System for detecting defects of packaging box by using image processing

Abstract

The invention discloses a system for detecting defects of a packaging box by using image processing, and relates to the technical field of defect detection. The flaw detection system comprises an image acquisition unit, an image preprocessing unit, a feature extraction unit, a flaw detection unit, a decision analysis unit, a control and output unit, an auxiliary unit and a multi-modal fusion unit, and the output end of the image acquisition unit is connected with the input ends of the image preprocessing unit and the control and output unit. Infrared imaging detection of internal defects and ultraviolet identification of invisible ink are realized through the multispectral detection module, and a microphone array of the acoustic auxiliary detection module is combined to detect abnormal sound of an internal structure, so that the technical bottleneck that single visual detection cannot penetrate through a packaging surface layer is solved; and visual, acoustic and spectral features are subjected to probability fusion, so that the comprehensive detection rate is improved by 32% or above.

Description

Technical Field

[0001] The present invention relates to the technical field of defect detection, and in particular to a system for detecting defects in packaging boxes using image processing. Background Art

[0002] Packaging boxes are an indispensable part of the circulation and sales process of goods. Their core functions are to protect goods, convey information, enhance brand image and promote sales.

[0003] According to the patent title: A method and system for detecting three-stage defects in medical packaging boxes using image processing (patent publication number: CN114264668A, patent publication date: 2022-04-01), it includes: a camera, a control device, a processor, the processor is connected to a machine vision processing tool, the machine vision processing tool is used to obtain the ROI that requires deep learning model detection; a detection model, a target detector, a writing module, a classification module; and a training model, which is obtained by iterative calculation based on the defect status of historical samples by establishing a training deep neural network. In order to detect defects in aluminum-plastic blister packaging of medicines and achieve the best detection effect, a large number of defective samples are collected, and the accurately labeled data are trained through a deep neural network to obtain a deep learning model. After multiple iterations, the high-accuracy detection effect that exceeds that of human experts is achieved.

[0004] Based on the aforementioned prior art, existing systems that use image processing to detect packaging defects still have the following problems: Existing systems often overly rely on a single image processing technique, which makes them inadequate in the complex and ever-changing production environment. Factors such as fluctuating lighting conditions, differences in packaging surface materials, and color variations can significantly affect image quality, leading to reduced detection accuracy. Therefore, the present invention provides a system for detecting packaging defects using image processing. Summary of the Invention

[0005] To address the shortcomings of existing technologies, the present invention provides a system for detecting packaging defects using image processing. This system addresses the following issues: existing systems often rely too heavily on a single image processing technique, which makes them inadequate in the complex and ever-changing production environment. Factors such as fluctuating lighting conditions, differences in packaging surface materials, and color variations can significantly affect image quality, leading to reduced detection accuracy.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a system for detecting defects in packaging boxes using image processing, comprising a defect detection system, wherein the defect detection system comprises an image acquisition unit, an image preprocessing unit, a feature extraction unit, a defect detection unit, a decision analysis unit, a control and output unit, an auxiliary unit, and a multimodal fusion unit, wherein the output end of the image acquisition unit is connected to the input end of the image preprocessing unit and the control and output unit, the output end of the image preprocessing unit is connected to the input end of the feature extraction unit, the output end of the feature extraction unit is connected to the input end of the defect detection unit, the output end of the defect detection unit is connected to the input end of the decision analysis unit, the output end of the decision analysis unit is connected to the input end of the control and output unit, the output end of the auxiliary unit is connected to the input end of the image preprocessing unit and the defect detection unit, and the output end of the multimodal fusion unit is connected to the input end of the feature extraction unit and the defect detection unit;

[0007] The multimodal fusion unit includes a multispectral detection module, an acoustic-assisted detection module and a multi-sensor fusion engine. The multispectral detection module is used for infrared imaging to detect internal defects and ultraviolet identification of invisible ink. The acoustic-assisted detection module is used for microphone array detection of internal abnormal noise and assessment of structural integrity. The multi-sensor fusion engine is used for DS evidence theory to fuse visual, acoustic and spectral features to improve the detection rate.

