CN104568749B - A kind of article surface Material Identification method, apparatus and identification equipment and system - Google Patents
A kind of article surface Material Identification method, apparatus and identification equipment and system Download PDFInfo
- Publication number
- CN104568749B CN104568749B CN201310512792.6A CN201310512792A CN104568749B CN 104568749 B CN104568749 B CN 104568749B CN 201310512792 A CN201310512792 A CN 201310512792A CN 104568749 B CN104568749 B CN 104568749B
- Authority
- CN
- China
- Prior art keywords
- article surface
- identified
- spectral signature
- classification
- image
- 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
Landscapes
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of article surface Material Identification method, apparatus and identification equipment and system, including:Obtain the image of the article surface to be identified gathered by camera;By carrying out texture recognition to described image, from default multiple material classifications, the affiliated material classification of the article surface to be identified is determined;Then the spectral signature for the feature light launched after the designated light irradiation of the article surface to be identified is obtained;And by the way that respectively compared with spectral signature corresponding to each material that the affiliated material classification includes, the spectral signature is determined into the material of the article surface to be identified.Using scheme provided in an embodiment of the present invention, compared with prior art, the volume of high-precision article surface Material Identification equipment is reduced.
Description
Technical field
The present invention relates to Material Identification technical field and field of computer technology, more particularly to a kind of article surface material to know
Other method, apparatus and identification equipment and system.
Background technology
The material of current all kinds of articles is varied, and people are limited to the recognition capability of material, it is easy to causes with false random
Very, spectral matching factor technology is Material Identification technology more accurate at present, and spectral matching factor is irradiated using the sun or artificial radiation source
During material surface, the reflection of unlike material surface, radiation and the regularity that is showed of electromagnetic wave absorption identify material species.
Spectral matching factor technology carries out the identification of material using spectrometric instrument, but high-precision spectrometric instrument because
Testing process is complicated, database is huge, causes bulky, expensive, can not obtain wide popularization and application.
The content of the invention
The embodiment of the present invention provides a kind of article surface Material Identification method, apparatus and identification equipment and system, to solve
The problem of certainly high-precision Material Identification equipment volume present in prior art is larger.
The embodiment of the present invention provides a kind of article surface Material Identification method, including:
Obtain the image of the article surface to be identified gathered by camera;
By carrying out texture recognition to described image, from default multiple material classifications, the thing to be identified is determined
The affiliated material classification in product surface;
Obtain the spectral signature for the feature light launched after the designated light irradiation of the article surface to be identified;
By the way that by the spectral signature, spectral signature corresponding with each material that the affiliated material classification includes is entered respectively
Row compares, and determines the material of the article surface to be identified.
Method provided in an embodiment of the present invention, after obtaining the image by the article surface to be identified of camera collection;It is logical
Cross and texture recognition is carried out to the image, from default multiple material classifications, determine the affiliated material of article surface to be identified
Classification;Then the spectral signature for the feature light launched after the designated light irradiation of article surface to be identified is obtained;And pass through
By the spectral signature respectively compared with spectral signature corresponding to each material that the affiliated material classification includes, it is determined that this waits to know
The material of other article surface, in this method, texture recognition is combined with spectral matching factor, texture recognition goes out to material preliminary judgement
Substantially classification, makes spectral matching factor to complete the comparison of characteristic spectrum in less database, and the combination of the two both ensured
The precision of identification, will not make the volume of equipment excessive, reduce the volume of high-precision article surface Material Identification equipment again.
Further, by carrying out texture recognition to described image, from default multiple material classifications, institute is determined
Before stating the material classification belonging to article surface to be identified, in addition to:
Determine that regularity distribution is presented in the pixel value of described image.
This way it is possible to avoid the article surface image to be identified obtained obscures, the texture recognition of image is not used to, or lead
Causing the result of texture recognition has deviation.
Further, by carrying out texture recognition to described image, from default multiple material classifications, determine described
Material classification belonging to article surface to be identified, is specifically included:
Texture recognition is carried out to described image, obtains the textural characteristics of described image;
By the textural characteristics respectively compared with textural characteristics corresponding to default multiple material classifications, obtain and institute
State multiple texture comparative results corresponding to multiple material classifications difference;
According to the multiple texture comparative result, the line for meeting preset matching condition is selected from the multiple material classification
Material classification corresponding to comparative result is managed, as the affiliated material classification of article surface to be identified.
So, by carrying out texture recognition to article surface image to be identified, the substantially classification of material can be obtained, is pair
The preliminary judgement of article material to be identified.
