Image processing methods and devices for 5S management

Abstract

This specification provides an image processing method and apparatus for 5S management. The image processing method for 5S management includes: acquiring an image to be processed taken of a target area; identifying and locating at least one target object from the image using target detection technology; extracting local features of each target object from the image area where each target object is located; determining the degree of satisfaction between each target object and the corresponding 5S management evaluation rule based on the local features of each target object; summarizing the obtained satisfaction levels to generate a first score at the object level; and generating a 5S management evaluation score for the image to be processed based on the first score.

Description

Technical Field

[0001] The embodiments in this specification generally relate to the field of computer technology, and in particular to image processing methods and apparatus for 5S management. Background Technology

[0002] Currently, image processing technology is gradually being widely applied in various fields. For manufacturing enterprises such as chemical companies, 5S management, as a widely recognized on-site management method, includes five aspects: sorting (Seiri), straightening (Seiton), sweeping (Seiso), standardizing (Seiketsu), and sustaining (Shitsuke). It is crucial for ensuring production safety, improving production efficiency, and guaranteeing product quality.

[0003] Traditional 5S management methods rely primarily on manual inspections and assessments, which have numerous limitations. For example, manual inspections are inefficient, prone to omissions, and susceptible to subjective inaccuracies; furthermore, they struggle to provide comprehensive and timely monitoring for large-scale chemical production areas. Therefore, developing an image processing technology to specifically improve the efficiency of 5S management and reduce its costs is of significant practical importance. Summary of the Invention

[0004] In view of the above, embodiments of this specification provide an image processing method and apparatus for 5S management. Using this image processing scheme, a first score at the object level is obtained by measuring the degree of satisfaction between extracted local features and corresponding 5S management evaluation rules, thereby providing a reference for the final 5S management evaluation score. This scheme can analyze the degree of conformity between the image to be processed and the corresponding 5S management evaluation rules from the perspective of image understanding, thus making it suitable for scenarios without corresponding standard images and significantly reducing the storage requirements of standard images.

[0005] According to one aspect of an embodiment of this specification, an image processing method for 5S management is provided, comprising: acquiring an image to be processed taken of a target area; identifying and locating at least one target object from the image to be processed using target detection technology; extracting local features of each target object from the image area where each target object is located; determining the degree of satisfaction between each target object and the corresponding 5S management evaluation rule based on the local features of each target object; summarizing the obtained satisfaction degrees to generate a first score at the object level; and generating a 5S management evaluation score for the image to be processed based on the first score.

[0006] According to another aspect of the embodiments of this specification, an image processing apparatus for 5S management is provided, comprising: an image acquisition unit configured to acquire an image to be processed taken of a target area; a target detection unit configured to identify and locate at least one target object from the image to be processed using target detection technology; a feature extraction unit configured to extract local features of each target object from the image area where each target object is located; a first score determination unit configured to determine the degree of satisfaction between each target object and the corresponding 5S management evaluation rule based on the local features of each target object; summarizing the obtained satisfaction degrees to generate a first score at the object level; and a final score generation unit configured to generate a 5S management evaluation score of the image to be processed based on the first score.

[0007] According to another aspect of the embodiments of this specification, an image processing apparatus for 5S management is provided, comprising: at least one processor, and a memory coupled to the at least one processor, the memory storing instructions that, when executed by the at least one processor, cause the at least one processor to perform the image processing method for 5S management as described above.

[0008] According to another aspect of the embodiments of this specification, a computer-readable storage medium is provided that stores a computer program, which, when executed by a processor, implements the image processing method for 5S management as described above.

[0009] According to another aspect of the embodiments of this specification, a computer program product is provided, including a computer program that is executed by a processor to implement the image processing method for 5S management as described above. Attached Figure Description

[0010] A further understanding of the nature and advantages of this specification can be achieved by referring to the following figures. In the figures, similar components or features may have the same reference numerals.

[0011] Figure 1 An exemplary architecture of an image processing method and apparatus for 5S management according to embodiments of this specification is shown.

[0012] Figure 2 A flowchart illustrating an example of an image processing method for 5S management according to an embodiment of this specification is shown.

[0013] Figure 3 A schematic diagram illustrating an example of the process for generating 5S management evaluation rules according to an embodiment of this specification is shown.

[0014] Figure 4A flowchart illustrating yet another example of the process for generating 5S management evaluation rules according to an embodiment of this specification is shown.

[0015] Figure 5 A flowchart is shown as yet another example of an image processing method for 5S management according to an embodiment of this specification.

[0016] Figure 6 A flowchart illustrating an example of a process for determining the global similarity between an image to be processed and a corresponding reference image according to an embodiment of this specification is provided.

[0017] Figure 7 A flowchart illustrating an example of the process for generating 5S management evaluation scores according to an embodiment of this specification is shown.

[0018] Figure 8 A block diagram of an example image processing apparatus for 5S management according to an embodiment of this specification is shown.

[0019] Figure 9 A schematic diagram of an example image processing apparatus for 5S management according to an embodiment of this specification is shown. Detailed Implementation

[0020] The subject matter described herein will be discussed below with reference to exemplary embodiments. It should be understood that these embodiments are discussed merely to enable those skilled in the art to better understand and implement the subject matter described herein, and are not intended to limit the scope, applicability, or examples set forth in the claims. The function and arrangement of the elements discussed may be changed without departing from the scope of the embodiments described herein. Various processes or components may be omitted, substituted, or added as needed in the various examples. Furthermore, features described in some examples may be combined in other examples.

[0021] As used herein, the term "comprising" and its variations are open terms meaning "including but not limited to". The term "based on" means "at least partially based on". The terms "one embodiment" and "an embodiment" mean "at least one embodiment". The term "another embodiment" means "at least one other embodiment". The terms "first", "second", etc., may refer to different or the same objects. Other definitions, whether explicit or implicit, may be included below. Unless explicitly indicated by the context, the definition of a term shall remain consistent throughout the specification.

[0022] The flowcharts used in this specification illustrate operations implemented according to some embodiments of this specification. It should be clearly understood that the operations in the flowcharts may not be implemented in a sequential order. Instead, the operations may be implemented in reverse order or simultaneously. Furthermore, one or more additional operations may be added to the flowcharts. One or more operations may be removed from the flowcharts.

