CN116990450B - Defect detection method and system for cornea shaping mirror - Google Patents
Defect detection method and system for cornea shaping mirror Download PDFInfo
- Publication number
- CN116990450B CN116990450B CN202310881696.2A CN202310881696A CN116990450B CN 116990450 B CN116990450 B CN 116990450B CN 202310881696 A CN202310881696 A CN 202310881696A CN 116990450 B CN116990450 B CN 116990450B
- Authority
- CN
- China
- Prior art keywords
- defect detection
- data extraction
- data
- target
- sets
- 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.)
- Active
Links
- 230000007547 defect Effects 0.000 title claims abstract description 280
- 238000001514 detection method Methods 0.000 title claims abstract description 255
- 210000004087 cornea Anatomy 0.000 title claims abstract description 50
- 238000007493 shaping process Methods 0.000 title claims abstract description 49
- 238000013075 data extraction Methods 0.000 claims abstract description 209
- 238000012545 processing Methods 0.000 claims abstract description 164
- 238000013461 design Methods 0.000 claims abstract description 80
- 238000000034 method Methods 0.000 claims abstract description 37
- 238000004458 analytical method Methods 0.000 claims abstract description 34
- 230000009467 reduction Effects 0.000 claims abstract description 25
- 238000010276 construction Methods 0.000 claims description 14
- 238000003066 decision tree Methods 0.000 claims description 11
- 238000013528 artificial neural network Methods 0.000 claims description 10
- 238000013507 mapping Methods 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 8
- 238000005457 optimization Methods 0.000 claims description 5
- 230000000694 effects Effects 0.000 abstract description 5
- 230000008569 process Effects 0.000 description 6
- 238000007689 inspection Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 210000005252 bulbus oculi Anatomy 0.000 description 2
- 230000004931 aggregating effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Chemical & Material Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Computer Hardware Design (AREA)
- Food Science & Technology (AREA)
- Geometry (AREA)
- General Health & Medical Sciences (AREA)
- Pathology (AREA)
- Medicinal Chemistry (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Analytical Chemistry (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Eyeglasses (AREA)
Abstract
The invention discloses a defect detection method and a defect detection system for a cornea shaping lens, and relates to the technical field of cornea shaping lens detection, wherein the method comprises the following steps: acquiring processing information of a target lens; performing data dimension reduction processing to obtain N historical defect detection data sets; obtaining N design parameter intervals and N processing equipment sets; determining N first data extraction frequencies and N second data extraction frequencies; constructing a defect detection library; obtaining a target first data extraction frequency and a target second data extraction frequency; performing defect detection on the target lens to obtain a target defect detection data set; and inputting the target first data extraction frequency and the target second data extraction frequency into a defect detection analysis model to obtain a defect detection result. The invention solves the technical problems of low accuracy and poor reliability of detection results of the defect detection of the cornea shaping lens in the prior art, and achieves the technical effect of improving the defect detection efficiency of the cornea shaping lens.
Description
Technical Field
The invention relates to the technical field of cornea shaping mirror detection, in particular to a defect detection method and system of a cornea shaping mirror.
Background
The cornea shaping lens is in direct contact with the cornea of the eyeball, so that the cornea shaping lens has higher quality requirement. At present, the defect detection of the cornea shaping lens mainly utilizes a scientific detection technology to detect the cornea shaping lens, and utilizes an intelligent data processing technology to analyze lens detection data, however, because the cornea shaping lens is closely related to the eyeball structure of a wearer, the detection requirements are changed along with the difference of the wearer. Therefore, the general data processing technology cannot reliably process the detection data with high efficiency. In the prior art, the defect detection accuracy of the cornea shaping lens is low, and the reliability of the detection result is poor.
Disclosure of Invention
The application provides a defect detection method and a defect detection system for a cornea shaping lens, which are used for solving the technical problems of low defect detection accuracy and poor reliability of detection results of the cornea shaping lens in the prior art.
In view of the above problems, the present application provides a method and a system for detecting defects of a cornea shaping lens.
In a first aspect of the present application, there is provided a defect detection method for a cornea shaping mirror, the method comprising:
acquiring processing information of a target lens, wherein the processing information comprises design parameter information and processing equipment information;
extracting a historical defect detection data set processed by a cornea shaping mirror in a preset historical time window, and performing data dimension reduction processing to obtain N historical defect detection data sets, wherein each historical defect detection data set corresponds to one defect type;
Matching the N historical defect detection data sets with a historical processing database to obtain N design parameter intervals and N processing equipment sets, wherein the N design parameter intervals and the N processing equipment sets are in one-to-one correspondence;
Determining N first data extraction frequencies and N second data extraction frequencies based on the N sets of historical defect detection data;
constructing a defect detection library according to the N first data extraction frequencies, the N second data extraction frequencies, the N design parameter intervals and the N processing equipment sets;
inputting the design parameter information and the processing equipment information into the defect detection library for matching to obtain a target first data extraction frequency and a target second data extraction frequency;
performing defect detection on the target lens to obtain a target defect detection data set;
and inputting the target first data extraction frequency and the target second data extraction frequency into a defect detection analysis model by combining the target defect detection data set to obtain a defect detection result.
