CN109544514A - A kind of sawn timber identity identification method, device and equipment merging performance characteristic - Google Patents
A kind of sawn timber identity identification method, device and equipment merging performance characteristic Download PDFInfo
- Publication number
- CN109544514A CN109544514A CN201811307821.4A CN201811307821A CN109544514A CN 109544514 A CN109544514 A CN 109544514A CN 201811307821 A CN201811307821 A CN 201811307821A CN 109544514 A CN109544514 A CN 109544514A
- Authority
- CN
- China
- Prior art keywords
- timber
- identified
- appearance features
- image
- database
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30161—Wood; Lumber
Abstract
The present invention provides a kind of sawn timber identity identification method, device and equipment for merging performance characteristic, method includes: to extract the appearance features of all timber, and the timber ID of each timber and corresponding appearance features are stored in database;Wherein, the appearance features include the defective locations of the color histogram and each timber of each timber on multiple surfaces;Obtain the timber image of the timber to be identified transmitted on a moving belt;The appearance features of timber to be identified are obtained according to the timber image;The defective locations of timber in the defective locations and the database on multiple surfaces of the timber to be identified on multiple surfaces are matched, timber ID set corresponding with the timber to be identified is obtained;The flexibility of lumber's production line with the accurate quick identification problem of effective solution timber, can be promoted based on the present invention, customize processing.
Description
Technical field
The present invention relates to timber processing, timber assembly field more particularly to a kind of sawn timber bodies for merging performance characteristic
Part discrimination method, equipment and device.
Background technique
Although compared with other countries, accounting is seldom per capita, and timber it is well known that China's forest reserves are abundant
Demand, especially the demand of solid wood again increasingly increase.Therefore, in production and manufacturing process, the utilization of timber is improved
Rate is becoming extremely urgent problem.
Due to the less investment that the forestry in current China processes, automation level is low, therefore, improves the benefit of timber
It is mainly to be unfolded from around judgement Defects in sawn timber with rate.Traditional Defects in sawn timber detection is mainly completed by experienced operator, but base
Will receive subjective difference in the defects detection of naked-eye observation leads to the difference of testing result.In order to overcome Defects in sawn timber manually to regard
The shortcomings that feeling detection, the technologies such as machine vision, ultrasonic wave, microwave, nuclear magnetic resonance, X-ray density imaging have been attempted for sawing
The automatic detection of material surface defect.Wherein, machine vision technique is identified because its high performance-price ratio has been confirmed to be arithmetic for lumber surface defects'
One of effective technology.
However, the rise year by year of log material price is existing to be examined with defect with the aggravation of timber resources situation in short supply
Survey be core sawn timber expose some shortcomings using improvement method, firstly, traditional Defects in sawn timber detection method just for
The defect of current sawn timber is analyzed and is identified, is only capable of the use of a piece timber of optimization, be cannot achieve the group of same batch sawn timber
Optimization is closed, the utilization rate of timber is limited.Secondly, these existing detection methods can only generally provide current production superiority and inferiority according to
According to can not effectively be recognized to sawn timber itself and with the sawn timber of batch, it is difficult to realize customize, the production and processing work of flexibility
Skill optimization, system combination are insufficient.
Summary of the invention
In order to overcome timber that can not effectively recognize to sawn timber itself and with the sawn timber of batch, it is difficult to realization customization,
The production and processing technology of flexibility optimizes, and system combination is insufficient, and the invention discloses a kind of sawn timber bodies for merging appearance features
Part discrimination method, device and equipment can be promoted gloomy based on the present invention with the accurate quick identification problem of effective solution timber
The flexibility of work production line customizes processing.
