each column of pixels are compared using a column-by-column scanning algorithm to determine the center point of each column of strip; and the center curve of the strip is generated based on the center points of all columns; the center point of the strip is the pixel with the largest intensity value;

[0062] S42, using the center point of each strip as a reference, adopts a column-by-column scanning algorithm, combined with intensity threshold judgment or gradient change judgment criteria, to search for boundary points and determine the upper and lower boundary points of each column.

[0063] The intensity threshold determination involves finding the position where the intensity value drops to a certain threshold (e.g., 85% of the maximum value). The gradient change determination criterion is to find the point where the intensity gradient changes significantly.

[0064] S43, connect the upper and lower boundary points of each column to determine the upper and lower boundary curves of the strip.

[0065] S105, the strip is positioned based on the center curve, upper boundary curve and lower boundary curve of the strip.

[0066] The following is an illustration through specific examples:

[0067] Example 1 is to verify the overall performance of this application in strip detection tasks, including detection efficiency and detection accuracy, and is applicable to straight strips and curved strips.

[0068] The study prepared 20 electrophoretic band images, including 10 straight bands and 10 curved bands (containing weak signal regions). An Intel i9 processor with 16GB of memory was used. The total time from data reading to detection completion was recorded, and the detection accuracy (precision) and sensitivity (recall) were calculated.

[0069] The specific steps of the experiment are as follows:

[0070] 1. Data Reading and Preprocessing: Image data is read and processed for denoising, illumination correction, and normalization to improve the contrast and discernibility of the strip signals. The preprocessed image is then used to generate a 16-channel image to enhance the ability to express strip features.

[0071] 2. One-dimensional fast detection: Based on the one-dimensional intensity curve, the approximate area of ​​the strip is quickly located, and the search interval is generated, reducing the amount of computation in irrelevant areas.

[0072] 3. Two-dimensional precise detection: Based on the one-dimensional rapid positioning results, combined with intensity threshold and gradient change standard, the strip region is scanned column by column to accurately extract the center curve and boundary of the strip.

[0073] Experimental results show that this application demonstrates high efficiency and accuracy in detecting both straight and curved stripes. For the detection of straight stripes, the average total time per image is approximately 0.12 seconds, with a detection accuracy (precision) of 98.7% and a sensitivity (recall) of 98.4%. In the detection of curved stripes, the average total time per image is approximately 0.13 seconds, with a detection accuracy of 97.5% and a sensitivity of 96.8%. These results indicate that this application can quickly and accurately detect the center position and boundaries of both regularly shaped straight stripes and complex curved stripes.

[0074] Further analysis revealed that data reading and preprocessing took approximately 0.02 seconds, one-dimensional rapid detection took only 0.001 seconds, and two-dimensional precise detection took approximately 0.02 seconds. The overall efficiency of the process is attributed to one-dimensional rapid detection, which accurately locates the approximate area of ​​the bands by quickly analyzing the intensity distribution curve, significantly reducing the computational load of subsequent detections. Two-dimensional precise detection, on the other hand, accurately extracts the band boundaries and center curves through column-by-column scanning and dual-standard judgment.

[0075] Example 2 compares and verifies the advantages of this application in strip detection accuracy with the one-dimensional peak localization method, especially in the detection of curved strips and weak signal strips, and compares its performance difference with the traditional one-dimensional peak localization method.

[0076] Experiments show that the average time for one-dimensional peak localization in detecting straight strips is approximately 0.11 seconds per strip, with a detection accuracy of 95.2% and a sensitivity (recall) of 92.4%. However, for detecting curved strips, the average time increases to 0.11 seconds per strip, and the detection accuracy drops significantly to only 78.6%, with a sensitivity of only 76.3%. These results indicate that one-dimensional peak localization has poor adaptability to curved strips and exhibits a high false negative rate.

[0077] In comparison, this application demonstrates extremely high detection accuracy and sensitivity in the detection of straight strips, reaching 98.7% and 98.4% respectively, with an average detection time of only 0.12 seconds per strip. In the detection of curved strips, this application also performs excellently, with a detection accuracy of 97.5% and a sensitivity of 96.8%, and a detection time of only 0.13 seconds per strip. This indicates that the accuracy and sensitivity of this application in the detection of curved strips are far superior to the one-dimensional peak localization method, while significantly reducing the detection time.

[0078] One-dimensional peak localization methods rely on the regularity of the strips and are only suitable for detecting straight strips with high signal-to-noise ratios. When the strips are curved or the signal is weak, the detection accuracy and sensitivity of the above methods decrease significantly, easily leading to missed detections and false detections, making it difficult to meet the detection needs of complex scenarios.

