CN116708633B - Mobile phone screen dead pixel automatic detection method and detection system based on significance analysis - Google Patents
Mobile phone screen dead pixel automatic detection method and detection system based on significance analysis Download PDFInfo
- Publication number
- CN116708633B CN116708633B CN202310981048.4A CN202310981048A CN116708633B CN 116708633 B CN116708633 B CN 116708633B CN 202310981048 A CN202310981048 A CN 202310981048A CN 116708633 B CN116708633 B CN 116708633B
- Authority
- CN
- China
- Prior art keywords
- value
- sample
- dead pixel
- mobile phone
- detection
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 149
- 238000004458 analytical method Methods 0.000 title claims abstract description 58
- 238000004519 manufacturing process Methods 0.000 claims abstract description 51
- 238000007405 data analysis Methods 0.000 claims abstract description 26
- 238000012544 monitoring process Methods 0.000 claims abstract description 13
- 239000008186 active pharmaceutical agent Substances 0.000 claims description 23
- 238000000034 method Methods 0.000 claims description 18
- 230000002159 abnormal effect Effects 0.000 claims description 8
- 239000003086 colorant Substances 0.000 claims description 3
- 239000000463 material Substances 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/24—Arrangements for testing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M11/00—Testing of optical apparatus; Testing structures by optical methods not otherwise provided for
- G01M11/02—Testing optical properties
- G01M11/0242—Testing optical properties by measuring geometrical properties or aberrations
- G01M11/0278—Detecting defects of the object to be tested, e.g. scratches or dust
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
- G08B25/01—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium
- G08B25/08—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium using communication transmission lines
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B3/00—Audible signalling systems; Audible personal calling systems
- G08B3/10—Audible signalling systems; Audible personal calling systems using electric transmission; using electromagnetic transmission
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Electromagnetism (AREA)
- Geometry (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Telephone Function (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
Abstract
The invention relates to the technical field of telecommunication, in particular to a mobile phone screen dead spot automatic detection method and a mobile phone screen dead spot automatic detection system based on significance analysis, which are used for solving the problems that the existing mobile phone screen dead spot automatic detection method based on significance analysis cannot monitor mobile phones and mobile phone production processes efficiently, cannot find out the mobile phones with dead spots in time, correct the mobile phone production processes, easily cause low mobile phone production standard reaching rate and influence mobile phone production cost and production efficiency; the mobile phone screen dead pixel automatic detection system comprises a dead pixel monitoring module, a dead pixel detection platform, a data acquisition module, a data analysis module and an error alarm module; the mobile phone screen dead pixel automatic detection method can monitor mobile phones and mobile phone production processes, improves mobile phone dead pixel detection efficiency, improves mobile phone standard reaching rate, reduces mobile phone production cost and improves mobile phone production efficiency.
Description
Technical Field
The invention relates to the technical field of telecommunication, in particular to a mobile phone screen dead pixel automatic detection method and system based on significance analysis.
Background
In the process of mobile phone production and maintenance, screen dead spots are common problems, and the traditional dead spot detection method generally relies on manual visual inspection, and has low efficiency and limited accuracy. Therefore, an automatic and accurate mobile phone screen dead pixel detection method is needed.
The patent with the application number of CN201611119578.4 discloses an automatic detection method of dead pixels of a mobile phone screen based on significance analysis, which comprises the steps of firstly determining a mobile phone screen area by adopting a method of combining projection with angular point analysis; then extracting mobile phone screen region image data according to the positioning result and the mobile phone screen region color information; then, carrying out significance analysis on the mobile phone screen region image to obtain a comprehensive significance map; extracting a salient region from the comprehensive salient map; then, marking the extracted significant region by adopting a projection marking method to obtain a dead pixel region of the mobile phone screen; finally, the dead pixel information is extracted from the marked dead pixel area of the mobile phone screen, and the invention also provides an automatic detection system for the dead pixel of the mobile phone screen based on significance analysis. The mobile phone and the mobile phone production process cannot be monitored efficiently, the mobile phone with dead spots cannot be found timely, the mobile phone production process is corrected, the mobile phone production standard reaching rate is easy to be low, and the mobile phone production cost and the production efficiency are affected.