It include: to extract all timber the embodiment of the invention discloses a kind of sawn timber identity identification method for merging performance characteristic
Appearance features, and the timber ID of each timber and corresponding appearance features are stored in database;Wherein, the appearance features
The defective locations of color histogram and each timber on multiple surfaces including each timber;
Obtain the timber image of the timber to be identified transmitted on a moving belt;
The appearance features of timber to be identified are obtained according to the timber image;
By the timber in the defective locations and the database on multiple surfaces of the timber to be identified multiple
Defective locations on surface are matched, and timber ID set corresponding with the timber to be identified is obtained;
It is when the quantity for judging the timber ID in the timber ID set is not unique, the color of the timber to be identified is straight
Side's figure and the color histogram of the timber in the database are matched, with it is determining with it is described it is to be identified it is corresponding at present most
Whole timber ID.
Preferably, the timber image for obtaining the timber to be identified transmitted on a moving belt, specifically:
Obtain the transmission image of line scan camera shooting;
Timber is judged whether there is according to the colour brightness of the transmission image, the preceding part of transmission image is not wrapped if detecting
Containing no timber, partially have afterwards comprising timber, then judges that the transmission image for start frame, and is marked;If detecting transmission figure
The front subpackage of picture contains timber, and rear part does not include timber, then judges that the transmission image for end frame, and is marked;
Image spelling is carried out according to the start frame, end frame and all transmission images between start frame and end frame
It connects, to generate the timber image of timber to be identified.
Preferably, the scan frequency of the line scan camera is consistent with the frequency of delivery of the conveyer belt.
Preferably, according to every a line on the colour brightness judgement transmission image on transmission image, whether there is or not wood grains, and then really
Surely transmitting whether there is timber in image.
Preferably, the appearance features for extracting all timber, and by the timber ID of each timber and corresponding apparent
Feature is stored in database specifically:
The surface of each timber in the timber image is traversed, and selects defect profile area on each surface
Greater than the region of M pixel value, candidate local defect region to be selected is obtained;
Obtain the boundary rectangle in the candidate local defect region, and the Y by the central point of boundary rectangle away from most short end point
Defective locations of the coordinate value as timber in respective surfaces;
According to the statistical pixel values range A of all timber, the color histogram feature of each timber image is obtained;
According on each surface defective locations and color histogram feature generate the appearance features of each timber, and
The timber ID of each timber and corresponding appearance features are stored in database.
Preferably, the value of the M is 4000, and the A range is 7-120.
Preferably, in the defective locations and the database on multiple surfaces by the timber to be identified
The defective locations of timber on multiple surfaces are matched, and obtain timber ID set corresponding with the timber to be identified specifically
Are as follows:
By the timber in the defective locations and the database on multiple surfaces of the timber to be identified in multiple tables
Defective locations on face compare, when the distance of two defective locations be less than N when, by corresponding timber ID be added to it is described
In the corresponding timber ID set of timber to be identified.
Preferably, described when the quantity for judging the timber ID in the timber ID set is not unique, it will be described to be identified
The color histogram of the color histogram of timber and the timber in the database is matched, with it is determining with it is described to be identified
The corresponding final timber ID of mesh specifically:
When the quantity for judging the timber ID in the timber ID set is not unique, each of described timber to be identified is calculated
The Euclidean distance of the color histogram feature in each face of the color histogram feature and timber in the database in face, will
To numerical value sorted from small to large, X before retaining, obtains and the timber ID on each surface gathers;
The highest timber ID of frequency of occurrence in the timber ID set on multiple surfaces is counted, that is, determines the timber pair to be identified
The final ID for the timber to be retrieved answered.
The embodiment of the invention also provides a kind of sawn timber identification devices for merging performance characteristic, comprising:
Appearance features extraction unit, for extracting the appearance features of all timber, and by the timber ID of each timber and
Corresponding appearance features are stored in database;Wherein, the appearance features include the color histogram and each wood of each timber
The defective locations of material on multiple surfaces;
Timber image acquisition unit obtains the timber image of the timber to be identified transmitted on a moving belt;
Appearance features recognition unit obtains the appearance features of timber to be identified according to the timber image;
Defect matching unit, will be in the defective locations and the database on multiple surfaces of the timber to be identified
Timber defective locations on multiple surfaces matched, obtain timber ID set corresponding with the timber to be identified;
Color histogram match unit, when the quantity for judging the timber ID in the timber ID set is not unique, by institute
The color histogram of the color histogram and the timber in the database of stating timber to be identified is matched, with determining and institute
State corresponding final timber ID at present to be identified.
