CN117670259A - Sample detection information management method - Google Patents
Sample detection information management method Download PDFInfo
- Publication number
- CN117670259A CN117670259A CN202410130673.2A CN202410130673A CN117670259A CN 117670259 A CN117670259 A CN 117670259A CN 202410130673 A CN202410130673 A CN 202410130673A CN 117670259 A CN117670259 A CN 117670259A
- Authority
- CN
- China
- Prior art keywords
- image
- information
- resolution
- axis direction
- sitting
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000007726 management method Methods 0.000 title claims abstract description 62
- 238000001514 detection method Methods 0.000 title claims abstract description 35
- 238000012545 processing Methods 0.000 claims abstract description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 17
- 238000000034 method Methods 0.000 claims description 17
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000012216 screening Methods 0.000 claims description 9
- 238000012795 verification Methods 0.000 claims description 4
- 238000013215 result calculation Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 230000002159 abnormal effect Effects 0.000 description 10
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000013524 data verification Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000000338 in vitro Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of data processing, and particularly discloses a sample detection information management method.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a sample detection information management method.
Background
Referring to Chinese patent, the patent name is: a sample detection information management method and a sample detection apparatus (patent publication No. CN112334930A, patent publication No. 2021-02-05) comprising detecting a sample; if the sample detection result comprises abnormal sample detection information, carrying out classification statistics on the abnormal sample detection information to obtain at least one classification statistical result, wherein each classification statistical result comprises an abnormal category and abnormal sample statistical information belonging to the abnormal category; the embodiment of the application also provides sample detection equipment, wherein the abnormal category and the abnormal sample statistical information belonging to the abnormal category can be directly obtained from the sample detection result according to the abnormal category of the sample, and the detection information of each abnormal sample does not need to be searched from a large number of detection results, so that the workload is reduced, and the in-vitro detection efficiency is improved.
Based on the description of the above patent, the existing enterprises or administrative units are involved in the operation of voting for the implementation of decisions in the development decision making process of the enterprises, and in the current voting information management process, the decision making operation needs to be completed by manual statistics of personnel or by a voter, so that the time required is long, the error rate is high, and the management of sample information is messy and inconvenient for the subsequent use or the retrieval of consulting.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a sample detection information management method, which solves the problems that in the process of carrying out development decision of a company, the prior enterprise or administrative unit can be involved in carrying out voting operation on decision implementation, in the process of carrying out the prior voting information management, personnel are required to manually count or a voter is required to complete the decision operation, the required time is long, the error rate is high, the management of sample information is messy, and the follow-up use or the retrieval of the reference is inconvenient.
In order to achieve the above purpose, the invention is realized by the following technical scheme: the sample detection information management method specifically comprises the following steps:
a1, arranging sitting personnel according to the sequence positions, collecting sample images of the operation of the personnel when making a resolution, and storing all collected sample information;
a2, summarizing the sample information to form a data set, and performing management operation on the data set information;
a01, leading out data from an information management database, positioning information in a data set and information of sitting people through a positioning algorithm, and finishing information verification of the sitting people at a sequence position;
a02, leading out data from the information management database, and completing matching of the checking completion information in a01 and the characteristic information in the data set through a matching algorithm to realize screening of useful sample image information;
a03, carrying out identification processing on useful sample image information, finding out required feature points, and marking the required feature points as M;
a3, counting and storing the sample images with the useful characteristic points, and collecting the counting result of the resolution operation;
and A4, displaying the resolution result on a display screen.
Preferably, the specific operation steps of the positioning algorithm in the a01 are as follows:
b1, selecting a plurality of data subsets containing blank images of no sitting person in a data set, forming a complete sitting position image with a mark P according to image combination, and marking a characteristic seat in the image P;
b2, leading out the information of the resolution personnel from the information management database, and carrying out corresponding sequencing on the information of the resolution personnel and the characteristic seats in the image P to finish the positioning operation of the information of the personnel sitting seats;
b3, selecting a plurality of corresponding image data subsets containing sitting persons in the data set, forming a complete image mark Q corresponding to the image P according to image combination, and identifying the sitting persons in the image Q;
and B4, finishing the comparison positioning operation of the information of the sitting person and the arrangement information of the sitting person.