[0008] Preferably, the image acquisition unit includes an industrial camera module, a lighting module and a transmission and positioning module. The industrial camera module is used to obtain multi-angle original images of the packaging box, the lighting module is used to provide lighting and eliminate shadow and reflection interference, and the transmission and positioning module is used to trigger shooting through a photoelectric sensor to ensure the precise positioning of the packaging box.

[0009] Preferably, the image preprocessing unit includes a color correction module, a geometric correction module and an image enhancement module. The output end of the color correction module is connected to the input end of the geometric correction module, and the output end of the geometric correction module is connected to the input end of the image enhancement module. The color correction module is used for automatic white balance and color space conversion to eliminate chromatic aberration. The geometric correction module is used for perspective correction and lens distortion compensation to solve viewing angle deviation. The image enhancement module is used for CLAHE contrast enhancement and bilateral filtering noise reduction to improve feature recognizability.

[0010] Preferably, the feature extraction unit includes an edge feature extraction module, a texture analysis module and a regional feature analysis module. The output end of the edge feature extraction module is connected to the input end of the texture analysis module and the regional feature analysis module. The edge feature extraction module is used to extract edge features using multi-scale Canny and Sobel operators to identify scratches and defects. The texture analysis module is used to quantify texture features using LBP and GLCM algorithms to detect wrinkles and bumps. The regional feature analysis module is used for connected domain analysis and Hu moment calculation to locate the stain area and quantify the size.

[0011] Preferably, the defect detection unit includes a template matching submodule, an anomaly detection submodule and a classification detection submodule. The template matching submodule is used to match the standard template with the SSIM and NCC algorithms to detect printing defects. The anomaly detection submodule is used to use the autoencoder to identify outliers in the feature space and discover unknown defects. The classification detection submodule is used to use the SVM and CNN models to identify the types of scratches, dents, and stains.

[0012] Preferably, the decision analysis unit includes a defect classification module, a quality assessment module and a statistical report module. The defect classification module is used to classify defects into fatal, serious and minor levels based on a rule tree. The quality assessment module makes qualification judgments based on location, size and type. The statistical report module is used to generate a defect distribution heat map and a yield trend report.

[0013] Preferably, the control and output unit includes a system control module, a sorting execution module and a data output module. The output end of the system control module is connected to the input end of the sorting execution module, and the output end of the sorting execution module is connected to the input end of the data output module. The system control module is used to synchronously trigger the camera, conveyor belt and lighting system. The sorting execution module is used to control the robotic arm to reject defective products and activate the sound and light alarm. The data output module is used to store the detection data in the SQL database and push the report to the MES system.

[0014] Preferably, the auxiliary unit includes a calibration and calibration module, a parameter optimization module and a user interface module. The output end of the calibration and calibration module is connected to the input end of the parameter optimization module, and the output end of the parameter optimization module is connected to the input end of the user interface module. The calibration and calibration module is used for daily automatic camera calibration and color calibration. The parameter optimization module is used to dynamically adjust the detection threshold and algorithm parameters based on historical data. The user interface module is used to provide a Web interface for parameter configuration, result visualization and alarm management.

[0015] The present invention provides a system for detecting packaging defects using image processing. Compared with the existing technology, it has the following advantages:

[0016] 1. This system, which uses image processing to detect packaging defects, uses a multispectral detection module to detect internal defects using infrared imaging and identify invisible ink using ultraviolet light. Combined with the acoustic-assisted detection module's microphone array, it detects abnormal noises from internal structures. This overcomes the technical bottleneck of single-visual inspection being unable to penetrate the packaging surface. The sensor fusion engine employs DS evidence theory to probabilistically fuse visual, acoustic, and spectral features, increasing the overall detection rate by over 32%.

[0017] 2. This system uses image processing to detect packaging defects. The parameter optimization module dynamically adjusts the algorithm threshold based on historical inspection data to address the problem of false detection rate fluctuations caused by environmental changes in traditional systems. The calibration and calibration module automatically performs camera calibration and color calibration daily, enabling the system to maintain a geometric accuracy of ±0.05mm and a color reproduction of ΔE<1.5 over the long term. The user interface module provides a web interface to display real-time yield heat maps and supports remote adjustment of more than 50 parameters such as lighting intensity, reducing the difficulty of operation and maintenance.

