Gas meter detection method and system based on image processing

Abstract

The present invention discloses a gas meter detection method and system based on image processing, which relates to the field of gas meter detection technology, and solves the problem that the original detection method only performs numerical detection, does not identify stolen goods or cracks, and its detection method is not comprehensive. The present invention aims at the situation where there is recognition abnormality, based on the relevant pixel values ​​of the internal points of the corresponding image, performs feature analysis of pixel values, thereby performing feature confirmation on the pixel values ​​with clustering features, so as to confirm the corresponding pixel value interval, and then performs relevant verification of the standard interval for such confirmed pixel value interval, and based on the verification result, confirms whether there is a problem with the appearance of the gas meter. Based on this detection method, not only can the corresponding gas parameters be effectively confirmed, but also whether there is a problem with the gas meter itself can be effectively identified. The detection method is more comprehensive and can obtain better detection effect.

Description

Technical Field

[0001] The present invention relates to the technical field of gas meter detection, and in particular to a gas meter detection method and system based on image processing. Background Art

[0002] As a key device for gas metering, the accuracy of gas meters is directly related to the economic interests of gas companies and users, and also has an important impact on the safety of gas use. Accurate detection can ensure the accuracy of gas meter measurement, prevent disputes caused by measurement errors, and timely discover potential safety hazards of gas meters, such as gas leaks.

[0003] The application with publication number CN118225209A discloses a gas meter detection method and system based on image processing, which relates to the technical field of gas meters. By obtaining the distance information between the gas meter and the surrounding environment, evaluating the ventilation conditions, and monitoring morphological data, image processing technology is used for data acquisition and analysis, thereby realizing the automated processing of installation position evaluation and morphological data analysis, improving efficiency and accuracy, and realizing comprehensive evaluation and safety monitoring of the installation position of the gas meter. It can not only timely discover improper installation positions or modification behaviors, but also provide early warning prompts to ensure the safe and compliant operation of the gas meter. This comprehensive detection method helps to reduce safety risks such as fire and leakage, and ensure the safety of people's lives and property. By judging whether the gas meter is located in the specified area, issuing early warning prompts and notifying the installer to reinstall, standardized management of the installation position of the gas meter is realized.

[0004] When the gas meter is being inspected, it is necessary to perform correlation detection on the gas meter header based on the corresponding camera equipment, and to perform relevant confirmation of the gas parameters based on the corresponding image processing algorithm. However, the original confirmation processing method can only identify parameters based on the corresponding digital features. When the corresponding gas meter header has unexpected situations such as dirt or cracks, numerical errors will occur, resulting in large deviations in the output values. The original detection method only performs numerical detection, and does not identify dirt or cracks. Therefore, the detection method is not comprehensive. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides a gas meter detection method and system based on image processing, which solves the problem that the original detection method only performs numerical detection and does not identify stolen goods or cracks, and its detection method is not comprehensive.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: A gas meter detection method based on image processing comprises the following steps:

[0007] Step 1: Based on the set high-resolution industrial camera, the parameter area of ​​the gas meter is imaged, the parameter area image is confirmed, and the confirmed parameter area image is compared with the set specimen image to determine the gas parameters of the parameter area image. The specific sub-steps are:

[0008] S11, based on the gas parameters confirmed in the previous stage, the associated digital sequence of the gas parameters is used as the starting digital sequence of the sample image;

[0009] S12, identify the pixel values ​​of different points in the parameter area image and calibrate them as D i , where i represents different points, and the pixel values ​​D associated with several groups of points i Perform mean processing to determine the pixel mean D j , and then based on the proposed specimen image, the pixel value X at the same point in the specimen image is confirmed in the same way i And the overall pixel mean X j ;

[0010] Assume i = 1, 2, ..., n, and determine the correlation value Z between the parameter region image and the specimen image, where Then confirm the associated feature L1 of the parameter area image and the associated feature L2 of the specimen image, where in

[0011] use Confirm the assessment value Ncc;

[0012] S13, gradually increasing the gas parameters inside the sample image until the confirmed evaluation value Ncc=1, taking the data column associated with the current sample image as the gas parameters detected this time, and if the evaluation value Ncc still cannot be made to be 1 within the subsequent preset period, performing subsequent analysis;