[0079] This application demonstrates higher detection accuracy and sensitivity in both straight and curved strip detection, and is more adaptable to strip morphology and signal-to-noise ratio. The overall detection efficiency is comparable to one-dimensional methods, but the detection results are more stable and reliable, making it more suitable for diverse and complex samples in practical applications.

[0080] Example 3 compares the present application with a two-dimensional direct detection method to verify its advantage in detection efficiency, especially when processing high-resolution strip images, comparing its performance with that of the traditional two-dimensional direct detection method.

[0081] Experimental results show that the two-dimensional direct detection method has an average time of 1.8 seconds per strip for straight strip detection, with a detection accuracy of 98.5% and a sensitivity of 97.9%. For curved strip detection, the time increases to 1.8 seconds per strip, with a detection accuracy of 97.2% and a sensitivity of 96.5%. Although the two-dimensional direct detection method performs similarly to this application in terms of accuracy and sensitivity, its detection efficiency is significantly lower.

[0082] In comparison, this application achieves an average detection time of only 0.12 seconds per strip for straight strip detection, with a detection accuracy of 98.7% and a sensitivity of 98.4%; for curved strip detection, the average detection time is 0.13 seconds per strip, with a detection accuracy of 97.2% and a sensitivity of 96.5%. This application significantly outperforms the two-dimensional direct detection method in terms of detection time, while maintaining high levels of detection accuracy and sensitivity.

[0083] Two-dimensional direct detection methods process the entire image pixel by pixel, resulting in extremely high computational costs and significantly extended detection time, especially when processing high-resolution images, where the time consumption can become a bottleneck in practical applications. Although this method has high detection accuracy and sensitivity, its efficiency cannot meet the needs of real-time detection or high-throughput experiments.

[0084] This application introduces one-dimensional rapid detection to quickly locate the approximate region of the strip, effectively reducing the computational scope of subsequent processing. Based on this, two-dimensional precise detection is used to scan the strip region column by column and extract its boundaries, thereby significantly improving detection efficiency while maintaining detection accuracy and sensitivity. Compared to traditional two-dimensional direct detection methods, this application significantly shortens the detection time while maintaining high accuracy and sensitivity, fully demonstrating its technical advantages in high-resolution strip image detection.

[0085] This invention significantly improves detection efficiency and accuracy by combining a phased process of rapid one-dimensional detection with precise two-dimensional detection, while also significantly reducing computational costs and deployment complexity. This application is not only applicable to straight strips but can also effectively handle complex strip shapes such as curved and tilted strips, demonstrating greater practicality and technical advantages, and providing an efficient, accurate, and low-cost solution for strip detection tasks.

[0086] Based on the same inventive concept, this application also provides a strip detection device for implementing the strip detection method described above. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations in one or more strip detection device embodiments provided below can be found in the limitations of the strip detection method described above, and will not be repeated here.

[0087] In one exemplary embodiment, a strip detection device is provided, comprising:

[0088] The data preprocessing module is used to preprocess the two-dimensional electrophoresis images; the data preprocessing includes: background removal, background removal, and normalization;

[0089] The one-dimensional intensity curve generation module is used to perform one-dimensional intensity projection on the preprocessed image to generate a one-dimensional intensity curve; the one-dimensional intensity curve is used to characterize the overall intensity distribution of each row of pixels in the preprocessed image.

[0090] The search interval determination module is used to detect peak values ​​on a one-dimensional intensity curve and determine the search interval of the band.

[0091] The boundary and center determination module is used to determine the center curve, upper boundary curve, and lower boundary curve of each strip within the search interval corresponding to each strip using a column-by-column scanning algorithm;

[0092] The strip positioning module is used to position the strip based on its center curve, upper boundary curve, and lower boundary curve.

[0093] The one-dimensional intensity curve generation module and the search interval determination module constitute a one-dimensional fast detection module: by extracting the intensity distribution curve of the image, it quickly locates the approximate position of the band and marks the regions that may contain the band. Subsequently, it generates the search interval of the band based on the intensity changes, efficiently narrowing the detection range and providing a clear localization basis for subsequent accurate calculations;

[0094] The boundary and center determination module is a two-dimensional precision detection module. Based on the results of rapid detection, it uses a column-by-column scanning algorithm to accurately detect the center curve and upper and lower boundaries of the strip. The center point and boundary point of each column are determined by intensity threshold or gradient change standard to ensure that it adapts to the strip characteristics under different experimental conditions and accurately reflects the shape and boundary position of the strip.

[0095] The data preprocessing module effectively improves image quality and the discernibility of band signals by automatically removing background noise and reducing the impact of uneven illumination. Through smoothing and normalization operations, it further optimizes image contrast and band features, making them more prominent in subsequent detection. This module fully considers the characteristics of different experimental images, ensuring good adaptability of the preprocessing results.

[0096] This application features a modular design that enables automated detection processes. Through rapid region localization and image optimization, strip detection can be completed without manual user intervention, significantly simplifying the operation steps and improving the user experience.

[0097] This application achieves a comprehensive improvement over existing technologies in terms of efficiency, accuracy, sensitivity, and applicability through the efficient synergy between a data preprocessing module, a one-dimensional rapid detection module, and a two-dimensional precise detection module. Each module is responsible for image optimization, strip localization, and precise detection, respectively.

[0098] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal. The computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is connected to the system bus via the I / O interfaces. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The I / O interfaces of the computer device are used for exchanging information between the processor and external devices. The communication interface of the computer device is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a stripe detection method.

[0099] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0100] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0101] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0102] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0103] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0104] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0105] In this application, all actions to acquire signals, information, or data are carried out in compliance with the relevant data protection laws and policies of the country where the location is situated, and with the authorization granted by the owner of the relevant device.

[0106] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0107] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A strip detection method, characterized in that, The strip detection method includes: The two-dimensional electrophoretic image is preprocessed; the data preprocessing includes: background removal, smoothing, and normalization. The preprocessed image is subjected to one-dimensional intensity projection to generate a one-dimensional intensity curve; the one-dimensional intensity curve is used to characterize the intensity distribution of each row of pixels in the preprocessed image. The peak value of the one-dimensional intensity curve is detected to determine the search interval of the strip; Within the search interval corresponding to each strip, the center curve, upper boundary curve, and lower boundary curve of the strip are determined by a column-by-column scanning algorithm; Strip positioning is performed based on the center curve, upper boundary curve, and lower boundary curve of the strip.

2. The strip detection method according to claim 1, characterized in that, The data preprocessing of the two-dimensional electrophoresis image specifically includes: Based on the two-dimensional electrophoresis image, background removal is performed using a sliding window or low-pass filtering; Gaussian filtering or median filtering is used to smooth the image after background removal; The smoothed image is normalized to obtain the preprocessed image.

3. The strip detection method according to claim 1, characterized in that, The step of performing one-dimensional intensity projection on the preprocessed image to generate a one-dimensional intensity curve specifically includes: The preprocessed image is subjected to one-dimensional intensity projection along the row direction; and the intensity of each row of pixels is summed or averaged to generate a one-dimensional intensity curve.

4. The strip detection method according to claim 1, characterized in that, The step of detecting peak values ​​on a one-dimensional intensity curve to determine the search interval for the band specifically includes: Based on the one-dimensional intensity curve, the local maximum algorithm is used to detect the peak value; Based on the peak position, the search range of the band is determined by expanding the range upwards and downwards respectively.

5. The strip detection method according to claim 4, characterized in that, The local maximum algorithm includes: sliding window method and threshold method.

6. The strip detection method according to claim 1, characterized in that, Within the search interval corresponding to each strip, a column-by-column scanning algorithm is used to determine the center curve, upper boundary curve, and lower boundary curve of the strip, specifically including: Within the search interval corresponding to each strip, a column-by-column scanning algorithm is used to compare the intensity values ​​of each column of pixels to determine the center point of each strip; and the center curve of the strip is generated based on the center points of all columns; the center point of the strip is the pixel with the largest intensity value. Using the center point of each strip as a reference, a column-by-column scanning algorithm is adopted, combined with intensity threshold judgment or gradient change judgment criteria, to search for boundary points and determine the upper and lower boundary points of each column. Connect the upper and lower boundary points of each column to determine the upper and lower boundary curves of the strip.

7. A strip detection device, characterized in that, The strip detection device includes: The data preprocessing module is used to preprocess the two-dimensional electrophoresis images; the data preprocessing includes: background removal, smoothing, and normalization. A one-dimensional intensity curve generation module is used to perform one-dimensional intensity projection on the preprocessed image to generate a one-dimensional intensity curve; the one-dimensional intensity curve is used to characterize the intensity distribution of each row of pixels in the preprocessed image. The search interval determination module is used to detect peak values ​​on a one-dimensional intensity curve and determine the search interval of the band. The boundary and center determination module is used to determine the center curve, upper boundary curve, and lower boundary curve of each strip within the search interval corresponding to each strip using a column-by-column scanning algorithm; The strip positioning module is used to position the strip based on its center curve, upper boundary curve, and lower boundary curve.

8. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the strip detection method according to any one of claims 1-6.

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

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

Images