Intelligent accounting file management cabinet with retrieval function

Abstract

The invention belongs to the field of archive management, and discloses an intelligent accounting archive management cabinet with a retrieval function, which comprises a retrieval device, and the retrieval device comprises a face acquisition module, a database module and a face comparison module; the face acquisition module is used for acquiring an image of a face of a user; the database module is used for storing images for comparison; the face comparison module is used for comparing the image acquired by the face acquisition module with the image stored in the database module, and judging whether the user has the permission to check the accounting file or not; the face comparison module comprises a comparison serial number maintenance unit and a comparison unit; the comparison sequence number maintenance unit is used for regularly updating comparison sequence numbers of the images which are stored in the database module and are used for comparison; and the comparison unit is used for comparing the image acquired by the face acquisition module with the image stored in the database module based on the comparison serial number, and judging whether the user has the permission to check the accounting archive or not. The time consumed for obtaining the judgment result can be shortened.

Description

Technical Field

[0001] The present invention relates to the field of file management, and particularly to an intelligent accounting file management cabinet with a retrieval function. Background Art

[0002] An accounting file management cabinet refers to a cabinet used to store accounting file materials. Traditional accounting file management cabinets only have the function of storage, and retrieving the materials stored in the accounting file management cabinet requires the use of additional equipment. With the development of technology, there are now also devices with retrieval functions integrated on the side of accounting file management cabinets, so that there is no need to additionally set up a device for retrieval, which can further expand the effective available space of the archive room.

[0003] Since accounting file materials usually need to be kept confidential, before retrieval, face recognition is usually required to determine whether the user has the viewing permission for accounting file materials. When performing face recognition, the image of the user's face obtained needs to be compared with the images stored in the database to determine whether there is permission. The images stored in the database are all images of personnel with viewing permissions. The existing comparison methods generally randomly select an image from the database for comparison. If an image with a similarity meeting the requirements is found in the database during the comparison process, it means that the user has the viewing permission. If no image with a similarity meeting the requirements is found after comparing all the images in the database, it means that the user does not have the viewing permission.

[0004] Obviously, this way of randomly selecting and traversing for comparison easily leads to a long permission judgment process. When the user has the viewing permission, it is easy for the user to wait for a relatively long time to obtain the judgment result, which makes the use experience of the intelligent accounting file management cabinet not good enough. Summary of the Invention

[0005] The purpose of the present invention is to disclose an intelligent accounting file management cabinet with a retrieval function to solve the technical problems raised in the background art.

[0006] To achieve the above purpose, the present invention provides the following technical solutions:

[0007] The present invention provides an intelligent accounting file management cabinet with a retrieval function, including a retrieval device, and the retrieval device includes a face acquisition module, a database module, and a face comparison module;

[0008] The face acquisition module is used to acquire an image of the user's face;

[0009] The database module is used to store images for comparison;

[0010] The face comparison module is used to compare the images obtained by the face acquisition module with the images stored in the database module to determine whether the user has the viewing permission for accounting files;

[0011] The face comparison module includes a comparison serial number maintenance unit and a comparison unit;

[0012] The comparison serial number maintenance unit is used to regularly update the comparison serial numbers of the images stored in the database module for comparison;

[0013] The comparison unit is used to compare the images obtained by the face acquisition module with the images stored in the database module based on the comparison serial numbers to determine whether the user has the viewing permission for accounting files;

[0014] The process of determining the comparison serial number includes:

[0015] Calculate the comparison values of each image in the database module;

[0016] Determine the comparison serial numbers of the images in the database module in descending order of the comparison values. The larger the comparison value, the smaller the comparison serial number.

[0017] Preferably, the retrieval device further includes a retrieval module, and the retrieval module includes an input unit, a retrieval unit, and an information storage unit;

[0018] The input unit is used to obtain the retrieval information input by the user after the face comparison module determines that the user has the viewing permission;

[0019] The information storage unit is used to store the location information of the accounting files;

[0020] The retrieval unit is used to obtain the location information of the accounting file corresponding to the retrieval information from the location information stored in the information storage unit according to the retrieval information.

[0021] Preferably, it further includes a filing cabinet body, and the filing cabinet body is used to store paper accounting file materials;

[0022] The retrieval device is arranged on the side of the filing cabinet body.

[0023] Preferably, it further includes a wireless monitoring device;

[0024] The wireless monitoring device includes a wireless monitoring sensor and a monitoring terminal;

[0025] The wireless monitoring sensor is arranged inside the filing cabinet body, and is used to obtain the environmental data inside the filing cabinet body and transmit the environmental data to the monitoring terminal;

[0026] The monitoring terminal is used to determine whether the environment inside the filing cabinet body is abnormal based on environmental data, and to send a reminder to the file management personnel when the environment inside the filing cabinet body is abnormal.

[0027] Preferably, the image stored in the database module is an image of the face of a person with the viewing permission of accounting files.

[0028] Preferably, the comparison serial number is a positive integer, and the value range is [1, np], where np represents the total number of images stored in the database module.

[0029] Preferably, based on the comparison serial number, comparing the image obtained by the face acquisition module with the image stored in the database module to determine whether the user has the viewing permission of accounting files, including:

[0030] The first step is to initialize the value of the comparison serial number cp to 1;

[0031] The second step is to compare the image obtained by the face acquisition module with the image with the comparison serial number cp stored in the database module, and determine whether the similarity between the two images meets the judgment requirements. If so, end the comparison process; if not, enter the third step;

[0032] The third step is to determine whether the value of cp is greater than or equal to np. If so, it means that the user does not have the viewing permission of accounting files; if not, enter the fourth step;

[0033] The fourth step is to add 1 to the value of cp and enter the second step.

[0034] Preferably, determining whether the similarity between the two images meets the judgment requirements includes:

[0035] Calculate the cosine similarity between the two images, and determine whether the cosine similarity is greater than the set threshold. If so, it means that the similarity between the two images meets the judgment requirements; if not, it means that the similarity between the two images does not meet the judgment requirements.

[0036] Preferably, the calculation function of the comparison value of the images in the database module is:

[0037]

[0038] calcv b is the comparison value of image b in the database module, N represents the number of times the face acquisition module obtains images within a set time interval; nsuc b represents the number of times it is determined that the user has the viewing permission based on image b within a set time interval; qual b is the status value of image b, qual maxis the maximum value of the status values of all the images in the database module; w1 and w2 are the frequency weight and the status value weight respectively.

[0039] Preferably, qual b The calculation function of is:

[0040]

[0041] bpu is the set of pixel points in the image gb, gb is the grayscale image corresponding to the image b, gr c is the grayscale value of the pixel point c, nbpu is the total number of pixel points included in gb, gr max is the maximum value of the grayscale values of the pixel points in gb, nfce b is the number of pixel points belonging to the skin area included in the image b, and λ is the calculation weight.

[0042] Beneficial effects:

[0043] Compared with the prior art, in the process of judging the viewing permission, the intelligent accounting file management cabinet of the present invention compares the image obtained by the face acquisition module with the image stored in the database module based on the comparison serial number, so as to place the image with a higher comparison success rate in the front comparison order. In this way, when the user has the viewing permission, the probability of the event that only a relatively small number of comparisons are required to obtain the comparison result in a single comparison can be increased, the time consumption for obtaining the judgment result can be shortened, and the use experience of the intelligent accounting file management cabinet can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0045] Figure 1 is a schematic diagram of an intelligent accounting file management cabinet with a retrieval function of the present invention.

[0046] Figure 2 is a schematic diagram of the positional relationship between the retrieval device and the file cabinet body of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0047] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0048] The present invention provides an intelligent accounting file management cabinet with a retrieval function, including a retrieval device, and the retrieval device includes a face acquisition module, a database module, and a face comparison module;

[0049] The face acquisition module is used to obtain an image of the user's face;

[0050] The database module is used to store the images for comparison;

[0051] The face comparison module is used to compare the image obtained by the face acquisition module with the images stored in the database module to determine whether the user has the viewing permission for accounting files;

[0052] The face comparison module includes a comparison serial number maintenance unit and a comparison unit;

[0053] The comparison serial number maintenance unit is used to regularly update the comparison serial numbers of the images stored in the database module for comparison;

[0054] The regular update can be once a day, once a week, etc. In addition, the comparison serial number maintenance unit is also used to re-update the comparison serial numbers when new images are stored in the database module;

[0055] The comparison unit is used to compare the image obtained by the face acquisition module with the images stored in the database module based on the comparison serial numbers to determine whether the user has the viewing permission for accounting files;

[0056] The process of determining the comparison serial numbers includes:

[0057] Calculate the comparison values of each image in the database module;

[0058] Determine the comparison serial numbers of the images in the database module in descending order of the comparison values. The larger the comparison value, the smaller the comparison serial number.

[0059] In the process of judging the viewing permission of the intelligent accounting file management cabinet of the present invention, the image acquired by the face collection module is compared with the image stored in the database module based on the comparison serial number, so that the image with a higher comparison success rate is placed in the front comparison order. In this way, when the user has the viewing permission, the probability of an event where only a small number of comparisons are required to obtain the comparison result during a single comparison can be increased, the time-consuming for obtaining the judgment result can be shortened, and the use experience of the intelligent accounting file management cabinet can be improved.

[0060] The user of the present invention refers to the user who needs to use the retrieval device.

[0061] Preferably, the retrieval device further includes a retrieval module, and the retrieval module includes an input unit, a retrieval unit, and an information storage unit;

[0062] The input unit is used to obtain the retrieval information input by the user after the face comparison module determines that the user has the viewing permission;

[0063] The information storage unit is used to store the location information of the accounting files;

[0064] The retrieval unit is used to obtain the location information of the accounting file corresponding to the retrieval information from the location information stored in the information storage unit.

[0065] The retrieval information of the present invention includes one or more of the type of accounting file, the name of the accounting file, the formation date of the accounting file, and the number of the accounting file.

[0066] The types of accounting files include invoices, receipts, bills of exchange, contracts, etc.

[0067] The location information of the accounting file includes the number of the file cabinet where the accounting file is located, as well as the row number and column number of the grid where it is located.

[0068] Obtaining the location information of the accounting file corresponding to the retrieval information from the location information stored in the information storage unit includes:

[0069] In the information storage unit, the location information of the accounting file further includes the attribute information of the accounting file, and the attribute information includes the type of the accounting file, the name of the accounting file, the formation date of the accounting file, etc. Therefore, the corresponding location information of the accounting file can be found based on the retrieval information.

[0070] Preferably, it further includes a file cabinet body, and the file cabinet body is used to store paper accounting file materials;

[0071] As Figure 2 shown, the retrieval device is arranged on the side of the file cabinet body. In Figure 2 it, A represents the file cabinet body, and B is the retrieval device.

[0072] Figure 2 Only 4 closely arranged filing cabinet bodies are drawn. There can be multiple filing cabinet bodies in the present invention, and the retrieval device is arranged on the side of at least one filing cabinet body.

[0073] The filing cabinet body can be in the form of a filing compactus.

[0074] Preferably, it further includes a wireless monitoring device;

[0075] The wireless monitoring device includes a wireless monitoring sensor and a monitoring terminal;

[0076] The wireless monitoring sensor is arranged inside the filing cabinet body, used to obtain the environmental data inside the filing cabinet body, and used to transmit the environmental data to the monitoring terminal;

[0077] The monitoring terminal is used to judge whether the environment inside the filing cabinet body is abnormal according to the environmental data, and used to send a reminder to the file management personnel when the environment inside the filing cabinet body is abnormal.

[0078] The environmental data of the present invention includes temperature and humidity.

[0079] Judging whether the environment inside the filing cabinet body is abnormal according to the environmental data includes:

[0080] Judging whether the temperature is greater than a set temperature threshold (such as 50 degrees Celsius). If so, it means that the environment inside the filing cabinet body is abnormal. If not, judge whether the humidity is greater than the set humidity threshold.

[0081] If the humidity is greater than the set humidity threshold (such as 60%), it means that the environment is abnormal.

[0082] The way to send a reminder to the file management personnel includes playing an alarm sound.

[0083] The monitoring terminal can be a computer device used by file management personnel.

[0084] By setting sensors to monitor the environment inside the filing cabinet, it can timely inform the file management personnel to handle it when the environment changes, effectively ensuring the safe storage of accounting files.

[0085] Furthermore, the intelligent accounting file management cabinet of the present invention further includes a locking device. Only when the face comparison module judges that the user has the viewing permission, it will be unlocked. After the locking device is locked, it can make the filing cabinet body unable to move. In this way, when the filing cabinet bodies are placed with a very small interval between each other, the user cannot enter between the two filing cabinet bodies to obtain accounting materials, thus ensuring the security of accounting materials.

[0086] Preferably, the images stored in the database module are images of the faces of personnel with the viewing permission of accounting files.

[0087] The images of these personnel can be input into the database module for storage by the method of manual input by the file management personnel.

[0088] Preferably, the comparison serial number is a positive integer, and the value range is [1, np], where np represents the total number of images stored in the database module.

[0089] The interval of the comparison serial number of the present invention is 1.

[0090] Preferably, based on the comparison serial number, the image obtained by the face acquisition module is compared with the image stored in the database module to determine whether the user has the viewing permission of accounting files, including:

[0091] First step, initialize the value of the comparison serial number cp to 1;

[0092] Second step, compare the image obtained by the face acquisition module with the image with the comparison serial number cp stored in the database module, and determine whether the similarity between the two images meets the judgment requirements. If so, end the comparison process; if not, enter the third step;

[0093] Third step, determine whether the value of cp is greater than or equal to np. If so, it means that the user does not have the viewing permission of accounting files; if not, enter the fourth step;

[0094] Fourth step, add 1 to the value of cp and enter the second step.

[0095] Through the above comparison process, it can be known that since the present invention sets the comparison serial number of the image with a high comparison success probability to be smaller, the comparison can be preferentially performed, so that the comparison efficiency can be improved.

[0096] Preferably, determining whether the similarity between two images meets the judgment requirements includes:

[0097] Calculate the cosine similarity between the two images, and determine whether the cosine similarity is greater than the set threshold. If so, it means that the similarity between the two images meets the judgment requirements; if not, it means that the similarity between the two images does not meet the judgment requirements.

[0098] The set threshold can be 0.8.

[0099] Preferably, calculating the cosine similarity between two images includes:

[0100] For images p1 and p2, the process of calculating the cosine similarity between p1 and p2 is as follows:

[0101] Perform noise reduction processing on p1 and p2 respectively using a preset noise reduction method to obtain images p10 and p20;

[0102] Calculate the cosine similarity between p10 and p20.

[0103] After noise reduction processing, noise can be suppressed, thereby improving the accuracy of the calculated cosine similarity.

[0104] Preferably, the preset noise reduction method includes:

[0105] S1, use dp to represent the image to be denoised, and convert dp into a grayscale image dps;

[0106] S2, obtain the connected components in dp;

[0107] S3, perform the following processing on each pixel point in dps respectively:

[0108] Use px to represent the pixel point in the grayscale image dps, and calculate the noise reduction area control value corresponding to px;

[0109] Perform noise reduction on px based on the noise reduction area control value.

[0110] The noise reduction algorithm of the present invention improves the existing noise reduction algorithm. In the process of noise reduction, the existing noise reduction algorithm generally sets a noise reduction window of a fixed size and does not consider the factor of the distance between the pixel point and the center of the minimum circumscribed circle of the connected component. When the pixel point to be denoised is farther away from the center, the closer it is to the intersection area of the two connected components, and the greater the probability of being a pixel point at the edge position of the image. The existing noise reduction algorithm easily causes the details at the edge of the image after noise reduction to be greatly suppressed, reducing the effective information content at the edge of the image. Obviously, this will reduce the accuracy of the calculated cosine similarity. Therefore, by calculating the noise reduction area control value, the present invention can make the range of pixel points participating in the noise reduction process change with the change of the noise reduction area control value, and can more effectively retain the clarity of the edge after noise reduction.

[0111] Preferably, a seed filling algorithm can be used to obtain the connected components in dp.

[0112] Preferably, the calculation function of the noise reduction area control value is:

[0113]

[0114] crlv px is the noise reduction area control value corresponding to px, dtmid px is the distance between px and the center of the minimum circumscribed circle of the connected component where px is located, dtmid maxThe diameter of the minimum circumscribed circle of the connected component where px is located, fcstd px The standard deviation of the grayscale values of the pixels whose distance from px is less than dst, grmx is the maximum value of the grayscale values of the pixels whose distance from px is less than dst, and wb is the distance weight; Φ is the maximum value of the control value.