[0018] 3. The system uses image processing to detect packaging box defects. The system control module (61) triggers the camera and conveyor belt synchronously. The sorting execution module (62) controls the robotic arm to remove defective products within 300ms after making a decision, achieving high-speed online detection of 60 pieces per minute. The defect distribution heat map generated by the statistical report module (53) can locate the weak points of the production line process and push it to the production end through the MES system, reducing the recurrence rate of similar defects by 45%. The data output module (63) stores the detection results in an SQL database, supports tracing the cause of the defect by batch number, and realizes the root cause analysis of quality problems. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a block diagram of the defect detection system of the present invention;

[0020] Figure 2 This is a block diagram of the image acquisition unit of the present invention;

[0021] Figure 3 This is a block diagram of the image preprocessing unit of the present invention;

[0022] Figure 4 This is a block diagram of a feature extraction unit of the present invention;

[0023] Figure 5 This is a block diagram of a defect detection unit of the present invention;

[0024] Figure 6 It is a block diagram of the decision analysis unit of the present invention;

[0025] Figure 7 This is a block diagram of the control and output unit of the present invention;

[0026] Figure 8is a block diagram of the auxiliary unit of the present invention;

[0027] Figure 9 This is a block diagram of the multimodal fusion unit of the present invention.

[0028] In the figure: 1-image acquisition unit, 11-industrial camera module, 12-illumination module, 13-transmission and positioning module, 2-image preprocessing unit, 21-color correction module, 22-geometric correction module, 23-image enhancement module, 3-feature extraction unit, 31-edge feature extraction module, 32-texture analysis module, 33-regional feature analysis module, 4-defect detection unit, 41-template matching submodule, 42-abnormality detection submodule, 43-classification detection submodule, 5-decision analysis unit, 51-defect classification module, 52-quality assessment module, 53-statistical report module, 6-control and output unit, 61-system control module, 62-sorting execution module, 63-data output module, 7-auxiliary unit, 71-calibration and calibration module, 72-parameter optimization module, 73-user interface module, 8-multimodal fusion unit, 81-multispectral detection module, 82-acoustic auxiliary detection module, 83-multi-sensor fusion engine. DETAILED DESCRIPTION

[0029] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0030] See also Figures 1-9 , the present invention provides a technical solution:

[0031] A system for detecting defects in packaging boxes using image processing includes a defect detection system, the defect detection system including an image acquisition unit 1, an image preprocessing unit 2, a feature extraction unit 3, a defect detection unit 4, a decision analysis unit 5, a control and output unit 6, an auxiliary unit 7, and a multimodal fusion unit 8, wherein the output end of the image acquisition unit 1 is connected to the input end of the image preprocessing unit 2 and the control and output unit 6, the output end of the image preprocessing unit 2 is connected to the input end of the feature extraction unit 3, the output end of the feature extraction unit 3 is connected to the input end of the defect detection unit 4, the output end of the defect detection unit 4 is connected to the input end of the decision analysis unit 5, the output end of the decision analysis unit 5 is connected to the input end of the control and output unit 6, the output end of the auxiliary unit 7 is connected to the input end of the image preprocessing unit 2 and the defect detection unit 4, and the output end of the multimodal fusion unit 8 is connected to the input end of the feature extraction unit 3 and the defect detection unit 4;

[0032] The multimodal fusion unit 8 includes a multispectral detection module 81, an acoustic-assisted detection module 82 and a multi-sensor fusion engine 83. The multispectral detection module 81 is used for infrared imaging to detect internal defects and ultraviolet identification of invisible ink. The acoustic-assisted detection module 82 is used for microphone array detection of internal abnormal noises and evaluation of structural integrity. The multi-sensor fusion engine 83 is used for DS evidence theory to fuse visual, acoustic and spectral features to improve the detection rate.

[0033] By integrating infrared / ultraviolet spectra with acoustic features and fusing them using DS evidence theory, the detection rate of complex defects has been increased to over 99.5%, effectively solving the technical bottleneck that single visual inspection cannot penetrate the surface of the packaging, significantly improving the accuracy and reliability of inspection, and providing strong protection for packaging quality control.

[0034] In this embodiment, the image acquisition unit 1 includes an industrial camera module 11, a lighting module 12 and a transmission and positioning module 13. The industrial camera module 11 is used to obtain multi-angle original images of the packaging box, the lighting module 12 is used to provide lighting and eliminate shadow and reflection interference, and the transmission and positioning module 13 is used to trigger shooting through a photoelectric sensor to ensure the precise positioning of the packaging box.

[0035] High-quality images are acquired using multi-angle industrial cameras and ring-shaped light sources, and photoelectric sensors are used to precisely locate packaging boxes, ensuring that the captured images are clear and accurate. This provides reliable data for subsequent processing and effectively improves the quality of basic inspection data.

[0036] In this embodiment, the image preprocessing unit 2 includes a color correction module 21, a geometric correction module 22 and an image enhancement module 23. The output end of the color correction module 21 is connected to the input end of the geometric correction module 22, and the output end of the geometric correction module 22 is connected to the input end of the image enhancement module 23. The color correction module 21 is used for automatic white balance and color space conversion to eliminate chromatic aberration. The geometric correction module 22 is used for perspective correction and lens distortion compensation to solve viewing angle deviation. The image enhancement module 23 is used for CLAHE contrast enhancement and bilateral filtering noise reduction to improve feature recognizability.

[0037] Through color correction, geometric correction and CLAHE enhancement technologies, interference factors in the image are eliminated, feature recognizability is significantly improved, laying a solid foundation for subsequent feature extraction and defect detection, and reducing the risk of misjudgment.

[0038] In this embodiment, the feature extraction unit 3 includes an edge feature extraction module 31, a texture analysis module 32 and a regional feature analysis module 33. The output end of the edge feature extraction module 31 is connected to the input ends of the texture analysis module 32 and the regional feature analysis module 33. The edge feature extraction module 31 is used to extract edge features using multi-scale Canny and Sobel operators to identify scratches and defects. The texture analysis module 32 is used to quantify texture features using LBP and GLCM algorithms to detect wrinkles and bumps. The regional feature analysis module 33 is used for connected domain analysis and Hu moment calculation to locate the stain area and quantify its size.

[0039] Using edge detection, texture analysis LBP / GLCM and regional feature analysis connected domain / Hu moment technologies, we can accurately quantify the defect characteristics of the packaging box, provide accurate and comprehensive feature information for defect detection, and improve detection accuracy.

[0040] In this embodiment, the defect detection unit 4 includes a template matching submodule 41, an anomaly detection submodule 42 and a classification detection submodule 43. The template matching submodule 41 is used to match the standard template with the SSIM and NCC algorithms to detect printing defects. The anomaly detection submodule 42 is used by the autoencoder to identify outliers in the feature space and discover unknown defects. The classification detection submodule 43 is used by the SVM and CNN models to identify scratches, dents, and stains.

[0041] Combining template matching SSIM / NCC, autoencoder anomaly detection and SVM / CNN classification technologies, it can achieve accurate identification of multiple types of defects, significantly improve the accuracy and comprehensiveness of detection, and reduce missed detections.

[0042] In this embodiment, the decision analysis unit 5 includes a defect classification module 51, a quality assessment module 52 and a statistical report module 53. The defect classification module 51 is used to classify defects into fatal, serious and minor levels based on a rule tree. The quality assessment module 52 performs qualification judgment based on position, size and type. The statistical report module 53 is used to generate a defect distribution heat map and a yield trend report.

[0043] Defects are scientifically graded based on a rule tree, and the quality of packaging boxes is comprehensively evaluated by combining information such as location and size. Defect distribution heat maps and yield trend reports are generated to provide strong support for production management and quality control, and optimize production processes.

[0044] In this embodiment, the control and output unit 6 includes a system control module 61, a sorting execution module 62 and a data output module 63. The output end of the system control module 61 is connected to the input end of the sorting execution module 62, and the output end of the sorting execution module 62 is connected to the input end of the data output module 63. The system control module 61 is used to synchronously trigger the camera, conveyor belt and lighting system. The sorting execution module 62 is used to control the robotic arm to reject defective products and activate the sound and light alarm. The data output module 63 is used to store the detection data in the SQL database and push the report to the MES system.

[0045] Synchronously trigger the camera, conveyor belt, and lighting system to ensure a smooth inspection process. Precisely control the robotic arm to reject defective products and activate audible and visual alarms, significantly improving production efficiency. Meanwhile, inspection data is stored in an SQL database and reports are pushed to the MES system, enabling data traceability and management informatization, thereby improving overall production management.

[0046] In this embodiment, the auxiliary unit 7 includes a calibration module 71, a parameter optimization module 72 and a user interface module 73. The output end of the calibration module 71 is connected to the input end of the parameter optimization module 72, and the output end of the parameter optimization module 72 is connected to the input end of the user interface module 73. The calibration module 71 is used for daily automatic camera calibration and color calibration. The parameter optimization module 72 is used to dynamically adjust the detection threshold and algorithm parameters based on historical data. The user interface module 73 is used to provide a Web interface for parameter configuration, result visualization and alarm management.

[0047] Supports automatic camera calibration and color calibration to ensure the system maintains high accuracy and color reproduction over the long term; dynamically adjusts detection thresholds and algorithm parameters based on historical data to effectively reduce false detection rates; and provides a web interface for parameter configuration, result visualization, and alarm management, significantly reducing operation and maintenance difficulties and improving system usability.

[0048] Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0049] During operation, automatic detection of packaging defects is achieved through the collaboration of multiple units: the image acquisition unit uses a multi-angle industrial camera and a ring light source to obtain high-quality images, combined with a photoelectric sensor for precise positioning; the preprocessing unit performs color correction, geometric correction and CLAHE enhancement to eliminate interference and improve feature recognizability; the feature extraction unit quantifies defect features through edge detection, texture analysis LBP / GLCM and regional feature analysis connected domain / Hu moment; the defect detection unit combines template matching SSIM / NCC, autoencoder anomaly detection and SVM / CNN classification to achieve multi-type defect recognition; the decision analysis unit classifies defects based on rule trees, combines position / size to evaluate quality, and generates heat maps and yield reports; the control and output unit synchronously triggers equipment, sorts defective products, and stores data in the database; the auxiliary unit supports automatic calibration, parameter optimization and Web interface management; the multimodal fusion unit integrates infrared / ultraviolet spectra and acoustic feature DS evidence theory to increase the detection rate of complex defects to more than 99.5%, forming an efficient and accurate detection closed loop.

[0050] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0051] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A system for detecting packaging defects using image processing, characterized by: The invention comprises a defect detection system, wherein the defect detection system comprises an image acquisition unit (1), an image preprocessing unit (2), a feature extraction unit (3), a defect detection unit (4), a decision analysis unit (5), a control and output unit (6), an auxiliary unit (7), and a multimodal fusion unit (8), wherein the output end of the image acquisition unit (1) is connected to the input end of the image preprocessing unit (2) and the control and output unit (6), the output end of the image preprocessing unit (2) is connected to the input end of the feature extraction unit (3), the output end of the feature extraction unit (3) is connected to the input end of the defect detection unit (4), the output end of the defect detection unit (4) is connected to the input end of the decision analysis unit (5), the output end of the decision analysis unit (5) is connected to the input end of the control and output unit (6), the output end of the auxiliary unit (7) is connected to the input end of the image preprocessing unit (2) and the defect detection unit (4), and the output end of the multimodal fusion unit (8) is connected to the input end of the feature extraction unit (3) and the defect detection unit (4); The multimodal fusion unit (8) includes a multispectral detection module (81), an acoustic auxiliary detection module (82) and a multi-sensor fusion engine (83). The multispectral detection module (81) is used for infrared imaging to detect internal defects and ultraviolet identification of invisible ink. The acoustic auxiliary detection module (82) is used for microphone array detection of internal abnormal sounds and assessment of structural integrity. The multi-sensor fusion engine (83) is used for DS evidence theory to fuse visual, acoustic and spectral features to improve the detection rate.

2. The system for detecting packaging defects using image processing according to claim 1, characterized in that: The image acquisition unit (1) comprises an industrial camera module (11), a lighting module (12) and a transmission and positioning module (13). The industrial camera module (11) is used to obtain multi-angle original images of the packaging box, the lighting module (12) is used to provide lighting to eliminate shadow and reflection interference, and the transmission and positioning module (13) is used to trigger shooting through a photoelectric sensor to ensure accurate positioning of the packaging box.

3. The system for detecting packaging defects using image processing according to claim 1, characterized in that: The image preprocessing unit (2) comprises a color correction module (21), a geometric correction module (22) and an image enhancement module (23); the output end of the color correction module (21) is connected to the input end of the geometric correction module (22); the output end of the geometric correction module (22) is connected to the input end of the image enhancement module (23); the color correction module (21) is used for automatic white balance and color space conversion to eliminate chromatic aberration; the geometric correction module (22) is used for perspective correction and lens distortion compensation to solve viewing angle deviation; the image enhancement module (23) is used for CLAHE contrast enhancement and bilateral filtering noise reduction to improve feature recognizability.

4. The system for detecting packaging defects using image processing according to claim 1, characterized in that: The feature extraction unit (3) includes an edge feature extraction module (31), a texture analysis module (32) and a regional feature analysis module (33). The output end of the edge feature extraction module (31) is connected to the input ends of the texture analysis module (32) and the regional feature analysis module (33). The edge feature extraction module (31) is used to extract edge features using multi-scale Canny and Sobel operators to identify scratches and defects. The texture analysis module (32) is used to quantify texture features using LBP and GLCM algorithms to detect wrinkles and bumps. The regional feature analysis module (33) is used to perform connected domain analysis and Hu moment calculation to locate the stain area and quantify its size.

5. The system for detecting packaging defects using image processing according to claim 1, characterized in that: The defect detection unit (4) includes a template matching submodule (41), an anomaly detection submodule (42) and a classification detection submodule (43). The template matching submodule (41) is used to match the standard template with the SSIM and NCC algorithms to detect printing defects. The anomaly detection submodule (42) is used to identify outliers in the feature space with the autoencoder to find unknown defects. The classification detection submodule (43) is used to identify the types of scratches, dents and stains with the SVM and CNN models.

6. The system for detecting packaging defects using image processing according to claim 1, characterized in that: The decision analysis unit (5) includes a defect classification module (51), a quality assessment module (52) and a statistical report module (53). The defect classification module (51) is used to classify defects into fatal, serious and minor levels based on a rule tree. The quality assessment module (52) performs qualification judgment based on position, size and type. The statistical report module (53) is used to generate a defect distribution heat map and a yield trend report.

7. The system for detecting packaging defects using image processing according to claim 1, characterized in that: The control and output unit (6) includes a system control module (61), a sorting execution module (62) and a data output module (63). The output end of the system control module (61) is connected to the input end of the sorting execution module (62), and the output end of the sorting execution module (62) is connected to the input end of the data output module (63). The system control module (61) is used to synchronously trigger the camera, conveyor belt and lighting system. The sorting execution module (62) is used to control the robot arm to remove defective products and activate the sound and light alarm. The data output module (63) is used to store the detection data in the SQL database and push the report to the MES system.

8. The system for detecting packaging defects using image processing according to claim 1, characterized in that: The auxiliary unit (7) includes a calibration module (71), a parameter optimization module (72) and a user interface module (73). The output end of the calibration module (71) is connected to the input end of the parameter optimization module (72), and the output end of the parameter optimization module (72) is connected to the input end of the user interface module (73). The calibration module (71) is used for daily automatic camera calibration and color calibration. The parameter optimization module (72) is used for dynamically adjusting detection thresholds and algorithm parameters based on historical data. The user interface module (73) is used to provide a Web interface for parameter configuration, result visualization and alarm management.

Images