[0013] Step 2: Identify the gas change value generated in the past stage from the historical completion data, and then confirm the maximum gas value of the next stage based on the gas parameters confirmed in the previous stage, and then identify whether the confirmation process needs to be continuously confirmed, and generate an error signal based on the confirmation result. The specific sub-steps are:

[0014] S21. Confirm the gas change value Cr generated in the past stage from the historical completion data k , where k represents different past stages, and Cr k =Rq1-Rq2, where Rq1 is the gas parameter confirmed in the next stage in the past stage, and Rq2 is the gas parameter in the previous stage in the past stage. k In the above example, the maximum value Cr is selected. k max;

[0015] S22, based on the gas parameter Rs confirmed in the previous stage, identify and determine the calibration value JX, where JX = Rs + Cr k max, and identify the gas parameter Rz finally confirmed at the end of the preset time period in step S13:

[0016] If Rz is less than JX, the corresponding confirmation process is continued, so that the associated digital column in the sample image gradually increases until the associated digital column reaches JX, and whether Ncc=1 exists in the process of its increase is identified. If so, the digital column associated with Ncc=1 is used as the final confirmed gas parameter and displayed. If not, an error signal is generated;

[0017] If Rz ≥ JX, an error signal is directly generated;

[0018] Step 3: Based on the confirmed error signal, the acquired parameter area image is reprocessed, the pixel values ​​at different points in the parameter area image are reanalyzed, the pixel values ​​with the same numerical features are classified, the pixel value intervals of different classifications are confirmed, and the intersection of the corresponding pixel value interval and the preset standard interval is confirmed to determine the abnormal area. The specific method is as follows:

[0019] S31, the pixel values ​​D of different points in the parameter area image i Confirm them one by one, and determine the pixel value sequence according to the pixel value from small to large, starting from pixel value D i The minimum value D i min, and then confirm the values ​​one by one. The proposed range value is Y1, where Y1 is the preset value. Select the pixel value sequence that belongs to [D i min,D i min+Y1] as a set of pixel value intervals, and then reselect the minimum value from the remaining pixel value sequence and determine the corresponding pixel value interval according to the range value Y1, and mark the confirmed different pixel value intervals as J v , where v represents different pixel value intervals;

[0020] S32, different pixel value intervals J v Compare with the preset standard interval, where the standard interval is the preset interval, identify the intersection range of different pixel value intervals and the standard interval, and then determine the proportion value ZB of the intersection range in the corresponding pixel value interval v , ZB v The pixel value interval of <Y3 is marked as abnormal interval, ZB v No calibration is performed on the pixel value interval ≥Y3;

[0021] S33, based on the pixel values ​​of the corresponding points associated with the abnormal interval, marking the image area covered by the corresponding points as the abnormal area;

[0022] Step 4: Determine the associated contour of the abnormal area based on the confirmed abnormal area, then compare the confirmed associated contour with the preset feature contour to identify whether there is a comparison result, and confirm and display the abnormal signal existing in the abnormal area based on the identification result; the specific sub-steps are:

[0023] S41, based on the confirmed abnormal area, identifying the associated contour of the abnormal area, comparing the corresponding associated contour with the preset characteristic contour, and identifying whether there is a characteristic contour that is consistent with the comparison:

[0024] If it exists, the abnormal area is marked as a normal area, a calibration signal is generated for display, and the external operator adjusts the camera angle based on the displayed calibration signal;

[0025] If not, the abnormal area is marked as a problem area, and an appearance abnormality signal is generated for display.

[0026] Preferably, the gas meter detection system based on image processing includes:

[0027] The gas parameter acquisition end acquires an image of the parameter area of ​​the gas meter based on a set high-resolution industrial camera, confirms the parameter area image, compares the confirmed parameter area image with the set specimen image, and determines the gas parameters of the parameter area image;

[0028] The change value analysis end identifies the gas change values ​​generated in the past stages from the historical completion data, and then confirms the maximum gas value of the next stage based on the gas parameters confirmed in the previous stage, and then identifies whether the confirmation process needs to be continuously confirmed, and generates an error signal based on the confirmation result;

[0029] The out-of-region confirmation terminal reprocesses the acquired parameter region image based on the confirmed error signal, reanalyzes the pixel values ​​at different points in the parameter region image, classifies the pixel values ​​with the same numerical features, confirms the pixel value intervals of different classifications, and then confirms the intersection of the corresponding pixel value interval and the preset standard interval to determine the abnormal region;

[0030] The result generating end determines the associated contour about the abnormal area based on the confirmed abnormal area, and then compares the confirmed associated contour with the preset characteristic contour to identify whether there is a comparison result, and confirms and displays the abnormal signal existing in the abnormal area based on the identification result.