[0115] The noise reduction area control value of the present invention is affected by dtmid px and fcstd px The larger dtmid px is, the greater the probability that the distance between px and the average coordinate of the connected component is farther. The larger fcstd px is, the higher the degree of dispersion of the grayscale values of the pixels around px. Based on dtmid px and fcstd px The calculated noise reduction area control value can make the noise reduction area control value smaller when the distance between px and the average coordinate of the connected component is farther and the degree of dispersion of the grayscale values of the surrounding pixels is higher, so as to reduce the impact on the edge sharpness.

[0116] The maximum value of the control value of the present invention can be 10.

[0117] The distance weight can be

[0118] Preferably, denoising px based on the noise reduction area control value includes:

[0119]

[0120] lspx is the grayscale value of px after denoising, gr px is the grayscale value of px before denoising, gr j is the grayscale value of j, wd is the set of pixels whose distance from px is less than crlv px dsqt px,j is the distance between px and j, σ1 is the standard deviation of the grayscale values of the pixels in wd, and σ2 is the standard deviation of the distances between the pixels in wd and px.

[0121] The above function for denoising can make the pixels with a smaller distance from px and a smaller difference in grayscale value from px obtain a higher influence weight during denoising, and can further retain the boundary information between connected components.

[0122] Preferably, the calculation function of the comparison value of the images in the database module is:

[0123]

[0124] calcv b is the comparison value of image b in the database module, N represents the number of images acquired by the face acquisition module within a set time interval; nsuc b represents the number of times that the user is judged to have viewing permission based on image b within the set time interval; qual b is the status value of image b, qual max is the maximum value of the status values of all images in the database module; w1 and w2 are the number weight and the status value weight respectively.

[0125] The comparison value of the present invention is calculated based on two aspects: the number of successful comparisons of image b and the status value of image b. When the value of nsuc b is larger and the value of qual b is larger, the comparison value of image b is larger, and image b is preferentially used to compare with the image obtained by the face acquisition module. Both static parameters and dynamic parameters are adopted in the calculation. In this way, the comparison values of the images in the database module can change dynamically, and the probability of successful comparison with only a few times can be improved.

[0126] In the present invention, the number weight and the status value weight can be respectively and

[0127] In the present invention, the set time interval can be the most recent week, and the end time of the time interval is the moment when the face acquisition module acquires the latest face image of the user.

[0128] Preferably, the calculation function of qual b is:

[0129]

[0130] bpu is the set of pixel points in image gb, gb is the grayscale image corresponding to image b, gr c is the grayscale value of pixel point c, nbpu is the total number of pixel points included in gb, gr max is the maximum value of the grayscale values of the pixel points in gb, nfce b is the number of pixel points belonging to the skin area included in image b, and λ is the calculation weight.

[0131] The status value is a static parameter. Therefore, it can be calculated and stored in advance so that it can be directly called when calculating the comparison value, thereby effectively improving the efficiency of calculating the comparison value. The status value of the present invention is obtained by comprehensively calculating the degree of dispersion of the gray values of the pixel points and the number of pixel points belonging to the skin area. Therefore, when the value of the degree of dispersion of the gray values of the pixel points is higher and the proportion of the pixel points belonging to the skin area is larger, the status value is larger, indicating that the more detailed information of the human face is included in such an image, and the more accurate comparison result can be obtained.

[0132] The calculation weight of the present invention can be

[0133] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and variations can be made according to the content of this specification. These embodiments are selected and specifically described in this specification to better explain the principle and practical application of the present invention, so that those skilled in the art can understand and utilize the present invention well. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. An intelligent accounting file management cabinet with a retrieval function, characterized in that, It includes a retrieval device, which includes a face collection module, a database module, and a face comparison module; The face collection module is used to obtain an image of the user's face; The database module is used to store the images for comparison; The face comparison module is used to compare the image obtained by the face collection module with the images stored in the database module to determine whether the user has the viewing permission for accounting files; The face comparison module includes a comparison serial number maintenance unit and a comparison unit; The comparison serial number maintenance unit is used to regularly update the comparison serial numbers of the images stored in the database module for comparison; The comparison unit is used to compare the image obtained by the face collection module with the images stored in the database module based on the comparison serial numbers to determine whether the user has the viewing permission for accounting files; The determination process of the comparison serial number includes: Calculating the comparison values of each image in the database module; Determining the comparison serial numbers of the images in the database module in descending order of the comparison values. The larger the comparison value, the smaller the comparison serial number.