Further, by by spectral signature light corresponding with each material that the affiliated material classification includes respectively
Spectrum signature is compared, and is determined the material of the article surface to be identified, is specifically included:
By the spectral signature, spectral signature corresponding with each material that the affiliated material classification includes is compared respectively
Compared with obtaining and each material corresponding multiple spectrum comparative results respectively;
According to the multiple spectrum comparative result, material corresponding to immediate spectrum comparative result in each material is determined
Matter is the material of the article surface to be identified.
So, the article surface material classification determined based on above-mentioned texture recognition, then it is further true by spectral matching factor
Make the specific material of article surface to be identified.
The embodiment of the present invention also provides a kind of article surface Material Identification device, including:
Image acquisition unit, for obtaining the image of the article surface to be identified gathered by camera;
Texture recognition unit, for by described image carry out texture recognition, from default multiple material classifications, really
Make the affiliated material classification of the article surface to be identified;
Feature acquiring unit, for obtaining the feature light launched after the designated light irradiation of the article surface to be identified
Spectral signature;
Material determining unit, for each material by the way that the spectral signature is included with the affiliated material classification respectively
Corresponding spectral signature is compared, and determines the material of the article surface to be identified.
In device provided in an embodiment of the present invention, after the image for obtaining the article surface to be identified gathered by camera;
By carrying out texture recognition to the image, from default multiple material classifications, the affiliated material of article surface to be identified is determined
Matter classification;Then the spectral signature for the feature light launched after the designated light irradiation of article surface to be identified is obtained;And lead to
Cross by the spectral signature respectively compared with spectral signature corresponding to each material that the affiliated material classification includes, it is determined that this is treated
The material of article surface is identified, in this method, texture recognition is combined with spectral matching factor, texture recognition is to material preliminary judgement
Go out substantially classification, spectral matching factor is completed the comparison of characteristic spectrum in less database, the combination of the two was both protected
The precision of identification has been demonstrate,proved, will not make the volume of equipment excessive again, reduce the body of high-precision article surface Material Identification equipment
Product.
Further, texture recognition unit, it is additionally operable to by carrying out texture recognition to described image, from default multiple
In material classification, before determining the material classification belonging to the article surface to be identified, the pixel value for determining described image is in
Existing regularity distribution.
This way it is possible to avoid the article surface image to be identified obtained obscures, the texture recognition of image is not used to, or lead
Causing the result of texture recognition has deviation.
Further, texture recognition unit, specifically for carrying out texture recognition to described image, the line of described image is obtained
Manage feature;And by the textural characteristics respectively compared with textural characteristics corresponding to default multiple material classifications, obtain with
Multiple texture comparative results corresponding to the multiple material classification difference;And according to the multiple texture comparative result, from institute
State selection in multiple material classifications and meet material classification corresponding to the texture comparative result of preset matching condition, wait to know as described
The other affiliated material classification of article surface.
So, by carrying out texture recognition to article surface image to be identified, the substantially classification of material can be obtained, is pair
The preliminary judgement of article material to be identified.
Further, material determining unit, specifically for by the spectral signature respectively with the affiliated material classification bag
Spectral signature corresponding to each material included is compared, and obtains distinguishing corresponding multiple spectrum comparative results with each material;
And according to the multiple spectrum comparative result, determine that material corresponding to immediate spectrum comparative result is institute in each material
State the material of article surface to be identified.
So, the article surface material classification determined based on above-mentioned texture recognition, then it is further true by spectral matching factor
Make the specific material of article surface to be identified.
The embodiment of the present invention also provides a kind of Material Identification equipment, including:Above-mentioned article surface Material Identification device, shooting
Head and light sending and receiving apparatus, wherein:
The camera, for shooting article surface to be identified, obtain the image of the article surface to be identified;
The light sending and receiving apparatus, the article surface to be identified is irradiated for launching specified light, and receive institute
State the feature light that article surface to be identified is launched after the specified light irradiation.
Using Material Identification equipment provided in an embodiment of the present invention, the article surface to be identified gathered by camera is obtained
Image after;By carrying out texture recognition to the image, from default multiple material classifications, the article table to be identified is determined
The affiliated material classification in face;Then the Spectral Properties for the feature light launched after the designated light irradiation of article surface to be identified are obtained
Sign;And by by the spectral signature respectively compared with spectral signature corresponding to each material that the affiliated material classification includes,
Determine the material of the article surface to be identified, in this method, texture recognition is combined with spectral matching factor, texture recognition is to material
Preliminary judgement goes out substantially classification, spectral matching factor is completed the comparison of characteristic spectrum in less database, the two
With reference to the precision that both ensure that identification, it will not make the volume of equipment excessive again, reduce high-precision article surface Material Identification
The volume of equipment.
