CN109297975A - Mobile terminal and detection method, storage device - Google Patents
Mobile terminal and detection method, storage device Download PDFInfo
- Publication number
- CN109297975A CN109297975A CN201810936489.1A CN201810936489A CN109297975A CN 109297975 A CN109297975 A CN 109297975A CN 201810936489 A CN201810936489 A CN 201810936489A CN 109297975 A CN109297975 A CN 109297975A
- Authority
- CN
- China
- Prior art keywords
- glasses
- data
- target object
- distance
- rendering
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8806—Specially adapted optical and illumination features
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/94—Investigating contamination, e.g. dust
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/94—Investigating contamination, e.g. dust
- G01N2021/945—Liquid or solid deposits of macroscopic size on surfaces, e.g. drops, films, or clustered contaminants
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
Abstract
The invention discloses a kind of mobile terminal and detection method, storage device, the detection method includes: the 3D rendering that shooting includes target object；Obtain the 3D data of 3D rendering；Identify the target object in 3D rendering；The 3D data of target object are extracted from the 3D data according to target object；And the 3D data of target object are detected to judge whether target object normal, by the above-mentioned means, remind user to adopt remedial measures in time to facilitate user to carry out glasses deformation and dirty detection whenever and wherever possible, it is time saving and energy saving.
Description
Technical field
The present invention relates to technical field of image detection, more particularly to a kind of mobile terminal and detection method, storage device.
Background technique
People are busy with living in modern society's life, work, and few people can periodically go whether optician's shop checks glasses
There are deformation, in addition periodically spend the time that optician's shop is gone to check that glasses can also feel pretty troublesome with the presence or absence of deformation user, very unrestrained
It is time-consuming, but the user to wear glasses often by glasses deformation and it is dirty annoying, do not notice that glasses are dirty and deformation, when long
Between wear deformation or dirty glasses will affect the eyesight of user, and user's eye is also resulted in when glasses deformation is serious
Eyeball surrounding deforms (girl especially to like to be beautiful can not put up with), pays attention to glasses deformation, the compartment time goes optician's shop inspection, and too
It bothers and wastes time.
Summary of the invention
The invention mainly solves the technical problem of providing a kind of mobile terminal and detection methods, storage device, with convenient
User carries out glasses deformation and dirty detection whenever and wherever possible, and user is reminded to adopt remedial measures in time, time saving and energy saving.
In order to solve the above technical problems, one technical scheme adopted by the invention is that:
A kind of detection method is provided, comprising:
Shooting includes the 3D rendering of target object；
Obtain the 3D data of the 3D rendering；
Identify the target object in the 3D rendering；
The 3D data of the target object are extracted from the 3D data according to the target object；And
The 3D data of the target object are detected to judge whether the target object is normal.
In order to solve the above technical problems, another technical solution used in the present invention is:
A kind of mobile terminal, including processor and memory are provided, the memory is for storing detection device to execute
The program of above-mentioned detection method, the processor is configured to for executing the program stored in the memory.
In order to solve the above technical problems, another technical solution used in the present invention is:
A kind of storage device is provided, program file is stored with, described program file can be performed to realize as above-mentioned
Detection method.
The beneficial effects of the present invention are: being in contrast to the prior art, the present invention includes the object by shooting
The 3D rendering of body；Obtain the 3D data of the 3D rendering；Identify the target object in the 3D rendering；According to the target object
The 3D data of the target object are extracted from the 3D data；The 3D data of the target object are detected to judge
State whether target object is normal, to facilitate user to carry out glasses deformation and dirty detection whenever and wherever possible, reminds user timely
It adopts remedial measures, it is time saving and energy saving.
Detailed description of the invention
Fig. 1 to Fig. 3 is the flow diagram of detection method；
Fig. 4 is the structural schematic diagram of mobile terminal of the present invention；
Fig. 5 is the structural schematic diagram of inventive memory device；
Fig. 6 is the structural schematic diagram of detection device of the present invention；
Fig. 7 is the structural schematic diagram of identification module of the present invention；
Fig. 8 is the structural schematic diagram of detection module of the present invention；
Fig. 9 is the structural schematic diagram that mobile terminal of the present invention carries out shape changing detection to glasses.
Specific embodiment
The present invention will be described in detail with reference to the accompanying drawings and examples.
Referring to Fig. 1, being the flow diagram of detection method.The detection method in conjunction with described in Fig. 5~Fig. 9 includes:
Step S1: shooting includes the 3D rendering of target object.
It include the 3D rendering of target object by the shooting of photographing module 10.
Wherein, the photographing module 10 is 3D camera, and the target object is glasses 100.
Step S2: the 3D data of the 3D rendering are obtained.
The 3D data of the 3D rendering are obtained by obtaining module 20, the 3D data include that the pixel of the 3D rendering is sat
Mark data.