The embodiment of the invention also provides a kind of sawn timber identity identification equipment for merging performance characteristic, including processor, deposit
Reservoir and storage in the memory and are configured the computer program executed by the processing, and the processor executes institute
The sawn timber identity identification method such as above-mentioned fusion performance characteristic is realized when stating computer program.
Based on a kind of sawn timber identity identification method, equipment and device for merging performance characteristic provided by the invention, pass through line
Scanning camera obtains the appearance features of timber to be identified, and the timber ID of each timber and corresponding appearance features are stored in number
According to library, is matched by defective locations on timber image to be identified and color histogram feature, determine timber to be identified
Final ID, the effective solution utilization rate of timber and the problem of system combination deficiency, promote lumber's production line flexibility,
Customize processing.
Detailed description of the invention
Fig. 1 is the sawn timber identity identification method flow diagram for the fusion appearance features that first embodiment of the invention provides;
Fig. 2 is the module diagram for the sawn timber identification device that second embodiment of the invention provides fusion appearance features.
Specific embodiment
To keep the purposes, technical schemes and advantages of embodiment of the present invention clearer, implement below in conjunction with the present invention
The technical solution in embodiment of the present invention is clearly and completely described in attached drawing in mode, it is clear that described reality
The mode of applying is some embodiments of the invention, rather than whole embodiments.Based on the embodiment in the present invention, ability
Domain those of ordinary skill every other embodiment obtained without creative efforts, belongs to the present invention
The range of protection.Therefore, the detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit below and is wanted
The scope of the present invention of protection is sought, but is merely representative of selected embodiment of the invention.Based on the embodiment in the present invention,
Every other embodiment obtained by those of ordinary skill in the art without making creative efforts belongs to this
Invent the range of protection.
It refering to fig. 1, can be by melting the embodiment of the invention discloses a kind of sawn timber identity identification method for merging appearance features
Sawn timber identity identification equipment (hereinafter referred to as sawn timber identity identification equipment) Lai Zhihang of appearance features is closed, and includes:
S101 extracts the appearance features of all timber, and the timber ID of each timber and corresponding appearance features is deposited
Enter database;Wherein, the color histogram and each timber that the appearance features include each timber are on multiple surfaces
Defective locations.
In the present embodiment, the sawn timber identity identification equipment can for computer or have calculation processing power terminal,
Server etc., the present invention is not specifically limited.
In the present embodiment, the sawn timber identity identification equipment can first extract the appearance features of timber by the gross offline first,
Appearance features may include color histogram feature and each wood the lacking on multiple surfaces (usually four surfaces) of each timber
Fall into position.After having extracted appearance features, the timber ID of each timber and corresponding appearance features are stored in database, formed special
Levy library.
S102 obtains the timber image of the timber to be identified transmitted on a moving belt.
Specifically, in the present embodiment, the timber flowed through on line scan camera shooting conveyer belt, the sawn timber body can be used
Part identification apparatus obtains the timber image flowed through from the line scan camera.
Wherein, it is contemplated that the length of timber is often long, thus the image shot to line scan camera is needed to spell
Complete timber image can just be obtained by connecing.Specifically, step S102 can include:
S1021 obtains the transmission image of line scan camera shooting.
Wherein, the 400 row pixels that line scan camera sweeps each line form a small image, alternately splice frame, are
Guarantee that these splicing frames are not interfere with each other, distributes a caching in memory for each frame and save image.
S1022 judges whether there is timber according to the colour brightness of the transmission image, if detecting the front of transmission image
Point not comprising no timber, partially have afterwards comprising timber, then judges that the transmission image for start frame, and is marked;If detecting
The front subpackage for transmitting image contains timber, and rear part does not include timber, then judge the transmission image for end frame, rower of going forward side by side
Note.