The embodiment of the present invention also provides a kind of article surface Material Identification system, including:Material Identification equipment and distal end take
Business device, wherein:
The Material Identification equipment, for obtaining the image of the article surface to be identified gathered by camera;By right
Described image carries out texture recognition, from default multiple material classifications, determines the affiliated material of article surface to be identified
Classification;Obtain the spectral signature for the feature light launched after the designated light irradiation of the article surface to be identified;Taken to distal end
Device of being engaged in sends the spectral signature, and receive that the far-end server returns by the spectral signature determine described in wait to know
The material information of the material of other article surface;
The far-end server, the spectral signature sent for receiving the Material Identification equipment, by the spectrum
Feature determines the article table to be identified compared with spectral signature corresponding to each material that the affiliated material classification includes
The material in face, and the material information of the material of determination is back to the Material Identification equipment.
Using article surface Material Identification system provided in an embodiment of the present invention, obtain by the to be identified of camera collection
After the image of article surface;By carrying out texture recognition to the image, from default multiple material classifications, determine that this waits to know
The other affiliated material classification of article surface;Then the feature light launched after the designated light irradiation of article surface to be identified is obtained
Spectral signature;And by the way that by the spectral signature, spectral signature corresponding with each material that the affiliated material classification includes is entered respectively
Row compares, and determines the material of the article surface to be identified, in this method, texture recognition is combined with spectral matching factor, texture knowledge
It is other that substantially classification is gone out to material preliminary judgement, spectral matching factor is completed the ratio of characteristic spectrum in less database
Compared with the combination of the two both ensure that the precision of identification, will not make the volume of equipment excessive again, reduce high-precision article surface
The volume of Material Identification equipment.
Other features and advantage will illustrate in the following description, also, partly become from specification
Obtain it is clear that or being understood by implementing the application.The purpose of the application and other advantages can be by the explanations write
Specifically noted structure is realized and obtained in book, claims and accompanying drawing.
Brief description of the drawings
Accompanying drawing is used for providing a further understanding of the present invention, and a part for constitution instruction, implements with the present invention
Example is used to explain the present invention together, is not construed as limiting the invention.In the accompanying drawings:
Fig. 1 is one of flow chart of article surface Material Identification method provided in an embodiment of the present invention;
Fig. 2 is the flow chart that the article surface material that the embodiment of the present invention 1 provides carries out texture recognition;
Fig. 3 is the flow chart that the article surface material that the embodiment of the present invention 1 provides carries out spectral matching factor;
Fig. 4 is the two of the flow chart for the article surface Material Identification method that the embodiment of the present invention 2 provides;
Fig. 5 is the structural representation for the article surface Material Identification device that the embodiment of the present invention 3 provides;
Fig. 6 is the structural representation for the Material Identification equipment that the embodiment of the present invention 3 provides;
Fig. 7 is the structural representation for the article surface Material Identification system that the embodiment of the present invention 4 provides.
Embodiment
In order to provide the implementation for the volume for reducing high-precision Material Identification equipment, the embodiments of the invention provide one
Kind article surface Material Identification method, apparatus and identification equipment, below in conjunction with Figure of description to the preferred embodiments of the present invention
Illustrate, it will be appreciated that preferred embodiment described herein is merely to illustrate and explain the present invention, and is not used to limit this
Invention.And in the case where not conflicting, the feature in embodiment and embodiment in the application can be mutually combined.
The embodiment of the present invention provides a kind of article surface Material Identification method, as shown in figure 1, including:
Step 101, the image for obtaining the article surface to be identified gathered by camera.
Step 102, by the image carry out texture recognition, from default multiple material classifications, determine that this waits to know
The other affiliated material classification of article surface.
Step 103, the spectral signature for obtaining the feature light launched after the designated light irradiation of article surface to be identified.
Step 104, by by spectral signature Spectral Properties corresponding with each material that the affiliated material classification includes respectively
Sign is compared, and determines the material of the article surface to be identified.
Further, when camera gathers article surface image to be identified, may be influenceed due to extraneous various factors, light
According to the shake of, camera, wide-long shot etc., cause collected image to obscure, be not used to the texture recognition of image, because
This from default multiple material classifications, determines the article surface institute to be identified by carrying out texture recognition to the image
Before the material classification of category, it can also determine whether the pixel value of the image is presented regularity distribution, if the pixel value of image
Regularity distribution is presented, then it represents that the image can be used for Material Identification, and enter above-mentioned steps 102, if the pixel value of image
Regularity distribution is not presented, needs camera to resurvey.When can ensure that camera acquired image can be used for Material Identification,
Whether the pixel value that the above-mentioned determination image can be cancelled is presented the judgement of regularity distribution.