Step S3: the target object in the 3D rendering is identified.
By the convolutional neural networks unit 31 in identification module 30 to include the glasses 100 several 3D renderings into
Row training obtains the information of the glasses, with from it is described include glasses 100 3D rendering in identify the glasses 100.
Step S4: the 3D data of the target object are extracted from the 3D data according to the target object.
The glasses are extracted from the pixel coordinate data of the 3D rendering according to the glasses 100 by extraction module 40
100 pixel coordinate data.
Step S5: the 3D data of the target object are detected to judge whether the target object is normal.
Referring to Fig. 2, wherein, step S5 includes:
Step S51: shape changing detection is carried out to the glasses 100.
Wherein, the glasses 100 include eyeglass 101, frame 102, temple 103 and nose support 104.The glasses 100
3D rendering includes datum level 130, the first reference point 110 and the second reference point 120 and other symmetrical reference points, with
For 141 and 142.
Step S52: the 3D data of the target object extracted and the 3D data of pre-stored normal glasses are compared
Compared with.
Step S53: when consistent, the glasses 100 are normal.
Step S54: when inconsistent, described two other mutually symmetrical reference points 141 and 142 is obtained and arrive the datum level
130 first distance L1 and second distance L2 and described two other symmetrical reference points 141 and 142 arrive the datum level 130
Projected position.
Step S55: judge whether the first distance L1 is equal with the second distance L2 and whether described project intersects
With the same point on the datum level 130.
If the first distance L1 it is equal with second distance L2 and it is described projection mutually give it is same on the datum level 130
Point, the glasses 100 are normal.
Step S56: if the first distance L1 and second distance L2 is unequal and described project intersects at the base
On quasi- face 130 when same point；Or the first distance L1 and second distance L2 is unequal and described project does not intersect at institute
When stating same point on datum level 130；Or the first distance L1 is equal with the second distance L2 and described project does not intersect at
On the datum level 130 when same point, 100 deformation of glasses.
In the present embodiment, select to be not easy on the glasses 100 deformation o'clock as the first reference point 110 and the second reference
Point 120, with the midpoint O by 120 connecting line S of first reference point 110 and the second reference point perpendicular to the connecting line S's
Plane carries out shape changing detection as datum level 130.
Wherein, first reference point 110 is the left frame 102 of glasses 100 and the tie point of left mirror leg 103, described the
Two reference points 120 are the right frame 102 of glasses 100 and the tie point of right temple 103.The datum level 130 is by described the
The midpoint O of one reference point 110 and the 120 connecting line S of the second reference point and perpendicular to the plane of the connecting line S, it is described mutually
Other symmetrical reference points 141 and 142 are the glasses 100 except excessively described first reference point 110 and the second reference point 120
Other symmetrical reference points in eyeglass 101 under normal circumstances, frame 102, temple 103 and nose support 104.
Referring to Fig. 3, wherein, step S5 includes:
Step S15: dirty to the eyeglass 101 of the glasses 100 to detect.
Step S25: by the 3D data (base of 101 Pixel Information of eyeglass of the glasses 100 and pre-stored normal glasses
Quasi- image) Pixel Information be compared.
Step S35: when 101 Pixel Information of eyeglass of the glasses 100 is consistent with benchmark image Pixel Information, the eye
Mirror 100 is normal.
Step S45: when 101 Pixel Information of eyeglass and benchmark image Pixel Information of the glasses 100 have differences, institute
State glasses 100 eyeglass 101 have it is dirty.
In present embodiment, the Pixel Information include pixel color and pixel it is bright dark.The benchmark image is
It shoots in advance and background that when clean unstrained glasses 3D rendering under the same background environment that stores or detection shoots is equal
One glasses 3D rendering itself.A kind of 3D rendering for the glasses that dirty detection mode is shot when being by will test with it is described
The eyeglass of the uniform glasses 3D rendering of the background shot when the lens area or detection of the 3D rendering of the eyes shot in advance itself
Region carries out pixel color and bright dark comparison.The glasses 3D rendering lens area shot when detection and the glasses 3D shot in advance
The pixel color of the lens area of image and/or bright dark comparing result are identical (in allowable range of error), then the eyeglass
Normal nothing is obvious dirty；If the pixel color of the lens area and/or bright dark comparing result be not identical (beyond error permission model
Enclose), then the eyeglass is abnormal in the presence of obvious dirty；The eye that another dirty detection mode is shot when being to detection
The lens area of mirror 3D rendering itself carries out pixel color and bright dark itself homogeneity comparison.If the lens area is not deposited
In the color of pixel and/or bright secretly visibly different with surrounding pixel electricity, homogeneity is preferable, then the eyeglass is normally without bright
Show dirty；If there are the color of pixel and/or bright secretly visibly different with surrounding pixel electricity, the glasses for the lens area
Eyeglass is abnormal in the presence of obvious dirty.