[0023] Therefore, embodiments of this specification propose an image processing scheme for 5S management. In this scheme, a first score at the object level is obtained by assessing the degree of conformity between extracted local features and corresponding 5S management evaluation rules, thus providing a reference for the final 5S management evaluation score. This scheme can analyze the conformity between the image to be processed and the corresponding 5S management evaluation rules from an image understanding perspective, making it suitable for scenarios without corresponding standard images and significantly reducing the storage requirements of standard images.

[0024] The image processing method and apparatus for 5S management according to embodiments of this specification will now be described in detail with reference to the accompanying drawings.

[0025] Figure 1 An exemplary architecture 100 for an image processing method and apparatus for 5S management according to embodiments of this specification is shown.

[0026] exist Figure 1 In this context, network 110 is used to interconnect terminal device 120 and application server 130.

[0027] Network 110 can be any type of network capable of interconnecting network entities. Network 110 can be a single network or a combination of various networks. In terms of coverage, network 110 can be a local area network (LAN), a wide area network (WAN), etc. In terms of the carrying medium, network 110 can be a wired network, a wireless network, etc. In terms of data switching technology, network 110 can be a circuit-switched network, a packet-switched network, etc.

[0028] Terminal device 120 can be any type of electronic computing device capable of connecting to network 110, accessing servers or websites on network 110, processing data or signals, etc. For example, terminal device 120 can be a laptop, tablet, smartphone, camera, automated inspection robot with a camera, etc. Although in Figure 1 Only one terminal device is shown in the diagram, but it should be understood that a different number of terminal devices may be connected to network 110.

[0029] In one implementation, terminal device 120 can be used by a user. In some examples, terminal device 120 can transmit images captured by the user to be processed to application server 130. In one implementation, terminal device 120 can operate automatically. In some examples, terminal device 120 can transmit captured images to be processed to application server 130. In some cases, terminal device 120 can also receive relevant responses (e.g., 5S management evaluation scores for the images to be processed) from application server 130.

[0030] However, it should be understood that in one implementation, the application server 130 may execute the image processing method for 5S management described above. In one implementation, the terminal device 120 may also execute the image processing method for 5S management described above, instead of interacting with the application server 130.

[0031] It should be understood that Figure 1 All network entities shown are exemplary, and any other network entities may be involved in Architecture 100 depending on the specific application requirements.

[0032] Figure 2 A flowchart illustrating an example of an image processing method 200 for 5S management according to an embodiment of this specification is shown.

[0033] like Figure 2 As shown, at 210, the image to be processed is acquired for the target area.

[0034] In this embodiment, the image to be processed can be a photo taken by a user through a terminal device (e.g., a smartphone). In this embodiment, the image to be processed can also be a photo taken by automated equipment (e.g., a surveillance camera or an inspection robot). In some examples, images to be processed can be taken from individual workstations in office areas, production equipment in production workshops, material storage areas in warehouses, public areas, etc.

[0035] In step 220, at least one target object is identified and located from the image to be processed using object detection technology.

[0036] In this embodiment, the target object can be any object that needs to be considered during 5S management evaluation. In some examples, a trained machine learning model can be used for object detection to identify the target object from the image to be processed and determine its location within the image. In one example, training samples containing the target object can be used to supervise the training of the machine learning model so that the trained machine learning model can identify the aforementioned object from new images. In some examples, the target object may include, but is not limited to, at least one of the following: personal items such as laptops, mice, keyboards, mobile phones, and water cups; production equipment such as extruders, mixers, granulators, and reaction vessels; warehousing equipment such as silos, storage tanks, shelves, forklifts, and palletizing robots; and public equipment such as fire extinguishers, exhaust fans, emergency lighting fixtures, cleaning tools, and protective equipment.

[0037] In step 230, local features of each target object are extracted from the image regions where each target object is located.

[0038] In this embodiment, image feature extraction technology can be used to extract features such as color, shape, and texture of the local image region where the target object is located, forming the local features of the target object. It can be understood that the local features of the target object can be one (e.g., color feature) or multiple (e.g., color feature, shape feature, and texture feature). These features are then compared with the features required by the 5S management evaluation rules corresponding to the target object, and the satisfaction level is determined based on the comparison results. In step 240, based on the local features of each target object, the satisfaction level between each target object and the corresponding 5S management evaluation rules is determined.

[0039] In this embodiment, different objects can correspond to different 5S management evaluation rules. In some examples, for personal items such as laptops, mice, keyboards, and water cups, the corresponding 5S management evaluation rule could be "remove unused items, place them in fixed locations, and keep them tidy." In some examples, for production equipment such as extruders, mixers, granulators, and reactors, the corresponding 5S management evaluation rule could be "clean up unnecessary items around the equipment, ensure unobstructed operating space, clearly label the equipment, place it in a designated area, and clean and maintain it regularly." In some examples, for silos and storage tanks, the corresponding 5S management evaluation rules could be "maintain good sealing, no leakage, clean appearance, clear and accurate labeling, and orderly internal material storage"; for shelves, the corresponding 5S management evaluation rules could be "ensure sturdiness and stability, no deformation or damage, and proper labeling of categorized items"; for forklifts, the corresponding 5S management evaluation rules could be "regular inspection and maintenance, clean appearance, no oil stains or damage, standardized operation, and parking in designated areas"; and for palletizing robots, the corresponding 5S management evaluation rules could be "stable operation, no surrounding debris interference, regular cleaning and maintenance, and labeling of their working status and maintenance responsibility." In some examples, the corresponding 5S management evaluation rules for fire extinguishers could be "within their expiration date, under normal pressure, in a clearly visible and easily accessible location, and regularly inspected and maintained"; for exhaust fans, the corresponding 5S management evaluation rules could be "maintain good ventilation, free from noise and abnormal vibration, and with a clean surface free of dust"; for emergency lighting fixtures, the corresponding 5S management evaluation rules could be "should function normally, have sufficient power, be securely installed, and be regularly tested"; for cleaning tools, the corresponding 5S management evaluation rules could be "placed in designated areas, undamaged, and clean without stains"; and for protective equipment, the corresponding 5S management evaluation rules could be "complete and intact, stored in categories, regularly inspected and updated, and ensured to be usable when needed."