Disclosure of Invention
In order to overcome the technical problems, the invention aims to provide a mobile phone screen dead pixel automatic detection method and a detection system based on significance analysis: the method comprises the steps that a mobile phone which needs to be subjected to mobile phone screen dead spot detection is marked as a detection sample through a dead spot monitoring module, a mobile phone screen photo of the detection sample is shot, the mobile phone screen photo of the detection sample is marked as an analysis photo, all the analysis photos are formed into a sample detection packet, the dead spot parameters of the analysis photos in the corresponding sample detection packet are obtained after data acquisition information is received through a data acquisition module, the dead spot parameters comprise dead spot values, area values and bright difference values, the dead spot values are obtained through a data analysis module according to the dead spot parameters, a dead spot average value is obtained according to the dead spot values, the detection sample is classified into a normal sample and an abnormal sample through a dead spot detection platform according to the dead spot average value, a sample error alarm instruction is generated at the same time, an error coefficient is obtained through an error alarm module according to the sample error alarm instruction, and a production error alarm instruction is generated through an error alarm module.
The aim of the invention can be achieved by the following technical scheme:
a mobile phone screen dead pixel automatic detection system based on significance analysis comprises:
the dead pixel monitoring module is used for marking the mobile phones needing to carry out dead pixel detection on the mobile phone screen as detection samples i in sequence, shooting mobile phone screen photos of the detection samples i, marking the mobile phone screen photos as analysis photos j, forming a detection sample packet Ji by all the analysis photos j, and sending the detection sample packet Ji to the dead pixel detection platform;
the dead pixel detection platform is used for generating data acquisition information after receiving the sample detection packet Ji and sending the data acquisition information to the data acquisition module; the system is also used for classifying the detection sample i into a normal sample and an abnormal sample according to the bad mean value HJ, generating a sample error alarm instruction at the same time, and sending the sample error alarm instruction to an error alarm module; the production error warning module is used for generating a production error warning command according to the error coefficient WC and sending the production error warning command to the error warning module;
the data acquisition module is used for acquiring the dead pixel parameters of the analysis photo j in the corresponding sample detection packet Ji after receiving the data acquisition information and sending the dead pixel parameters to the data analysis module; wherein, the dead pixel parameters comprise a dot value DS, an area value MJ and a bright difference value LC;
the data analysis module is used for obtaining a dead pixel value HDj according to the dead pixel parameters, obtaining a dead pixel mean value HJ according to a dead pixel value HDj and sending the dead pixel mean value HJ to the dead pixel detection platform;
the error alarm module is used for ringing a sample error alarm bell after receiving the sample error alarm instruction, obtaining an error coefficient WC according to the sample error alarm instruction and sending the error coefficient WC to the dead point detection platform; and the alarm device is also used for ringing the production error alarm instruction bell after receiving the production error alarm instruction.
As a further scheme of the invention: the specific process of the data acquisition module for acquiring the dead pixel parameters is as follows:
after receiving the data acquisition information, acquiring an analysis photo j in a corresponding sample detection packet Ji, acquiring the total number of dead pixels in the analysis photo j, and marking the total number as a point value DS;
acquisition scoreAnalyzing the total area of all dead pixels in the photo j, marking the total area as a dot-surface value DM, obtaining the area of each dead pixel, marking the area as a dot-product value DJ, obtaining the average value of all the dot-product values DJ, marking the average value as a mean-product value JJ, and substituting the dot-product value DJ and the mean-product value JJ into a formulaObtaining a partial product value PJ, substituting the dot-surface value DM and the partial product value PJ into the formula +.>Wherein, h1 and h2 are respectively preset proportional coefficients of a dot value DM and a partial product value PJ, and h1+h2=1, 0 < h1 < h2 < 1, h1=0.43 and h2=0.57;
dividing an analysis photo j into a plurality of detection areas uniformly, obtaining the brightness of the detection areas, marking the brightness of the detection areas as brightness values LD, obtaining the maximum value and the minimum value in all the brightness values LD, obtaining the difference between the maximum value and the minimum value, and marking the difference as a brightness difference LC;
the point value DS, the area value MJ and the luminance difference value LC are sent to a data analysis module.
As a further scheme of the invention: the specific process of obtaining the dead point value HDj by the data analysis module is as follows:
substituting the dot value DS, the area value MJ and the luminance difference LC into the formulaObtaining a dead pixel value HDj, wherein k is an error adjustment factor, k=1.254, z1, z2 and z3 are preset weight coefficients of a point value DS, an area value MJ and a bright difference value LC respectively, z2 is larger than z1 and larger than z3 is larger than 1.03, z1=1.61, z2=1.93 and z3=1.25;
sorting the dead pixel values HDj in order from big to small, obtaining the average value of the dead pixel values HDj positioned in the first three bits, and marking the average value as a dead average value HJ;
and sending the bad mean value HJ to a bad point detection platform.
As a further scheme of the invention: the specific process of the error alarm module for obtaining the error coefficient WC is as follows:
after receiving the sample error alarm instruction, ringing a sample error alarm bell;
acquiring the total number of times of ringing a sample error alarm bell in unit time, and marking the total number of times as an alarm value JC;
acquiring the shortest time interval of two adjacent times of ringing sample error alarm bell in unit time, and marking the shortest time interval as an alarm value JS;
substituting the alert value JC and the alert value JS into the formulaThe error coefficient WC is obtained, wherein w1 and w2 are preset proportional coefficients of an alert value JC and an alert value JS respectively, and w1+w2=1, 0 < w2 < w1 < 1, w1=0.59 and w2=0.41 are taken;
and sending the error coefficient WC to a dead pixel detection platform.
As a further scheme of the invention: the mobile phone screen dead pixel automatic detection method based on the saliency analysis comprises the following steps:
step a1: the method comprises the steps that a dead pixel monitoring module marks a mobile phone which needs to be subjected to dead pixel detection on a mobile phone screen as a detection sample i, i=1, … … and n, wherein n is a natural number;
step a2: the method comprises the steps that a bad point monitoring module shoots a plurality of mobile phone screen photos of a mobile phone screen of a detection sample i with different brightness and different colors, sequentially marks the mobile phone screen photos as analysis photos j, j=1, … …, m and m are natural numbers, forms a data packet of all the analysis photos j of the same detection sample i, marks the data packet as a detection packet Ji, and sends the detection packet Ji to a bad point detection platform;
step a3: the dead pixel detection platform generates data acquisition information after receiving the detection sample packet Ji, and sends the data acquisition information to the data acquisition module;
step a4: the data acquisition module acquires an analysis photo j in a corresponding sample detection packet Ji after receiving the data acquisition information, acquires the total number of dead pixels in the analysis photo j, and marks the total number as a point value DS;
step a5: the data acquisition module acquires and analyzes the total area of all dead pixels in the photo j and marks the dead pixelsFor the dot-surface value DM, the area of each bad dot is obtained and marked as dot-product value DJ, the average value of all dot-product values DJ is obtained and marked as average value JJ, and the dot-product value DJ and the average value JJ are substituted into a formulaObtaining a partial product value PJ, substituting the dot-surface value DM and the partial product value PJ into the formula +.>Wherein, h1 and h2 are respectively preset proportional coefficients of a dot value DM and a partial product value PJ, and h1+h2=1, 0 < h1 < h2 < 1, h1=0.43 and h2=0.57;
step a6: the data acquisition module evenly divides the analysis photo j into a plurality of detection areas, acquires the brightness of the detection areas, marks the brightness as brightness values LD, acquires the maximum value and the minimum value in all the brightness values LD, acquires the difference between the maximum value and the minimum value, and marks the difference as a brightness difference LC;
step a7: the data acquisition module sends the point value DS, the area value MJ and the brightness difference LC to the data analysis module;
step a8: the data analysis module substitutes the point value DS, the area value MJ and the brightness difference LC into a formulaObtaining a dead pixel value HDj, wherein k is an error adjustment factor, k=1.254, z1, z2 and z3 are preset weight coefficients of a point value DS, an area value MJ and a bright difference value LC respectively, z2 is larger than z1 and larger than z3 is larger than 1.03, z1=1.61, z2=1.93 and z3=1.25;
step a9: the data analysis module sorts the dead pixel values HDj according to the sequence from big to small, obtains the average value of the dead pixel values HDj positioned in the first three bits, and marks the average value as a dead average value HJ;
step a10: the data analysis module sends the bad mean value HJ to a bad point detection platform;
step a11: the dead pixel detection platform compares the dead average value HJ with a preset dead average threshold HJy: if the bad average value HJ is less than or equal to a bad average threshold value HJy, marking a detection sample i corresponding to the bad average value HJ as a normal sample; if the bad average value HJ is larger than the bad average threshold value HJy, marking the detection sample i corresponding to the bad average value HJ as an abnormal sample, generating a sample error alarm instruction at the same time, and sending the sample error alarm instruction to an error alarm module;
step a12: the error alarm module sounds a sample error alarm bell after receiving the sample error alarm instruction;
step a13: the error alarm module obtains the total number of times of ringing the sample error alarm bell in unit time and marks the total number of times as an alarm value JC;
step a14: the error alarm module obtains the shortest time interval of two adjacent sample error alarm bell sounds in unit time and marks the shortest time interval as an alarm value JS;
step a15: the error alarm module substitutes the alert value JC and the alert value JS into a formulaThe error coefficient WC is obtained, wherein w1 and w2 are preset proportional coefficients of an alert value JC and an alert value JS respectively, and w1+w2=1, 0 < w2 < w1 < 1, w1=0.59 and w2=0.41 are taken;
step a16: the error alarm module sends an error coefficient WC to the dead pixel detection platform;
step a17: the dead pixel detection platform compares the error coefficient WC with a preset error threshold WCy: if the error coefficient WC is larger than the error threshold WCy, generating a production error alarm instruction, and sending the production error alarm instruction to an error alarm module;
step a18: and the error alarm module sounds a production error alarm instruction bell after receiving the production error alarm instruction.
The invention has the beneficial effects that:
according to the mobile phone screen dead pixel automatic detection method and the detection system based on the significance analysis, a mobile phone which is required to be subjected to mobile phone screen dead pixel detection is marked as a detection sample through a dead pixel monitoring module, a mobile phone screen photo of the detection sample is shot, the mobile phone screen photo of the detection sample is marked as an analysis photo, all the analysis photos are formed into a sample detection packet, dead pixel parameters of the analysis photo in the corresponding sample detection packet are obtained after data acquisition information is received through a data acquisition module, the dead pixel parameters comprise a dead pixel value, an area value and a bright difference value, the dead pixel value is obtained through a data analysis module according to the dead pixel parameter, a dead pixel value is obtained according to the dead pixel value, a dead pixel detection platform classifies the detection sample into a normal sample and an abnormal sample according to the dead pixel value, a sample error alarm instruction is generated at the same time, an error coefficient is obtained through an error alarm module according to the sample error alarm instruction, a production error alarm instruction is generated through the dead pixel detection platform according to the error coefficient, and an alarm bell sound is generated through the error alarm module; the method for automatically detecting the dead pixel on the mobile phone screen comprises the steps of firstly collecting dead pixel parameters of an analysis photo, obtaining a dead pixel value according to the dead pixel parameters, wherein the dead pixel value is used for measuring the dead pixel severity in the analysis photo, the larger the dead pixel value is, the higher the dead pixel severity in the analysis photo is, and the dead pixel severity of a detection sample is measured according to a dead pixel value, so that the mobile phone with the dead pixel severity being too high can be screened out, unqualified products are removed, then the unqualified products are analyzed, an error coefficient is obtained, the error coefficient is used for measuring the production error condition of a mobile phone production process, and the larger the error coefficient is, the more serious the production error of the mobile phone production process is, and the mobile phone production process is required to be corrected, thereby improving the mobile phone quality; the mobile phone screen dead pixel automatic detection method can monitor mobile phones and mobile phone production processes, improves mobile phone dead pixel detection efficiency, improves mobile phone standard reaching rate, reduces mobile phone production cost and improves mobile phone production efficiency.
Drawings
The invention is further described below with reference to the accompanying drawings.
Fig. 1 is a schematic block diagram of a mobile phone screen dead pixel automatic detection system based on significance analysis in the invention.
Detailed Description
The technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, 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.
Example 1: referring to fig. 1, the embodiment is a mobile phone screen dead pixel automatic detection system based on significance analysis, which comprises the following modules: the system comprises a dead pixel monitoring module, a dead pixel detection platform, a data acquisition module, a data analysis module and an error alarm module;
the bad point monitoring module is used for marking a mobile phone which needs to be subjected to mobile phone screen bad point detection as a detection sample i in sequence, shooting a mobile phone screen photo of the detection sample i, marking the mobile phone screen photo as an analysis photo j, forming a detection sample packet Ji by all the analysis photos j, and sending the detection sample packet Ji to the bad point detection platform;
the bad point detection platform is used for generating data acquisition information after receiving the sample detection packet Ji and sending the data acquisition information to the data acquisition module; the system is also used for classifying the detection sample i into a normal sample and an abnormal sample according to the bad mean value HJ, generating a sample error alarm instruction at the same time, and sending the sample error alarm instruction to an error alarm module; the production error warning module is used for generating a production error warning command according to the error coefficient WC and sending the production error warning command to the error warning module;
the data acquisition module is used for acquiring the bad point parameters of the analysis photo j in the corresponding sample detection packet Ji after receiving the data acquisition information, and sending the bad point parameters to the data analysis module; wherein, the dead pixel parameters comprise a dot value DS, an area value MJ and a bright difference value LC;
the data analysis module is used for obtaining a dead pixel value HDj according to the dead pixel parameters, obtaining a dead pixel mean value HJ according to the dead pixel value HDj, and sending the dead pixel mean value HJ to the dead pixel detection platform;
the error alarm module is used for ringing a sample error alarm bell after receiving a sample error alarm instruction, obtaining an error coefficient WC according to the sample error alarm instruction and sending the error coefficient WC to the dead point detection platform; and the alarm device is also used for ringing the production error alarm instruction bell after receiving the production error alarm instruction.
Example 2: referring to fig. 1, the embodiment is a method for automatically detecting dead pixels on a mobile phone screen based on saliency analysis, comprising the following steps:
step a1: the method comprises the steps that a dead pixel monitoring module marks a mobile phone which needs to be subjected to dead pixel detection on a mobile phone screen as a detection sample i, i=1, … … and n, wherein n is a natural number;
step a2: the method comprises the steps that a bad point monitoring module shoots a plurality of mobile phone screen photos of a mobile phone screen of a detection sample i with different brightness and different colors, sequentially marks the mobile phone screen photos as analysis photos j, j=1, … …, m and m are natural numbers, forms a data packet of all the analysis photos j of the same detection sample i, marks the data packet as a detection packet Ji, and sends the detection packet Ji to a bad point detection platform;
step a3: the dead pixel detection platform generates data acquisition information after receiving the detection sample packet Ji, and sends the data acquisition information to the data acquisition module;
step a4: the data acquisition module acquires an analysis photo j in a corresponding sample detection packet Ji after receiving the data acquisition information, acquires the total number of dead pixels in the analysis photo j, and marks the total number as a point value DS;
step a5: the data acquisition module acquires and analyzes the total area of all dead points in the photo j, marks the total area as a dot-surface value DM, acquires the area of each dead point, marks the area as a dot-product value DJ, acquires the average value of all the dot-product values DJ, marks the average value as a mean-product value JJ, and substitutes the dot-product value DJ and the mean-product value JJ into a formulaObtaining a partial product value PJ, substituting the dot-surface value DM and the partial product value PJ into the formula +.>Wherein, h1 and h2 are respectively preset proportional coefficients of a dot value DM and a partial product value PJ, and h1+h2=1, 0 < h1 < h2 < 1, h1=0.43 and h2=0.57;
step a6: the data acquisition module evenly divides the analysis photo j into a plurality of detection areas, acquires the brightness of the detection areas, marks the brightness as brightness values LD, acquires the maximum value and the minimum value in all the brightness values LD, acquires the difference between the maximum value and the minimum value, and marks the difference as a brightness difference LC;
step a7: the data acquisition module sends the point value DS, the area value MJ and the brightness difference LC to the data analysis module;
step a8: the data analysis module substitutes the point value DS, the area value MJ and the brightness difference LC into a formulaObtaining a dead pixel value HDj, wherein k is an error adjustment factor, k=1.254, z1, z2 and z3 are preset weight coefficients of a point value DS, an area value MJ and a bright difference value LC respectively, z2 is larger than z1 and larger than z3 is larger than 1.03, z1=1.61, z2=1.93 and z3=1.25;
step a9: the data analysis module sorts the dead pixel values HDj according to the sequence from big to small, obtains the average value of the dead pixel values HDj positioned in the first three bits, and marks the average value as a dead average value HJ;
step a10: the data analysis module sends the bad mean value HJ to a bad point detection platform;
step a11: the dead pixel detection platform compares the dead average value HJ with a preset dead average threshold HJy: if the bad average value HJ is less than or equal to a bad average threshold value HJy, marking a detection sample i corresponding to the bad average value HJ as a normal sample; if the bad average value HJ is larger than the bad average threshold value HJy, marking the detection sample i corresponding to the bad average value HJ as an abnormal sample, generating a sample error alarm instruction at the same time, and sending the sample error alarm instruction to an error alarm module;
step a12: the error alarm module sounds a sample error alarm bell after receiving the sample error alarm instruction;
step a13: the error alarm module obtains the total number of times of ringing the sample error alarm bell in unit time and marks the total number of times as an alarm value JC;
step a14: the error alarm module obtains the shortest time interval of two adjacent sample error alarm bell sounds in unit time and marks the shortest time interval as an alarm value JS;
step a15: the error alarm module substitutes the alert value JC and the alert value JS into a formulaThe error coefficient WC is obtained, wherein w1 and w2 are preset proportional coefficients of an alert value JC and an alert value JS respectively, and w1+w2=1, 0 < w2 < w1 < 1, w1=0.59 and w2=0.41 are taken;
step a16: the error alarm module sends an error coefficient WC to the dead pixel detection platform;
step a17: the dead pixel detection platform compares the error coefficient WC with a preset error threshold WCy: if the error coefficient WC is larger than the error threshold WCy, generating a production error alarm instruction, and sending the production error alarm instruction to an error alarm module;
step a18: and the error alarm module sounds a production error alarm instruction bell after receiving the production error alarm instruction.
In the description of the present specification, the descriptions of the terms "one embodiment," "example," "specific example," and the like, mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The foregoing is merely illustrative and explanatory of the invention, as various modifications and additions may be made to the particular embodiments described, or in a similar manner, by those skilled in the art, without departing from the scope of the invention or exceeding the scope of the invention as defined in the claims.
Claims (2)
1. The mobile phone screen dead pixel automatic detection system based on the saliency analysis is characterized by comprising the following steps:
the dead pixel monitoring module is used for marking the mobile phones needing to carry out dead pixel detection on the mobile phone screen as detection samples i in sequence, shooting mobile phone screen photos of the detection samples i, marking the mobile phone screen photos as analysis photos j, forming a detection sample packet Ji by all the analysis photos j, and sending the detection sample packet Ji to the dead pixel detection platform;
the dead pixel detection platform is used for generating data acquisition information after receiving the sample detection packet Ji and sending the data acquisition information to the data acquisition module; the system is also used for classifying the detection sample i into a normal sample and an abnormal sample according to the bad mean value HJ, generating a sample error alarm instruction at the same time, and sending the sample error alarm instruction to an error alarm module; the production error warning module is used for generating a production error warning command according to the error coefficient WC and sending the production error warning command to the error warning module;
the data acquisition module is used for acquiring the dead pixel parameters of the analysis photo j in the corresponding sample detection packet Ji after receiving the data acquisition information and sending the dead pixel parameters to the data analysis module; wherein, the dead pixel parameters comprise a dot value DS, an area value MJ and a bright difference value LC; the specific process of the data acquisition module for acquiring the dead pixel parameters is as follows:
after receiving the data acquisition information, acquiring an analysis photo j in a corresponding sample detection packet Ji, acquiring the total number of dead pixels in the analysis photo j, and marking the total number as a point value DS;
the total area of all bad points in the analysis photo j is obtained and marked as a point face value DM, the area of each bad point is obtained and marked as a dot product value DJ, the average value of all the dot product values DJ is obtained and marked as a mean product value JJ, and the dot product value DJ and the mean product value JJ are substituted into a formulaObtaining a partial product value PJ, substituting the dot-surface value DM and the partial product value PJ into the formula +.>Wherein, h1 and h2 are respectively preset proportional coefficients of a dot value DM and a partial product value PJ, and h1+h2=1, 0 < h1 < h2 < 1, h1=0.43 and h2=0.57;
dividing an analysis photo j into a plurality of detection areas uniformly, obtaining the brightness of the detection areas, marking the brightness of the detection areas as brightness values LD, obtaining the maximum value and the minimum value in all the brightness values LD, obtaining the difference between the maximum value and the minimum value, and marking the difference as a brightness difference LC;
transmitting the point value DS, the area value MJ and the bright difference value LC to a data analysis module;
the data analysis module is used for obtaining a dead pixel value HDj according to the dead pixel parameters, obtaining a dead pixel mean value HJ according to a dead pixel value HDj and sending the dead pixel mean value HJ to the dead pixel detection platform; the specific process of obtaining the dead point value HDj by the data analysis module is as follows:
substituting the dot value DS, the area value MJ and the luminance difference LC into the formulaObtaining a dead pixel value HDj, wherein k is an error adjustment factor, k=1.254, z1, z2 and z3 are preset weight coefficients of a point value DS, an area value MJ and a bright difference value LC respectively, z2 is larger than z1 and larger than z3 is larger than 1.03, z1=1.61, z2=1.93 and z3=1.25;
sorting the dead pixel values HDj in order from big to small, obtaining the average value of the dead pixel values HDj positioned in the first three bits, and marking the average value as a dead average value HJ;
sending the bad mean value HJ to a bad point detection platform;
the error alarm module is used for ringing a sample error alarm bell after receiving the sample error alarm instruction, obtaining an error coefficient WC according to the sample error alarm instruction and sending the error coefficient WC to the dead point detection platform; the alarm device is also used for ringing a production error alarm instruction bell after receiving the production error alarm instruction; the specific process of the error alarm module for obtaining the error coefficient WC is as follows:
after receiving the sample error alarm instruction, ringing a sample error alarm bell;
acquiring the total number of times of ringing a sample error alarm bell in unit time, and marking the total number of times as an alarm value JC;
acquiring the shortest time interval of two adjacent times of ringing sample error alarm bell in unit time, and marking the shortest time interval as an alarm value JS;
substituting the alert value JC and the alert value JS into the formulaThe error coefficient WC is obtained, wherein w1 and w2 are preset proportional coefficients of an alert value JC and an alert value JS respectively, and w1+w2=1, 0 < w2 < w1 < 1, w1=0.59 and w2=0.41 are taken;
and sending the error coefficient WC to a dead pixel detection platform.
2. The mobile phone screen dead pixel automatic detection method based on the saliency analysis is characterized by comprising the following steps of:
step a1: the method comprises the steps that a dead pixel monitoring module marks a mobile phone which needs to be subjected to dead pixel detection on a mobile phone screen as a detection sample i, i=1, … … and n, wherein n is a natural number;
step a2: the method comprises the steps that a bad point monitoring module shoots a plurality of mobile phone screen photos of a mobile phone screen of a detection sample i with different brightness and different colors, sequentially marks the mobile phone screen photos as analysis photos j, j=1, … …, m and m are natural numbers, forms a data packet of all the analysis photos j of the same detection sample i, marks the data packet as a detection packet Ji, and sends the detection packet Ji to a bad point detection platform;
step a3: the dead pixel detection platform generates data acquisition information after receiving the detection sample packet Ji, and sends the data acquisition information to the data acquisition module;
step a4: the data acquisition module acquires an analysis photo j in a corresponding sample detection packet Ji after receiving the data acquisition information, acquires the total number of dead pixels in the analysis photo j, and marks the total number as a point value DS;
step a5: the data acquisition module acquires and analyzes the total area of all dead points in the photo j, marks the total area as a dot-surface value DM, acquires the area of each dead point, marks the area as a dot-product value DJ, acquires the average value of all the dot-product values DJ, marks the average value as a mean-product value JJ, and substitutes the dot-product value DJ and the mean-product value JJ into a formulaObtaining a partial product value PJ, substituting the dot-surface value DM and the partial product value PJ into the formula +.>Wherein, h1 and h2 are respectively preset proportional coefficients of a dot value DM and a partial product value PJ, and h1+h2=1, 0 < h1 < h2 < 1, h1=0.43 and h2=0.57;
step a6: the data acquisition module evenly divides the analysis photo j into a plurality of detection areas, acquires the brightness of the detection areas, marks the brightness as brightness values LD, acquires the maximum value and the minimum value in all the brightness values LD, acquires the difference between the maximum value and the minimum value, and marks the difference as a brightness difference LC;
step a7: the data acquisition module sends the point value DS, the area value MJ and the brightness difference LC to the data analysis module;
step a8: the data analysis module substitutes the point value DS, the area value MJ and the brightness difference LC into a formulaObtaining a dead pixel value HDj, wherein k is an error adjustment factor, k=1.254, z1, z2 and z3 are preset weight coefficients of a point value DS, an area value MJ and a bright difference value LC respectively, z2 is larger than z1 and larger than z3 is larger than 1.03, z1=1.61, z2=1.93 and z3=1.25;
step a9: the data analysis module sorts the dead pixel values HDj according to the sequence from big to small, obtains the average value of the dead pixel values HDj positioned in the first three bits, and marks the average value as a dead average value HJ;
step a10: the data analysis module sends the bad mean value HJ to a bad point detection platform;
step a11: the dead pixel detection platform compares the dead average value HJ with a preset dead average threshold HJy: if the bad average value HJ is less than or equal to a bad average threshold value HJy, marking a detection sample i corresponding to the bad average value HJ as a normal sample; if the bad average value HJ is larger than the bad average threshold value HJy, marking the detection sample i corresponding to the bad average value HJ as an abnormal sample, generating a sample error alarm instruction at the same time, and sending the sample error alarm instruction to an error alarm module;
step a12: the error alarm module sounds a sample error alarm bell after receiving the sample error alarm instruction;
step a13: the error alarm module obtains the total number of times of ringing the sample error alarm bell in unit time and marks the total number of times as an alarm value JC;
step a14: the error alarm module obtains the shortest time interval of two adjacent sample error alarm bell sounds in unit time and marks the shortest time interval as an alarm value JS;
step a15: the error alarm module substitutes the alert value JC and the alert value JS into a formulaThe error coefficient WC is obtained, wherein w1 and w2 are preset proportional coefficients of an alert value JC and an alert value JS respectively, and w1+w2=1, 0 < w2 < w1 < 1, w1=0.59 and w2=0.41 are taken;
step a16: the error alarm module sends an error coefficient WC to the dead pixel detection platform;
step a17: the dead pixel detection platform compares the error coefficient WC with a preset error threshold WCy: if the error coefficient WC is larger than the error threshold WCy, generating a production error alarm instruction, and sending the production error alarm instruction to an error alarm module;
step a18: and the error alarm module sounds a production error alarm instruction bell after receiving the production error alarm instruction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310981048.4A CN116708633B (en) | 2023-08-07 | 2023-08-07 | Mobile phone screen dead pixel automatic detection method and detection system based on significance analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310981048.4A CN116708633B (en) | 2023-08-07 | 2023-08-07 | Mobile phone screen dead pixel automatic detection method and detection system based on significance analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116708633A CN116708633A (en) | 2023-09-05 |
| CN116708633B true CN116708633B (en) | 2023-11-07 |
Family
ID=87841697
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310981048.4A Active CN116708633B (en) | 2023-08-07 | 2023-08-07 | Mobile phone screen dead pixel automatic detection method and detection system based on significance analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116708633B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107483917A (en) * | 2017-07-17 | 2017-12-15 | 深圳威特姆光电科技有限公司 | The method of display screen bad point on-line measuring device and display screen bad point on-line checking |
| CN110009607A (en) * | 2019-03-25 | 2019-07-12 | 深圳市洲明科技股份有限公司 | Show screen dead pixel detection method, device, computer equipment and storage medium |
| CN110175997A (en) * | 2019-05-30 | 2019-08-27 | 深圳市洲明科技股份有限公司 | Show screen dead pixel detection method, device, computer equipment and storage medium |
| CN114637134A (en) * | 2022-02-15 | 2022-06-17 | 深圳市奋达机器人有限公司 | Anti-failure method of LCD (liquid crystal display) bad point detection system |
| CN115063342A (en) * | 2022-04-27 | 2022-09-16 | 珠海视熙科技有限公司 | Lens dead pixel detection method and device, electronic equipment and storage medium |
-
2023
- 2023-08-07 CN CN202310981048.4A patent/CN116708633B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107483917A (en) * | 2017-07-17 | 2017-12-15 | 深圳威特姆光电科技有限公司 | The method of display screen bad point on-line measuring device and display screen bad point on-line checking |
| CN110009607A (en) * | 2019-03-25 | 2019-07-12 | 深圳市洲明科技股份有限公司 | Show screen dead pixel detection method, device, computer equipment and storage medium |
| CN110175997A (en) * | 2019-05-30 | 2019-08-27 | 深圳市洲明科技股份有限公司 | Show screen dead pixel detection method, device, computer equipment and storage medium |
| CN114637134A (en) * | 2022-02-15 | 2022-06-17 | 深圳市奋达机器人有限公司 | Anti-failure method of LCD (liquid crystal display) bad point detection system |
| CN115063342A (en) * | 2022-04-27 | 2022-09-16 | 珠海视熙科技有限公司 | Lens dead pixel detection method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116708633A (en) | 2023-09-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| TW202036353A (en) | Solder paste printing quality detecting method, data processing device and computer storage medium | |
| CN116309378B (en) | Electronic product intelligent detection system based on artificial intelligence | |
| CN113470005B (en) | Welding spot detection device and welding spot detection method for cylindrical battery cap | |
| CN110570146A (en) | Product sorting method and device and computer readable storage medium | |
| CN111385536A (en) | Workshop monitoring method and system based on acousto-optic signal identification | |
| CN113873229B (en) | Image dead pixel detection method, system and device | |
| CN111912850A (en) | Slice cigarette debris detecting system based on artificial intelligence | |
| CN112474411A (en) | Product detection automatic processing control system based on flexible production line | |
| CN111416960B (en) | Video monitoring system based on cloud service | |
| CN108089071A (en) | A kind of ambient threshold interference detection method | |
| CN115201444A (en) | Aluminum substrate defect detection screening system and method | |
| CN116708633B (en) | Mobile phone screen dead pixel automatic detection method and detection system based on significance analysis | |
| CN106713492A (en) | Garbage station relay monitoring system and monitoring method based on cloud computing | |
| CN111045402B (en) | Central control terminal, control method thereof, intermediate device and computer storage medium | |
| CN117173133A (en) | Glass bead defect detection algorithm based on Ghostnet and attention mechanism | |
| CN116778316A (en) | AI crop material weather period identification system | |
| CN116704440A (en) | Intelligent comprehensive acquisition and analysis system based on big data | |
| EP1397001B1 (en) | Automatic measurement of video parameters | |
| CN108521571A (en) | SDI chip automatic detection methods and device, storage medium, terminal | |
| CN114757939A (en) | Optical cable production detection supervisory systems based on machine vision | |
| CN115456984A (en) | High-speed image recognition defect detection system based on two-dimensional code | |
| CN113310996A (en) | Defect detection device and detection method thereof | |
| CN112083693A (en) | Paint production line information management system based on internet of things technology | |
| CN112218040A (en) | Background monitoring device and system for high-voltage cable accessory installation | |
| CN112931482B (en) | Shaft tower drives bird ware |
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 |