By the above-mentioned means, user without take excessive time with energy go optician's shop detection glasses deformation whether shape
Become, glasses deformation and dirty detection can be carried out by way of self-timer whenever and wherever possible, can timely detect that glasses are
It is no there are deformation and dirty, to avoid glasses deformation seriously to eyes of user bring eyes deformation and eyesight influence.
Referring to Fig. 4, being the structural schematic diagram of mobile terminal of the present invention.The mobile terminal 200 include processor 210 and
Memory 220, the memory 220 is for storing detection device 1 to execute the program of above-mentioned detection method, the processor
210 are configurable for executing the program stored in the memory 220, other elements and function in the mobile terminal 200
Can be identical as the device of existing mobile terminal and function, details are not described herein.
Wherein, processor 210 can also be known as CPU (Central Processing Unit, central processing unit).Place
Managing device 210 may be a kind of IC chip, the processing capacity with signal.Processor 210 can also be general processor,
Digital signal processor (DSP), specific integrated circuit (ASIC), ready-made programmable gate array (FPGA) or other programmable patrol
Collect device, discrete gate or transistor logic, discrete hardware components.General processor can be microprocessor or this at
Reason device is also possible to any conventional processor etc..
The detection device 1 can be installed in the mobile terminal 200 with the formation of software, corresponding to open the software
It can carry out coherent detection.
The mobile terminal 200 can be mobile phone, PAD and other smart electronics and show equipment.
By the above-mentioned means, the detection device 1 is installed in mobile phone in the form of self-timer software.User is in daily life
In work open self-timer software carry out self-timer when, so that it may while self-timer to the deformation of glasses and it is dirty detect, simply
It is convenient, it kills two birds with one stone, and save and spend time and efforts that optician's shop is periodically gone to detect glasses.
Referring to Fig. 5, being the structural schematic diagram of inventive memory device.The storage device 300 is stored with program file
310, described program file 310 can be performed to realize above-mentioned detection method.
Wherein, which can be stored in the form of software products in above-mentioned storage device 300, if including
Dry instruction is used so that a computer equipment (can be personal computer, server or the network equipment etc.) or processor
(processor) all or part of the steps of each embodiment the method for the application is executed.And storage device 300 above-mentioned
It include: USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random
Access Memory), the various media that can store program code such as magnetic or disk or computer, server,
The terminal devices such as mobile phone, plate.
In several embodiments provided herein, it should be understood that disclosed terminal, device and method can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the division of unit,
Only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components can be with
In conjunction with or be desirably integrated into another system, or some features can be ignored or not executed.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
Referring to Fig. 6, being the structural schematic diagram of detection device of the present invention, the detection device 1 is used to detect target object,
The detection device 1 includes:
Photographing module 10, for shooting the 3D rendering comprising the target object；
Module 20 is obtained, is connect with the photographing module 10, for obtaining the 3D data of the 3D rendering；
Identification module 30 is connect with the photographing module 10, for identification the target object in the 3D rendering；
Extraction module 40 is connect with the acquisition module 20 and identification module 30, for according to the target object from institute
State the 3D data that the target object is extracted in 3D data；And
Detection module 50 is connect with the extraction module 40, for the 3D data to the target object detected with
Judge whether the target object is normal.
Wherein, the photographing module 10 is 3D camera, and the target object is glasses.
In conjunction with Fig. 7, the identification module 30 includes convolutional neural networks unit 31, passes through the convolutional neural networks unit
31 pairs include that several 3D renderings of the glasses are trained to obtain the information of the glasses, with from it is described include glasses
3D rendering in identify the glasses.
In conjunction with Fig. 8, the detection module 50 includes symmetrical detection unit 51 and pixel detection unit 52.The symmetrical detection
Unit 51 is used to carry out shape changing detection to the glasses, as shown in figure 9, the glasses 100 include eyeglass 101, frame 102, mirror
Leg 103 and nose support 104.The 3D rendering of the glasses 100 includes datum level 130, the first reference point 110 and the second reference point
120 and other symmetrical reference points, described other symmetrical reference points are by taking 141 and 142 as an example, the glasses
100 3D data include pixel coordinate data (such as coordinate of the reference point 141 and 142 in X-axis, Y-axis and Z axis of the glasses 100
Data), the shape changing detection unit 51 by the 3D data of the target object received from the extraction module 40 be stored in advance
The 3D data of normal glasses (wherein, the 3D data of the pre-stored normal glasses are after wearer buys the glasses
Pass through the data of the glasses for acquisition of taking pictures) it is compared, when consistent, the glasses normal (the i.e. described glasses and purchase
When shape it is identical), the symmetrical detection unit 51 obtains described two other mutually symmetrical 141 Hes of reference point when inconsistent
142 arrive the first distance L1 and second distance L2 of the datum level 130, and judge the first distance L1 and the second distance
Whether L2 equal and whether the projection of described two mutually symmetrical other reference points 141 and 142 to datum levels 130 meets at one
Point, if the first distance L1 and second distance L2 is equal and described two other mutually symmetrical reference points 141 and 142 arrive benchmark
The projection in face 130 is met at a bit (as shown in figure 9, other symmetrical reference points 141 and 142 arrive the projection of datum level 130
To meet to collude a point M), the glasses 100 it is normal (artificially think normal, may be due to wearer according to their needs
Have adjusted the shape of the glasses)；If the first distance L1 is unequal with the second distance L2 and described project intersects at
On the datum level 130 when same point；Or the first distance L1 is unequal with the second distance L2 and the projection not phase
When meeting at same point on the datum level 130；Or the first distance L1 it is equal with the second distance L2 and it is described projection not
When intersecting at same point on the datum level 130,100 deformation of glasses.