[0040] In some examples, for 5S management evaluation rules that instruct items to be placed in designated locations, edge detection technology can be used to extract the edge features of the target object, and the degree of compliance with the 5S management evaluation rule can be determined based on whether the target object is located within the designated area. In some examples, the placement areas for production equipment, fire extinguishers, protective equipment, etc., are usually physically marked (e.g., lines), allowing the designated area to be identified from an image. In some examples, for cases without explicit placement area markings, the location of the target object can be determined by judging whether it belongs to the same category as other surrounding target objects. For example, if a water cup is surrounded by office supplies such as a laptop, mouse, keyboard, and documents, the water cup can be considered outside the designated area. Similarly, if a broom is surrounded by cleaning supplies such as a mop, rag, trash can, and gloves, the broom can be considered within the designated area.

[0041] In some examples, for 5S management evaluation rules indicating cleanliness, image feature extraction technology can be used to extract the color and texture features of the target object, and then classifiers such as support vector machines, neural networks, and decision trees can be used to determine whether there is dust or stains on the surface of the target object. In other examples, for 5S management evaluation rules requiring clear signage, OCR (Optical Character Recognition) technology can be used to recognize the text of the corresponding signs, and the clarity of the signage can be determined based on the confidence level of the text recognition results (e.g., the confidence level of the OCR model output). Furthermore, the text recognition results can be used to determine the degree of fulfillment with 5S management evaluation rules indicating regular maintenance, upkeep, testing, and updates that require recording. In some examples, for 5S management evaluation rules requiring guaranteed normal operation, image recognition technology can be used to determine whether indicator lights indicating normal operation are lit, or whether there are signs such as "Under Maintenance" on the equipment, thereby determining the degree of fulfillment with this 5S management evaluation rule.

[0042] In this embodiment, the range of satisfaction level can be set according to the actual application. For example, the satisfaction level can be set from 0 to 100 points. The satisfaction level between the target object and the corresponding 5S management evaluation rules can be determined in various ways. In some examples, for a target object, the corresponding 5S management evaluation rules can be checked sequentially based on the analysis results. A base score of 100 points can be used, with 10 points deducted for each non-compliance, down to a minimum of 0 points. In some examples, different 5S management evaluation rules can be assigned corresponding scores, and the corresponding score is deducted when a rule is not met. In some examples, the satisfaction level of the target object can be determined by multiplying the ratio of the number of satisfied 5S management evaluation rules to the total number of checked management evaluation rules by 100 points. Thus, the satisfaction level corresponding to each target object can be determined.

[0043] At 250, the obtained satisfaction levels are summarized to generate the first score of the object level.

[0044] In this embodiment, various methods can be used to summarize the obtained satisfaction scores. In some examples, the average satisfaction score corresponding to multiple target objects can be determined as the first score of the object level of the image to be processed. For example, if the satisfaction scores of the laptop, mouse, keyboard, and water cup in the image to be processed taken at an office workstation are 80, 90, 80, and 30 respectively, then the first score can be (80+90+80+30) / 4 = 70. In some examples, different weights can be assigned to different categories of target objects in advance, and the first score can be determined by weighted summation. For example, in the above example, the weights of the laptop, mouse, keyboard, and water cup can be 30%, 20%, 20%, and 30% respectively, then the first score can be 80×30%+90×20%+80×20%+30×30% = 67.

[0045] At 260, a 5S management evaluation score for the image to be processed is generated based on the first score.

[0046] In this embodiment, based on the first score, the 5S management evaluation score of the image to be processed can be generated in various ways. In some examples, the first score can be directly determined as the 5S management evaluation score of the image to be processed. In some examples, the 5S management evaluation score of the image to be processed can be generated using a preset piecewise function based on the interval in which the first score falls.

[0047] It should be understood that all steps in process 200 and their order are exemplary, and embodiments of this disclosure will also cover any modifications to process 200.

[0048] The following is for reference. Figure 3 , Figure 3 A schematic diagram illustrating an example of a 5S management evaluation rule generation process 300 according to an embodiment of this specification is shown. Generation process 300 is applicable when the image to be processed has a corresponding reference image.

[0049] In this embodiment, the corresponding 5S management evaluation rules may include local feature sets of each reference object extracted from the reference image of the image to be processed. The reference objects can be identified and located from the corresponding reference image using object detection technology; for details, please refer to the relevant description of "target object" in step 220 of the aforementioned embodiment.

[0050] In this embodiment, the image to be processed can have a corresponding reference image. The reference image can be an image that meets the requirements of 5S management, such as an image with a 5S management evaluation score of full marks or close to full marks. In some examples, for areas with relatively fixed uses, such as employee workstations or a product production line, pre-stored reference images can be used. In some examples, the reference image can be associated with its corresponding area; that is, different areas can correspond to different reference images. For example, the reference image for an office area is different from the reference image for a production area. In some examples, the reference image can have area identifiers. For example, although employee A and employee B's workstations both belong to the office area, they can each have corresponding reference images. For example, reference image X has area identifier 100, and reference image Y has area identifier 200. Area identifiers 100 and 200 can be used to indicate the workstations of employee A and employee B, respectively.

[0051] like Figure 3 As shown, the reference image set 310 may include multiple reference images. For one of the reference images 311, the reference object 320 can first be identified and located using the method described in step 220 of the aforementioned embodiment, thereby ensuring the consistency of the standards used to identify and locate a specific object from the image as much as possible. In one example, there may be multiple reference objects 320, such as reference objects 321, 322, etc. Next, the local features of the reference objects can be extracted using the method described in step 230 of the aforementioned embodiment, thereby ensuring the consistency of the standards used to extract local features from a specific object as much as possible. In one example, taking reference object 321 as an example, its local features may include, for example, local features 331, 332, 333, etc. All local features of each reference object can form the local feature set of that reference object. Similarly, the local features of each reference object can be extracted to form the local feature set of each reference object in the reference image. Thus, the local feature set of each reference object in the reference image can be used to characterize the characteristics that the reference object should possess when meeting the 5S management requirements. Furthermore, the obtained local feature set can be used as the 5S management evaluation rule corresponding to the respective reference object.

[0052] In some examples, the generation process 300 described above can be performed after the image to be processed is acquired. Once the image to be processed is acquired, a corresponding reference image can be matched based on the target region. Then, local feature sets of each reference object extracted from the matched reference image can be used. After identifying the target object from the image to be processed, the local feature set that matches the target object can be selected from the extracted local feature sets of each reference object as the 5S management evaluation rule corresponding to the target object.

[0053] In some examples, the generation process 300 described above can be performed before acquiring the image to be processed. For example, the above operation can be performed in advance for each reference image in the reference image set 310, thereby obtaining local feature sets corresponding to reference objects in each reference image. In these examples, the obtained local feature sets, which serve as 5S management evaluation rules, can be stored. Thus, when the image processing method 200 is executed subsequently, it is not necessary to re-execute process 300 each time to generate the corresponding 5S management evaluation rules. Optionally, the 5S management evaluation rules can be further stored using region identifiers as indexes. For example, local feature sets corresponding to the same reference image can be queried according to region identifiers. In some examples, after acquiring the image to be processed, the corresponding local feature sets can be directly matched according to the target region it targets. It is understood that the matched 5S management evaluation rules can correspond to multiple reference objects in the same reference image. Furthermore, after identifying the target object from the image to be processed, the local feature sets that match the target object can be further selected as the 5S management evaluation rules corresponding to the target object.

[0054] Through the above approach, this solution creatively proposes to represent the 5S management evaluation rules corresponding to different objects in the form of local feature sets of reference objects in reference images, and specifically provides a method for generating 5S management evaluation rules when the image to be processed has a corresponding reference image.

[0055] Continue to refer Figure 4 , Figure 4 A flowchart illustrating yet another example of a 5S management evaluation rule generation process 400 according to an embodiment of this specification is shown. Generation process 400 is applicable when the image to be processed does not have a corresponding reference image.

[0056] At 410, obtain a set of similar reference images that match the image to be processed.

[0057] In this embodiment, a set of similar reference images may consist of reference images containing the target reference object. A description of the reference images can be found in the foregoing. Figure 3The relevant descriptions in the embodiments are as follows. The target reference object can belong to the same object category as the target object. In some examples, for areas with less fixed uses, such as temporary storage areas, it is often impossible to pre-define corresponding reference images. When the target area targeted by the image to be processed falls into the above-mentioned category, a set of similar reference images matching the image to be processed can be obtained. For example, when the target objects identified from the image to be processed include protective equipment and a toolbox, reference images containing protective equipment and / or a toolbox can be selected from the reference images to form a set of similar reference images matching the image to be processed. For example, the set of similar reference images may include 100 reference images, of which 80 images include protective equipment and 70 images include a toolbox, that is, 50 images include both protective equipment and a toolbox.

[0058] At 420, at least one reference object is identified and located from each reference image in the same set of reference images using object detection technology.

[0059] In step 430, for each reference image in the same set of reference images, local features of each reference object are extracted from the image region where each reference object is located in the reference image.

[0060] It should be noted that steps 420-430 above can be used as a reference. Figure 2 The description of steps 220-230 in the embodiment simply involves replacing the image to be processed with various reference images from the same set of reference images.

[0061] In step 440, taking a reference object as a unit, the local features of the obtained reference object are fused to generate a fused local feature set corresponding to each reference object as a 5S management evaluation rule.

[0062] In this embodiment, various feature fusion methods (such as averaging) can be used to generate the fused local feature sets corresponding to each reference object. In some examples, feature fusion can be performed separately for different types of local features. For example, when the local features include color features, shape features, and texture features, the generated fused local feature set can include fused color features, fused shape features, and fused texture features.

[0063] In some examples, feature fusion can also be performed using a weighted summation method. For instance, a reference image that includes only one reference object (such as protective gear or a toolbox) can be assigned a lower weight, while a reference image that includes more reference objects (such as protective gear and a toolbox) can be assigned a higher weight. Optionally, the more reference objects included, the closer the overall scene corresponding to the reference image is to the image to be processed, and therefore it should be assigned a higher weight.

[0064] In some examples, feature fusion can also be performed by first clustering and then averaging. For instance, taking protective equipment as a reference object, for 80 reference images containing protective equipment in a similar reference image set, 80 sets of local features corresponding to the protective equipment in each reference image can be obtained. Each set of local features can include, but is not limited to, at least one of the following: color features, shape features, and texture features. Taking 80 sets of color features as an example, these 80 sets of color features can be clustered, for example, using K-means clustering to obtain 3 clusters, each containing 50, 20, and 10 sets of color features respectively. Then, the color features in the cluster with the largest number of color features can be averaged, for example, averaging the aforementioned 50 sets of color features, and the result is determined as the fused color features. It is understood that similar methods can also be used for feature fusion of other local features such as shape features and texture features.

[0065] Through the above methods, this solution creatively proposes to generate local features of reference objects belonging to the same object category as the target object by using a set of similar reference images selected from the reference images. Furthermore, it obtains 5S management evaluation rules corresponding to different objects by feature fusion based on reference objects, in the form of a fused local feature set. It also provides a specific method for generating 5S management evaluation rules when the image to be processed does not have a corresponding reference image.

[0066] In some examples, the generation process 400 described above can be performed after acquiring the image to be processed and identifying at least one target object. At this point, a corresponding set of similar reference images can be matched based on the target region and the identified target object. Then, based on each reference image in the matched set of similar reference images, a fused local feature set corresponding to each reference object can be generated. Furthermore, the fused local feature set corresponding to each reference object obtained above can be selected to match the target object as the 5S management evaluation rule corresponding to the target object.

[0067] In some examples, the generation process 400 described above can be performed before acquiring the image to be processed. For example, a subset of the reference image set can be pre-selected as a similar reference image set. By performing operations 420-440, a fused local feature set corresponding to each displayed reference object in the similar reference image set can be obtained. In these examples, the obtained fused local feature set, which serves as the 5S management evaluation rule, can be stored. Therefore, when the image processing method 200 is subsequently executed, it is not necessary to re-execute process 400 each time to generate the corresponding 5S management evaluation rule. Optionally, the 5S management evaluation rule can be further stored using object identifiers as indexes. In some examples, after acquiring the image to be processed and identifying at least one target object, the corresponding fused local feature set can be directly matched based on the identified target object.

[0068] The following is for reference. Figure 5 , Figure 5 A flowchart is shown as yet another example of an image processing method 500 for 5S management according to an embodiment of this specification.

[0069] At 510, acquire the image to be processed taken for the target area.

[0070] In 520, at least one target object is identified and located from the image to be processed using object detection technology.

[0071] In step 530, local features of each target object are extracted from the image regions where each target object is located.