S1023 is carried out according to the start frame, end frame and all transmission images between start frame and end frame
Image mosaic, to generate the timber image of timber to be identified.
S103 obtains the appearance features of timber to be identified according to the timber image.
In the present embodiment, after getting timber image, the color histogram feature and wood of the timber image are obtained
The defective locations of material on multiple surfaces.
Wherein, defective locations can be extracted by the following method:
Firstly, four surfaces to each timber in the timber image traverse, and select to lack on each surface
The region that contour area is greater than M pixel value is fallen into, candidate local defect region to be selected is obtained;Then, the candidate part is obtained
The boundary rectangle of defect area, and the Y-coordinate value using the central point of boundary rectangle away from most short end point as timber in respective surfaces
On defective locations.
Wherein, it should be noted that in the present embodiment, M is preferably 4000.But it should be recognized that of the invention
In other embodiments, the numerical value of M can be adjusted according to actual needs, such as value is 3500 or 5000, these schemes exist
Within protection scope of the present invention.In addition it is also necessary to explanation, when choosing defective locations, being also possible to will be external
X-coordinate value of the central point of rectangle away from most short end point is as defective locations of the timber in respective surfaces or other settings
Method, the present invention do not do specific restriction.
The color histogram feature of timber image can be obtained by the following method:
According to the statistical pixel values range A of all timber, the color histogram feature of each timber image is obtained.
Wherein, range A is the gray value of 7-120.Certainly, it should be noted that A can be adjusted according to the actual needs
Range, such as according to different timber kinds come adjustable range A, these schemes are within the scope of the present invention.
S104 exists the timber in the defective locations and the database on multiple surfaces of the timber to be identified
Defective locations on multiple surfaces are matched, and timber ID set corresponding with the timber to be identified is obtained.
Specifically, if when the timber existing defects currently to be retrieved, according to first in four surfaces of the timber acquired in real time
First defective locations on a surface and the defective locations on the surface of timber all in database do and compare one by one, as long as two numbers
The difference of value is within N, and fixing tentatively the two defects in position is that approximation is consistent, this timber image in database is protected
It stays alternately, ergodic data library completes to screen for the first time, obtains the wood surface set for meeting first defective locations
C1。
Then, according to first time the selection result, to second of first surface of current timber image in set C1
Defective locations carry out once comparing screening again, obtain a smaller set D1, and so on, obtain the to be selected of first surface
Same processing is done on face set S1, excess-three surface, will obtain four set { S1, S2, S3, S4 }.
Finally, each of this four set surface all corresponds to a unique timber ID, this four set are counted
Timber ID corresponding to middle occurred surface as obtains the corresponding timber ID of timber to be identified by defect screening and gathers
A。
S105, when the quantity for judging the timber ID in the timber ID set is not unique, by the timber to be identified
The color histogram of color histogram and the timber in the database is matched, with it is determining with it is described to be identified current right
The final timber ID answered.
Specifically, (for example, timber itself is without defect or existing defects position if the timber ID in set A is not unique
Set very similar timber), then illustrate the current timber of the identification that cannot still prepare, needs to do further identification judgement.
At this point it is possible to be done according to the color histogram feature in four faces of the timber to be identified being calculated early period further
Judgement.
Specifically, first with the color histogram feature in first face in the set A all faces of all timber it is straight
Square figure feature carries out similitude detection, that is, calculates all timber in the color histogram feature and the set A in first face
The Euclidean distance of the histogram feature in all faces, and sequence from small to large is carried out to obtained numerical value, X face before retaining obtains
Gather to a face.Same step calculates its excess-three surface, obtains the other three surface set, counts it to each set
In timber ID belonging to each face, obtain the set { W1, W2, W3, W4 } of four timber ID, count this four set later
The middle highest timber ID of frequency of occurrence, this ID are the final ID of timber to be known.
Wherein, the value of the X is set according to the size of database, and the value of X takes 20 here.First implements through the invention
Example can effectively realize same batch sawn timber Combinatorial Optimization, effectively be identified solve timber to same batch sawn timber
The problem of utilization rate and system combination deficiency promotes the flexibility of lumber's production line, customizes processing.
The embodiment of the invention also provides a kind of sawn timber identification devices for merging performance characteristic, comprising:
Appearance features extraction unit 10, for extracting the appearance features of all timber, and by the timber ID of each timber with
And corresponding appearance features are stored in database;Wherein, the appearance features include the color histogram of each timber and each
The defective locations of timber on multiple surfaces;
Timber image acquisition unit 20 obtains the timber image of the timber to be identified transmitted on a moving belt;
Appearance features recognition unit 30 obtains the appearance features of timber to be identified according to the timber image;
Defect matching unit 40, by the defective locations and the database on multiple surfaces of the timber to be identified
In timber defective locations on multiple surfaces matched, obtain timber ID set corresponding with the timber to be identified;
Color histogram match unit 50 will when the quantity for judging the timber ID in the timber ID set is not unique
The color histogram of the timber to be identified and the color histogram of the timber in the database are matched, with determine with
The corresponding final timber ID at present to be identified.
Preferably, the timber image acquisition unit 20 specifically includes:
Image collection module is transmitted, for obtaining the transmission image of line scan camera shooting;
Timber is judged whether there is according to the colour brightness of the transmission image, the preceding part of transmission image is not wrapped if detecting
Containing no timber, partially have afterwards comprising timber, then judges that the transmission image for start frame, and is marked;If detecting transmission figure
The front subpackage of picture contains timber, and rear part does not include timber, then judges that the transmission image for end frame, and is marked;
Image spelling is carried out according to the start frame, end frame and all transmission images between start frame and end frame
It connects, to generate the timber image of timber to be identified.
Preferably, the appearance features recognition unit 30, the transmission image collection module generates to be identified for identification
Appearance features in the timber image of timber, the appearance features include the timber color of image histogram feature of timber to be identified
And the timber image deflects position of timber to be identified.
Preferably, the defect matching unit 40, specifically includes:
Defective locations contrast module: for by the defective locations on multiple surfaces and the number of the timber to be identified
It is compared according to the defective locations of the timber in library on multiple surfaces, it, will be corresponding when the distance of two defective locations is less than N
Timber ID be added in timber ID set corresponding with the timber to be identified.
Preferably, the value for taking N here is 100.
Preferably, color histogram match unit 50, specifically includes:
Timber ID quantity judgment module: for judging whether the timber ID quantity in the timber ID set is unique.
Color histogram characteristic matching module: when the timber ID quantity judgment module judges in the timber ID set
When timber ID quantity is not unique, calculate in color histogram feature and the database in each face of the timber to be identified
The Euclidean distance of the color histogram feature in each face of timber, obtained numerical value is sorted from small to large, X before retaining
It is a, it obtains gathering with the timber ID on each surface;
Timber ID statistical module: the highest timber ID of frequency of occurrence in the timber ID set for counting multiple surfaces, i.e.,
Determine the final ID of the corresponding timber to be retrieved of the timber to be identified.
Preferably, the value of X takes 20 here.
The embodiment of the invention also provides a kind of sawn timber identity identification equipment for merging performance characteristic, including processor, deposit
Reservoir and storage in the memory and are configured the computer program executed by the processing, and the processor executes institute
The sawn timber identity identification method such as above-mentioned fusion performance characteristic is realized when stating computer program.
A kind of sawn timber identity identification method, equipment and device merging performance characteristic provided by the invention, is scanned by line
Camera obtains the appearance features of timber to be identified, and the timber ID of each timber and corresponding appearance features are stored in data
Library is matched by defective locations on timber image to be identified and color histogram feature, determines timber to be identified most
Whole ID, the effective solution utilization rate of timber and the problem of system combination deficiency promote the flexibility, fixed of lumber's production line
Inhibition and generation processing.
The foregoing is only a preferred embodiment of the present invention, but scope of protection of the present invention is not limited thereto,
In the technical scope disclosed by the present invention, any changes or substitutions that can be easily thought of by anyone skilled in the art,
It should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with scope of protection of the claims
Subject to.
Claims (10)
1. a kind of sawn timber identity identification method for merging performance characteristic characterized by comprising
The appearance features of all timber are extracted, and the timber ID of each timber and corresponding appearance features are stored in database;
Wherein, the appearance features include the defective locations of the color histogram and each timber of each timber on multiple surfaces;
Obtain the timber image of the timber to be identified transmitted on a moving belt;
The appearance features of timber to be identified are obtained according to the timber image;
By the timber in the defective locations and the database on multiple surfaces of the timber to be identified on multiple surfaces
On defective locations matched, obtain timber ID set corresponding with the timber to be identified;
When the quantity for judging the timber ID in the timber ID set is not unique, by the color histogram of the timber to be identified
And the color histogram of the timber in the database is matched, with determination and the corresponding final wood at present to be identified
Material ID.
2. the sawn timber identity identification method of fusion appearance features according to claim 1, which is characterized in that
The timber image for obtaining the timber to be identified transmitted on a moving belt, specifically:
Obtain the transmission image of line scan camera shooting;
Timber is judged whether there is according to the colour brightness of the transmission image, the preceding part of transmission image does not include nothing if detecting
Timber partially has afterwards comprising timber, then judges that the transmission image for start frame, and is marked;If detecting transmission image
Front subpackage contains timber, and rear part does not include timber, then judges that the transmission image for end frame, and is marked;
Image mosaic is carried out according to the start frame, end frame and all transmission images between start frame and end frame,
To generate the timber image of timber to be identified.
3. a kind of sawn timber identity identification method for merging performance characteristic according to claim 2, which is characterized in that the line is swept
The scan frequency for retouching camera is consistent with the frequency of delivery of the conveyer belt.
4. a kind of sawn timber identity identification method for merging performance characteristic according to claim 2, which is characterized in that
According to every a line on the colour brightness judgement transmission image on transmission image, whether there is or not wood grains, and then determine in transmission image
With the presence or absence of timber.
5. a kind of sawn timber identity identification method for merging appearance features according to claim 1, which is characterized in that the extraction
The appearance features of all timber, and the timber ID of each timber and corresponding appearance features are stored in database specifically:
The surface of each timber in the timber image is traversed, and defect profile area on each surface is selected to be greater than
The region of M pixel value obtains candidate local defect region to be selected;
Obtain the boundary rectangle in the candidate local defect region, and the Y-coordinate by the central point of boundary rectangle away from most short end point
It is worth the defective locations as timber in respective surfaces;
According to the statistical pixel values range A of all timber, the color histogram feature of each timber image is obtained;
According on each surface defective locations and color histogram feature generate the appearance features of each timber, and will be every
The timber ID of a timber and corresponding appearance features are stored in database.
6. a kind of sawn timber identity identification method for merging performance characteristic according to claim 5, which is characterized in that the M's
Value is 4000, and the A range is 7-120.
7. a kind of sawn timber identity identification method for merging appearance features according to claim 1, which is characterized in that described by institute
State the defect of timber on multiple surfaces in the defective locations and the database on multiple surfaces of timber to be identified
Position is matched, and timber ID set corresponding with the timber to be identified is obtained specifically:
On multiple surfaces by the timber in the defective locations and the database on multiple surfaces of the timber to be identified
Defective locations compare, when the distance of two defective locations be less than N when, corresponding timber ID is added to described wait know
In the corresponding timber ID set of other timber.