In the above method provided in an embodiment of the present invention, the figure of the article surface to be identified gathered by camera is obtained
As after;By carrying out texture recognition to the image, from default multiple material classifications, the article surface institute to be identified is determined
Belong to material classification;Then the spectral signature for the feature light launched after the designated light irradiation of article surface to be identified is obtained;
And by by the spectral signature respectively compared with spectral signature corresponding to each material that the affiliated material classification includes, it is determined that
The material of the article surface to be identified, in this method, texture recognition is combined with spectral matching factor, texture recognition is preliminary to material
Substantially classification is determined, spectral matching factor is completed the comparison of characteristic spectrum, the combination of the two in less database
Both the precision of identification had been ensure that, will not make the volume of equipment excessive again, has reduced high-precision article surface Material Identification equipment
Volume.
Below in conjunction with the accompanying drawings, method and device provided by the invention and corresponding system are retouched in detail with specific embodiment
State.
Embodiment 1:
The flow that the embodiment of the present invention 1 carries out texture recognition to material is described in detail, as shown in Fig. 2 by this
Image carries out texture recognition, from default multiple material classifications, determines the material classification belonging to the article surface to be identified,
Specifically include:
Step 201, texture recognition is carried out to the image, obtain the textural characteristics of described image.
Step 202, by the textural characteristics respectively compared with textural characteristics corresponding to default multiple material classifications, obtain
To multiple texture comparative results corresponding with the plurality of material classification difference.
Step 203, according to the plurality of texture comparative result, from the plurality of material classification selection meet preset matching condition
Texture comparative result corresponding to material classification, as the affiliated material classification of article surface to be identified.
The texture of image is that occurred repeatedly by the gray scale being distributed on locus and formed, and texture is in image recognition
A key character, in the prior art, the extracting methods of textural characteristics has a variety of, in practical application, can use extraction ash
The method for spending co-occurrence matrix extracts the textural characteristics of image, and gray level co-occurrence matrixes reflect the space correlation of gray scale in image
Property, it is a kind of conventional means of texture feature extraction.
After the gray level co-occurrence matrixes for extracting image, corresponding characteristic value is calculated, it is corresponding with default multiple material classifications
Textural characteristics be compared, obtain with the plurality of material classification corresponding multiple texture comparative results respectively, according to actual need
Will, the texture comparative result for meeting preset matching condition in above-mentioned steps 203, can be specifically to represent immediate texture ratio
Relatively result, can also the predetermined number texture comparative result of degree of closeness from high to low.
Texture recognition is carried out to article surface image to be identified in above-mentioned flow, the substantially class of obtained simply material
Not, such as, leather, metal, plastics etc., if needing finer judgement to article surface material to be identified, also need further
Identification.
On the process base of texture recognition shown in Fig. 2, the substantially classification of the affiliated material of article surface to be identified is determined
Afterwards, according to being actually needed, article surface material to be identified can also be further determined that using spectral matching factor, passes through above-mentioned steps
104 determine the material of article surfaces to be identified, process step as shown in figure 3, including:
Step 301, by the spectral signature, spectral signature corresponding with each material that the affiliated material classification includes is entered respectively
It is capable to compare, obtain distinguishing corresponding multiple spectrum comparative results with each material.
Step 302, according to the plurality of spectrum comparative result, determine that immediate spectrum comparative result is corresponding in each material
Material be the article surface to be identified material.
The component of unlike material is different, different elements exciting by particular light ray high energy, between atom
Interaction can launch different feature light, by analyzing the spectral signature of feature light, judge the constituent of material,
Determine the material of article surface to be identified.At present, what spectral matching factor was conventional is infrared spectrum identification, is sent out to article surface to be identified
Infrared light is penetrated, article surface to be identified launches feature light after infrared light is irradiated, by the Spectral Properties of this feature light
Levy compared with spectral signature corresponding to each material that the affiliated material classification determined in above-described embodiment 2 includes, it is determined that
Go out the material of article surface to be identified, spectral signature can be stored in far-end server corresponding to each material, by far-end server
Result of determination is returned.
Embodiment 2:
The method flow being combined below to article surface Material Identification using texture recognition and spectral matching factor carries out detailed
Description, in case of texture recognition uses infrared light using gray level co-occurrence matrixes extraction feature, spectral matching factor, such as Fig. 4
It is shown, including:
Step 401, when user needs to differentiate the material of certain article, utilize the camera of article surface Material Identification equipment
Article surface to be identified is shot, collects the image of article surface to be identified.
Step 402, determine whether the pixel value of the image is presented regularity distribution, if it is, step 403 is performed, otherwise,
Perform step 404.
Step 403, the gray level co-occurrence matrixes for extracting the image, calculate corresponding characteristic value, and this feature value represents the image
Textural characteristics.
Step 404, with camera article surface to be identified is re-shoot, obtain article surface image to be identified.During shooting
As far as possible under suitable light, selection suitably distance shooting.