2. The intelligent accounting file management cabinet with a retrieval function according to claim 1, characterized in that, The retrieval device further includes a retrieval module, which includes an input unit, a retrieval unit, and an information storage unit; The input unit is used to obtain the retrieval information input by the user after the face comparison module determines that the user has the viewing permission; The information storage unit is used to store the location information of the accounting files; The retrieval unit is used to obtain the location information of the accounting file corresponding to the retrieval information from the location information stored in the information storage unit according to the retrieval information.

3. An intelligent accounting archive management cabinet with a retrieval function according to claim 1, characterized in that, It further includes a filing cabinet body, which is used to store paper accounting file materials; The retrieval device is arranged on the side of the filing cabinet body.

4. The intelligent accounting file management cabinet with a retrieval function according to claim 3, characterized in that, It further includes a wireless monitoring device; The wireless monitoring device includes a wireless monitoring sensor and a monitoring terminal; The wireless monitoring sensor is arranged inside the filing cabinet body and is used to obtain the environmental data inside the filing cabinet body and to transmit the environmental data to the monitoring terminal; The monitoring terminal is used to judge whether the environment inside the filing cabinet body is abnormal according to the environmental data, and to send a reminder to the file management personnel when the environment inside the filing cabinet body is abnormal.

5. The intelligent accounting file management cabinet with a retrieval function according to claim 1, characterized in that The images stored in the database module are the images of the faces of the personnel who have the viewing permission for accounting files.

6. The intelligent accounting archive management cabinet with a retrieval function according to claim 1, characterized in that, The comparison serial number is a positive integer, and its value range is [1, np], where np represents the total number of images stored in the database module.

7. The intelligent accounting file management cabinet with a retrieval function according to claim 6, characterized in that, Based on the comparison serial number, comparing the image obtained by the face collection module with the images stored in the database module to determine whether the user has the viewing permission for accounting files includes: First step, initializing the value of the comparison serial number cp to 1; Second step, comparing the image obtained by the face collection module with the image in the database module with the comparison serial number cp, and judging whether the similarity between the two images meets the judgment requirements. If so, end the comparison process; if not, enter the third step; Third step, judging whether the value of cp is greater than or equal to np. If so, it means that the user does not have the viewing permission for accounting files; if not, enter the fourth step; Fourth step, adding 1 to the value of cp and entering the second step.

8. The intelligent accounting file management cabinet with a retrieval function according to claim 7, characterized in that, Judging whether the similarity between the two images meets the judgment requirements includes: Calculate the cosine similarity between two images, and determine whether the cosine similarity is greater than the set threshold. If so, it means that the similarity between the two images meets the judgment requirements; if not, it means that the similarity between the two images does not meet the judgment requirements.

9. The intelligent accounting file management cabinet with a retrieval function according to claim 1, characterized in that, The calculation function of the comparison value of the images in the database module is: calcv b is the comparison value of image b in the database module, and N represents the number of images acquired by the face acquisition module within the set time interval; nsuc b represents the number of times that the user is judged to have viewing permission based on image b within the set time interval; qual b is the status value of image b, qual max is the maximum value of the status values of all images in the database module; w1 and w2 are the frequency weight and the status value weight respectively.

10. The intelligent accounting file management cabinet with a retrieval function according to claim 9, characterized in that, qual b The calculation function is as follows: The bpu is a set of pixel points in the image gb, where gb is the grayscale image corresponding to the image b, and gr c is the grayscale value of the pixel point c, nbpu is the total number of pixel points included in gb, and gr max is the maximum value of the grayscale values of the pixel points in gb, and nfce b is the number of pixel points belonging to the skin region included in the image b, and λ is the calculation weight.

Images