Preferably, the specific operations of B1 and B3 for identifying the feature seat in the image P and for identifying the sitting person in the image Q are as follows:
b01, establishing coordinate axis marks by taking the left lower corner end points of the image P and the image Q as original points, wherein the right side is an X axis, and the rear side is a Y axis;
b02 and marking the seating features in a left-to-right, bottom-to-top order asAnd seat feature indicia P n Is +.>And the information characteristic of the sitting person is marked as +.>And the sitting person information feature mark Q n Corresponding coordinates of +.>。
Preferably, the specific operations for image combination in B1 and B3 are:
c1, firstly selecting two adjacent image subsets, and keeping consistency after finishing the exchange of the image directions;
c2, determining that adjacent image subsets are adjacent in the X-axis direction or adjacent in the Y-axis direction, and knowing whether overlapping parts exist in the adjacent image subsets through the marked characteristic parts;
performing stitching operation on the images after the overlapping part is processed, so that the images are overlapped to form a new image subset;
and C4, selecting an adjacent image subset based on the processed image subset, and continuously repeating the operation steps of C1-C3 until the final image contains a complete sitting position image or a position image where a sitting person sits.
Preferably, the specific operation for the overlapping portion processing in C3 is:
c01, firstly marking the characteristic parts of the selected adjacent image subsets, and marking the characteristic parts as K in sequence, wherein the distinction of the corresponding different characteristic parts is expressed asAnd Kx denotes an xth feature in the X-axis direction, and Ky denotes a yth feature in the Y-axis direction on the Kx-based basis;
c02, finishing the feature overlapping operation of the adjacent image subsets, wherein the first image subset is positioned at the tail end or the top end of the Y-axis direction of the X-axis direction and the feature part in the second image subset is compared until the feature part of the first image subset positioned at the tail end or the top end of the Y-axis direction is identical to the feature part of the second image subset in the X-axis direction or the Y-axis direction, and recording the feature part of the second image subset in the X-axis direction or the Y-axis direction;
and c03, sequentially and sequentially connecting the characteristic parts in the X-axis direction or the Y-axis direction in the second image subset in a straight line manner to form a dividing line of the second image subset, performing image dividing operation according to the dividing line, and splicing the first image subset and the divided second image subset along the dividing line to form a new image subset after completion.
Preferably, the step of the alignment positioning operation in B4 is as follows:
d1, screening out face recognition information of personnel entering a meeting place from an information management database;
d2, comparing the face recognition information of the entered person with the position information of the seated person, and comparing the position information of the seated person with the information of the seated person at the position;
and D3, after confirming that the information compared by the D2 is correct, finishing the information checking operation of the sitting person at the sequence position, and carrying out subsequent resolution information statistics operation.
Preferably, the implementation of the matching algorithm in a02 is as follows:
e1, according to the acquired image information, the information comprises hand lifting characteristic parts at different stages, and the personnel information with the hand lifting characteristic parts is identified;
e2, carrying out matching operation of personnel information on the basis of the personnel information with the hand lifting characteristic part, introducing the information which accords with the resolution personnel for comparison, finally reserving useful sample image characteristics which have the hand lifting characteristic part and accord with the resolution personnel information, and screening out sample image characteristics which have the hand lifting characteristic part and are irrelevant to resolution;
and E3, storing and counting the useful sample image characteristics.
Preferably, the hand lifting feature parts in different stages expressed in E1 are expressed as a hand lifting feature part in the stage of agreeing to the resolution result and a hand lifting feature part in the stage of objecting to the resolution result, and the hand lifting feature part in the stage of agreeing to the resolution result is marked asThe hand lifting feature part under the objection resolution outcome stage is marked as +.>。
Preferably, the statistical result calculation algorithm for the resolution operation in A3 is:
f1, calculating the hand lifting characteristic part in the stage of agreeing to the resolution result, wherein a calculation formula is as followsAnd->Representing the sum of the numbers of the hand lifting characteristic parts;
f2, calculating the hand lifting characteristic part in the stage of the anti-resolution result, wherein the calculation formula is thatAnd->Representing the sum of the numbers of the hand lifting characteristic parts;
f3, calculating the resolution passing rate according to a calculation formula:wherein->Is the total number of people for resolution, and is +.>；
Resolution objection ratio:；
the abandoning rate is as follows:；
and according to R 1 、R 2 And R is 3 And (3) comparing the results of the decision to judge whether the decision result is valid.
Preferably, the determining manner of the decision result in F3 is as follows: according to the calculated resolution passing rate R 1 Or R in resolution of objection ratio 2 If the percentage of the solution is greater than 50%, the decision is passed or rejected, and the rejection rate R 3 Greater than 50%, the resolution is set aside.
Advantageous effects
The invention provides a sample detection information management method. Compared with the prior art, the method has the following beneficial effects:
(1) According to the sample detection information management method, the sample information is summarized to form the data set, and the data set information is managed, wherein data is led out from the information management database, positioning of information in the data set and information of the sitting staff is completed through a positioning algorithm, so that information before decision making can be managed, meanwhile, checking operation of the information of the sitting staff is facilitated, conversion of information through image acquisition operation on site in manual statistics operation is abandoned, a complete image subset on site is formed through combination of a plurality of images, recognition of information and decision result statistics operation are completed, efficiency and accuracy are improved, and information authenticity of the decision staff is guaranteed.
(2) The sample detection information management method marks the characteristic parts of the selected adjacent image subsets, wherein the characteristic parts of the first image subset positioned at the tail end or the top end in the Y-axis direction are compared with the characteristic parts of the second image subset until the characteristic parts of the first image subset positioned at the tail end or the top end in the X-axis direction are identical with the characteristic parts of the second image subset in the X-axis direction or the Y-axis direction, and the characteristic parts of the second image subset in the X-axis direction or the Y-axis direction are recorded to form a dividing line, so that the image is divided and the subsequent stitching operation is completed, the influence on the information management result caused by the repetition of the characteristic parts of the image is avoided, and the subsequent characteristic recognition and statistics are facilitated.
(3) According to the sample detection information management method, the information which accords with the resolution personnel is introduced for comparison through the collection of the image information of the hand lifting characteristic part at different stages, finally, the useful sample image characteristics which have the hand lifting characteristic part and accord with the resolution personnel information are reserved, statistics is carried out on the results after the verification information is completed, so that the process results of sample detection can be obtained conveniently and quickly, and the management of data is completed through an information management database, so that the management and control and the subsequent retrieval of the results are facilitated.
Drawings
FIG. 1 is a flow chart of an information management method of the present invention;
fig. 2 is a schematic block diagram of an information management system of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1-2, the present invention provides two technical schemes:
an embodiment one, a sample detection information management method, specifically includes the following steps:
a1, arranging sitting personnel according to the sequence positions, collecting sample images of the operation of the personnel when making a resolution, and storing all collected sample information;
a2, summarizing the sample information to form a data set, and performing management operation on the data set information;
a01, leading out data from an information management database, positioning information in a data set and information of sitting people through a positioning algorithm, and finishing information verification of the sitting people at a sequence position;
a02, leading out data from the information management database, and completing matching of the checking completion information in a01 and the characteristic information in the data set through a matching algorithm to realize screening of useful sample image information;
a03, carrying out identification processing on useful sample image information, finding out required feature points, and marking the required feature points as M;
a3, counting and storing the sample images with the useful characteristic points, and collecting the counting result of the resolution operation;
and A4, displaying the resolution result on a display screen.
A plurality of cameras are arranged above the resolution place to complete the collection operation of the information state in the meeting place, the information collected by the cameras is transmitted to an information management database using the information management method to be stored and used, and meanwhile, the face recognition and the storage operation of the information of personnel can be carried out in the entering process.
In the embodiment of the invention, the specific operation steps of the positioning algorithm in a01 are as follows:
b1, selecting a plurality of data subsets containing blank images of no sitting person in a data set, forming a complete sitting position image with a mark P according to image combination, and marking a characteristic seat in the image P;
b2, leading out the information of the resolution personnel from the information management database, and carrying out corresponding sequencing on the information of the resolution personnel and the characteristic seats in the image P to finish the positioning operation of the information of the personnel sitting seats;
b3, selecting a plurality of corresponding image data subsets containing sitting persons in the data set, forming a complete image mark Q corresponding to the image P according to image combination, and identifying the sitting persons in the image Q;
and B4, finishing the comparison positioning operation of the information of the sitting person and the arrangement information of the sitting person.
The method comprises the steps of collecting sample information to form a data set, carrying out management operation on the data set information, leading out data from an information management database, and positioning information in the data set and information of sitting staff through a positioning algorithm, so that the information before decision can be managed, meanwhile, the checking operation of the information of the sitting staff is facilitated, the conversion of the information through the image acquisition operation on site by manual statistics operation is abandoned, the combination of a plurality of images to form a complete image subset on site is completed, the identification of the information and the statistics operation of decision results are completed, the efficiency and the accuracy are improved, and meanwhile, the information authenticity of the decision staff is guaranteed.
In the embodiment of the invention, specific operations of identifying the characteristic seats in the image P and identifying the sitting person in the image Q in the B1 and the B3 are as follows:
b01, establishing coordinate axis marks by taking the left lower corner end points of the image P and the image Q as original points, wherein the right side is an X axis, and the rear side is a Y axis;
b02 and marking the seating features in a left-to-right, bottom-to-top order asAnd seat feature indicia P n Is +.>And the information characteristic of the sitting person is marked as +.>And the sitting person information feature mark Q n Corresponding coordinates of +.>。
In the embodiment of the present invention, specific operations for image combination in B1 and B3 are:
c1, firstly selecting two adjacent image subsets, and keeping consistency after finishing the exchange of the image directions;
c2, determining that adjacent image subsets are adjacent in the X-axis direction or adjacent in the Y-axis direction, and knowing whether overlapping parts exist in the adjacent image subsets through the marked characteristic parts;
performing stitching operation on the images after the overlapping part is processed, so that the images are overlapped to form a new image subset;
and C4, selecting an adjacent image subset based on the processed image subset, and continuously repeating the operation steps of C1-C3 until the final image contains a complete sitting position image or a position image where a sitting person sits.
In the embodiment of the present invention, the specific operation for the overlapping portion processing in C3 is:
c01, firstly marking the characteristic parts of the selected adjacent image subsets, and marking the characteristic parts as follows in sequenceWhile the distinction corresponding to the different characteristic parts is denoted +.>And Kx denotes an xth feature in the X-axis direction, and Ky denotes a yth feature in the Y-axis direction on the Kx-based basis;
c02, finishing the feature overlapping operation of the adjacent image subsets, wherein the first image subset is positioned at the tail end or the top end of the Y-axis direction of the X-axis direction and the feature part in the second image subset is compared until the feature part of the first image subset positioned at the tail end or the top end of the Y-axis direction is identical to the feature part of the second image subset in the X-axis direction or the Y-axis direction, and recording the feature part of the second image subset in the X-axis direction or the Y-axis direction;
and c03, sequentially and sequentially connecting the characteristic parts in the X-axis direction or the Y-axis direction in the second image subset in a straight line manner to form a dividing line of the second image subset, performing image dividing operation according to the dividing line, and splicing the first image subset and the divided second image subset along the dividing line to form a new image subset after completion.
The feature parts of the adjacent image subsets are selected to be marked, wherein the first image subset is positioned at the tail end or the top end of the Y-axis direction of the X-axis direction of the first image subset and the feature parts of the second image subset are paired, until the feature parts of the first image subset positioned at the tail end or the top end of the Y-axis direction of the X-axis direction of the first image subset are identical to the feature parts of the second image subset in the X-axis direction or the Y-axis direction of the second image subset, and the feature parts of the second image subset in the X-axis direction or the Y-axis direction of the second image subset are recorded to form a dividing line, so that the image is divided and the subsequent stitching operation is completed, the influence on the information management result caused by the repetition of the feature parts of the image is avoided, and the subsequent feature recognition and statistics are facilitated.
In the embodiment of the invention, the steps of the comparison positioning operation in the B4 are as follows:
d1, screening out face recognition information of personnel entering a meeting place from an information management database;
d2, comparing the face recognition information of the entered person with the position information of the seated person, and comparing the position information of the seated person with the information of the seated person at the position;
and D3, after confirming that the information compared by the D2 is correct, finishing the information checking operation of the sitting person at the sequence position, and carrying out subsequent resolution information statistics operation.
The difference between the second embodiment and the first embodiment is that: in the embodiment of the present invention, the implementation of the matching algorithm in a02 is:
e1, according to the acquired image information, the information comprises hand lifting characteristic parts at different stages, and the personnel information with the hand lifting characteristic parts is identified;
e2, carrying out matching operation of personnel information on the basis of the personnel information with the hand lifting characteristic part, introducing the information which accords with the resolution personnel for comparison, finally reserving useful sample image characteristics which have the hand lifting characteristic part and accord with the resolution personnel information, and screening out sample image characteristics which have the hand lifting characteristic part and are irrelevant to resolution;
and E3, storing and counting the useful sample image characteristics.
The embodiment of the invention also relates to an information management system of the information management method, which comprises the following steps:
the acquisition terminal is used for acquiring information on site and acquiring sample images of personnel operation during resolution;
the information management system is used for summarizing the sample information, finishing the checking operation of the image information and the personnel information, simultaneously finishing the identification of the characteristic parts in the image, and calculating the decision result after finishing the identification;
and the result display panel is used for displaying the calculation result or the called information.
In the embodiment of the invention, the hand-lifting feature parts expressed in E1 at different stages are expressed as a hand-lifting feature part at the stage of agreeing to the resolution result and a hand-lifting feature part at the stage of objecting to the resolution result, and the hand-lifting feature part at the stage of agreeing to the resolution result is marked asThe hand lifting feature part under the objection resolution outcome stage is marked as +.>。
In the embodiment of the present invention, the statistical result calculation algorithm for the resolution operation in A3 is:
f1, calculating the hand lifting characteristic part in the stage of agreeing to the resolution result, wherein a calculation formula is as followsAnd->Representing the sum of the numbers of the hand lifting characteristic parts;
f2, calculating the hand lifting characteristic part in the stage of the anti-resolution result, wherein the calculation formula is thatAnd->Representing the sum of the numbers of the hand lifting characteristic parts;
f3, calculating the resolution passing rate according to a calculation formula:wherein->Is the total number of people for resolution, and is +.>；
Resolution objection ratio:；
the abandoning rate is as follows:；
and according to R 1 、R 2 And R is 3 And (3) comparing the results of the decision to judge whether the decision result is valid.
In the embodiment of the present invention, the judgment manner for the decision result in F3 is: according to the calculated resolution passing rate R 1 Or R in resolution of objection ratio 2 Percent of (v)If the ratio is greater than 50%, the decision is passed or rejected, and the rejection rate R 3 Greater than 50%, the resolution is set aside.
The method comprises the steps of acquiring image information of a hand lifting characteristic part in different stages, introducing information conforming to a resolution person for comparison, finally reserving useful sample image characteristics which are provided with the hand lifting characteristic part and conform to the resolution person information, counting results after checking information is completed, facilitating quick acquisition of sample detection process results, completing data management through an information management database, and facilitating management and control and subsequent retrieval of the results.
Comparative experiments
A company a performs decision-making conference of the company at three places of a conference place X, Y, Z, wherein information and results in the conference are collected and counted in two ways, the data results on a voter are counted by a counting personnel in the first way, the data results on a voter are counted in the second way through a system adopting a sample detection information management method, and the time and accuracy results of the final counted results in the first and second ways are counted, so that the obtained results are shown in the following table:
in summary, after the sample detection information management method provided by the invention processes the decision conference data of company a at the three places of conference X, Y, Z, not only the accuracy and the authenticity of the information in the data verification of the information management can be ensured, but also the result statistics efficiency can be effectively improved in the process of counting the decision result, and the accuracy of the result is maintained, so that the information management operation is more convenient.
And all that is not described in detail in this specification is well known to those skilled in the art.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. A sample detection information management method is characterized in that: the method specifically comprises the following steps:
a1, arranging sitting personnel according to the sequence positions, collecting sample images of the operation of the personnel when making a resolution, and storing all collected sample information;
a2, summarizing the sample information to form a data set, and performing management operation on the data set information;
a01, leading out data from an information management database, positioning information in a data set and information of sitting people through a positioning algorithm, and finishing information verification of the sitting people at a sequence position;
a02, leading out data from the information management database, and completing matching of the checking completion information in a01 and the characteristic information in the data set through a matching algorithm to realize screening of useful sample image information;
a03, carrying out identification processing on useful sample image information, finding out required feature points, and marking the required feature points as M;
a3, counting and storing the sample images with the useful characteristic points, and collecting the counting result of the resolution operation;
and A4, displaying the resolution result on a display screen.
2. The sample detection information management method according to claim 1, wherein: the specific operation steps of the positioning algorithm in the a01 are as follows:
b1, selecting a plurality of data subsets containing blank images of no sitting person in a data set, forming a complete sitting position image with a mark P according to image combination, and marking a characteristic seat in the image P;
b2, leading out the information of the resolution personnel from the information management database, and carrying out corresponding sequencing on the information of the resolution personnel and the characteristic seats in the image P to finish the positioning operation of the information of the personnel sitting seats;
b3, selecting a plurality of corresponding image data subsets containing sitting persons in the data set, forming a complete image mark Q corresponding to the image P according to image combination, and identifying the sitting persons in the image Q;
and B4, finishing the comparison positioning operation of the information of the sitting person and the arrangement information of the sitting person.
3. The sample detection information management method according to claim 2, wherein: the specific operations of the B1 and the B3 for identifying the characteristic seats in the image P and the sitting person in the image Q are as follows:
b01, establishing coordinate axis marks by taking the left lower corner end points of the image P and the image Q as original points, wherein the right side is an X axis, and the rear side is a Y axis;
b02 and marking the seating features in a left-to-right, bottom-to-top order asAnd seat feature indicia P n Is +.>And the information characteristic of the sitting person is marked as +.>And the sitting person information feature mark Q n Corresponding coordinates of (a) are。
4. The sample detection information management method according to claim 2, wherein: the specific operations for image combination in B1 and B3 are:
c1, firstly selecting two adjacent image subsets, and keeping consistency after finishing the exchange of the image directions;
c2, determining that adjacent image subsets are adjacent in the X-axis direction or adjacent in the Y-axis direction, and knowing whether overlapping parts exist in the adjacent image subsets through the marked characteristic parts;
performing stitching operation on the images after the overlapping part is processed, so that the images are overlapped to form a new image subset;
and C4, selecting an adjacent image subset based on the processed image subset, and continuously repeating the operation steps of C1-C3 until the final image contains a complete sitting position image or a position image where a sitting person sits.
5. The sample detection information management method according to claim 4, wherein: the specific operation of the overlapping part processing in the C3 is as follows:
c01, firstly marking the characteristic parts of the selected adjacent image subsets, and marking the characteristic parts as K in sequence, wherein the distinction of the corresponding different characteristic parts is expressed asAnd Kx denotes an xth feature in the X-axis direction, and Ky denotes a yth feature in the Y-axis direction on the Kx-based basis;
c02, finishing the feature overlapping operation of the adjacent image subsets, wherein the first image subset is positioned at the tail end or the top end of the Y-axis direction of the X-axis direction and the feature part in the second image subset is compared until the feature part of the first image subset positioned at the tail end or the top end of the Y-axis direction is identical to the feature part of the second image subset in the X-axis direction or the Y-axis direction, and recording the feature part of the second image subset in the X-axis direction or the Y-axis direction;
and c03, sequentially and sequentially connecting the characteristic parts in the X-axis direction or the Y-axis direction in the second image subset in a straight line manner to form a dividing line of the second image subset, performing image dividing operation according to the dividing line, and splicing the first image subset and the divided second image subset along the dividing line to form a new image subset after completion.
6. The sample detection information management method according to claim 2, wherein: the step of the comparison positioning operation in the B4 is as follows:
d1, screening out face recognition information of personnel entering a meeting place from an information management database;
d2, comparing the face recognition information of the entered person with the position information of the seated person, and comparing the position information of the seated person with the information of the seated person at the position;
and D3, after confirming that the information compared by the D2 is correct, finishing the information checking operation of the sitting person at the sequence position, and carrying out subsequent resolution information statistics operation.
7. The sample detection information management method according to claim 1, wherein: the implementation mode of the matching algorithm in the a02 is as follows:
e1, according to the acquired image information, the information comprises hand lifting characteristic parts at different stages, and the personnel information with the hand lifting characteristic parts is identified;
e2, carrying out matching operation of personnel information on the basis of the personnel information with the hand lifting characteristic part, introducing the information which accords with the resolution personnel for comparison, finally reserving useful sample image characteristics which have the hand lifting characteristic part and accord with the resolution personnel information, and screening out sample image characteristics which have the hand lifting characteristic part and are irrelevant to resolution;
and E3, storing and counting the useful sample image characteristics.
8. The sample detection information management method according to claim 7, wherein: the hand lifting characteristic parts under different stages expressed in the E1 are expressed as a hand lifting characteristic part under the stage of agreeing to the resolution result and a hand lifting characteristic part under the stage of objecting to the resolution result, and the hand lifting characteristic part under the stage of agreeing to the resolution result is marked asThe hand lifting characteristic part under the stage of objecting resolution result is marked as。
9. The sample detection information management method according to claim 8, wherein: the statistical result calculation algorithm for the resolution operation in the A3 is as follows:
f1, calculating the hand lifting characteristic part in the stage of agreeing to the resolution result, wherein a calculation formula is as followsAnd->Representing the sum of the numbers of the hand lifting characteristic parts;
f2, calculating the hand lifting characteristic part in the stage of the anti-resolution result, wherein the calculation formula is thatAnd->Representing the sum of the numbers of the hand lifting characteristic parts;
f3, calculating the resolution passing rate according to a calculation formula:wherein->Is the total number of people for resolution, and is +.>；
Resolution objection ratio:；
the abandoning rate is as follows:；
and according to R 1 、R 2 And R is 3 And (3) comparing the results of the decision to judge whether the decision result is valid.
10. The sample detection information management method according to claim 9, wherein: the judging mode of the decision result in F3 is as follows: according to the calculated resolution passing rate R 1 Or R in resolution of objection ratio 2 If the percentage of the solution is greater than 50%, the decision is passed or rejected, and the rejection rate R 3 Greater than 50%, the resolution is set aside.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410130673.2A CN117670259B (en) | 2024-01-31 | 2024-01-31 | Sample detection information management method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410130673.2A CN117670259B (en) | 2024-01-31 | 2024-01-31 | Sample detection information management method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117670259A true CN117670259A (en) | 2024-03-08 |
| CN117670259B CN117670259B (en) | 2024-04-19 |
Family
ID=90064459
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410130673.2A Active CN117670259B (en) | 2024-01-31 | 2024-01-31 | Sample detection information management method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117670259B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201203895Y (en) * | 2007-12-27 | 2009-03-04 | 武汉市工程科学技术研究院 | Ballot statistical apparatus base on image recognition |
| US20130301873A1 (en) * | 2012-05-11 | 2013-11-14 | Dominion Voting Systems, Inc. | Ballot adjudication in voting systems utilizing ballot images |
| CN107609517A (en) * | 2017-09-15 | 2018-01-19 | 华中科技大学 | A kind of classroom behavior detecting system based on computer vision |
| CN107808376A (en) * | 2017-10-31 | 2018-03-16 | 上海交通大学 | A kind of detection method of raising one's hand based on deep learning |
| CN108898728A (en) * | 2018-06-12 | 2018-11-27 | 广州视源电子科技股份有限公司 | Intelligent interaction device and its voting method, device and system |
| CN109035543A (en) * | 2018-07-28 | 2018-12-18 | 马鞍山悠生活网络文化科技有限公司 | A kind of exhibitions ballot automatic identification equipment and its application method |
| CN109165641A (en) * | 2018-10-31 | 2019-01-08 | 国网安徽省电力有限公司信息通信分公司 | Video conference order analysis method based on recognition of face |
| CN110399822A (en) * | 2019-07-17 | 2019-11-01 | 思百达物联网科技(北京)有限公司 | Action identification method of raising one's hand, device and storage medium based on deep learning |
| CN110782185A (en) * | 2019-11-09 | 2020-02-11 | 上海光数信息科技有限公司 | Classroom behavior recognition and analysis method |
| CN111951457A (en) * | 2020-07-06 | 2020-11-17 | 视联动力信息技术股份有限公司 | Electronic voting method, device, terminal equipment and storage medium |
| CN112668376A (en) * | 2019-10-16 | 2021-04-16 | 北京三好互动教育科技有限公司 | Hand-lifting statistic device, and hand-lifting people number statistic method and device |
| KR20210093611A (en) * | 2020-01-20 | 2021-07-28 | 한국예탁결제원 | Management server for shareholders'meetings and method thereof |
| CN113436379A (en) * | 2021-08-26 | 2021-09-24 | 深圳市永兴元科技股份有限公司 | Intelligent voting method, device, equipment and storage medium |
| CN115937971A (en) * | 2022-11-18 | 2023-04-07 | 广州市保伦电子有限公司 | Hand-raising voting identification method and device |
| CN116155475A (en) * | 2023-01-06 | 2023-05-23 | 天津师范大学 | Method for rapidly improving SPN type block cipher differential path probability |
-
2024
- 2024-01-31 CN CN202410130673.2A patent/CN117670259B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201203895Y (en) * | 2007-12-27 | 2009-03-04 | 武汉市工程科学技术研究院 | Ballot statistical apparatus base on image recognition |
| US20130301873A1 (en) * | 2012-05-11 | 2013-11-14 | Dominion Voting Systems, Inc. | Ballot adjudication in voting systems utilizing ballot images |
| CN107609517A (en) * | 2017-09-15 | 2018-01-19 | 华中科技大学 | A kind of classroom behavior detecting system based on computer vision |
| CN107808376A (en) * | 2017-10-31 | 2018-03-16 | 上海交通大学 | A kind of detection method of raising one's hand based on deep learning |
| CN108898728A (en) * | 2018-06-12 | 2018-11-27 | 广州视源电子科技股份有限公司 | Intelligent interaction device and its voting method, device and system |