8. a kind of sawn timber identity identification method for merging appearance features according to claim 1, which is characterized in that described to sentence
When the quantity of the timber ID to break in timber ID set is not unique, by the color histogram of the timber to be identified and described
The color histogram of timber in database is matched, and with determination, just corresponding final timber ID is specific with the mesh to be identified
Are as follows:
When the quantity for judging the timber ID in the timber ID set is not unique, each face of the timber to be identified is calculated
The Euclidean distance of the color histogram feature in each face of the timber in color histogram feature and the database, by what is obtained
Numerical value is sorted from small to large, X before retaining, obtains gathering with the timber ID on each surface;
The highest timber ID of frequency of occurrence in the timber ID set on multiple surfaces is counted, that is, determines that the timber to be identified is corresponding
The final ID of timber to be retrieved.
9. a kind of sawn timber identification device for merging performance characteristic characterized by comprising
Appearance features extraction unit, for extracting the appearance features of all timber, and by the timber ID and correspondence of each timber
Appearance features be stored in database;Wherein, the appearance features include that the color histogram of each timber and each timber exist
Defective locations on multiple surfaces;
Timber image acquisition unit obtains the timber image of the timber to be identified transmitted on a moving belt;
Appearance features recognition unit obtains the appearance features of timber to be identified according to the timber image;
Defect matching unit, by the wood in the defective locations and the database on multiple surfaces of the timber to be identified
The defective locations of material on multiple surfaces are matched, and timber ID set corresponding with the timber to be identified is obtained;
Color histogram match unit, when the quantity for judging the timber ID in timber ID set is not unique, will it is described to
The color histogram and the color histogram of the timber in the database for identifying timber are matched, with it is determining with it is described to
Identify corresponding final timber ID at present.
10. a kind of sawn timber identity identification equipment for merging performance characteristic, which is characterized in that including processor, memory and deposit
It stores up in the memory and is configured the computer program executed by the processing, the processor executes the computer journey
The sawn timber identity identification method of the fusion performance characteristic as described in claim 1 to 8 any one is realized when sequence.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811307821.4A CN109544514B (en) | 2018-11-05 | 2018-11-05 | Sawn timber identity identification method, device and equipment integrating apparent features |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811307821.4A CN109544514B (en) | 2018-11-05 | 2018-11-05 | Sawn timber identity identification method, device and equipment integrating apparent features |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109544514A true CN109544514A (en) | 2019-03-29 |
CN109544514B CN109544514B (en) | 2020-07-24 |
Family
ID=65846550
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811307821.4A Active CN109544514B (en) | 2018-11-05 | 2018-11-05 | Sawn timber identity identification method, device and equipment integrating apparent features |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109544514B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110782423A (en) * | 2019-10-29 | 2020-02-11 | 华侨大学 | Automatic splicing and matting method for solid wood sawn timber line scanning camera images |
CN112129773A (en) * | 2020-08-20 | 2020-12-25 | 湖南大学 | Wood surface defect detection method, device, equipment, system and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040186218A1 (en) * | 2003-03-18 | 2004-09-23 | Borden Chemical, Inc. | Novel tunable hybrid adhesive system for wood bonding applications |
CN102663098A (en) * | 2012-04-13 | 2012-09-12 | 保定天威英利新能源有限公司 | Method and system for processing defective photovoltaic modules |
CN106738736A (en) * | 2016-11-29 | 2017-05-31 | 延锋彼欧仪征汽车外饰系统有限公司 | Bumper manufactures modification method of tracing to the source |
CN108346153A (en) * | 2018-03-22 | 2018-07-31 | 北京木业邦科技有限公司 | The machine learning of defects in timber and restorative procedure, device, system, electronic equipment |
-
2018
- 2018-11-05 CN CN201811307821.4A patent/CN109544514B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040186218A1 (en) * | 2003-03-18 | 2004-09-23 | Borden Chemical, Inc. | Novel tunable hybrid adhesive system for wood bonding applications |
CN102663098A (en) * | 2012-04-13 | 2012-09-12 | 保定天威英利新能源有限公司 | Method and system for processing defective photovoltaic modules |
CN106738736A (en) * | 2016-11-29 | 2017-05-31 | 延锋彼欧仪征汽车外饰系统有限公司 | Bumper manufactures modification method of tracing to the source |
CN108346153A (en) * | 2018-03-22 | 2018-07-31 | 北京木业邦科技有限公司 | The machine learning of defects in timber and restorative procedure, device, system, electronic equipment |
Non-Patent Citations (2)
Title |
---|
李旭伟等: "坤甸木在潮州广济桥修复工程中的应用", 《建筑监督检测与造价》 * |
王再超等: "基于应力波和支持向量机的木材缺陷识别分类方法", 《 南京林业大学学报(自然科学版)》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110782423A (en) * | 2019-10-29 | 2020-02-11 | 华侨大学 | Automatic splicing and matting method for solid wood sawn timber line scanning camera images |
CN110782423B (en) * | 2019-10-29 | 2023-03-24 | 华侨大学 | Automatic splicing and matting method for solid wood sawn timber line scan camera images |
CN112129773A (en) * | 2020-08-20 | 2020-12-25 | 湖南大学 | Wood surface defect detection method, device, equipment, system and storage medium |
CN112129773B (en) * | 2020-08-20 | 2022-06-14 | 湖南大学 | Wood surface defect detection method, device, equipment, system and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN109544514B (en) | 2020-07-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110766679B (en) | Lens contamination detection method and device and terminal equipment | |
CN107256406B (en) | Method and device for segmenting overlapped fiber image, storage medium and computer equipment | |
CN102175700B (en) | Method for detecting welding seam segmentation and defects of digital X-ray images | |
US9147014B2 (en) | System and method for image selection of bundled objects | |
CN110909640A (en) | Method and device for determining water level line, storage medium and electronic device | |
CN108038838A (en) | A kind of cotton fibriia species automatic testing method and system | |
CN109714832B (en) | Network cutting control device | |
CN109544514A (en) | A kind of sawn timber identity identification method, device and equipment merging performance characteristic | |
CN110007493A (en) | Broken bright spot detection method in liquid crystal display | |
CN112200790B (en) | Cloth defect detection method, device and medium | |
CN108229232A (en) | The method of batch scanning Quick Response Code and the device of batch scanning Quick Response Code | |
CN109636793A (en) | The detection system and its detection method of display | |
CN115876823A (en) | Film defect detection method, film defect detection device and film defect detection system | |
CN116309518A (en) | PCB (printed circuit board) detection method and system based on computer vision | |
CN110119675A (en) | A kind of product identification method and apparatus | |
CN106204889B (en) | A kind of localization method and device of bank note fluorescence area | |
CN107403429B (en) | Method for quickly and automatically acquiring parameters of periodic sequence image model | |
CN109009216A (en) | A kind of ultrasonic image naked eye 3D system | |
CN115619725A (en) | Electronic component detection method and device, electronic equipment and automatic quality inspection equipment | |
CN104392436B (en) | A kind of remote sensing image processing method and device | |
CN111928944B (en) | Laser ray detection method, device and system | |
CN112215896B (en) | Multi-camera calibrated camera frame data processing method and device and computer equipment | |
CN107389677B (en) | Method and device for detecting quality of flannelette fluff | |
CN106529518B (en) | A kind of method and device of answering card identification | |
CN111192253A (en) | Definition checking method and system based on contrast sensitivity and contrast |
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 | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20200421 Address after: 361021 No. 668, Jimei Avenue, Jimei District, Fujian, Xiamen Applicant after: HUAQIAO University Applicant after: Xiamen jixinde Group Co., Ltd Address before: 361000 No. 668, Jimei Avenue, Jimei District, Fujian, Xiamen Applicant before: HUAQIAO University |
|
TA01 | Transfer of patent application right | ||
GR01 | Patent grant | ||
GR01 | Patent grant |