[0072] In step 540, based on the local characteristics of each target object, the degree of satisfaction between each target object and the corresponding 5S management evaluation rules is determined.

[0073] At 550, the obtained satisfaction levels are summarized to generate the first score of the object level.

[0074] In step 560, determine the region category to which the target region belongs.

[0075] In this embodiment, the region category to which the target area belongs can be determined in various ways. In some examples, the shooting location information of the image to be processed can be obtained. Then, the region category can be determined according to a pre-set shooting location information and region lookup table. In some examples, the shooting location information can be specified by the photographer, for example, the photographer can pre-input or select from a drop-down list "XX workstation", "XX production equipment", "west side of the corridor on the second floor of the office building", etc. In some examples, the shooting location information can be geotagging of the photo generated by the shooting device, that is, embedding GPS coordinates into the EXIF ​​data of the photo. In some examples, the target region category can also be determined directly from the image to be processed using a pre-trained image region recognition model or based on a specific image feature extraction and analysis algorithm. For example, the image to be processed can be provided to a trained convolutional neural network model, which can output the region category to which the target area most likely belongs. This convolutional neural network model can be trained on a large amount of image data labeled with different region categories, and can learn the visual feature patterns of different regions in the image.

[0076] In some examples, the area category may include at least one of the following: office workstation area, indoor general production area, indoor key production area, outdoor general production area, outdoor key production area, temporary area, experimental area, testing area, etc. In some examples, the office workstation area may have specific shapes and layout features such as desks, chairs, and computers; the indoor general production area may have specific production equipment layout and spatial features; the indoor key production area may have high-precision production equipment and higher environmental requirements; the outdoor general production area may have natural lighting, a large space, and specific outdoor facilities; the outdoor key production area may have special protective facilities and equipment layout features; and the temporary area may be characterized by being relatively cluttered and having items placed haphazardly.

[0077] At 570, the second score of the image level is determined in a corresponding manner based on whether the determined region category belongs to the region category with the corresponding reference image.

[0078] In this embodiment, a reference image library can be pre-stored. In some examples, the reference images in the reference image library can be stored according to region categories. The target region category determined in step 560 can be compared and matched with the region categories in the reference image library. For example, the category labels in the reference image library can be traversed to see if there are any label records with the same region category as the target region. If they exist, it is determined that the determined region category belongs to the region category with the corresponding reference image; if they do not exist, it is determined that the determined region category does not belong to the region category with the corresponding reference image. Then, a second score for the image level can be determined using appropriate methods. The second score for the image level can be used to reflect the degree to which the image to be processed conforms to the 5S management evaluation rules as a whole.

[0079] In some examples, if the identified region category belongs to the region category with the corresponding reference image, the global similarity between the image to be processed and the corresponding reference image can be determined as the second score.

[0080] In these examples, various global similarity calculation methods can be used to determine the global similarity between the image to be processed and the corresponding reference image. In some examples, simple similarity calculation methods based on color histograms, the difference in pixel values ​​between two images, or the structural similarity index (SSIM) can be used to determine global similarity. In other examples, similarity calculation methods based on feature vectors can also be used. For example, feature vectors of the image to be processed and the corresponding reference image can be extracted first, for example, using algorithms such as SIFT (Scale-invariant feature transform), SURF (Speeded Up Robust Feature), or ORB (Oriented FAST and Rotated BRIEF) to extract feature points and construct feature vectors. Then, the distance between the two feature vectors, such as Euclidean distance or cosine similarity, can be calculated to quantify the similarity between them. It should be noted that the higher the global similarity, the closer the two images are. This means that if the directly calculated result represents the distance between the two images, the result needs to be mapped to meet the requirements of the second score.

[0081] In some examples, if the determined region category does not belong to the region category with the corresponding reference image, the 5S adjustment score corresponding to the determined region category can be determined as the second score.

[0082] In these examples, since the 5S management standards and implementation difficulties differ across different area categories, 5S adjustment scores can be pre-set for different area categories to reduce significant differences in scores due to area category factors. For example, for office workstations, since 5S management standards are easier to meet, a relatively stricter scoring is required, thus a lower 5S adjustment score (e.g., 70 points) can be set. Conversely, for production areas, since 5S management standards are more difficult to meet, a relatively more lenient scoring is required, thus a higher 5S adjustment score (e.g., 80 points) can be set. In some examples, key production areas often require stricter standards than ordinary production areas; therefore, the 5S adjustment score corresponding to key production areas (e.g., 78 points) can be slightly lower than the 5S adjustment score corresponding to ordinary production areas (e.g., 82 points). Furthermore, due to the temporary and uncertain nature of temporary areas, their corresponding 5S adjustment scores can be set based on the historical scores (e.g., average values) of temporary areas.

[0083] At 580, based on the first score and the second score, a 5S management evaluation score for the image to be processed is generated.

[0084] In this embodiment, the 5S management evaluation score of the image to be processed can be generated by combining the first score and the second score in various ways. In some examples, a weighted summation method can be used to generate the 5S management evaluation score of the image to be processed. Thus, the final 5S management evaluation score can more comprehensively and objectively reflect the overall performance level of the scene represented by the image to be processed in terms of 5S management.

[0085] It should be noted that steps 510-550 above can be referred to the corresponding descriptions of steps 210-250 in the foregoing embodiments, and will not be repeated here. It is understood that steps 560-570 can also be performed before any of steps 520-550.

[0086] Continue to refer Figure 6 , Figure 6 A flowchart illustrating an example of a process 600 for determining the global similarity between an image to be processed and a corresponding reference image according to an embodiment of this specification is provided. Process 600 may be... Figure 5 An exemplary implementation of step 570 in the example.

[0087] In step 610, the first key point and the second key point are determined from the image to be processed and the corresponding reference image, respectively.

[0088] In this embodiment, algorithms such as SIFT, SURF, and ORB can be used to determine key points. For example, taking the SIFT algorithm, extreme point detection can first be performed in different scale spaces of the image to be processed and the corresponding reference image. By constructing a Gaussian difference pyramid, local extreme points are searched at different levels of the pyramid as candidate key points. Then, low-contrast and unstable edge response points can be removed from these candidate key points to obtain relatively stable and representative first key point (in the image to be processed) and second key point (in the reference image). The key points determined by the above method have good properties such as scale invariance and rotation invariance, and can effectively represent the local feature information of the image under different viewpoints and scale changes. For example, in the reference image corresponding to the production area, the corners of the equipment and the positions of specific logos may be detected as key points.

[0089] At 620, based on the matching point pair formed by the first key point and the second key point, the perspective transformation matrix of the image to be processed to the corresponding reference image is determined.

[0090] In this embodiment, after obtaining the first and second keypoints, these keypoints can be matched using feature descriptors to form matching point pairs. For example, SIFT feature descriptors can be used to describe the local feature information around each keypoint, and then the similarity between different keypoint descriptors (such as Euclidean distance) is calculated. Keypoint pairs whose similarity meets a certain threshold are determined as matching point pairs. Next, these matching point pairs can be used to calculate the perspective transformation matrix using the Random Sample Consensus (RANSAC) algorithm. The RANSAC algorithm can estimate the transformation model by randomly selecting subsets from the matching point pairs multiple times, and then calculate the number of inliers of the transformation model (i.e., the number of matching point pairs that conform to the transformation model). By repeating the above process, the perspective transformation matrix corresponding to the transformation model with the most inliers is finally selected as the perspective transformation matrix for transforming the image to be processed into the reference image. This effectively removes incorrectly matched point pairs and improves the accuracy and reliability of the perspective transformation matrix. The aforementioned perspective transformation matrix is ​​typically a 3x3 homography matrix, which describes the projection relationship between images. In one example, the above process can be efficiently implemented using relevant functions (such as the findHomography function) in image processing libraries (such as OpenCV).

[0091] In step 630, the perspective transformation matrix is ​​used to perform a perspective transformation on the image to be processed, resulting in a perspective-transformed image aligned with the corresponding reference image.

[0092] In this embodiment, the perspective transformation matrix determined in step 620 can be used to perform a perspective transformation on the image to be processed, aligning it with the corresponding reference image. In one example, for any pixel coordinate (x, y) in the image to be processed, its homogeneous coordinates can be represented as [x, y, 1]. T Let H be the perspective transformation matrix. The homogeneous coordinates (x, y, 1) of a pixel can be obtained through matrix multiplication. T Multiplying by the perspective transformation matrix H yields the homogeneous coordinates [x', y', 1] after the perspective transformation. T This allows us to obtain the perspective-transformed pixel coordinates (x', y'). By performing the above perspective transformation operation on each pixel in the image to be processed, we can obtain a perspective-transformed image aligned with the corresponding reference image. In one example, the above process can be efficiently implemented using relevant functions (such as the warpPerspective function) in image processing libraries (such as OpenCV).

[0093] At 640, the global similarity between the perspective-transformed image and the corresponding reference image is determined.

[0094] In this embodiment, the global similarity can be determined by using simple similarity calculation methods based on color histograms, the difference in pixel values ​​between two images, or structural similarity indices, with reference to the description of step 572 above.

[0095] By combining perspective transformation with global similarity determination, this solution ensures that the image to be processed is aligned as closely as possible with the corresponding reference image in terms of geometry and position. By transforming objects in the image from different perspective angles to a unified viewpoint, it enables more accurate comparison and evaluation of image similarity and 5S management status. This is particularly suitable for processing images with depth information or significant differences in shooting angle, common in manufacturing enterprises. For example, when analyzing images of factory workshops or warehouses with different shooting angles for 5S management purposes, it can determine whether shelves are neatly arranged and whether aisles are unobstructed. Similarly, when analyzing images of office areas for 5S management purposes, it can ensure that objects such as tables, chairs, and filing cabinets in two images correspond spatially, effectively reducing scoring errors caused by different perspectives.

[0096] Continue to refer Figure 7 , Figure 7 A flowchart illustrating an example of a 5S management evaluation score generation process 700 according to an embodiment of this specification is shown. Process 700 may be... Figure 5 An exemplary implementation of step 580 in the example.

[0097] In 710, determine whether the first score and the second score match.

[0098] In this embodiment, if the first score and the second score are not significantly different, for example, not exceeding a preset threshold (e.g., 10 points), it can be determined that the first score and the second score match. If the difference exceeds the preset threshold, it can be determined that the first score and the second score do not match.

[0099] If 710 determines a mismatch, proceed with the following steps 720-740.

[0100] In step 720, the perspective-transformed image and the corresponding reference image are provided to the non-scoring sensitive region recognition model to determine whether a non-scoring sensitive region exists.

[0101] In this embodiment, non-scoring-sensitive regions are used to indicate areas where differences exist between the perspective-transformed image and the corresponding reference image, but do not affect whether the 5S management evaluation rules are met. In some examples, the non-scoring-sensitive region identification model can be a model trained based on machine learning methods. The perspective-transformed image and the corresponding reference image can be provided to the non-scoring-sensitive region identification model. If non-scoring-sensitive regions exist, the non-scoring-sensitive region identification model can mark the corresponding non-scoring-sensitive regions in the perspective-transformed image and the corresponding reference image. If no non-scoring-sensitive regions exist, there are no corresponding non-scoring-sensitive region marks in either the perspective-transformed image or the corresponding reference image. In some examples, the non-scoring-sensitive region identification model can be trained using images as training samples. The image pair used as training samples can consist of a first sample image and a second sample image. The content presented in the first sample image and the second sample image may differ, but the manually labeled scores corresponding to the first sample image and the second sample image are basically the same. For example, in an office building corridor, if the decorative painting on the wall changes from painting A to painting B, the area where the decorative painting is located can be identified as a non-scoring-sensitive region. For example, if the content displayed on a laptop screen at the same workstation should not affect the 5S management evaluation score, then the laptop screen area can be identified as a non-scoring-sensitive area. Similarly, in production areas, minor scratches on the floor caused by normal production wear and tear, if they do not affect key 5S indicators such as cleanliness, safety, and the orderly placement of equipment and materials, can also be considered non-scoring-sensitive areas.

[0102] If step 720 is determined to exist, proceed to steps 730-740.

[0103] At 730, at least one of the first score and the second score is corrected based on the identified non-scoring sensitive area.

[0104] In this embodiment, at least one of the first score and the second score can be corrected based on the location and area proportion of the non-scoring-sensitive region in the image, the satisfaction level of the corresponding determined target object, and the relative size of the first score and the second score. In some examples, if the non-scoring-sensitive region is located in the central area or a key area of ​​the 5S management evaluation, or if its area proportion is large (e.g., exceeding an area proportion threshold, such as 10%), it means that it will affect both the first and second scores simultaneously, with a greater impact on the second score, which represents the overall picture. In this case, the first and second scores can be corrected with a first upward adjustment, and the upward adjustment of the second score is greater than that of the first score. In some examples, if the non-scoring-sensitive region is located in the edge area or a non-key area of ​​the 5S management evaluation, or if its area proportion is small, the first and second scores can be corrected with a second upward adjustment, and the second upward adjustment is less than the first upward adjustment. In some examples, the correction of the first score can also be based on recalculating the first score of the image to be processed after removing the satisfaction level of the target object corresponding to the non-scoring-sensitive region. In some examples, the smaller of the first and second scores can be corrected to the average of the first and second scores.

[0105] At 740, based on the correction results, a 5S management evaluation score for the image to be processed is generated.

[0106] In this embodiment, the 5S management evaluation score of the image to be processed can be generated with reference to the description of step 270, simply by replacing the first score and / or the second score with the corresponding correction results.

[0107] By using the above method, this solution creatively combines the deviation between the first and second scores with the identification of non-scoring sensitive areas, thereby reducing the deviation caused by factors unrelated to 5S management, and thus achieving more accurate image comparison and generating a more objective 5S management evaluation score.

[0108] use Figures 1-7 The image processing method for 5S management disclosed herein can obtain a first score at the object level by measuring the degree of satisfaction between the extracted local features and the corresponding 5S management evaluation rules, thus providing a reference for the final 5S management evaluation score. Compared with the conventional method of directly comparing with a standard image of the area, this solution analyzes the conformity between the image to be processed and the corresponding 5S management evaluation rules from the perspective of image understanding. This makes it suitable for scenarios where there is no corresponding standard image and can also significantly reduce the storage requirements of the standard image.

[0109] Figure 8 A block diagram of an example of an image processing apparatus 800 for 5S management according to an embodiment is shown.

[0110] The image processing apparatus 800 may include: an image acquisition unit 810 configured to acquire an image to be processed captured targeting a target area; a target detection unit 820 configured to identify and locate at least one target object from the image to be processed using target detection technology; a feature extraction unit 830 configured to extract local features of each target object from the image area where each target object is located; a first score determination unit 840 configured to determine the degree of satisfaction between each target object and the corresponding 5S management evaluation rule based on the local features of each target object; summarize the obtained satisfaction levels to generate a first score at the object level; and a final score generation unit 850 configured to generate a 5S management evaluation score for the image to be processed based on the first score.

[0111] In addition, the image processing apparatus 800 may also include any other modules configured to perform any operation of the image processing method for 5S management according to the above-described embodiments of the present disclosure.

[0112] Reference above Figures 1 to 8 Embodiments of the image processing method and apparatus for 5S management according to the embodiments of this specification have been described.

[0113] The image processing device for 5S management described in this specification can be implemented in hardware, software, or a combination of both. Taking software implementation as an example, as a logical device, it is formed by the processor of its host device reading the corresponding computer program instructions from the memory into memory and executing them. In the embodiments of this specification, the image processing device for 5S management can, for example, be implemented using an electronic device.

[0114] Figure 9 A schematic diagram of an example of an image processing apparatus 900 for 5S management according to an embodiment of this specification is shown.

[0115] like Figure 9 As shown, the image processing apparatus 900 for 5S management may include at least one processor 910, a memory (e.g., non-volatile memory) 920, a main memory 930, and a communication interface 940, and the at least one processor 910, memory 920, main memory 930, and communication interface 940 are connected together via a bus 950. The at least one processor 910 executes at least one computer-readable instruction (i.e., the elements implemented in software above) stored or encoded in the memory.

[0116] In one embodiment, computer-executable instructions are stored in a memory, which, when executed, cause at least one processor 910 to: acquire an image to be processed taken of a target area; identify and locate at least one target object from the image to be processed using target detection technology; extract local features of each target object from the image area where each target object is located; determine the degree of satisfaction between each target object and the corresponding 5S management evaluation rule based on the local features of each target object; summarize the obtained satisfaction levels to generate a first score at the object level; and generate a 5S management evaluation score for the image to be processed based on the first score.

[0117] It should be understood that the computer-executable instructions stored in memory, when executed, cause at least one processor 910 to perform the above-described combinations in the various embodiments of this specification. Figures 1-7 The description includes various operations and functions.

[0118] Specifically, a system or apparatus equipped with a readable storage medium may be provided, on which software program code implementing the functions of any of the embodiments described above is stored, and the computer or processor of the system or apparatus can read and execute the instructions stored in the readable storage medium.

[0119] In this case, the program code itself, which can be read from a readable medium, can perform the functions of any of the above embodiments. Therefore, the machine-readable code and the readable storage medium storing the machine-readable code constitute a part of the present invention.

[0120] The computer program code required for the operation of each part of this manual can be written in any one or more programming languages, including object-oriented programming languages ​​such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB, .NET, and Python; conventional procedural programming languages ​​such as C, Visual Basic 2003, Perl, COBOL 2002, PHP, and ABAP; dynamic programming languages ​​such as Python, Ruby, and Groovy; or other programming languages. This program code can run on the user's computer, or as a standalone software package on the user's computer, or partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter case, the remote computer can be connected to the user's computer via any network, such as a local area network (LAN) or wide area network (WAN), or connected to an external computer (e.g., via the Internet), or in a cloud computing environment, or used as a service, such as Software as a Service (SaaS).

[0121] Examples of readable storage media include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD-RW), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, program code can be downloaded from a server computer or the cloud via a communication network.

[0122] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0123] Not all steps and units in the above process and system structure diagrams are mandatory; some steps or units can be omitted as needed. The execution order of each step is not fixed and can be determined as required. The device structure described in the above embodiments can be a physical structure or a logical structure. That is, some units may be implemented by the same physical entity, or some units may be implemented by multiple physical entities, or they may be jointly implemented by certain components in multiple independent devices.

[0124] The term "exemplary" as used throughout this specification means "serving as an example, instance, or illustration" and does not imply that it is "preferred" or "advantageous" over other embodiments. Detailed descriptions are included for the purpose of providing an understanding of the described techniques. However, these techniques may be practiced without these detailed descriptions. In some instances, well-known structures and apparatuses are shown in block diagram form to avoid obscuring the concepts of the described embodiments.

[0125] The optional embodiments of the present specification have been described in detail above with reference to the accompanying drawings. However, the embodiments of the present specification are not limited to the specific details in the above embodiments. Within the scope of the technical concept of the embodiments of the present specification, various simple modifications can be made to the technical solutions of the embodiments of the present specification, and these simple modifications all fall within the protection scope of the embodiments of the present specification.

[0126] The foregoing description of this specification is provided to enable any person skilled in the art to implement or use the content of this specification. Various modifications to the content of this specification will be apparent to those skilled in the art, and the general principles defined herein can be applied to other variations without departing from the scope of protection of this specification. Therefore, this specification is not limited to the examples and designs described herein, but is consistent with the widest scope of the principles and novel features disclosed herein.

Claims

1. An image processing method for 5S management, comprising: Acquire the images to be processed captured for the target area; At least one target object is identified and located from the image to be processed using target detection technology; Extract local features of each target object from the image region where each target object is located; Based on the local characteristics of each target object, determine the degree of satisfaction between each target object and the corresponding 5S management evaluation rules; Summarize the obtained satisfaction levels to generate the first score for the object level; as well as A 5S management evaluation score for the image to be processed is generated based on the first score. The image processing method further includes: Determine the region category to which the target region belongs; Based on whether the determined region category belongs to the region category with the corresponding reference image, a second score for the image level is determined using an appropriate method. If the determined region category belongs to the region category with the corresponding reference image, the second score is the global similarity between the perspective-transformed image and the corresponding reference image. The perspective-transformed image is obtained by aligning the image to be processed with the corresponding reference image through keypoint matching and perspective transformation. The process of generating the 5S management evaluation score for the image to be processed based on the first score includes: Determine whether the first score and the second score match; In response to mismatch, The perspective-transformed image and the corresponding reference image are provided to the non-scoring sensitive area recognition model to determine whether there are non-scoring sensitive areas. The non-scoring sensitive areas are used to indicate areas where there are differences between the perspective-transformed image and the corresponding reference image, but these differences do not affect whether the 5S management evaluation rules are met. If present, at least one of the first score and the second score is corrected based on the identified non-scoring sensitive area; and based on the correction result, a 5S management evaluation score for the image to be processed is generated.

2. The image processing method as described in claim 1, wherein, If the image to be processed has a corresponding reference image, the corresponding 5S management evaluation rule includes the local feature set of each reference object extracted from the reference image of the image to be processed, wherein the reference object is identified and located from the corresponding reference image using target detection technology.

3. The image processing method as described in claim 1, wherein, If the image to be processed does not have a corresponding reference image. The 5S management evaluation rules are generated through the following steps: Obtain a set of similar reference images that match the image to be processed, wherein the set of similar reference images consists of reference images containing the target reference object, and the target reference object and the target object belong to the same object category; At least one reference object is identified and located from each reference image in the same set of reference images using target detection technology; For each reference image in the aforementioned set of similar reference images, local features of each reference object are extracted from the image region where each reference object is located in the reference image; and Using a reference object as a unit, the local features of the obtained reference object are fused to generate a fused local feature set corresponding to each reference object, which serves as the 5S management evaluation rule.

4. The image processing method as described in claim 1, wherein, The step of determining the second score of the image level based on whether the determined region category belongs to the region category with the corresponding reference image, and using an appropriate method, includes: If the determined region category belongs to the region category with the corresponding reference image, the global similarity between the image to be processed and the corresponding reference image is determined as the second score.

5. The image processing method as described in claim 4, wherein, The global similarity between the image to be processed and the corresponding reference image is determined through the following steps: The first key point and the second key point are determined from the image to be processed and the corresponding reference image, respectively; Based on the matching point pair formed by the first key point and the second key point, the perspective transformation matrix of the image to be processed to the corresponding reference image is determined. The perspective transformation matrix is ​​used to perform a perspective transformation on the image to be processed, resulting in a perspective-transformed image aligned with the corresponding reference image. as well as Determine the global similarity between the perspective-transformed image and the corresponding reference image.

6. The image processing method as described in claim 1, wherein, The step of determining the second score of the image level based on whether the determined region category belongs to the region category with the corresponding reference image, and using an appropriate method, includes: If the determined region category does not belong to the region category with the corresponding reference image, the 5S adjustment score corresponding to the determined region category will be determined as the second score.

7. An image processing device for 5S management, comprising: The image acquisition unit is configured to acquire a target area image to be processed. The target detection unit is configured to identify and locate at least one target object from the image to be processed using target detection technology; The feature extraction unit is configured to extract local features of each target object from the image region where each target object is located; The first score determination unit is configured to determine the degree of satisfaction between each target object and the corresponding 5S management evaluation rules based on the local characteristics of each target object; and to summarize the obtained satisfaction levels to generate the first score at the object level. as well as The final score generation unit is configured to generate a 5S management evaluation score for the image to be processed based on the first score. The image processing device is further configured to: determine the region category to which the target region belongs; Based on whether the determined region category belongs to the region category with the corresponding reference image, the second score of the image level is determined in a corresponding manner. If the determined region category belongs to the region category with the corresponding reference image, the second score is the global similarity between the perspective-transformed image and the corresponding reference image. The perspective-transformed image is obtained by aligning the image to be processed with the corresponding reference image through key point matching and perspective transformation. The final score generation unit is further configured to determine whether the first score and the second score match; In response to mismatch, The perspective-transformed image and the corresponding reference image are provided to the non-scoring sensitive area recognition model to determine whether there are non-scoring sensitive areas. The non-scoring sensitive areas are used to indicate areas where there are differences between the perspective-transformed image and the corresponding reference image, but these differences do not affect whether the 5S management evaluation rules are met. If present, at least one of the first score and the second score is corrected based on the identified non-scoring sensitive area; and based on the correction result, a 5S management evaluation score for the image to be processed is generated.

8. An image processing device for 5S management, comprising: At least one processor, a memory coupled to the at least one processor, and a computer program stored on the memory, wherein the at least one processor executes the computer program to implement the image processing method for 5S management as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program that, when executed by a processor, implements the image processing method for 5S management as described in any one of claims 1 to 6.

10. A computer program product is provided, comprising a computer program that is executed by a processor to implement the image processing method for 5S management as described in any one of claims 1 to 6.

Images