Step 405, by the textural characteristics for the image being calculated line corresponding with default multiple material classifications respectively
Reason feature is compared, and obtains multiple texture comparative results corresponding with the plurality of material classification difference.
Step 406, according to the plurality of texture comparative result, from the plurality of material classification selection meet preset matching condition
Texture comparative result corresponding to material classification, as the affiliated material classification of article surface to be identified, be designated as material classification A.
Step 407, when user needs to further determine that article to be identified belongs to certain material, can utilize light launch
Device launches infrared light to the article surface to be identified, carries out spectral matching factor.
In this step, the transmitter of infrared light can be started, launch infrared light to article to be identified.
Step 408, the spy that the article surface to be identified is launched after infrared light is irradiated is received using light receiver device
Light is levied, obtains the spectral signature of this feature light.
Step 409, by the spectral signature, spectral signature corresponding with each material that material classification A includes is compared respectively
Compared with obtaining and each material corresponding multiple spectrum comparative results respectively.
Step 410, according to the plurality of spectrum comparative result, determine that immediate spectrum comparative result is corresponding in each material
Material be the article surface to be identified material.
In the step, the plurality of spectrum comparative result can also be ranked up, determine in each material degree of closeness from
Several materials corresponding to high to Low predetermined number spectrum comparative result.
In actual applications, the article Material Identification method that above-described embodiment provides reduces high-precision article identification and set
Standby volume, therefore portable equipment can be applied to, such as mobile phone mobile terminal, such as when buying clothes, can use
Article surface Material Identification differentiates cloth, provides a convenient, practical, has very big popularization space.
Embodiment 3:
Based on same inventive concept, the article surface Material Identification method provided according to the above embodiment of the present invention, accordingly
Ground, another embodiment of the present invention 3 additionally provide article surface Material Identification device, and apparatus structure schematic diagram is as shown in figure 5, specific
Including:
Image acquisition unit 501, the image for obtaining the article surface to be identified gathered by camera;
Texture recognition unit 502, for by the image carry out texture recognition, from default multiple material classifications,
Determine the affiliated material classification of article surface to be identified;
Feature acquiring unit 503, for obtaining the feature launched after the irradiation of the article surface to be identified designated light
The spectral signature of light;
Material determining unit 504, for each material by the way that the spectral signature is included with the affiliated material classification respectively
Corresponding spectral signature is compared, and determines the material of the article surface to be identified.
Further, in above-mentioned article surface Material Identification device, texture recognition unit 502, it is additionally operable to by this
Image carries out texture recognition, from default multiple material classifications, determines the material classification belonging to the article surface to be identified
Before, determine that regularity distribution is presented in the pixel value of the image.
Further, texture recognition unit 502, specifically for carrying out texture recognition to described image, described image is obtained
Textural characteristics;And the textural characteristics are obtained respectively compared with textural characteristics corresponding to default multiple material classifications
To multiple texture comparative results corresponding with the multiple material classification difference;And according to the multiple texture comparative result,
Selection meets material classification corresponding to the texture comparative result of preset matching condition from the multiple material classification, as described
The affiliated material classification of article surface to be identified.
Further, material determining unit 504, specifically for the spectral signature is included with the affiliated material classification respectively
Each material corresponding to spectral signature be compared, obtain and each material corresponding multiple spectrum comparative results respectively;And root
According to the plurality of spectrum comparative result, determine that material corresponding to immediate spectrum comparative result is described to be identified in each material
The material of article surface.
The respective handling step that the function of above-mentioned each unit may correspond in flow shown in Fig. 1 to Fig. 4, it is no longer superfluous herein
State.
The embodiment of the present invention 3 additionally provides a kind of Material Identification equipment, and the equipment includes the article surface shown in above-mentioned Fig. 5
Material Identification device, in addition to camera and light sending and receiving apparatus, structural representation it is as shown in Figure 6:
Material Identification device 601, the structure of the device are identical with the apparatus structure shown in above-mentioned Fig. 5, and each unit function can
Referring to the implementation of aforementioned means, to repeat part and repeat no more;
Camera 602, for shooting article surface to be identified, obtain the image of the article surface to be identified;
Light sending and receiving apparatus 603, for launching specified light the article surface to be identified is irradiated, and receive this and wait to know
The feature light that other article surface is launched after this specifies light to irradiate.
Embodiment 4:
The embodiment of the present invention 4 also provides a kind of article surface Material Identification system, including the material that above-described embodiment provides
Identification equipment and far-end server, as shown in Figure 7:
Material Identification equipment 701, the image for obtaining the article surface to be identified gathered by camera;By to institute
State image and carry out texture recognition, from default multiple material classifications, determine the affiliated material class of the article surface to be identified
Not;Obtain the spectral signature for the feature light launched after the designated light irradiation of the article surface to be identified;To remote service
Device sends the spectral signature, and being determined by the spectral signature of receiving that the far-end server returns is described to be identified
The material information of the material of article surface;
Far-end server 702, the spectral signature sent for receiving the Material Identification equipment, by the Spectral Properties
Sign determines the article surface to be identified compared with spectral signature corresponding to each material that the affiliated material classification includes
Material, and the material information of the material of determination is back to the Material Identification equipment.
In summary, scheme provided in an embodiment of the present invention, including:Obtain the article table to be identified gathered by camera
The image in face;By carrying out texture recognition to described image, from default multiple material classifications, the thing to be identified is determined
The affiliated material classification in product surface;Then the feature light launched after the irradiation of the article surface to be identified designated light is obtained
Spectral signature;And by by spectral signature spectral signature corresponding with each material that the affiliated material classification includes respectively
It is compared, determines the material of the article surface to be identified.Using scheme provided in an embodiment of the present invention, compared to existing skill
Art, reduce the volume of high-precision article surface Material Identification equipment.
The article surface Material Identification device that embodiments herein is provided can be realized by computer program.This area
Technical staff is it should be appreciated that above-mentioned Module Division mode is only one kind in numerous Module Division modes, if division
, all should be the application's as long as article surface Material Identification device has above-mentioned function for other modules or non-division module
Within protection domain.
The application is with reference to method, the equipment according to the embodiment of the present application(System)And the flow of computer program product
Figure and/or block diagram describe.It should be understood that can be by every first-class in computer program instructions implementation process figure and/or block diagram
Journey and/or the flow in square frame and flow chart and/or block diagram and/or the combination of square frame.These computer programs can be provided
The processors of all-purpose computer, special-purpose computer, Embedded Processor or other programmable data processing devices is instructed to produce
A raw machine so that produced by the instruction of computer or the computing device of other programmable data processing devices for real
The device for the function of being specified in present one flow of flow chart or one square frame of multiple flows and/or block diagram or multiple square frames.
These computer program instructions, which may be alternatively stored in, can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that the instruction being stored in the computer-readable memory, which produces, to be included referring to
Make the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one square frame of block diagram or
The function of being specified in multiple square frames.
These computer program instructions can be also loaded into computer or other programmable data processing devices so that counted
Series of operation steps is performed on calculation machine or other programmable devices to produce computer implemented processing, so as in computer or
The instruction performed on other programmable devices is provided for realizing in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in individual square frame or multiple square frames.
Obviously, those skilled in the art can carry out the essence of various changes and modification without departing from the present invention to the present invention
God and scope.So, if these modifications and variations of the present invention belong to the scope of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to comprising including these changes and modification.
Claims (8)
- A kind of 1. article surface Material Identification method, it is characterised in that including:Obtain the image of the article surface to be identified gathered by camera;By carrying out texture recognition to described image, from default multiple material classifications, the article table to be identified is determined The affiliated material classification in face;Obtain the spectral signature for the feature light launched after the designated light irradiation of the article surface to be identified;By the way that by the spectral signature, spectral signature corresponding with each material that the affiliated material classification includes is compared respectively Compared with determining the material of the article surface to be identified;Wherein, by carrying out texture recognition to described image, from default multiple material classifications, determine described to be identified Before material classification belonging to article surface, in addition to:Determine that regularity distribution is presented in the pixel value of described image;If regularity distribution is not presented for the pixel value of described image, the image of article surface to be identified is resurveyed.
- 2. the method as described in claim 1, it is characterised in that by carrying out texture recognition to described image, from default more In individual material classification, the material classification belonging to the article surface to be identified is determined, is specifically included:Texture recognition is carried out to described image, obtains the textural characteristics of described image;By the textural characteristics respectively compared with textural characteristics corresponding to default multiple material classifications, obtain with it is described more Multiple texture comparative results corresponding to individual material classification difference;According to the multiple texture comparative result, the texture ratio for meeting preset matching condition is selected from the multiple material classification Compared with material classification corresponding to result, as the affiliated material classification of article surface to be identified.
- 3. the method as described in claim 1, it is characterised in that by by the spectral signature respectively with the affiliated material class Spectral signature corresponding to each material not included is compared, and is determined the material of the article surface to be identified, is specifically included:By the spectral signature respectively compared with spectral signature corresponding to each material that the affiliated material classification includes, obtain Distinguish corresponding multiple spectrum comparative results to each material;According to the multiple spectrum comparative result, determine that material corresponding to immediate spectrum comparative result is in each material The material of the article surface to be identified.
- A kind of 4. article surface Material Identification device, it is characterised in that including:Image acquisition unit, for obtaining the image of the article surface to be identified gathered by camera;Texture recognition unit, for by carrying out texture recognition to described image, from default multiple material classifications, determining The affiliated material classification of article surface to be identified;Feature acquiring unit, for obtaining the light for the feature light launched after the designated light irradiation of the article surface to be identified Spectrum signature;Material determining unit, for by the way that the spectral signature is corresponding with each material that the affiliated material classification includes respectively Spectral signature be compared, determine the material of the article surface to be identified;Wherein, the texture recognition unit, be additionally operable to by described image carry out texture recognition, from default multiple materials In classification, before determining the material classification belonging to the article surface to be identified, determine that rule are presented in the pixel value of described image The distribution of rule property, and if the pixel value of described image regularity distribution is not presented, resurvey the figure of article surface to be identified Picture.
- 5. device as claimed in claim 4, it is characterised in that texture recognition unit, specifically for carrying out line to described image Reason identification, obtains the textural characteristics of described image;It is and the textural characteristics are corresponding with default multiple material classifications respectively Textural characteristics are compared, and obtain multiple texture comparative results corresponding with the multiple material classification difference;And according to institute Multiple texture comparative results are stated, select to meet that the texture comparative result of preset matching condition is corresponding from the multiple material classification Material classification, as the affiliated material classification of article surface to be identified.
- 6. device as claimed in claim 4, it is characterised in that material determining unit, specifically for the spectral signature is divided Not compared with spectral signature corresponding to each material that the affiliated material classification includes, it is right respectively with each material to obtain The multiple spectrum comparative results answered;And according to the multiple spectrum comparative result, determine immediate spectrum in each material Material corresponding to comparative result is the material of the article surface to be identified.
- A kind of 7. Material Identification equipment, it is characterised in that including:Article surface Material Identification device, camera and light sending and receiving apparatus as described in claim 4-6 is any, its In:The camera, for shooting article surface to be identified, obtain the image of the article surface to be identified;The light sending and receiving apparatus, the article surface to be identified is irradiated for launching specified light, and treated described in reception The feature light that identification article surface is launched after the specified light irradiation.
- A kind of 8. article surface Material Identification system, it is characterised in that including:Material Identification equipment and far-end server, wherein:The Material Identification equipment, for obtaining the image of the article surface to be identified gathered by camera;By to described Image carries out texture recognition, from default multiple material classifications, determines the affiliated material classification of the article surface to be identified; Obtain the spectral signature for the feature light launched after the designated light irradiation of the article surface to be identified;Sent out to far-end server The spectral signature is sent, and receives the article to be identified determined by the spectral signature that the far-end server returns The material information of the material on surface;And by described image carry out texture recognition, from default multiple material classifications, Before determining the material classification belonging to the article surface to be identified, determine that the pixel value of described image is presented regular point Cloth;If regularity distribution is not presented for the pixel value of described image, the image of article surface to be identified is resurveyed;The far-end server, the spectral signature sent for receiving the Material Identification equipment, by the spectral signature Compared with spectral signature corresponding to each material that the affiliated material classification includes, the article surface to be identified is determined Material, and the material information of the material of determination is back to the Material Identification equipment.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310512792.6A CN104568749B (en) | 2013-10-25 | 2013-10-25 | A kind of article surface Material Identification method, apparatus and identification equipment and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310512792.6A CN104568749B (en) | 2013-10-25 | 2013-10-25 | A kind of article surface Material Identification method, apparatus and identification equipment and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104568749A CN104568749A (en) | 2015-04-29 |
CN104568749B true CN104568749B (en) | 2017-12-19 |
Family
ID=53085327
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310512792.6A Active CN104568749B (en) | 2013-10-25 | 2013-10-25 | A kind of article surface Material Identification method, apparatus and identification equipment and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104568749B (en) |
Families Citing this family (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105701804A (en) * | 2016-01-05 | 2016-06-22 | 百度在线网络技术(北京)有限公司 | Object material identifying method and device |
CN109752346B (en) * | 2017-11-01 | 2022-07-26 | 青岛海尔智能技术研发有限公司 | Optical method and device for identifying material of clothes |
CN108254375B (en) * | 2017-12-29 | 2020-10-27 | 广州检验检测认证集团有限公司 | Method for identifying buffalo leather and buffalo leather |
CN108734079B (en) * | 2018-02-07 | 2019-05-03 | 上海利莫网络科技有限公司 | Image big data instant analysis method |
CN108335295B (en) * | 2018-02-08 | 2019-04-30 | 扬州宇天玻璃有限公司 | Brightness adaptive equalization formula windowsill in a kind of ward |
CN109152160B (en) * | 2018-02-08 | 2019-04-12 | 山东大学齐鲁医院(青岛) | Hospital ward brightness adaptive regulation method |
CN110702559A (en) * | 2019-10-11 | 2020-01-17 | 广东美的厨房电器制造有限公司 | Object identification method and device, cooking equipment and computer readable storage medium |
CN111027601B (en) * | 2019-11-25 | 2023-10-17 | 歌尔股份有限公司 | Plane detection method and device based on laser sensor |
CN110924066B (en) * | 2019-12-20 | 2021-10-22 | 吉林求是光谱数据科技有限公司 | Clothes material identification method and device based on image identification technology and spectrum technology |
CN111766303B (en) * | 2020-09-03 | 2020-12-11 | 深圳市声扬科技有限公司 | Voice acquisition method, device, equipment and medium based on acoustic environment evaluation |
CN112785553A (en) * | 2020-12-30 | 2021-05-11 | 深兰人工智能芯片研究院(江苏)有限公司 | Density estimation method, density estimation device, electronic equipment and computer-readable storage medium |
CN113489869A (en) * | 2021-07-05 | 2021-10-08 | 深圳市威视佰科科技有限公司 | Clothing material identification method based on hyperspectral camera |
CN113989618A (en) * | 2021-11-03 | 2022-01-28 | 深圳黑蚂蚁环保科技有限公司 | Recyclable article classification and identification method |
CN115273249A (en) * | 2022-08-01 | 2022-11-01 | 思博特集成科技(珠海横琴)有限公司 | Spectrum three-dimensional identification method, spectrum three-dimensional identification method device and readable storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1093619A (en) * | 1992-12-08 | 1994-10-19 | Rwe安东根股份公司 | A kind of method of identify objects and realize the device of this method |
CN101551341A (en) * | 2009-04-09 | 2009-10-07 | 浙江大学 | Meat online non-destructive testing method and apparatus based on fusion of image and spectrum information |
CN102812357A (en) * | 2009-11-26 | 2012-12-05 | 马来西亚理工大学 | Methods And System For Recognizing Wood Species |
CN103310182A (en) * | 2012-03-14 | 2013-09-18 | 联想(北京)有限公司 | Identification method and device for object |
-
2013
- 2013-10-25 CN CN201310512792.6A patent/CN104568749B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1093619A (en) * | 1992-12-08 | 1994-10-19 | Rwe安东根股份公司 | A kind of method of identify objects and realize the device of this method |
CN101551341A (en) * | 2009-04-09 | 2009-10-07 | 浙江大学 | Meat online non-destructive testing method and apparatus based on fusion of image and spectrum information |
CN102812357A (en) * | 2009-11-26 | 2012-12-05 | 马来西亚理工大学 | Methods And System For Recognizing Wood Species |
CN103310182A (en) * | 2012-03-14 | 2013-09-18 | 联想(北京)有限公司 | Identification method and device for object |
Also Published As
Publication number | Publication date |
---|---|
CN104568749A (en) | 2015-04-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104568749B (en) | A kind of article surface Material Identification method, apparatus and identification equipment and system | |
CN110210571A (en) | Image-recognizing method, device, computer equipment and computer readable storage medium | |
CN108235770A (en) | image identification method and cloud system | |
CN109961009A (en) | Pedestrian detection method, system, device and storage medium based on deep learning | |
CN109558864A (en) | Face critical point detection method, apparatus and storage medium | |
CN108538311A (en) | Audio frequency classification method, device and computer readable storage medium | |
US20080062262A1 (en) | Apparatus, method and system for screening receptacles and persons | |
CN110400304A (en) | Object detecting method, device, equipment and storage medium based on deep learning | |
CN105608699B (en) | A kind of image processing method and electronic equipment | |
CN109117725A (en) | Face identification method and device | |
CN102855681B (en) | The true and false judges auxiliary device and householder methods, true and false judgment means and method | |
CN108509888B (en) | Method and apparatus for generating information | |
CN109766786A (en) | Character relation analysis method and Related product | |
CN109871492B (en) | Task processing method and device, computer equipment and computer storage medium | |
CN110221681A (en) | The method of adjustment and equipment of image-recognizing method, image rendering time | |
CN108235733A (en) | Substance identification and cloud system based on Raman spectrum | |
CN109992685A (en) | A kind of method and device of retrieving image | |
CN109711441A (en) | Image classification method, device, storage medium and electronic equipment | |
CN109145716A (en) | Boarding gate verifying bench based on face recognition | |
CN105701804A (en) | Object material identifying method and device | |
CN108267465A (en) | Various visual angles imaging data processing method and equipment | |
CN108984242A (en) | Virtual note display method and device, storage medium and mobile terminal | |
CN105100341A (en) | Mobile phone with infrared spectrum material analysis function | |
CN110210401B (en) | Intelligent target detection method under weak light | |
CN110163206A (en) | Licence plate recognition method, system, storage medium and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |