Strip detection method, equipment, medium and product

Abstract

The invention discloses a strip detection method and device, a medium and a product, and relates to the field of strip detection, and the method comprises the steps: carrying out the data preprocessing of a two-dimensional electrophoresis image; the data preprocessing comprises the steps of background removal, background removal and normalization; performing one-dimensional intensity projection on the preprocessed image to generate a one-dimensional intensity curve; the one-dimensional intensity curve is used for representing the overall intensity distribution of each row of pixels in the preprocessed image; carrying out peak value detection on the one-dimensional intensity curve, and determining a search interval of a stripe; determining a center curve, an upper boundary curve and a lower boundary curve of the strip by adopting a column-by-column scanning algorithm in the search interval corresponding to each strip; and carrying out strip positioning according to the center curve, the upper boundary curve and the lower boundary curve of the strip. According to the invention, the efficiency, accuracy, adaptability and operation convenience of strip detection in an electrophoresis experiment can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of band detection, and particularly relates to a band detection method, device, medium and product. BACKGROUND

[0002] In electrophoresis experiment image analysis, the detection of bands is an important basis for molecular distribution and concentration analysis. The accurate detection of bands directly affects the subsequent density calculation, band correction and reliability of experimental results. However, the band detection method in the prior art is only for one-dimensional images, and there is no systematic optimized solution for band detection in two-dimensional data, especially the accurate search combined with band boundary shape. And the existing band detection technology has the following problems: (1) Complex band shape: bands usually have irregularity (such as curvature or deformation), and traditional methods often assume that bands are rectangular, resulting in inaccurate boundary detection.

[0003] (2) Low computational efficiency: direct global band detection on two-dimensional data has large computational load, especially in the case of high resolution or large data volume, the processing efficiency is low.

[0004] (3) Insufficient support for subsequent processing: due to the inaccuracy of the detection results, it is difficult to provide reliable basis for subsequent band correction, density calculation or other analysis.

[0005] Therefore, it is urgent to provide a band detection method with high efficiency and high accuracy, which can adapt to the irregularity of bands and provide high-precision basic data for subsequent analysis. SUMMARY

[0006] The purpose of the present application is to provide a band detection method, device, medium and product, which can improve the efficiency, accuracy, adaptability and operation convenience of band detection in electrophoresis experiments.

[0007] To achieve the above purpose, the present application provides the following solutions: In a first aspect, the present application provides a band detection method, comprising: data preprocessing of a two-dimensional electrophoresis image; the data preprocessing comprises background removal, background removal and normalization; performing one-dimensional intensity projection on the preprocessed image to generate a one-dimensional intensity curve; the one-dimensional intensity curve is used to represent the overall intensity distribution of each row of pixels in the preprocessed image; detecting peaks of the one-dimensional intensity curve to determine the search interval of the bands; using a column-by-column scanning algorithm to determine the center curve, upper boundary curve and lower boundary curve of the bands in the search interval corresponding to each band; The strip positioning is performed according to the center curve, the upper boundary curve and the lower boundary curve of the strip.

[0008] Optionally, the data preprocessing of the two-dimensional electrophoresis image comprises the following steps: The background removal is performed on the two-dimensional electrophoresis image by using a sliding window or a low-pass filter. The image after the background removal is smoothed by using a Gaussian filter or a median filter. The image after the smoothing is normalized to obtain a preprocessed image.

[0009] Optionally, the preprocessed image is subjected to one-dimensional intensity projection to generate a one-dimensional intensity curve, which comprises the following steps: The preprocessed image is subjected to one-dimensional intensity projection along a row direction, and each row of pixel intensity is summed or averaged to generate a one-dimensional intensity curve.

[0010] Optionally, the one-dimensional intensity curve is subjected to peak detection to determine a search interval of the strip, which comprises the following steps: The peak detection is performed on the one-dimensional intensity curve by using a local maximum value algorithm. The search interval of the strip is determined by extending the range upward and downward respectively according to the position of the peak.

[0011] Optionally, the local maximum value algorithm comprises a sliding window method and a threshold method.

[0012] Optionally, the center curve, the upper boundary curve and the lower boundary curve of the strip are determined by using a column-by-column scanning algorithm in the search interval corresponding to each strip, which comprises the following steps: The intensity value of each column of pixel points is compared by using a column-by-column scanning algorithm in the search interval corresponding to each strip to determine the strip center point of each column, and the center curve of the strip is generated according to the center points of all columns; the strip center point is the pixel point with the maximum intensity value. The upper boundary point and the lower boundary point of each column are searched by using a column-by-column scanning algorithm in combination with an intensity threshold judgment or a gradient change judgment standard, with the strip center point of each column as a reference. The upper boundary curve and the lower boundary curve of the strip are determined by connecting the upper boundary points and the lower boundary points of all columns respectively.

[0013] In a second aspect, the application provides a strip detection device, which comprises: A data preprocessing module is configured to perform data preprocessing on a two-dimensional electrophoresis image, and the data preprocessing comprises background removal, background removal and normalization. A one-dimensional intensity curve generation module is configured to generate a one-dimensional intensity curve by performing one-dimensional intensity projection on the preprocessed image, wherein the one-dimensional intensity curve is used to represent the overall intensity distribution of each row of pixels in the preprocessed image. A search interval determination module is configured to determine a search interval of the strip by detecting a peak value of the one-dimensional intensity curve. A boundary and center determination module is configured to determine a center curve, an upper boundary curve and a lower boundary curve of the strip by using a column-by-column scanning algorithm within the search interval corresponding to each strip. A strip positioning module is configured to position the strip according to the center curve, the upper boundary curve and the lower boundary curve of the strip.

[0014] In a third aspect, the present application provides a computer device, comprising 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.

[0015] In a fourth aspect, the present application provides a computer readable storage medium, which stores a computer program, wherein the computer program is executable on a processor to implement the strip detection method.

[0016] In a fifth aspect, the present application provides a computer program product, comprising a computer program, wherein the computer program is executable on a processor to implement the strip detection method.

[0017] According to the embodiments provided in the present application, the present application has the following technical effects: The application provides a strip detection method, device, medium and product. Through data preprocessing on a two-dimensional electrophoresis image, background noise is removed, and the influence of uneven illumination is reduced, thereby effectively improving the quality of the image and the distinguishability of the strip signal. Through smoothing processing and normalization operation, the contrast of the image and the strip feature are further optimized, so that the image is more prominent in subsequent detection. Then, the characteristics of different experimental images are fully considered to ensure that the preprocessing result has good adaptability. One-dimensional intensity projection is performed on the preprocessed image to generate a one-dimensional intensity curve. The search interval of the strip is determined by detecting the peak value of the one-dimensional intensity curve. The approximate position of the strip is quickly located by extracting the intensity distribution curve of the image, and the area possibly containing the strip is marked. Then, the search interval of the strip is generated according to the intensity change, the detection range is efficiently reduced, a clear positioning basis is provided for subsequent accurate calculation, unnecessary calculation amount is reduced, the detection speed is significantly improved, and the method is more efficient than the traditional pixel-by-pixel scanning method. In the search interval corresponding to each strip, a column-by-column scanning algorithm is used to determine the center curve, the upper boundary curve and the lower boundary curve of the strip. Then, the center curve and the upper and lower boundaries of the strip can be accurately extracted, the complex strip morphologies such as bending and tilting can be adapted, and the misjudgment problem caused by boundary blur or noise interference can be avoided. The application combines one-dimensional rapid detection and two-dimensional accurate detection methods to realize efficient and accurate automatic detection of the strip, can adapt to the complex strip feature analysis of bending, tilting and other complex morphologies, and significantly improves the efficiency and reliability of experimental data processing. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0019] Figure 1 It is an embodiment of the present application to provide a strip detection method flowchart. DETAILED DESCRIPTION

[0020] The technical solutions in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0021] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application will be further described in detail in combination with the drawings and specific embodiments.

[0022] In one exemplary embodiment, as shown in Figure 1 A strip detection method is provided, which comprises the following S101-S105. Among them: S101, data preprocessing is performed on the two-dimensional electrophoresis image; the data preprocessing comprises background removal, background removal and normalization; S101 specifically comprises: S11, according to the two-dimensional electrophoresis image, the background signal of the image is calculated and removed by using sliding window or low-pass filter, so that the intensity of the strip is more prominent; S12, the image after background removal is smoothed by using Gaussian filter or median filter, and noise points are eliminated while the main structural features of the strip are retained.

[0023] S13, the image after smoothing is normalized to obtain the preprocessed image, so as to reduce the influence of intensity difference in the image on subsequent detection.

[0024] By removing background noise, reducing uneven illumination and normalization processing, the image quality and strip signal are more prominent, and optimization is made for different experimental image characteristics, which can adapt to various experimental conditions and sample types.

[0025] S102, one-dimensional intensity projection is performed on the preprocessed image to generate a one-dimensional intensity curve; the one-dimensional intensity curve is used to represent the overall intensity distribution of each row of pixels in the preprocessed image; As a specific embodiment, one-dimensional intensity projection is performed on the preprocessed image along the row direction; and the one-dimensional intensity curve is generated by summing or averaging the intensity of each row of pixels, and the strip region corresponds to the significant peak in the curve.

[0026] S103, detecting peak value is performed on the one-dimensional intensity curve to determine the search interval of the strip; S103 specifically comprises: S31, according to the one-dimensional intensity curve, local maximum value algorithm is used to detect peak value; the local maximum value algorithm comprises sliding window method and threshold method.

[0027] Among them, the sliding window method is to find the point with the maximum intensity in the window as the peak value. The threshold method is to set an intensity threshold, and only the peaks exceeding the threshold are retained.

[0028] S32, according to the peak position, the search interval of the strip is determined by respectively expanding the range (for example, 5-10 rows up and down) up and down; the search interval covers the possible upper and lower boundaries of the strip, ensuring the integrity of the strip, while reducing unnecessary calculation; 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. 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. S104 specifically includes: 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; 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. 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.

[0029] S43, connect the upper and lower boundary points of each column to determine the upper and lower boundary curves of the strip.

[0030] S105, the strip is positioned based on the center curve, upper boundary curve and lower boundary curve of the strip.

[0031] The following is an illustration through specific examples: 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.

[0032] 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. The specific steps of the experiment are as follows: 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.

[0033] 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.

[0034] 3. Two-dimensional accurate detection: Based on the one-dimensional fast positioning result, the strip region is scanned column by column combined with the intensity threshold and gradient change standard, and the center curve and boundary of the strip are accurately extracted.

[0035] The experimental results show that the present application shows high efficiency and high precision in the detection of straight-line strips and curved strips. For the detection of straight-line strips, the average total time per image is about 0.12 seconds, the detection precision (accuracy) reaches 98.7%, and the sensitivity (recall rate) is 98.4%. In the detection of curved strips, the average total time per image is about 0.13 seconds, the detection precision is 97.5%, and the sensitivity is 96.8%. These results show that whether it is a straight-line strip with regular shape or a curved strip with complex shape, the present application can quickly and accurately detect the center position and boundary of the strip.

[0036] Further analysis shows that the data reading and preprocessing time is about 0.02 seconds, the one-dimensional fast detection time is only 0.001 seconds, and the two-dimensional accurate detection time is about 0.02 seconds. The high efficiency of the overall process is due to the one-dimensional fast detection, which quickly analyzes the intensity distribution curve, accurately locates the approximate area of the strip, and greatly reduces the calculation amount of subsequent detection; the two-dimensional accurate detection accurately extracts the strip boundary and center curve through column-by-column scanning and double-standard judgment.

[0037] Example 2 is to compare and verify the advantages of the present application in strip detection precision, especially in the detection of curved strips and weak signal strips, and to compare the performance differences between the present application and the traditional one-dimensional peak positioning method.

[0038] Experiments show that the average time per image of one-dimensional peak positioning in straight-line strip detection is about 0.11 seconds, the detection precision (accuracy) is 95.2%, and the sensitivity (recall rate) is 92.4%. However, for the detection of curved strips, the average time per image of this method increases to 0.11 seconds, the detection precision significantly decreases to 78.6%, and the sensitivity is only 76.3%. These results show that one-dimensional peak positioning has poor adaptability to curved strips and has a high miss rate.

[0039] In contrast, the present application shows very high detection precision and sensitivity in the detection of straight-line strips, reaching 98.7% and 98.4% respectively, and the average detection time per image is only 0.12 seconds. In the detection of curved strips, the present application also performs well, with a detection precision of 97.5%, a sensitivity of 96.8%, and a detection time per image of only 0.13 seconds. This shows that the precision and sensitivity of the present application in curved strip detection are much higher than those of the one-dimensional peak positioning method, and the time consumption is significantly reduced.

[0040] The one-dimensional peak positioning method relies on the regularity of the strip and is only applicable to straight strip detection with high signal-to-noise ratio. When the strip is curved or the signal is weak, the detection accuracy and sensitivity of the above method are greatly reduced, and false negatives and false positives are prone to occur, which is difficult to meet the detection requirements of complex scenes.

[0041] The present application has 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 that of the one-dimensional method, but the detection results are more stable and reliable, and are more suitable for diversified and complex samples in actual applications.

[0042] Example 3 is a comparison with the two-dimensional direct detection method to verify the advantages of the present application in detection efficiency, especially when processing high-resolution strip images.

[0043] The experimental results show that the two-dimensional direct detection method takes an average of 1.8 seconds per image in straight strip detection, with a detection accuracy of 98.5% and a sensitivity of 97.9%. In curved strip detection, the time consumption increases to 1.8 seconds per image, with a detection accuracy of 97.2% and a sensitivity of 96.5%. Although the two-dimensional direct detection method performs similarly to the present application in terms of accuracy and sensitivity, its detection efficiency is much lower than that of the present application.

[0044] In contrast, the present application takes an average of 0.12 seconds per image in straight strip detection, with a detection accuracy of 98.7% and a sensitivity of 98.4%. In curved strip detection, the average time consumption is 0.13 seconds per image, with a detection accuracy of 97.2% and a sensitivity of 96.5%. The present application significantly outperforms the two-dimensional direct detection method in terms of detection time, while maintaining high levels of detection accuracy and sensitivity.

[0045] The two-dimensional direct detection method directly processes each pixel of the entire image, resulting in a large amount of calculation and significantly prolonged detection time, especially when processing high-resolution images, which may 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.

[0046] The present application introduces one-dimensional fast detection to quickly locate the approximate area of the strip, effectively reducing the calculation range of subsequent processing. On this basis, two-dimensional accurate detection is used to scan each column and extract the boundary of the strip area, thereby achieving a significant improvement in detection efficiency while maintaining detection accuracy and sensitivity. Compared with the traditional two-dimensional direct detection method, the present application significantly shortens the detection time, and maintains high levels of accuracy and sensitivity, fully demonstrating its technical advantages in high-resolution strip image detection.

[0047] The application greatly improves the detection efficiency and accuracy, and significantly reduces the calculation cost and deployment difficulty by combining one-dimensional rapid detection and two-dimensional accurate detection in a phased process. The application is not only suitable for straight strips, but also effectively deals with complex strip forms such as bending and tilting, has stronger practicality and technical advantages, and provides an efficient, accurate and low-cost solution for strip detection tasks.

[0048] Based on the same inventive concept, the application also provides a strip detection device for implementing the above-mentioned strip detection method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more strip detection device embodiments provided below can refer to the limitations of the strip detection method in the foregoing, which will not be described here.

[0049] In an exemplary embodiment, a strip detection device is provided, comprising: a data preprocessing module for data preprocessing of a two-dimensional electrophoresis image; the data preprocessing includes background removal, background removal and normalization; a one-dimensional intensity curve generation module for one-dimensional intensity projection on the preprocessed image to generate a one-dimensional intensity curve; the one-dimensional intensity curve is used to represent the overall intensity distribution of each row of pixels in the preprocessed image; a search interval determination module for detecting peak values of the one-dimensional intensity curve to determine the search interval of the strip; a boundary and center determination module for determining the center curve, upper boundary curve and lower boundary curve of the strip in the search interval corresponding to each strip by using a column-by-column scanning algorithm; a strip positioning module for strip positioning according to the center curve, upper boundary curve and lower boundary curve of the strip.

[0050] The one-dimensional intensity curve generation module and the search interval determination module are one-dimensional rapid detection modules: the intensity distribution curve of the image is extracted to quickly locate the approximate position of the strip and mark the area that may contain the strip. Then, the search interval of the strip is generated according to the intensity change, which efficiently reduces the detection range and provides a clear positioning basis for subsequent accurate calculation; The boundary and center determination module is a two-dimensional accurate detection module, which uses a column-by-column scanning algorithm to accurately detect the center curve and upper and lower boundaries of the strip based on the results of rapid detection. The center point and boundary point of each column are determined by intensity threshold or gradient change standard, which ensures the adaptation to the strip characteristics under different experimental conditions and accurately reflects the shape and boundary position of the strip; The data preprocessing module effectively improves the quality of the image and the distinguishability of the strip signal by automatically removing background noise and reducing the influence of uneven illumination. Through smoothing processing and normalization operation, the contrast and strip features of the image are further optimized, so that they are more prominent in subsequent detection. The module fully considers the characteristics of different experimental images to ensure that the preprocessing results have good adaptability.

[0051] The modular design of the application constructs an automated detection process. Through fast region positioning and image optimization, strip detection can be completed without manual intervention of the user, greatly simplifying the operation steps and improving the user experience.

[0052] Through the efficient synergistic effect among the data preprocessing module, the one-dimensional fast detection module and the two-dimensional accurate detection module, each module is responsible for image optimization, strip positioning and accurate detection, thereby comprehensively surpassing the prior art in terms of efficiency, accuracy, sensitivity and applicability.

[0053] In an exemplary embodiment, a computer device, which can be a server or a terminal, is provided. The computer device includes a processor, a memory, an input / output interface (I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for running the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is configured to exchange information between the processor and external devices. The communication interface of the computer device is configured to communicate with external terminals through a network connection. The computer program is executed by the processor to implement a strip detection method.

[0054] In an exemplary embodiment, a computer device is provided, including a memory and a processor, and the memory stores a computer program. The processor executes the computer program to implement the steps in the above method embodiments.

[0055] In an exemplary embodiment, a computer readable storage medium is provided, which stores a computer program. The computer program is executed by a processor to implement the steps in the above method embodiments.

[0056] In an exemplary embodiment, a computer program product is provided, which includes a computer program. The computer program is executed by a processor to implement the steps in the above method embodiments.

[0057] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant regulations.

[0058] It can be understood by those skilled in the art that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing related hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiments. Any reference to memory, database or other medium used in the embodiments provided by the present 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 storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0059] The database involved in the embodiments provided by the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on blockchain, etc., without being limited thereto. The processor involved in the embodiments provided by the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0060] In the present application, all actions of obtaining signals, information or data are carried out on the premise of complying with the corresponding data protection regulations and policies of the country where the device is located, and on the premise of obtaining authorization from the owner of the corresponding device.

[0061] Any technical features in the above embodiments can be combined, and for the sake of brevity, not all possible combinations are described above, however, it should be understood that the application encompasses all possible combinations of the technical features unless such a combination is not technically possible.

[0062] The principles and implementation manners of the present application are described herein by using specific examples, and the above embodiments are only used to help understand the method of the present application and its core idea; meanwhile, according to the idea of the present application, the specific implementation manners and application scopes will be changed by those skilled in the art. In conclusion, the content of the present specification should not be understood as a limitation of the present application.

Claims

1. A method of strip detection, characterized by, The strip detection method comprises: data preprocessing of the two-dimensional electrophoresis image; the data preprocessing comprises background removal, background removal and normalization; one-dimensional intensity projection is performed on the preprocessed image to generate a one-dimensional intensity curve; the one-dimensional intensity curve is used to represent the overall intensity distribution of each row of pixels in the preprocessed image; peak detection is performed on the one-dimensional intensity curve to determine the search interval of the strip; the center curve, the upper boundary curve and the lower boundary curve of the strip are determined by using the column-by-column scanning algorithm in the search interval corresponding to each strip; the strip is positioned according to the center curve, the upper boundary curve and the lower boundary curve of the strip.

2. The tape detection method according to claim 1, wherein, The data preprocessing of the two-dimensional electrophoresis image comprises: background removal is performed on the two-dimensional electrophoresis image by using a sliding window or a low-pass filter; 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 tape detection method of claim 1, wherein, The one-dimensional intensity curve is generated by performing one-dimensional intensity projection on the preprocessed image, which specifically comprises: one-dimensional intensity projection is performed on the preprocessed image along the row direction; and the one-dimensional intensity curve is generated by summing or averaging the intensity of each row of pixels.

4. The tape detection method of claim 1, wherein, The peak detection is performed on the one-dimensional intensity curve to determine the search interval of the strip, which specifically comprises: the local maximum value algorithm is used to detect the peak value according to the one-dimensional intensity curve; the search interval of the strip is determined by expanding the range upward and downward respectively according to the position of the peak value.

5. The tape detection method of claim 4, wherein, The local maximum value algorithm comprises a sliding window method and a threshold method.

6. The tape detection method of claim 1, wherein, The center curve, the upper boundary curve and the lower boundary curve of the strip are determined by using the column-by-column scanning algorithm in the search interval corresponding to each strip, which specifically comprises: the intensity values of each column of pixel points are compared by using the column-by-column scanning algorithm in the search interval corresponding to each strip to determine the center point of each column; and the center curve of the strip is generated according to the center points of all columns; the center point of each column is the pixel point with the maximum intensity value; the upper boundary point and the lower boundary point of each column are determined by searching the boundary points by using the column-by-column scanning algorithm in combination with the intensity threshold judgment or the gradient change judgment standard, taking the center point of each column as the reference; the upper boundary curve and the lower boundary curve of the strip are determined by connecting the upper boundary points and the lower boundary points of each column respectively.

7. A web inspection apparatus characterized by, The strip detection device comprises: a data preprocessing module for data preprocessing of the two-dimensional electrophoresis image; the data preprocessing comprises background removal, background removal and normalization; a one-dimensional intensity curve generation module for one-dimensional intensity projection on the preprocessed image to generate a one-dimensional intensity curve; the one-dimensional intensity curve is used to represent the overall intensity distribution of each row of pixels in the preprocessed image; a search interval determination module for peak detection on the one-dimensional intensity curve to determine the search interval of the strip; a boundary and center determination module for determining the center curve, the upper boundary curve and the lower boundary curve of the strip by using the column-by-column scanning algorithm in the search interval corresponding to each strip; a strip positioning module for positioning the strip according to the center curve, the upper boundary curve and the lower boundary curve of the strip.

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

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

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

Images