In a second aspect of the present application, there is provided a defect detection system for a cornea shaping lens, the system comprising:
The processing information acquisition module is used for acquiring processing information of the target lens, wherein the processing information comprises design parameter information and processing equipment information;
The detecting data set obtaining module is used for extracting a historical defect detecting data set processed by the cornea shaping mirror in a preset historical time window and carrying out data dimension reduction processing to obtain N historical defect detecting data sets, wherein each historical defect detecting data set corresponds to one defect type;
The processing equipment set obtaining module is used for matching the N historical defect detection data sets with a historical processing database to obtain N design parameter intervals and N processing equipment sets, wherein the N design parameter intervals are in one-to-one correspondence with the N processing equipment sets;
a data extraction frequency determination module for determining N first data extraction frequencies and N second data extraction frequencies based on the N sets of historical defect detection data;
the defect detection library construction module is used for constructing a defect detection library according to N first data extraction frequencies, N second data extraction frequencies, N design parameter intervals and N processing equipment sets;
The target extraction frequency obtaining module is used for inputting the design parameter information and the processing equipment information into the defect detection library for matching to obtain a target first data extraction frequency and a target second data extraction frequency;
The target detection data acquisition module is used for carrying out defect detection on the target lens to obtain a target defect detection data set;
The defect detection result obtaining module is used for obtaining a defect detection result by utilizing the target first data extraction frequency and the target second data extraction frequency and combining the target defect detection data set to input a defect detection analysis model.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
Acquiring processing information of a target lens, wherein the processing information comprises design parameter information and processing equipment information; extracting a historical defect detection data set processed by a cornea shaping mirror in a preset historical time window, and performing data dimension reduction processing to obtain N historical defect detection data sets, wherein each historical defect detection data set corresponds to one defect type; matching the N historical defect detection data sets with a historical processing database to obtain N design parameter intervals and N processing equipment sets, wherein the N design parameter intervals and the N processing equipment sets are in one-to-one correspondence; determining N first data extraction frequencies and N second data extraction frequencies based on the N historical defect detection data sets; constructing a defect detection library according to the N first data extraction frequencies, the N second data extraction frequencies, the N design parameter intervals and the N processing equipment sets; inputting design parameter information and processing equipment information into a defect detection library for matching to obtain a target first data extraction frequency and a target second data extraction frequency; performing defect detection on the target lens to obtain a target defect detection data set; and inputting the target first data extraction frequency and the target second data extraction frequency into a defect detection analysis model by combining the target defect detection data set to obtain a defect detection result. The technical effect of improving the reliability of the defect detection result and the detection efficiency is achieved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method for detecting defects of a cornea shaping lens according to an embodiment of the present application;
FIG. 2 is a schematic flow chart of obtaining N historical defect detection data sets according to N leaf nodes in a defect detection method of a cornea shaping lens according to an embodiment of the present application;
FIG. 3 is a schematic flow chart of N design parameter intervals obtained in the defect detection method of the cornea shaping lens according to the embodiment of the present application;
fig. 4 is a schematic structural diagram of a defect detection system of a cornea shaping lens according to an embodiment of the present application.
Reference numerals illustrate: the device comprises a processing information acquisition module 11, a detection data set acquisition module 12, a processing equipment set acquisition module 13, a data extraction frequency determination module 14, a defect detection library construction module 15, a target extraction frequency acquisition module 16, a target detection data acquisition module 17 and a defect detection result acquisition module 18.
Detailed Description
The application provides a defect detection method and a defect detection system for a cornea shaping lens, which are used for solving the technical problems of low defect detection accuracy and poor reliability of detection results of the cornea shaping lens in the prior art.
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It should be noted that the terms "comprises" and "comprising," along with any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus, but may include other steps or modules not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
As shown in fig. 1, the present application provides a defect detection method of a cornea shaping mirror, wherein the method comprises:
step S100: acquiring processing information of a target lens, wherein the processing information comprises design parameter information and processing equipment information;
In one possible embodiment, the target lens is any cornea shaping lens for which defect detection is desired. The processing information is the operation information of processing the blank of the cornea shaping lens into the target lens, and comprises design parameter information and processing equipment information. Wherein the design parameter information includes a long axial distance, a short axial distance, a tear storage capacity, a radius of curvature of an arc of a side, and the like. The processing equipment information is information describing equipment conditions of processing the target lens, and comprises processing equipment types, processing equipment service lives and the like. And basic data is provided for the defect detection of the lens by acquiring the processing information of the target lens.
Step S200: extracting a historical defect detection data set processed by a cornea shaping mirror in a preset historical time window, and performing data dimension reduction processing to obtain N historical defect detection data sets, wherein each historical defect detection data set corresponds to one defect type;
further, as shown in fig. 2, the step S200 of the embodiment of the present application further includes extracting the historical defect detection data set processed by the cornea shaping lens in the preset historical time window, and performing data dimension reduction processing to obtain N historical defect detection data sets:
step S210: obtaining a defect type set during cornea shaping lens processing, wherein the defect type set comprises scratches, gaps and edge arc tilting;
Step S220: constructing a plurality of internal nodes of the dimension reduction decision tree according to the defect type set, and marking the defect type of each internal node;
Step S230: and respectively inputting the history detection data into a plurality of internal nodes in the dimension reduction decision tree to perform defect type matching, classifying the successfully matched history detection data into leaf nodes corresponding to the internal nodes, and obtaining N history defect detection data sets according to N leaf nodes.
Specifically, the preset history time window is a history time period for performing cornea shaping lens processing, and may be half a month, one quarter, or the like. The historical defect detection data set is a data set obtained after defect detection is carried out within a preset historical time window, and comprises a slit lamp inspection result, a lens surface detection result and the like. The historical defect detection data set comprises qualified detection data and unqualified detection data, and the amount of contained information is too large, so that the difficulty of data processing is reduced by data dimension reduction, N historical defect detection data sets are obtained through data dimension reduction, and each historical defect detection data set corresponds to one defect type.
Specifically, defect types generated in the cornea shaping mirror processing process are collected to obtain a defect type set, wherein the defect type set comprises scratches, notches and edge-arc tilting. And constructing a plurality of internal nodes of the dimension reduction decision tree according to the defect type set, and marking the defect type of each internal node. And taking the plurality of internal nodes as a basic framework of the dimension reduction decision tree, further respectively inputting the history detection data into the plurality of internal nodes in the dimension reduction decision tree to perform defect type matching, classifying the history detection data successfully matched into leaf nodes corresponding to the internal nodes, discarding the history detection data not successfully matched, and then obtaining N history defect detection data sets according to N leaf nodes. Therefore, the method and the device realize the aim of carrying out dimension reduction analysis on the historical defect detection data set efficiently and rapidly.
Step S300: matching the N historical defect detection data sets with a historical processing database to obtain N design parameter intervals and N processing equipment sets, wherein the N design parameter intervals and the N processing equipment sets are in one-to-one correspondence;
Further, as shown in fig. 3, step S300 of the embodiment of the present application further includes:
Step S310: matching corresponding design parameters according to the historical processing information in the historical processing database data to obtain a matching result;
Step S320: according to N design parameter sets corresponding to N historical defect detection data sets in the matching result;
step S330: and obtaining N design parameter intervals according to the maximum value and the minimum value in the N design parameter sets.
Further, step S300 of the embodiment of the present application further includes:
step S340: obtaining N processing equipment sets according to processing equipment corresponding to the N historical defect detection data sets in the matching result;
Step S350: and acquiring service lives of the processing equipment in the N processing equipment sets to obtain N processing equipment service life information sets.
In one possible embodiment, the N sets of historical defect detection data are matched with a historical processing database, wherein the historical processing database is data generated by processing within a preset historical time window, so as to obtain the N design parameter intervals and the N sets of processing equipment. The N design parameter intervals are corresponding cornea shaping mirror parameter ranges when N historical defect detection data sets are generated, and processing is performed when N historical defect detection data sets are generated when N processing equipment sets are generated. The N design parameter intervals are in one-to-one correspondence with the N processing equipment sets. By analyzing the N historical defect detection data sets, the design parameter range and the used processing equipment for generating similar defects are determined.
Specifically, the N historical defect detection data sets are matched with a historical processing database, and corresponding design parameters are matched according to historical processing information in the historical processing database data to obtain a matching result. And respectively extracting the maximum value and the minimum value in the sets as two endpoints of the design parameter interval according to N design parameter sets corresponding to the N historical defect detection data sets in the matching result, and further obtaining N design parameter intervals.
Specifically, corresponding N sets of processing apparatuses are obtained by processing apparatuses corresponding to N sets of historical defect detection data in the matching result. Furthermore, the service lives of the processing equipment in the N processing equipment sets are collected, and N processing equipment service life information sets are obtained. Wherein the N sets of processing equipment lifetime information comprise a length of time that the processing equipment has been in use.
Step S400: determining N first data extraction frequencies and N second data extraction frequencies based on the N sets of historical defect detection data;
Further, the determining N first data extraction frequencies and N second data extraction frequencies based on the N historical defect detection data sets in step S400 further includes:
step S410: determining time nodes corresponding to the N historical defect detection data sets according to the preset historical time window, and obtaining N time node sets;
step S420: traversing the N time node sets to determine defect interval time and obtaining N interval time sets;
Step S430: extracting minimum interval time from the N interval time sets as N first data extraction frequencies;
Step S440: the maximum interval time is extracted from the N sets of interval times as N second data extraction frequencies.
Specifically, N first data extraction frequencies and N second data extraction frequencies are determined according to defect data interval times in the N historical defect detection data sets. Wherein the N first data extraction frequencies are intervals for extracting frequently occurring defect data. The N second data extraction frequencies are intervals for extracting defect data with longer occurrence time intervals, and the N first data extraction frequencies are smaller than the N second data extraction frequencies. The amount of data extracted at the N first data extraction frequencies is greater than the amount of data extracted at the N second data extraction frequencies. By extracting data according to different extraction frequencies, the efficiency of data extraction can be improved on the premise of ensuring that defect data is not missed.
Specifically, determining time nodes corresponding to the N historical defect detection data sets according to the preset historical time window, and obtaining N time node sets. And then carrying out defect interval time analysis on each time node set to determine N interval time sets. Wherein the N interval time sets reflect the interval time size of the defect occurrence. Further, the minimum interval time is extracted from the N interval time sets as N first data extraction frequencies, and then the maximum interval time is extracted from the N interval time sets as N second data extraction frequencies.
Step S500: constructing a defect detection library according to the N first data extraction frequencies, the N second data extraction frequencies, the N design parameter intervals and the N processing equipment sets;
In one possible embodiment, the defect detection library is constructed by using N design parameter intervals and N sets of processing equipment as index items and N first data extraction frequencies and N second data extraction frequencies as indexed items. Wherein the defect detection library reflects the defect detection condition during cornea shaping lens processing.
Step S600: inputting the design parameter information and the processing equipment information into the defect detection library for matching to obtain a target first data extraction frequency and a target second data extraction frequency;
further, step S600 of the embodiment of the present application further includes:
Step S610: matching the design parameter information with N design parameter intervals in the defect detection library to obtain a target design parameter interval;
Step S620: searching in a defect detection library by taking a target design parameter interval as an index to obtain a target first data extraction frequency to be optimized and a target second data extraction frequency to be optimized;
Step S630: matching the processing equipment information with N processing equipment sets, judging whether the matching is successful, and if so, taking the target first data extraction frequency to be optimized and the target second data extraction frequency to be optimized as the target first data extraction frequency and the target second data extraction frequency;
Step S640: if not, optimizing the first data extraction frequency of the target to be optimized and the second data extraction frequency of the target to be optimized according to the processing equipment information and the N processing equipment life information sets, and obtaining the first data extraction frequency of the target and the second data extraction frequency of the target according to the optimization result.
Specifically, the design parameter information and the processing equipment information are input into the defect detection library for matching, and the target first data extraction frequency and the target second data extraction frequency which accord with the target lens are determined. The data extraction frequency of the actual condition of fitting the target lens is achieved, and therefore reliability of detection data is improved.
Specifically, the design parameter information is matched with N design parameter intervals in the defect detection library, the range of the design parameters in the design parameter information is determined, and a target design parameter interval is obtained from Russian. And taking the target design parameter interval as an index, and searching the indexed item in the defect detection library to obtain the first data extraction frequency of the target to be optimized and the second data extraction frequency of the target to be optimized. And matching the processing equipment information with the N processing equipment sets, judging whether the matching is successful, if so, indicating that the processing equipment is consistent, and taking the target first data extraction frequency to be optimized and the target second data extraction frequency to be optimized as the target first data extraction frequency and the target second data extraction frequency without considering the influence of the processing equipment on the processing defects.
Specifically, if not, the processing equipment is replaced, and the first data extraction frequency of the target to be optimized and the second data extraction frequency of the target to be optimized need to be optimized according to the information of the processing equipment, so that the extracted data is more reliable. Preferably, the ratio of the service life of the target lens processing equipment in the processing equipment information to the service life average value of the N processing equipment service life information sets is used as an optimization coefficient. Multiplying the optimization coefficient with the target first data extraction frequency to be optimized and the target second data extraction frequency to be optimized to obtain the target first data extraction frequency and the target second data extraction frequency.
Step S700: performing defect detection on the target lens to obtain a target defect detection data set;
in one possible embodiment, the target defect inspection data set is obtained by aggregating the defect inspection data by one skilled in the art using a defect inspection apparatus to inspect the target lens for defects. The method realizes the aim of providing basic data for the subsequent analysis of the defect detection result.
Step S800: and inputting the target first data extraction frequency and the target second data extraction frequency into a defect detection analysis model by combining the target defect detection data set to obtain a defect detection result.
Further, step S800 of the embodiment of the present application further includes:
Step S810: the defect detection analysis model comprises a first data extraction channel, a second data extraction channel and a defect detection analysis layer;
step S820: acquiring a plurality of sample first data extraction frequencies, a plurality of sample target defect detection data sets and a plurality of sample first data extraction results as construction data, and performing supervision training on a framework constructed based on a feedforward neural network to acquire a first data extraction channel;
Step S830: acquiring a plurality of sample second data extraction frequencies, a plurality of sample target defect detection data sets and a plurality of sample second data extraction results as construction data, and performing supervision training on a framework constructed based on a feedforward neural network to acquire a second data extraction channel;
Step S840: and constructing a mapping relation among the first data extraction results of the plurality of samples, the second data extraction results of the plurality of samples and the defect detection results of the plurality of samples, and generating a defect detection analysis layer based on the mapping relation.
Specifically, the target first data extraction frequency and the target second data extraction frequency are input into a defect detection analysis model in combination with a target defect detection data set, and a defect detection result is obtained through intelligent operation of the defect detection analysis model. The defect detection analysis model is used for carrying out differential extraction on data and carrying out intelligent analysis on detection results.
Specifically, the defect detection analysis model comprises a first data extraction channel, a second data extraction channel and a defect detection analysis layer. The first data extraction channel is used for carrying out data extraction on the defect detection data set according to the first data extraction frequency to obtain a first data extraction result. The second data extraction channel is used for carrying out data extraction on the defect detection data set according to the second data extraction frequency to obtain a second data extraction result. The defect detection analysis layer is used for comprehensively analyzing the first data extraction result and the second data extraction result to obtain a defect detection result.
Specifically, a plurality of sample first data extraction frequencies, a plurality of sample target defect detection data sets and a plurality of sample first data extraction results are obtained to serve as construction data, and supervision training is performed on a framework constructed based on a feedforward neural network until output reaches convergence, so that a first data extraction channel is obtained. And acquiring a plurality of sample second data extraction frequencies, a plurality of sample target defect detection data sets and a plurality of sample second data extraction results as construction data, and performing supervision training on a framework constructed based on the feedforward neural network until the output reaches convergence, so as to acquire a second data extraction channel. Further, a mapping relationship among the plurality of sample first data extraction results, the plurality of sample second data extraction results and the plurality of sample defect detection results is constructed, and a defect detection analysis layer is generated based on the mapping relationship. And then, the target first data extraction frequency and the target second data extraction frequency are combined with the target defect detection data set to be input into a defect detection analysis model, so that a defect detection result is obtained.
In summary, the embodiment of the application has at least the following technical effects:
According to the application, the processing information of the target lens is subjected to data analysis to obtain the processing information, data is provided for subsequent detection analysis, then the historical defect detection data is analyzed, N historical defect detection data sets after dimension reduction clustering are determined, then N first data extraction frequencies and N second data extraction frequencies are determined, the aim of comprehensively extracting the detection data is fulfilled, then a defect detection library is constructed according to the N first data extraction frequencies, the N second data extraction frequencies, N design parameter intervals and N processing equipment sets, defect detection is carried out on the target lens, a detected target defect detection data set is obtained, and intelligent analysis is carried out by combining the target first data extraction frequencies and the target second data extraction frequencies obtained through matching, so that a defect detection result is obtained. The technical effects of improving the detection efficiency and improving the reliability of the defect detection result are achieved.
Example two
Based on the same inventive concept as the defect detection method of a cornea shaping lens in the foregoing embodiments, as shown in fig. 4, the present application provides a defect detection system of a cornea shaping lens, and the system and method embodiments in the embodiments of the present application are based on the same inventive concept. Wherein the system comprises:
A processing information acquisition module 11, wherein the processing information acquisition module 11 is configured to acquire processing information of a target lens, and the processing information includes design parameter information and processing equipment information;
The detecting data set obtaining module 12 is configured to extract a historical defect detecting data set processed by the cornea shaping lens in a preset historical time window, and perform data dimension reduction processing to obtain N historical defect detecting data sets, where each historical defect detecting data set corresponds to a defect type;
The processing equipment set obtaining module 13 is configured to match the N historical defect detection data sets with a historical processing database to obtain N design parameter intervals and N processing equipment sets, where the N design parameter intervals and the N processing equipment sets are in one-to-one correspondence;
A data extraction frequency determination module 14, the data extraction frequency determination module 14 configured to determine N first data extraction frequencies and N second data extraction frequencies based on the N sets of historical defect detection data;
The defect detection library construction module 15 is used for constructing a defect detection library according to the N first data extraction frequencies, the N second data extraction frequencies, the N design parameter intervals and the N processing equipment sets;
The target extraction frequency obtaining module 16, wherein the target extraction frequency obtaining module 16 is configured to input the design parameter information and the processing equipment information into the defect detection library to match, and obtain a target first data extraction frequency and a target second data extraction frequency;
The target detection data obtaining module 17 is used for carrying out defect detection on the target lens to obtain a target defect detection data set;
the defect detection result obtaining module 18 is configured to obtain a defect detection result by using the target first data extraction frequency and the target second data extraction frequency and inputting the defect detection result into the defect detection analysis model in combination with the target defect detection data set.
Further, the detection data set obtaining module 12 is configured to perform the following method:
Obtaining a defect type set during cornea shaping lens processing, wherein the defect type set comprises scratches, gaps and edge arc tilting;
constructing a plurality of internal nodes of the dimension reduction decision tree according to the defect type set, and marking the defect type of each internal node;
And respectively inputting the history detection data into a plurality of internal nodes in the dimension reduction decision tree to perform defect type matching, classifying the successfully matched history detection data into leaf nodes corresponding to the internal nodes, and obtaining N history defect detection data sets according to N leaf nodes.
Further, the processing equipment set obtaining module 13 is configured to perform the following method:
matching corresponding design parameters according to the historical processing information in the historical processing database data to obtain a matching result;
According to N design parameter sets corresponding to N historical defect detection data sets in the matching result;
and obtaining N design parameter intervals according to the maximum value and the minimum value in the N design parameter sets.
Further, the processing equipment set obtaining module 13 is configured to perform the following method:
Obtaining N processing equipment sets according to processing equipment corresponding to the N historical defect detection data sets in the matching result;
and acquiring service lives of the processing equipment in the N processing equipment sets to obtain N processing equipment service life information sets.
Further, the data extraction frequency determining module 14 is configured to perform the following method:
Determining time nodes corresponding to the N historical defect detection data sets according to the preset historical time window, and obtaining N time node sets;
traversing the N time node sets to determine defect interval time and obtaining N interval time sets;
extracting minimum interval time from the N interval time sets as N first data extraction frequencies;
the maximum interval time is extracted from the N sets of interval times as N second data extraction frequencies.
Further, the target extraction frequency obtaining module 16 is configured to perform the following method:
matching the design parameter information with N design parameter intervals in the defect detection library to obtain a target design parameter interval;
Searching in a defect detection library by taking a target design parameter interval as an index to obtain a target first data extraction frequency to be optimized and a target second data extraction frequency to be optimized;
Matching the processing equipment information with N processing equipment sets, judging whether the matching is successful, and if so, taking the target first data extraction frequency to be optimized and the target second data extraction frequency to be optimized as the target first data extraction frequency and the target second data extraction frequency;
if not, optimizing the first data extraction frequency of the target to be optimized and the second data extraction frequency of the target to be optimized according to the processing equipment information and the N processing equipment life information sets, and obtaining the first data extraction frequency of the target and the second data extraction frequency of the target according to the optimization result.
Further, the defect detection result obtaining module 18 is configured to perform the following method:
the defect detection analysis model comprises a first data extraction channel, a second data extraction channel and a defect detection analysis layer;
acquiring a plurality of sample first data extraction frequencies, a plurality of sample target defect detection data sets and a plurality of sample first data extraction results as construction data, and performing supervision training on a framework constructed based on a feedforward neural network to acquire a first data extraction channel;
acquiring a plurality of sample second data extraction frequencies, a plurality of sample target defect detection data sets and a plurality of sample second data extraction results as construction data, and performing supervision training on a framework constructed based on a feedforward neural network to acquire a second data extraction channel;
And constructing a mapping relation among the first data extraction results of the plurality of samples, the second data extraction results of the plurality of samples and the defect detection results of the plurality of samples, and generating a defect detection analysis layer based on the mapping relation.
It should be noted that the sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The foregoing description of the preferred embodiments of the application is not intended to limit the application to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the application are intended to be included within the scope of the application.
The specification and figures are merely exemplary illustrations of the present application and are considered to cover any and all modifications, variations, combinations, or equivalents that fall within the scope of the application. It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the scope of the application. Thus, the present application is intended to include such modifications and alterations insofar as they come within the scope of the application or the equivalents thereof.
Claims (5)
1. A method for detecting defects in a cornea shaping lens, the method comprising:
acquiring processing information of a target lens, wherein the processing information comprises design parameter information and processing equipment information;
extracting a historical defect detection data set processed by a cornea shaping mirror in a preset historical time window, and performing data dimension reduction processing to obtain N historical defect detection data sets, wherein each historical defect detection data set corresponds to one defect type;
Matching the N historical defect detection data sets with a historical processing database to obtain N design parameter intervals and N processing equipment sets, wherein the N design parameter intervals and the N processing equipment sets are in one-to-one correspondence;
Determining N first data extraction frequencies and N second data extraction frequencies based on the N sets of historical defect detection data;
constructing a defect detection library according to the N first data extraction frequencies, the N second data extraction frequencies, the N design parameter intervals and the N processing equipment sets;
inputting the design parameter information and the processing equipment information into the defect detection library for matching to obtain a target first data extraction frequency and a target second data extraction frequency;
performing defect detection on the target lens to obtain a target defect detection data set;
Inputting the target first data extraction frequency and the target second data extraction frequency into a defect detection analysis model by combining the target defect detection data set to obtain a defect detection result;
The method comprises the steps of extracting a historical defect detection data set processed by a cornea shaping mirror in a preset historical time window, and performing data dimension reduction processing to obtain N historical defect detection data sets, wherein the method comprises the following steps:
Obtaining a defect type set during cornea shaping lens processing, wherein the defect type set comprises scratches, gaps and edge arc tilting;
constructing a plurality of internal nodes of the dimension reduction decision tree according to the defect type set, and marking the defect type of each internal node;
Respectively inputting the history detection data into a plurality of internal nodes in the dimension reduction decision tree to perform defect type matching, classifying the successfully matched history detection data into leaf nodes corresponding to the internal nodes, and obtaining N history defect detection data sets according to N leaf nodes;
The determining N first data extraction frequencies and N second data extraction frequencies based on the N sets of historical defect detection data, the method comprising:
Determining time nodes corresponding to the N historical defect detection data sets according to the preset historical time window, and obtaining N time node sets;
traversing the N time node sets to determine defect interval time and obtaining N interval time sets;
extracting minimum interval time from the N interval time sets as N first data extraction frequencies;
extracting the maximum interval time from the N interval time sets as N second data extraction frequencies;
the defect detection analysis model comprises a first data extraction channel, a second data extraction channel and a defect detection analysis layer;
acquiring a plurality of sample first data extraction frequencies, a plurality of sample target defect detection data sets and a plurality of sample first data extraction results as construction data, and performing supervision training on a framework constructed based on a feedforward neural network to acquire a first data extraction channel;
acquiring a plurality of sample second data extraction frequencies, a plurality of sample target defect detection data sets and a plurality of sample second data extraction results as construction data, and performing supervision training on a framework constructed based on a feedforward neural network to acquire a second data extraction channel;
And constructing a mapping relation among the first data extraction results of the plurality of samples, the second data extraction results of the plurality of samples and the defect detection results of the plurality of samples, and generating a defect detection analysis layer based on the mapping relation.
2. The method of claim 1, wherein the method comprises:
matching corresponding design parameters according to the historical processing information in the historical processing database data to obtain a matching result;
According to N design parameter sets corresponding to N historical defect detection data sets in the matching result;
and obtaining N design parameter intervals according to the maximum value and the minimum value in the N design parameter sets.
3. The method according to claim 2, wherein the method comprises:
Obtaining N processing equipment sets according to processing equipment corresponding to the N historical defect detection data sets in the matching result;
and acquiring service lives of the processing equipment in the N processing equipment sets to obtain N processing equipment service life information sets.
4.A method according to claim 3, wherein the method comprises:
matching the design parameter information with N design parameter intervals in the defect detection library to obtain a target design parameter interval;
Searching in a defect detection library by taking a target design parameter interval as an index to obtain a target first data extraction frequency to be optimized and a target second data extraction frequency to be optimized;
Matching the processing equipment information with N processing equipment sets, judging whether the matching is successful, and if so, taking the target first data extraction frequency to be optimized and the target second data extraction frequency to be optimized as the target first data extraction frequency and the target second data extraction frequency;
if not, optimizing the first data extraction frequency of the target to be optimized and the second data extraction frequency of the target to be optimized according to the processing equipment information and the N processing equipment life information sets, and obtaining the first data extraction frequency of the target and the second data extraction frequency of the target according to the optimization result.
5. A defect detection system for a cornea shaping lens, the system comprising:
The processing information acquisition module is used for acquiring processing information of the target lens, wherein the processing information comprises design parameter information and processing equipment information;
The detecting data set obtaining module is used for extracting a historical defect detecting data set processed by the cornea shaping mirror in a preset historical time window and carrying out data dimension reduction processing to obtain N historical defect detecting data sets, wherein each historical defect detecting data set corresponds to one defect type;
The processing equipment set obtaining module is used for matching the N historical defect detection data sets with a historical processing database to obtain N design parameter intervals and N processing equipment sets, wherein the N design parameter intervals are in one-to-one correspondence with the N processing equipment sets;
a data extraction frequency determination module for determining N first data extraction frequencies and N second data extraction frequencies based on the N sets of historical defect detection data;
the defect detection library construction module is used for constructing a defect detection library according to N first data extraction frequencies, N second data extraction frequencies, N design parameter intervals and N processing equipment sets;
The target extraction frequency obtaining module is used for inputting the design parameter information and the processing equipment information into the defect detection library for matching to obtain a target first data extraction frequency and a target second data extraction frequency;
The target detection data acquisition module is used for carrying out defect detection on the target lens to obtain a target defect detection data set;
The defect detection result obtaining module is used for obtaining a defect detection result by utilizing the target first data extraction frequency and the target second data extraction frequency and combining the target defect detection data set to input a defect detection analysis model;
The detection data set obtaining module is used for executing the following method:
Obtaining a defect type set during cornea shaping lens processing, wherein the defect type set comprises scratches, gaps and edge arc tilting;
constructing a plurality of internal nodes of the dimension reduction decision tree according to the defect type set, and marking the defect type of each internal node;
Respectively inputting the history detection data into a plurality of internal nodes in the dimension reduction decision tree to perform defect type matching, classifying the successfully matched history detection data into leaf nodes corresponding to the internal nodes, and obtaining N history defect detection data sets according to N leaf nodes;
The data extraction frequency determining module is used for executing the following method:
Determining time nodes corresponding to the N historical defect detection data sets according to the preset historical time window, and obtaining N time node sets;
traversing the N time node sets to determine defect interval time and obtaining N interval time sets;
extracting minimum interval time from the N interval time sets as N first data extraction frequencies;
extracting the maximum interval time from the N interval time sets as N second data extraction frequencies;
The defect detection result obtaining module is used for executing the following method:
the defect detection analysis model comprises a first data extraction channel, a second data extraction channel and a defect detection analysis layer;
acquiring a plurality of sample first data extraction frequencies, a plurality of sample target defect detection data sets and a plurality of sample first data extraction results as construction data, and performing supervision training on a framework constructed based on a feedforward neural network to acquire a first data extraction channel;
acquiring a plurality of sample second data extraction frequencies, a plurality of sample target defect detection data sets and a plurality of sample second data extraction results as construction data, and performing supervision training on a framework constructed based on a feedforward neural network to acquire a second data extraction channel;
And constructing a mapping relation among the first data extraction results of the plurality of samples, the second data extraction results of the plurality of samples and the defect detection results of the plurality of samples, and generating a defect detection analysis layer based on the mapping relation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310881696.2A CN116990450B (en) | 2023-07-18 | 2023-07-18 | Defect detection method and system for cornea shaping mirror |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310881696.2A CN116990450B (en) | 2023-07-18 | 2023-07-18 | Defect detection method and system for cornea shaping mirror |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116990450A CN116990450A (en) | 2023-11-03 |
| CN116990450B true CN116990450B (en) | 2024-04-26 |
Family
ID=88527732
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310881696.2A Active CN116990450B (en) | 2023-07-18 | 2023-07-18 | Defect detection method and system for cornea shaping mirror |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116990450B (en) |
Citations (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2057832A1 (en) * | 1990-12-19 | 1992-06-20 | Peter Hofer | Process and apparatus for examining optical components, especially optical components for the eye and device for illuminating clear-transparent test-objects |
| JP2003050209A (en) * | 2001-05-30 | 2003-02-21 | Hitachi Electronics Eng Co Ltd | Defect detection optical system, and effect inspection method and device using it |
| CN105115989A (en) * | 2015-10-09 | 2015-12-02 | 南京爱丁堡环保科技有限公司 | Automatic defect detecting equipment and detecting method for contact lenses |
| CN106204614A (en) * | 2016-07-21 | 2016-12-07 | 湘潭大学 | A kind of workpiece appearance defects detection method based on machine vision |
| JP6296584B1 (en) * | 2017-06-29 | 2018-03-20 | 石根 三井 | Orthokeratology lens decision supply method and decision supply system |
| CN110596150A (en) * | 2019-09-30 | 2019-12-20 | 万灵帮桥医疗器械(广州)有限责任公司 | Corneal plastic mirror detection device and detection method |
| CN110908140A (en) * | 2019-11-21 | 2020-03-24 | 明灏科技（北京）有限公司 | Production device of orthokeratology mirror |
| CN111062961A (en) * | 2019-12-30 | 2020-04-24 | 天津大学 | Contact lens edge defect detection method based on deep learning |
| KR20200080367A (en) * | 2018-12-14 | 2020-07-07 | 한국광기술원 | System and method for detecting bad contact lens |
| CN211122595U (en) * | 2019-09-30 | 2020-07-28 | 万灵帮桥医疗器械(广州)有限责任公司 | Orthokeratology mirror detection device |
| CN111551568A (en) * | 2020-06-04 | 2020-08-18 | 哈尔滨理工大学 | Lens defect detection and classification method based on machine vision |
| CN111553402A (en) * | 2020-04-22 | 2020-08-18 | 首都医科大学附属北京同仁医院 | Intelligent orthokeratology lens selecting system and method based on big data and deep learning |
| CN111836574A (en) * | 2018-03-13 | 2020-10-27 | 目立康株式会社 | System for collecting and utilizing health data |
| CN111965847A (en) * | 2020-08-28 | 2020-11-20 | 平安国际智慧城市科技股份有限公司 | Lens fitting method, device and medium |
| CN112147795A (en) * | 2019-06-28 | 2020-12-29 | 爱博诺德(北京)医疗科技股份有限公司 | Method for manufacturing orthokeratology mirror, method for selling orthokeratology mirror, and orthokeratology mirror assembly |
| CN112529876A (en) * | 2020-12-15 | 2021-03-19 | 天津大学 | Method for detecting edge defects of contact lenses |
| WO2021139112A1 (en) * | 2020-01-07 | 2021-07-15 | 平安科技（深圳）有限公司 | Data dimensionality reduction processing method and apparatus, computer device, and storage medium |
| KR20210102458A (en) * | 2020-03-11 | 2021-08-19 | 베이징 바이두 넷컴 사이언스 앤 테크놀로지 코., 엘티디. | Methods and devices for obtaining information |
| CN113378414A (en) * | 2021-08-12 | 2021-09-10 | 爱尔眼科医院集团股份有限公司 | Cornea shaping lens fitting method, device, equipment and readable storage medium |
| CN114167623A (en) * | 2021-12-31 | 2022-03-11 | 福州欧凯医疗科技有限公司 | Cornea shaping mirror and design method thereof |
| CN114239208A (en) * | 2021-08-04 | 2022-03-25 | 美视(杭州)人工智能科技有限公司 | Data processing method based on cornea shaping lens fitting and related equipment |
| DE102021211596A1 (en) * | 2020-10-14 | 2022-04-14 | Emage Vision PTE, Ltd. | CONTACT LENS FAULT ANALYSIS AND TRACK SYSTEM |
| WO2022088082A1 (en) * | 2020-10-30 | 2022-05-05 | 京东方科技集团股份有限公司 | Task processing method, apparatus and device based on defect detection, and storage medium |
| CN114878550A (en) * | 2022-06-09 | 2022-08-09 | 温州医科大学 | Multifunctional health monitoring contact lens and preparation and detection method thereof |
| CN115100110A (en) * | 2022-05-20 | 2022-09-23 | 厦门微亚智能科技有限公司 | Defect detection method, device and equipment for polarized lens and readable storage medium |
| CN115132309A (en) * | 2022-07-06 | 2022-09-30 | 潍坊眼科医院有限责任公司 | Method and device for fitting orthokeratology lens |
| CN217878967U (en) * | 2022-06-16 | 2022-11-22 | 首都医科大学附属北京同仁医院 | Detector for cornea shaping lens |
| CN115552435A (en) * | 2020-03-31 | 2022-12-30 | Ats自动化加工系统公司 | System and method for modeling a manufacturing assembly line |
| WO2023109251A1 (en) * | 2021-12-17 | 2023-06-22 | 浪潮电子信息产业股份有限公司 | System fault detection method and apparatus, device, and medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8628194B2 (en) * | 2009-10-13 | 2014-01-14 | Anton Sabeta | Method and system for contact lens care and compliance |
| US20230206420A1 (en) * | 2021-01-28 | 2023-06-29 | Beijing Zhongxiangying Technology Co., Ltd. | Method for detecting defect and method for training model |
| US11619593B2 (en) * | 2021-06-01 | 2023-04-04 | Zhejiang Gongshang University | Methods and systems for detecting a defect of a film |
-
2023
- 2023-07-18 CN CN202310881696.2A patent/CN116990450B/en active Active
Patent Citations (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2057832A1 (en) * | 1990-12-19 | 1992-06-20 | Peter Hofer | Process and apparatus for examining optical components, especially optical components for the eye and device for illuminating clear-transparent test-objects |
| JP2003050209A (en) * | 2001-05-30 | 2003-02-21 | Hitachi Electronics Eng Co Ltd | Defect detection optical system, and effect inspection method and device using it |
| CN105115989A (en) * | 2015-10-09 | 2015-12-02 | 南京爱丁堡环保科技有限公司 | Automatic defect detecting equipment and detecting method for contact lenses |
| CN106204614A (en) * | 2016-07-21 | 2016-12-07 | 湘潭大学 | A kind of workpiece appearance defects detection method based on machine vision |
| JP6296584B1 (en) * | 2017-06-29 | 2018-03-20 | 石根 三井 | Orthokeratology lens decision supply method and decision supply system |
| CN111836574A (en) * | 2018-03-13 | 2020-10-27 | 目立康株式会社 | System for collecting and utilizing health data |
| KR20200080367A (en) * | 2018-12-14 | 2020-07-07 | 한국광기술원 | System and method for detecting bad contact lens |
| CN112147795A (en) * | 2019-06-28 | 2020-12-29 | 爱博诺德(北京)医疗科技股份有限公司 | Method for manufacturing orthokeratology mirror, method for selling orthokeratology mirror, and orthokeratology mirror assembly |
| CN110596150A (en) * | 2019-09-30 | 2019-12-20 | 万灵帮桥医疗器械(广州)有限责任公司 | Corneal plastic mirror detection device and detection method |
| CN211122595U (en) * | 2019-09-30 | 2020-07-28 | 万灵帮桥医疗器械(广州)有限责任公司 | Orthokeratology mirror detection device |
| CN110908140A (en) * | 2019-11-21 | 2020-03-24 | 明灏科技（北京）有限公司 | Production device of orthokeratology mirror |
| CN111062961A (en) * | 2019-12-30 | 2020-04-24 | 天津大学 | Contact lens edge defect detection method based on deep learning |
| WO2021139112A1 (en) * | 2020-01-07 | 2021-07-15 | 平安科技（深圳）有限公司 | Data dimensionality reduction processing method and apparatus, computer device, and storage medium |
| KR20210102458A (en) * | 2020-03-11 | 2021-08-19 | 베이징 바이두 넷컴 사이언스 앤 테크놀로지 코., 엘티디. | Methods and devices for obtaining information |
| CN115552435A (en) * | 2020-03-31 | 2022-12-30 | Ats自动化加工系统公司 | System and method for modeling a manufacturing assembly line |
| CN111553402A (en) * | 2020-04-22 | 2020-08-18 | 首都医科大学附属北京同仁医院 | Intelligent orthokeratology lens selecting system and method based on big data and deep learning |
| CN111551568A (en) * | 2020-06-04 | 2020-08-18 | 哈尔滨理工大学 | Lens defect detection and classification method based on machine vision |
| CN111965847A (en) * | 2020-08-28 | 2020-11-20 | 平安国际智慧城市科技股份有限公司 | Lens fitting method, device and medium |
| DE102021211596A1 (en) * | 2020-10-14 | 2022-04-14 | Emage Vision PTE, Ltd. | CONTACT LENS FAULT ANALYSIS AND TRACK SYSTEM |
| WO2022088082A1 (en) * | 2020-10-30 | 2022-05-05 | 京东方科技集团股份有限公司 | Task processing method, apparatus and device based on defect detection, and storage medium |
| CN112529876A (en) * | 2020-12-15 | 2021-03-19 | 天津大学 | Method for detecting edge defects of contact lenses |
| CN114239208A (en) * | 2021-08-04 | 2022-03-25 | 美视(杭州)人工智能科技有限公司 | Data processing method based on cornea shaping lens fitting and related equipment |
| CN113378414A (en) * | 2021-08-12 | 2021-09-10 | 爱尔眼科医院集团股份有限公司 | Cornea shaping lens fitting method, device, equipment and readable storage medium |
| WO2023109251A1 (en) * | 2021-12-17 | 2023-06-22 | 浪潮电子信息产业股份有限公司 | System fault detection method and apparatus, device, and medium |
| CN114167623A (en) * | 2021-12-31 | 2022-03-11 | 福州欧凯医疗科技有限公司 | Cornea shaping mirror and design method thereof |
| CN115100110A (en) * | 2022-05-20 | 2022-09-23 | 厦门微亚智能科技有限公司 | Defect detection method, device and equipment for polarized lens and readable storage medium |
| CN114878550A (en) * | 2022-06-09 | 2022-08-09 | 温州医科大学 | Multifunctional health monitoring contact lens and preparation and detection method thereof |
| CN217878967U (en) * | 2022-06-16 | 2022-11-22 | 首都医科大学附属北京同仁医院 | Detector for cornea shaping lens |
| CN115132309A (en) * | 2022-07-06 | 2022-09-30 | 潍坊眼科医院有限责任公司 | Method and device for fitting orthokeratology lens |
Non-Patent Citations (3)
| Title |
|---|
| 基于BP神经网络的GIS缺陷图像识别系统的研究;万书亭;赵晓迪;肖珊珊;仝玎朔;;电力科学与工程(第11期);全文 * |
| 基于支持向量机的钢板缺陷分类问题的研究;丛成;吕哲;高翔;王敏;;物联网技术(第04期);全文 * |
| 基于机器视觉的塑料制品表面缺陷检测研究;孙琴;肖书浩;刘誉涵;陈齐山;;电子制作;20200801(第15期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116990450A (en) | 2023-11-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9607233B2 (en) | Classifier readiness and maintenance in automatic defect classification | |
| US20130279794A1 (en) | Integration of automatic and manual defect classification | |
| CN111275307A (en) | Quality control method for high-frequency continuous observation data of automatic online water quality station | |
| US7584162B2 (en) | Manufacture data analysis method and manufacture data analyzer apparatus | |
| CN113487533B (en) | Part assembly quality digital detection system and method based on machine learning | |
| CN116644351B (en) | Data processing method and system based on artificial intelligence | |
| CN111709775A (en) | House property price evaluation method and device, electronic equipment and storage medium | |
| CN112529109A (en) | Unsupervised multi-model-based anomaly detection method and system | |
| CN114186644A (en) | Defect report severity prediction method based on optimized random forest | |
| CN112116168A (en) | User behavior prediction method and device and electronic equipment | |
| CN1106572C (en) | Automatic evaluation method of casting ingot cross section quality | |
| CN116990450B (en) | Defect detection method and system for cornea shaping mirror | |
| CN113283768A (en) | Food detection item extraction method, device, equipment and storage medium | |
| CN117593273A (en) | Method and system for detecting surface defects of electronic component | |
| CN112508946B (en) | Cable tunnel anomaly detection method based on antagonistic neural network | |
| CN112532481B (en) | Network quality monitoring and analyzing method, system and storage medium | |
| CN111738188B (en) | Power transmission line crimping fitting identification method, device, terminal and storage medium | |
| CN114998597A (en) | Target detection method and device based on artificial intelligence | |
| Borkar et al. | Comparative study of supervised learning algorithms for fake news classification | |
| CN113516328A (en) | Data processing method, service providing method, device, equipment and storage medium | |
| CN117954036B (en) | Health management method and system based on big data | |
| CN115511106B (en) | Method, device and readable storage medium for generating training data based on time sequence data | |
| CN118261914B (en) | Inductance quality assessment method, system and storage medium based on artificial intelligence | |
| CN112633251B (en) | Target document acquisition method and device based on text recognition and storage medium | |
| Nanlohy et al. | Classification of Public Complaint Data in SMS Complaint Using Naive Bayes Multinomial Method |
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 |