In the present embodiment, select to be not easy on the glasses 100 deformation o'clock as the first reference point 110 and the second reference
Point 120, by the midpoint O of 120 connecting line S of first reference point 110 and the second reference point and perpendicular to first ginseng
The plane of the wiring S of examination point 110 and the second reference point 120 carries out shape changing detection as datum level 130.
Wherein, first reference point 110 is the left frame 102 of glasses 100 and the tie point of left mirror leg 103, described the
Two reference points 120 are the right frame 102 of glasses and the tie point of right temple 103.The datum level 130 is to join by described first
The midpoint O of examination point 110 and the 120 connecting line S of the second reference point and perpendicular to the plane of the connecting line S is described mutually opposite
Other reference points 141 and 142 be referred to as except the glasses of excessively described first reference point 110 and the second reference point 120 are normal
In the case of eyeglass 101, frame 102, other symmetrical reference points in temple 103 and nose support 104.
The pixel detection unit 52 is detected for dirty to the eyeglass 101 of the glasses 100.The pixel detection
101 Pixel Information of eyeglass of the glasses 100 is compared by unit 52 with the 3D data of pre-stored normal glasses, in institute
State glasses 100 101 Pixel Information of eyeglass it is consistent with the 3D data of pre-stored normal glasses when, the glasses are normal (i.e.
The eyeglass of the glasses does not have dirty), in 101 Pixel Information of eyeglass and the pre-stored normal glasses of the glasses 100
When 3D data have differences, the eyeglass 101 of the glasses 100 has dirty.
In present embodiment, the Pixel Information include pixel color and pixel it is bright dark.It is described pre-stored
The 3D data of normal glasses are the clean unstrained glasses 3D rendering under the same background environment for shooting and storing in advance.It is logical
The lens area for crossing the 3D rendering of the glasses shot when will test and the 3D rendering of the eyes shot in advance carries out picture
Plain color and bright dark comparison, if the pixel color of the lens area and/or identical (the error permission model of bright dark comparing result
In enclosing), then the eyeglass is normal, without obvious dirty；If the pixel color of the lens area and/or bright dark comparing result
Not identical (exceeding allowable range of error), then the eyeglass is abnormal, exists obvious dirty.
The 3D rendering shot when in the present embodiment can also be by will test and the 3D rendering comparison shot in advance are true
Determine the 3D data of glasses.
It is described pre-stored in the embodiment that other carry out dirty detection to eyeglass 101 by pixel unit 52
The 3D data (benchmark image) of normal glasses be the uniform glasses 3D rendering itself of the background that shoots when detecting.It is shot when to detection
The lens area of the glasses 3D rendering itself carry out pixel color and bright dark itself homogeneity comparison, if the eyeglass
There is no the colors of pixel and/or bright secretly visibly different with surrounding pixel electricity in region, and homogeneity is preferable, then the eyeglass
Normal nothing is obvious dirty；If the lens area there are the color of pixel and/or bright secretly visibly different with surrounding pixel electricity,
The eyeglass is abnormal in the presence of obvious dirty.
In addition, the glasses 3D rendering that the background shot when detection of the present invention is uniform, refers to and carries on the back when detection in solid color
Under scape or in the presence of the glasses 3D rendering shot under the background of regular lines.It is single in the uniform glasses 3D rendering of the background
When 3D rendering under color background, to avoid dirty color identical as background color caused by error be typically chosen different monochromatic back
It is dirty whether there is on the determination glasses that scape carries out repeated detection；When the uniform glasses 3D rendering of the background is in rule
When the glasses 3D rendering shot under the background of property lines, the identification module 40 may recognize that the regular lines of lens area is
The background pixel information can be excluded when carrying out Pixel Information detection, be avoided background by background, the pixel detection unit 52
Pixel Information is mistakenly considered dirty.
In the application, user opens the 3D camera of mobile terminal 200, shoots one by the 3D camera and wears just
The face 3D rendering of normal glasses, and stored the face 3D rendering as benchmark image.The 3D of a wearing spectacles is shot again
Image obtains the 3D data of the wearing spectacles 3D rendering by acquiring unit 20.By passing through training in identification module 30
The convolutional neural networks unit 31 of identification glasses identifies the 3D rendering, to identify the glasses 3D in the 3D rendering
Image, extraction module 40 extract the 3D data of the glasses according to the glasses from the 3D data, in detection module 50
Symmetrical detection unit 51 is used to carry out shape changing detection to the glasses.Wherein, with the left frame of glasses and the tie point of left mirror leg
For first reference point 110, with the right frame of glasses and the tie point of right temple for second reference point 120, to pass through
The midpoint O of first reference point 110 and the 120 connecting line S of the second reference point and perpendicular to the plane of the connecting line S it is
Datum level 130.The shape changing detection unit 51 is by the 3D data of the target object received from the extraction module 40 and in advance
The 3D data of the normal glasses of storage are compared, and when consistent, the glasses are normal；When inconsistent, the symmetrical detection unit
51, which obtain described two mutually symmetrical other reference points 141 and 142 symmetrical detection units 51, obtains described two symmetrically
Other reference points 141 and 142 (the first reference point 110 was removed on the glasses with second reference point 120 two symmetrically join
Examination point) to the first distance L1 and second distance L2 of the datum level 130 and described two other mutually symmetrical reference points 141
Whether the projection with 142 to datum level 130 meets at a bit, and judge the first distance L1 and second distance L2 whether phase
Deng and the projection whether mutually give same point on the datum level 130.If the first distance L1 and second distance L2
Equal and described two mutually symmetrical projections of other reference points 141 and 142 on the datum level 130 intersect at same point,
The glasses 100 are normal；If the first distance L1 and second distance L2 is unequal and described project intersects at the base
On quasi- face 130 when same point, 100 deformation of glasses；Or the first distance L1 and second distance L2 is unequal and institute
When stating projection and not intersecting at same point on the datum level 130,100 deformation of glasses；Or the first distance L1 with it is described
Second distance L2 is equal and the projection is not when intersecting at same point on the datum level 130,100 deformation of glasses.
The 3D rendering of the glasses shot when pixel detection unit 52 in detection module 50 is by will test with it is described
The lens area of the benchmark image shot in advance carries out pixel color and bright dark comparison, if the pixel face of the lens area
Color and/or bright dark comparing result are identical (in allowable range of error), then the eyeglass is normally without obvious dirty；If the mirror
The pixel color of panel region and/or bright dark comparing result be not identical (exceed allowable range of error), then the eyeglass is being not just
Be commonly present it is obvious dirty, to obtain testing result.
In addition, the identification module 40 may recognize that the human face structure (such as: eyebrow, eyelash, eyeball etc.) of lens area
For background, which can be excluded when carrying out Pixel Information detection, avoid to carry on the back by the pixel detection unit 52
Scene prime information is mistakenly considered dirty.
By the above-mentioned means, user voluntarily can carry out glasses deformation and dirty using the mobile terminal 200 of simple operations
Dirty detection, user can adopt remedial measures in time according to testing result, to avoid glasses deformation seriously to eyes of user band
The eyes deformation come and eyesight influence, it is time saving and labor saving.
3D rendering of the present invention by shooting comprising glasses, obtains the 3D data of the 3D rendering；Convolutional neural networks list
Member identifies the glasses in the 3D rendering；The 3D data of the glasses are extracted from the 3D data according to the glasses；Detection
Two symmetric points on the glasses at a distance from datum level whether equal and projection that two symmetric points are on datum level whether phase
Meet at a little with detect glasses whether deformation, the Pixel Information of the Pixel Information in eyeglass region and benchmark image is compared
Compared with to detect whether glasses dirty, to facilitate user to carry out glasses deformation and dirty detection whenever and wherever possible, remind user and
When adopt remedial measures, it is time saving and energy saving.
Mode the above is only the implementation of the present invention is not intended to limit the scope of the invention, all to utilize this
Equivalent structure or equivalent flow shift made by description of the invention and accompanying drawing content, it is relevant to be applied directly or indirectly in other
Technical field is included within the scope of the present invention.
Claims (10)
1. a kind of detection method characterized by comprising
Shooting includes the 3D rendering of target object；
Obtain the 3D data of the 3D rendering；
Identify the target object in the 3D rendering；
The 3D data of the target object are extracted from the 3D data according to the target object；And
The 3D data of the target object are detected to judge whether the target object is normal.
2. detection method according to claim 1, which is characterized in that the target object is glasses；
Target object in the identification 3D rendering, comprising:
Several 3D renderings for including the glasses are trained by convolutional neural networks to obtain the information of the glasses,
With from it is described include glasses 3D rendering in identify the glasses.
3. detection method according to claim 2, which is characterized in that the 3D data to the target object detect
To judge whether the target object is normal, comprising:
Shape changing detection is carried out to the glasses, wherein the 3D rendering of the glasses includes datum level, the first reference point and the second ginseng
Examination point and other symmetrical reference points, the 3D data of the glasses include the pixel coordinate data of the glasses；
The 3D data of the target object extracted are compared with the 3D data of pre-stored normal glasses；
When the 3D data of the target object received are consistent with the 3D data of pre-stored normal glasses, the glasses are just
Often.
4. detection method according to claim 3, which is characterized in that 3D data of the target object that will be extracted and pre-
The 3D data of the normal glasses first stored are compared, and further include；
In the 3D data of the target object received and the inconsistent 3D data of pre-stored normal glasses, described two are obtained
Other symmetrical reference points are referred to the first and second distances of the datum level and described two mutually symmetrical other
Point arrives the projected position of datum level；
Judge whether the first distance and the second distance equal and described two other mutually symmetrical reference points are to base
Whether the projection in quasi- face meets at a bit；
When equal in the first distance and second distance and described projection intersects at a point, the glasses are normal.
5. detection method according to claim 4, which is characterized in that the judgement first distance and the second distance
Whether whether equal and described two mutually symmetrical other reference points to datum levels projection meets at a bit, further includes:
When unequal in the first distance and the second distance and described projection intersects at a point, the glasses deformation；
When unequal in the first distance and the second distance and described projection does not intersect at a bit, the glasses deformation；
When equal with the second distance in the first distance and described projection does not intersect at a bit, the glasses deformation.
6. detection method according to claim 5, which is characterized in that first reference point is the left frame and left mirror of glasses
The tie point of leg, second reference point are the right frame of glasses and the tie point of right temple, and the datum level is by described
The midpoint of first reference point and the second reference point connecting line and perpendicular to first reference point and second reference point
The plane of connecting line.
7. detection method according to claim 2, which is characterized in that the 3D data to the target object detect
To judge whether the target object is normal, comprising:
It is dirty to the eyeglass of the glasses to detect；
The eyeglass Pixel Information of the glasses is compared with the 3D data of pre-stored normal glasses；
When difference is not present in the eyeglass Pixel Information of the glasses and the 3D data of pre-stored normal glasses, the glasses
Eyeglass without dirty.
8. detection method according to claim 7, which is characterized in that the eyeglass Pixel Information by the glasses and in advance
The 3D data of the normal glasses of storage are compared, and further include；
When the eyeglass Pixel Information of the glasses and the 3D data of pre-stored normal glasses have differences, the glasses
Eyeglass has dirty.
9. a kind of mobile terminal, which is characterized in that including processor and memory, the memory for store detection device with
Perform claim requires the program of detection method described in any one of 1-8, the processor is configured to for executing described deposit
The program stored in reservoir.
10. a kind of storage device, which is characterized in that be stored with program file, described program file can be performed to realize such as
Detection method of any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810936489.1A CN109297975A (en) | 2018-08-16 | 2018-08-16 | Mobile terminal and detection method, storage device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810936489.1A CN109297975A (en) | 2018-08-16 | 2018-08-16 | Mobile terminal and detection method, storage device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109297975A true CN109297975A (en) | 2019-02-01 |
Family
ID=65165203
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810936489.1A Pending CN109297975A (en) | 2018-08-16 | 2018-08-16 | Mobile terminal and detection method, storage device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109297975A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111343330A (en) * | 2019-03-29 | 2020-06-26 | 阿里巴巴集团控股有限公司 | Smart phone |
| CN111475733A (en) * | 2020-04-14 | 2020-07-31 | 维沃移动通信有限公司 | Information prompting method and intelligent glasses |
| CN114994060A (en) * | 2022-07-15 | 2022-09-02 | 君享科技(深圳)有限公司 | Intelligent detection system and method for magnetic ring appearance defects under machine vision |
| CN116596935A (en) * | 2023-07-18 | 2023-08-15 | 苏州思谋智能科技有限公司 | Deformation detection method, deformation detection device, computer equipment and computer readable storage medium |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4401893A (en) * | 1981-07-29 | 1983-08-30 | Intec Corporation | Method and apparatus for optically inspecting a moving web of glass |
| WO1997018994A1 (en) * | 1995-11-22 | 1997-05-29 | Laboratoires Merck Sharp & Dohme - Chibret Snc | Transfer system between a bag and a sterile enclosure |
| EP1797386B1 (en) * | 2004-10-04 | 2008-04-23 | Alfa Laval Vicarb | Heat exchanger with specific plates |
| CN101339140A (en) * | 2007-07-02 | 2009-01-07 | 台达电子工业股份有限公司 | Object flaw detection device and method, detection condition adjustment method |
| CN101598826A (en) * | 2009-06-01 | 2009-12-09 | 深圳欧菲光科技股份有限公司 | A kind of method for processing optical lens for camera |
| CN102346546A (en) * | 2010-07-26 | 2012-02-08 | 精工爱普生株式会社 | Detection device, electronic apparatus, and robot |
| CN102735695A (en) * | 2012-06-04 | 2012-10-17 | 华中科技大学 | Rapid lens flaw detection method and apparatus thereof |
| CN103887922A (en) * | 2012-12-19 | 2014-06-25 | 日本电产三协株式会社 | Gear motor and valve driving device |
| CN104680508A (en) * | 2013-11-29 | 2015-06-03 | 华为技术有限公司 | Convolutional neural network and target object detection method based on convolutional neural network |
| CN205253585U (en) * | 2016-02-26 | 2016-05-25 | 视悦光学有限公司 | Lens flaw precision measurement system |
| CN106406307A (en) * | 2016-09-20 | 2017-02-15 | 杭州南江机器人股份有限公司 | Movable platform movement control method based on load center of gravity |
| CN106454297A (en) * | 2016-11-15 | 2017-02-22 | 深圳Tcl数字技术有限公司 | Method and apparatus of debugging and installing projector |
| CN106469448A (en) * | 2015-06-26 | 2017-03-01 | 康耐视公司 | Carry out automatic industrial inspection using 3D vision |
| CN106485214A (en) * | 2016-09-28 | 2017-03-08 | 天津工业大学 | A kind of eyes based on convolutional neural networks and mouth state identification method |
| CN107053167A (en) * | 2015-12-01 | 2017-08-18 | 精工爱普生株式会社 | Control device, robot and robot system |
| CN107145849A (en) * | 2017-04-27 | 2017-09-08 | 努比亚技术有限公司 | A kind of target object condition detection method, mobile terminal and computer-readable recording medium |
| CN107850418A (en) * | 2015-07-31 | 2018-03-27 | 依视路国际公司 | The device verified the method for spectacle frame and the degree of conformity of predetermined service index and associated |
-
2018
- 2018-08-16 CN CN201810936489.1A patent/CN109297975A/en active Pending
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4401893A (en) * | 1981-07-29 | 1983-08-30 | Intec Corporation | Method and apparatus for optically inspecting a moving web of glass |
| WO1997018994A1 (en) * | 1995-11-22 | 1997-05-29 | Laboratoires Merck Sharp & Dohme - Chibret Snc | Transfer system between a bag and a sterile enclosure |
| EP1797386B1 (en) * | 2004-10-04 | 2008-04-23 | Alfa Laval Vicarb | Heat exchanger with specific plates |
| CN101339140A (en) * | 2007-07-02 | 2009-01-07 | 台达电子工业股份有限公司 | Object flaw detection device and method, detection condition adjustment method |
| CN101598826A (en) * | 2009-06-01 | 2009-12-09 | 深圳欧菲光科技股份有限公司 | A kind of method for processing optical lens for camera |
| CN102346546A (en) * | 2010-07-26 | 2012-02-08 | 精工爱普生株式会社 | Detection device, electronic apparatus, and robot |
| CN102735695A (en) * | 2012-06-04 | 2012-10-17 | 华中科技大学 | Rapid lens flaw detection method and apparatus thereof |
| CN103887922A (en) * | 2012-12-19 | 2014-06-25 | 日本电产三协株式会社 | Gear motor and valve driving device |
| CN104680508A (en) * | 2013-11-29 | 2015-06-03 | 华为技术有限公司 | Convolutional neural network and target object detection method based on convolutional neural network |
| CN106469448A (en) * | 2015-06-26 | 2017-03-01 | 康耐视公司 | Carry out automatic industrial inspection using 3D vision |
| CN107850418A (en) * | 2015-07-31 | 2018-03-27 | 依视路国际公司 | The device verified the method for spectacle frame and the degree of conformity of predetermined service index and associated |
| CN107053167A (en) * | 2015-12-01 | 2017-08-18 | 精工爱普生株式会社 | Control device, robot and robot system |
| CN205253585U (en) * | 2016-02-26 | 2016-05-25 | 视悦光学有限公司 | Lens flaw precision measurement system |
| CN106406307A (en) * | 2016-09-20 | 2017-02-15 | 杭州南江机器人股份有限公司 | Movable platform movement control method based on load center of gravity |
| CN106485214A (en) * | 2016-09-28 | 2017-03-08 | 天津工业大学 | A kind of eyes based on convolutional neural networks and mouth state identification method |
| CN106454297A (en) * | 2016-11-15 | 2017-02-22 | 深圳Tcl数字技术有限公司 | Method and apparatus of debugging and installing projector |
| CN107145849A (en) * | 2017-04-27 | 2017-09-08 | 努比亚技术有限公司 | A kind of target object condition detection method, mobile terminal and computer-readable recording medium |
Non-Patent Citations (4)
| Title |
|---|
| YA-HUI TSAI: "Surface defect detection of 3D objects using robot vision", 《INDUSTRIAL ROBOT: AN INTERNATIONAL JOURNAL》 * |
| 李良湾: "基于机器视觉的镜片缺陷瑕疵检测图像处理基础研究", 《万方数据库》 * |
| 肖国士等: "《验光与配镜必读 屈光不正诊断与矫治》", 31 December 2017 * |
| 陈雯柏编: "《人工神经网络原理与实践[M]》", 31 December 2016 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111343330A (en) * | 2019-03-29 | 2020-06-26 | 阿里巴巴集团控股有限公司 | Smart phone |
| CN111475733A (en) * | 2020-04-14 | 2020-07-31 | 维沃移动通信有限公司 | Information prompting method and intelligent glasses |
| CN111475733B (en) * | 2020-04-14 | 2024-04-12 | 维沃移动通信有限公司 | Information prompting method and intelligent glasses |
| CN114994060A (en) * | 2022-07-15 | 2022-09-02 | 君享科技(深圳)有限公司 | Intelligent detection system and method for magnetic ring appearance defects under machine vision |
| CN114994060B (en) * | 2022-07-15 | 2022-11-15 | 君享科技(深圳)有限公司 | Intelligent detection system and method for magnetic ring appearance defects under machine vision |
| CN116596935A (en) * | 2023-07-18 | 2023-08-15 | 苏州思谋智能科技有限公司 | Deformation detection method, deformation detection device, computer equipment and computer readable storage medium |
| CN116596935B (en) * | 2023-07-18 | 2023-11-03 | 苏州思谋智能科技有限公司 | Deformation detection method, deformation detection device, computer equipment and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109297975A (en) | Mobile terminal and detection method, storage device | |
| AU2019419376B2 (en) | Virtual try-on systems and methods for spectacles | |
| CN104408764B (en) | Method, device and system for trying on glasses in virtual mode | |
| CN104036169B (en) | Biological authentication method and biological authentication apparatus | |
| CN107003721A (en) | Improvement for eyes tracking system is calibrated | |
| CN107018323B (en) | Control method, control device and electronic device | |
| CN110378914A (en) | Rendering method and device, system, display equipment based on blinkpunkt information | |
| CN105556539A (en) | Detection devices and methods for detecting regions of interest | |
| CN107563325B (en) | Method and device for testing fatigue degree and terminal equipment | |
| US10620454B2 (en) | System and method of obtaining fit and fabrication measurements for eyeglasses using simultaneous localization and mapping of camera images | |
| US9924861B2 (en) | System and methods for assessing vision using a computing device | |
| CN109993115A (en) | Image processing method, device and wearable device | |
| KR102363130B1 (en) | Fixed lens meter system | |
| CN109214324A (en) | Most face image output method and output system based on polyphaser array | |
| CA2920728A1 (en) | Systems and methods of measuring facial characteristics | |
| CN106991378A (en) | Facial orientation detection method, detection means and electronic installation based on depth | |
| CN109255280A (en) | Skin condition detection method and electronic device | |
| CN104008360B (en) | A kind of automatic sensing bar code reading method and automatic sensing barcode reader | |
| BR102016009093A2 (en) | EQUIPMENT FOR ACQUISITION OF 3D IMAGE DATE OF A FACE AND AUTOMATIC METHOD FOR PERSONALIZED MODELING AND MANUFACTURE OF GLASS FRAMES | |
| CN109325917A (en) | The method and device of noise, computer readable storage medium in a kind of detection image | |
| US20190265517A1 (en) | Method for determining a parameter of an optical equipment | |
| CN110073406A (en) | Face detection means and its control method and program | |
| EP3843043B1 (en) | Apparatus, method, and computer-readable storage medium for expanding an image database for evaluation of eyewear compatibility | |
| CN110287797A (en) | A kind of dioptric screening technique based on mobile phone | |
| CN110287796B (en) | Refractive screening method based on mobile phone and external equipment |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 518000 1-10 Floor, Building A2, Nanshan Zhiyuan, 1001 Xueyuan Avenue, Nanshan District, Shenzhen City, Guangdong Province Applicant after: QIKU INTERNET NETWORK SCIENTIFIC (SHENZHEN) Co.,Ltd. Address before: 518000 1-10 Floor, Building A2, Nanshan Zhiyuan, 1001 Xueyuan Avenue, Shenzhen City, Guangdong Province Applicant before: QIKU INTERNET NETWORK SCIENTIFIC (SHENZHEN) Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190201 |