[0031] The present invention provides a gas meter detection method and system based on image processing. Compared with the prior art, it has the following beneficial effects:

[0032] The present invention obtains a regional image of the gas meter and compares the pixel values ​​of the obtained regional image with a preset specimen image to determine the corresponding evaluation value. Based on the specific confirmation result of the evaluation value, the corresponding gas parameter is locked. Then, through the numerical value changes in the past stages, it is identified whether the parameters covered by the specimen image are wide enough, so that it can be fully and effectively identified whether it is an abnormal situation or there is a problem with the image itself, and a better recognition effect can be achieved.

[0033] In the case of abnormal recognition, feature analysis of pixel values ​​is performed based on the relevant pixel values ​​of the corresponding internal points of the image, so as to confirm the features of pixel values ​​with clustering features, so as to confirm the corresponding pixel value interval. Subsequently, relevant verification of the standard interval is performed for such confirmed pixel value interval, and based on the verification results, it is confirmed whether there is a problem with the appearance of the gas meter. Based on this detection method, not only the corresponding gas parameters can be effectively confirmed, but also whether there is a problem with the gas meter itself can be effectively identified. The detection method is more comprehensive and can achieve better detection results. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 It is a schematic diagram of the process of the present invention;

[0035] Figure 2 It is a schematic diagram of the principle framework of the present invention. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] First embodiment

[0038] See also Figure 1 , the present application provides a gas meter detection method based on image processing, comprising the following steps:

[0039] Step 1: Based on the set high-resolution industrial camera, the parameter area of ​​the gas meter is imaged and confirmed. The high-resolution industrial camera generally adopts a CCD or CMOS camera, and the image acquisition position of the high-resolution industrial camera is set in advance. The associated image of the digital area of ​​the gas meter can be acquired, and the confirmed parameter area image is compared with the set specimen image to determine the gas parameters of the parameter area image. The specific sub-steps for determination are:

[0040] S11, based on the gas parameters confirmed in the previous stage, the associated digital sequence of the gas parameters is used as the starting digital sequence of the sample image;

[0041] S12, identify the pixel values ​​of different points in the parameter area image and calibrate them as D i , where i represents different points, and the pixel values ​​D associated with several groups of points i Perform mean processing to determine the pixel mean D j , and then based on the proposed specimen image, the pixel value X at the same point in the specimen image is confirmed in the same way i And the overall pixel mean X j ;

[0042] Assume i = 1, 2, ..., n, and determine the correlation value Z between the parameter region image and the specimen image, where Then confirm the associated feature L1 of the parameter area image and the associated feature L2 of the specimen image, where in

[0043] use Confirm the assessment value Ncc;

[0044] S13, gradually increase the gas parameters inside the sample image until the confirmed evaluation value Ncc=1, and use the data column associated with the current sample image as the gas parameters detected this time. If the evaluation value Ncc cannot be made to be 1 within the subsequent preset time period, perform subsequent analysis. The preset time period is set in advance by the operator and is generally 30 minutes.

[0045] Because the collected parameter area images are all related digital parameters, the corresponding specimen images are also corresponding digital parameters. Each different digital parameter has a specific regular pixel value change, so the pixel value can be determined to perform numerical evaluation to determine whether the corresponding specimen image is completely consistent with the collected area image, so as to perform evaluation and determine the gas parameters collected this time;

[0046] Step 2: Identify the gas change value generated in the past stage from the historical completion data, and then confirm the maximum gas value of the next stage based on the gas parameters confirmed in the previous stage, and then identify whether the confirmation process needs to be continuously confirmed, and generate an error signal based on the confirmation result. The specific sub-steps for identification are:

[0047] S21. Confirm the gas change value Cr generated in the past stage from the historical completion data k , where k represents different past stages, and Cr k=Rq1-Rq2, where Rq1 is the gas parameter confirmed in the next stage in the past stage, and Rq2 is the gas parameter in the previous stage in the past stage. k In the above example, the maximum value Cr is selected. k max, where the confirmed past stages are not less than 30 groups;

[0048] S22, based on the gas parameter Rs confirmed in the previous stage, identify and determine the calibration value JX, where JX = Rs + Cr k max, and identify the gas parameter Rz finally confirmed at the end of the preset time period in step S13:

[0049] If Rz is less than JX, the corresponding confirmation process is continued, so that the associated digital column in the sample image gradually increases until the associated digital column reaches JX, and whether Ncc=1 exists in the process of its increase is identified. If so, the digital column associated with Ncc=1 is used as the final confirmed gas parameter and displayed. If not, an error signal is generated;

[0050] If Rz ≥ JX, an error signal is directly generated;

[0051] The situation that the original identification did not obtain accurate numbers is not because the internal digital size of the specimen image is not enough, but because the acquired parameter area image itself may have related problems. There may be inconsistent pixels on the surface of the parameter area image, which may be affected by stolen goods, or other situations, such as cracks, which will cause large differences in the confirmed pixel values, making it impossible to confirm more accurate gas parameters;

[0052] Step 3: Based on the confirmed error signal, the acquired parameter area image is reprocessed, the pixel values ​​at different points in the parameter area image are reanalyzed, the pixel values ​​with the same numerical features are classified, the pixel value intervals of different classifications are confirmed, and the intersection of the corresponding pixel value interval and the preset standard interval is confirmed to determine the abnormal area. The specific method of determination is as follows:

[0053] S31, the pixel values ​​D of different points in the parameter area image i Confirm them one by one, and determine the pixel value sequence according to the pixel value from small to large, starting from pixel value D i The minimum value D i min, and then confirm the values ​​in turn. The proposed range value is Y1, where Y1 is a preset value, and its specific value is determined by the operator based on experience. The pixel value sequence is selected from [D i min,D imin+Y1] as a set of pixel value intervals, and then reselect the minimum value from the remaining pixel value sequence and determine the corresponding pixel value interval according to the range value Y1, and mark the confirmed different pixel value intervals as J v , where v represents different pixel value intervals;

[0054] S32, different pixel value intervals J v Check with the preset standard interval, where the standard interval is a preset interval, which is prepared by the operator in advance based on experience, identify the intersection range of different pixel value intervals and the standard interval, and then determine the proportion value ZB of the intersection range in the corresponding pixel value interval v , ZB v The pixel value interval of <Y3 is calibrated as an abnormal interval, otherwise, it is not calibrated. Specifically, its range ratio is the ratio of the length of the corresponding intersection range in the pixel value interval. The corresponding ratio value can be confirmed based on the corresponding value length;

[0055] S33, based on the pixel values ​​of the corresponding points associated with the abnormal interval, the image area covered by the corresponding points is marked as the abnormal area. Specifically, based on the associated pixel values ​​of the corresponding points, the relevant range area covered by the corresponding points can be identified, so as to lock the corresponding abnormal area. The abnormal area is most likely the corresponding stolen goods or cracks, which causes the relevant errors in the pixel recognition process;

[0056] Step 4: Determine the associated contour of the abnormal area based on the confirmed abnormal area, then compare the confirmed associated contour with the preset feature contour to identify whether there is a comparison result, and confirm and display the abnormal signal in the abnormal area based on the identification result. The specific sub-steps for identification are:

[0057] S41, based on the confirmed abnormal area, identifying the associated contour of the abnormal area, comparing the corresponding associated contour with the preset characteristic contour, and identifying whether there is a characteristic contour that is consistent with the comparison:

[0058] If it exists, the abnormal area is marked as a normal area (which means that the position captured by the camera is not accurate enough, resulting in a large deviation in the pixel value of the captured image, so the corresponding abnormal area belongs to the corresponding normal area), and a calibration signal is generated for display. The external operator adjusts the camera angle based on the displayed calibration signal;

[0059] If it does not exist, this abnormal area will be marked as the problem area, and an appearance abnormality signal will be generated for display. Based on such appearance abnormality signal, external personnel will conduct relevant inspections on the appearance of the gas meter and deal with it in a timely manner. Generally, such abnormal conditions represent problems with its appearance, basically the presence of dirt or related cracks on the surface, etc., so it is an appearance abnormality and a corresponding appearance abnormality signal needs to be generated for relevant display.

[0060] Second embodiment

[0061] The gas meter detection system based on image processing includes:

[0062] The gas parameter acquisition end acquires an image of the parameter area of ​​the gas meter based on a set high-resolution industrial camera, confirms the parameter area image, compares the confirmed parameter area image with the set specimen image, and determines the gas parameters of the parameter area image;

[0063] The change value analysis end identifies the gas change values ​​generated in the past stages from the historical completion data, and then confirms the maximum gas value of the next stage based on the gas parameters confirmed in the previous stage, and then identifies whether the confirmation process needs to be continuously confirmed, and generates an error signal based on the confirmation result;

[0064] The out-of-region confirmation terminal reprocesses the acquired parameter region image based on the confirmed error signal, reanalyzes the pixel values ​​at different points in the parameter region image, classifies the pixel values ​​with the same numerical features, confirms the pixel value intervals of different classifications, and then confirms the intersection of the corresponding pixel value interval and the preset standard interval to determine the abnormal region;

[0065] The result generating end determines the associated contour about the abnormal area based on the confirmed abnormal area, and then compares the confirmed associated contour with the preset characteristic contour to identify whether there is a comparison result, and confirms and displays the abnormal signal existing in the abnormal area based on the identification result.

[0066] Third embodiment

[0067] The specific implementation process of this embodiment includes the entire implementation process of the above two groups of embodiments.

[0068] Some of the data in the above formulas are numerically calculated by removing their dimensions. Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0069] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A gas meter detection method based on image processing, characterized in that: The following steps are involved: Step 1: Acquire an image of the parameter area of ​​the gas meter based on a set high-resolution industrial camera, confirm the parameter area image, compare the confirmed parameter area image with the set specimen image, and determine the gas parameters of the parameter area image; Step 2: Identify the gas change value generated in the past stage from the historical completion data, and then confirm the maximum value of the gas in the next stage based on the gas parameters confirmed in the previous stage, and then identify whether the confirmation process needs to be continuously confirmed, and generate an error signal based on the confirmation result; Step 3: Based on the confirmed error signal, the acquired parameter area image is reprocessed, the pixel values ​​at different points in the parameter area image are reanalyzed, the pixel values ​​with the same numerical features are classified, the pixel value intervals of different classifications are confirmed, and the intersection of the corresponding pixel value interval and the preset standard interval is confirmed to determine the abnormal area; Step 4: Determine the associated contour of the abnormal area based on the confirmed abnormal area, then compare the confirmed associated contour with the preset feature contour to identify whether there is a comparison result, and confirm and display the abnormal signal in the abnormal area based on the identification result. The specific sub-steps are: Based on the confirmed abnormal area, the associated contour of the abnormal area is identified, and the corresponding associated contour is compared with the preset characteristic contour to identify whether there is a characteristic contour that is consistent with the comparison: If it exists, the abnormal area is marked as a normal area, a calibration signal is generated for display, and the external operator adjusts the camera angle based on the displayed calibration signal; If not, the abnormal area is marked as a problem area, and an appearance abnormality signal is generated for display.

2. The gas meter detection method based on image processing according to claim 1, characterized in that: In the step 1, the specific sub-steps for determining the gas parameters of the parameter area image are: S11, based on the gas parameters confirmed in the previous stage, the associated digital sequence of the gas parameters is used as the starting digital sequence of the sample image; S12, identify the pixel values ​​of different points in the parameter area image and calibrate them as D i , where i represents different points, and the pixel values ​​D associated with several groups of points i Perform mean processing to determine the pixel mean D j , and then based on the proposed specimen image, the pixel value X at the same point in the specimen image is confirmed in the same way i And the overall pixel mean X j ; Assume i = 1, 2, ..., n, and determine the correlation value Z between the parameter region image and the specimen image, where Then confirm the associated feature L1 of the parameter area image and the associated feature L2 of the specimen image, where in use Confirm the assessment value Ncc; S13, gradually increase the gas parameters inside the sample image until the confirmed evaluation value Ncc=1, and use the data column associated with the current sample image as the gas parameters detected this time. If the evaluation value Ncc cannot be made to be 1 within the subsequent preset time period, perform subsequent analysis.

3. The gas meter detection method based on image processing according to claim 2 is characterized in that: In step 2, the specific sub-steps for identifying whether the confirmation process needs to be further confirmed are: S21. Confirm the gas change value Cr generated in the past stage from the historical completion data k , where k represents different past stages, and Cr k =Rq1-Rq2, where Rq1 is the gas parameter confirmed in the next stage in the past stage, and Rq2 is the gas parameter in the previous stage in the past stage. k In the above example, the maximum value Cr is selected. k max; S22, based on the gas parameter Rs confirmed in the previous stage, identify and determine the calibration value JX, where JX = Rs + Cr k max, and identify the gas parameter Rz finally confirmed at the end of the preset time period in step S13: If Rz is less than JX, the corresponding confirmation process is continued, so that the associated digital column in the specimen image gradually increases until the associated digital column reaches JX, and it is identified whether Ncc=1 exists during the increase process. If so, the digital column associated with Ncc=1 is used as the final confirmed gas parameter and displayed. If not, an error signal is generated.

4. The gas meter detection method based on image processing according to claim 3 is characterized in that: In step S22, if Rz≥JX, an error signal is directly generated.

5. The gas meter detection method based on image processing according to claim 3 is characterized in that: In step 3, the specific method of determining the abnormal area is: S31, the pixel values ​​D of different points in the parameter area image i Confirm them one by one, and determine the pixel value sequence according to the pixel value from small to large, starting from pixel value D i The minimum value D i min, and then confirm the values ​​one by one. The proposed range value is Y1, where Y1 is the preset value. Select the pixel value sequence that belongs to [D i min,D i min+Y1] as a set of pixel value intervals, and then reselect the minimum value from the remaining pixel value sequence and determine the corresponding pixel value interval according to the range value Y1, and mark the confirmed different pixel value intervals as J v , where v represents different pixel value intervals; S32, different pixel value intervals J v Compare with the preset standard interval, where the standard interval is the preset interval, identify the intersection range of different pixel value intervals and the standard interval, and then determine the proportion value ZB of the intersection range in the corresponding pixel value interval v , ZB v The pixel value interval <Y3 is marked as an abnormal interval; S33: Based on the pixel values ​​of the corresponding points associated with the abnormal interval, mark the image area covered by the corresponding points as the abnormal area.

6. The gas meter detection method based on image processing according to claim 5 is characterized in that: In step S32, ZB v No calibration is performed on the pixel value range ≥Y3.

7. A gas meter detection system based on image processing, the detection system operates according to the gas meter detection method based on image processing according to any one of claims 1 to 6, characterized in that: include: The gas parameter acquisition end acquires an image of the parameter area of ​​the gas meter based on a set high-resolution industrial camera, confirms the parameter area image, compares the confirmed parameter area image with the set specimen image, and determines the gas parameters of the parameter area image; The change value analysis end identifies the gas change values ​​generated in the past stages from the historical completion data, and then confirms the maximum gas value of the next stage based on the gas parameters confirmed in the previous stage, and then identifies whether the confirmation process needs to be continuously confirmed, and generates an error signal based on the confirmation result; The out-of-region confirmation terminal reprocesses the acquired parameter region image based on the confirmed error signal, reanalyzes the pixel values ​​at different points in the parameter region image, classifies the pixel values ​​with the same numerical features, confirms the pixel value intervals of different classifications, and then confirms the intersection of the corresponding pixel value interval and the preset standard interval to determine the abnormal region; The result generating end determines the associated contour about the abnormal area based on the confirmed abnormal area, and then compares the confirmed associated contour with the preset characteristic contour to identify whether there is a comparison result, and confirms and displays the abnormal signal existing in the abnormal area based on the identification result.

Images