| CN109035543A (en) * | 2018-07-28 | 2018-12-18 | 马鞍山悠生活网络文化科技有限公司 | A kind of exhibitions ballot automatic identification equipment and its application method |
| CN109165641A (en) * | 2018-10-31 | 2019-01-08 | 国网安徽省电力有限公司信息通信分公司 | Video conference order analysis method based on recognition of face |
| CN110399822A (en) * | 2019-07-17 | 2019-11-01 | 思百达物联网科技(北京)有限公司 | Action identification method of raising one's hand, device and storage medium based on deep learning |
| CN112668376A (en) * | 2019-10-16 | 2021-04-16 | 北京三好互动教育科技有限公司 | Hand-lifting statistic device, and hand-lifting people number statistic method and device |
| CN110782185A (en) * | 2019-11-09 | 2020-02-11 | 上海光数信息科技有限公司 | Classroom behavior recognition and analysis method |
| KR20210093611A (en) * | 2020-01-20 | 2021-07-28 | 한국예탁결제원 | Management server for shareholders'meetings and method thereof |
| CN111951457A (en) * | 2020-07-06 | 2020-11-17 | 视联动力信息技术股份有限公司 | Electronic voting method, device, terminal equipment and storage medium |
| CN113436379A (en) * | 2021-08-26 | 2021-09-24 | 深圳市永兴元科技股份有限公司 | Intelligent voting method, device, equipment and storage medium |
| CN115937971A (en) * | 2022-11-18 | 2023-04-07 | 广州市保伦电子有限公司 | Hand-raising voting identification method and device |
| CN116155475A (en) * | 2023-01-06 | 2023-05-23 | 天津师范大学 | Method for rapidly improving SPN type block cipher differential path probability |
Non-Patent Citations (1)
| Title |
|---|
| 祝江土;: "通过人脸识别技术限制重复投票的电子投票系统的设计", 电子测试, no. 09, 5 May 2017 (2017-05-05) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117670259B (en) | 2024-04-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109961421B (en) | Data generating device, data generating method, and data generating recording medium | |
| CN109692877B (en) | Cold-rolled strip steel surface quality management system and method | |
| US5040227A (en) | Image balancing system and method | |
| EP1907980B1 (en) | Manually-assisted automated indexing of images using facial recognition | |
| CN108777021B (en) | Bill identification method and system based on scanner mixed scanning | |
| CN113256636B (en) | Bottom-up parasite species development stage and image pixel classification method | |
| US20140092244A1 (en) | Object search method, search verification method and apparatuses thereof | |
| JPH09508739A (en) | Fingerprint matching device | |
| CN105184225B (en) | A kind of multinational banknote image recognition methods and device | |
| JP5331621B2 (en) | Vehicle inspection device | |
| CN110287940B (en) | Palm print identification method and system based on artificial intelligence | |
| CN105913014A (en) | Identity card chip photograph and video-based identity authenticating method and system | |
| US11527102B2 (en) | Systems and methods of automated biometric identification reporting | |
| CN117670259B (en) | Sample detection information management method | |
| EP1833002A1 (en) | Method and apparatus for obtaining biometric image samples or biometric data | |
| CN113870202A (en) | Far-end chip defect detection system based on deep learning technology | |
| CN112989990A (en) | Medical bill identification method, device, equipment and storage medium | |
| CN111833296A (en) | Automatic detection and verification system and method for bone marrow cell morphology | |
| CN115266728A (en) | Method for identifying inclusion defects on surface of cold-rolled strip steel | |
| CN107607205A (en) | Wire harness color sequences detecting system and method | |
| EP0851379A2 (en) | A method of an apparatus for pre-selecting fingerprint cards | |
| CN109003259A (en) | Fingerprint quality evaluation method based on streakline Quality Expert's visual cognition machine learning | |
| CN116486423A (en) | Financial ticketing data processing method based on image recognition | |
| JP2003346080A (en) | Character recognition method | |
| CN112598503A (en) | OCR recognition system and method based on credit investigation recognition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |