CN108375353A - A kind of log detection method, apparatus and equipment - Google Patents
A kind of log detection method, apparatus and equipment Download PDFInfo
- Publication number
- CN108375353A CN108375353A CN201711335528.4A CN201711335528A CN108375353A CN 108375353 A CN108375353 A CN 108375353A CN 201711335528 A CN201711335528 A CN 201711335528A CN 108375353 A CN108375353 A CN 108375353A
- Authority
- CN
- China
- Prior art keywords
- polishing
- timber
- image data
- strategy
- testing result
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 83
- 238000005498 polishing Methods 0.000 claims abstract description 289
- 238000000034 method Methods 0.000 claims abstract description 48
- 238000012360 testing method Methods 0.000 claims abstract description 45
- 239000000463 material Substances 0.000 claims description 35
- 238000012545 processing Methods 0.000 claims description 26
- 238000004422 calculation algorithm Methods 0.000 claims description 25
- 238000010801 machine learning Methods 0.000 claims description 16
- 238000003384 imaging method Methods 0.000 claims description 15
- 239000002023 wood Substances 0.000 claims description 13
- 238000012549 training Methods 0.000 claims description 12
- 238000007689 inspection Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 10
- 244000137852 Petrea volubilis Species 0.000 description 7
- 238000004590 computer program Methods 0.000 description 7
- 238000003860 storage Methods 0.000 description 7
- 238000013528 artificial neural network Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000013527 convolutional neural network Methods 0.000 description 4
- 238000012706 support-vector machine Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 230000001965 increasing effect Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000005520 cutting process Methods 0.000 description 2
- 239000000428 dust Substances 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000007517 polishing process Methods 0.000 description 2
- 241000894007 species Species 0.000 description 2
- 244000050510 Cunninghamia lanceolata Species 0.000 description 1
- 235000008331 Pinus X rigitaeda Nutrition 0.000 description 1
- 241000018646 Pinus brutia Species 0.000 description 1
- 235000011613 Pinus brutia Nutrition 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 239000011248 coating agent Substances 0.000 description 1
- 238000000576 coating method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000003306 harvesting Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000002427 irreversible effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000011148 porous material Substances 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/30—Measuring arrangements characterised by the use of optical techniques for measuring roughness or irregularity of surfaces
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B24—GRINDING; POLISHING
- B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
- B24B19/00—Single-purpose machines or devices for particular grinding operations not covered by any other main group
- B24B19/22—Single-purpose machines or devices for particular grinding operations not covered by any other main group characterised by a special design with respect to properties of the material of non-metallic articles to be ground
- B24B19/24—Single-purpose machines or devices for particular grinding operations not covered by any other main group characterised by a special design with respect to properties of the material of non-metallic articles to be ground of wood, e.g. furniture
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B24—GRINDING; POLISHING
- B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
- B24B49/00—Measuring or gauging equipment for controlling the feed movement of the grinding tool or work; Arrangements of indicating or measuring equipment, e.g. for indicating the start of the grinding operation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/08—Measuring arrangements characterised by the use of optical techniques for measuring diameters
- G01B11/12—Measuring arrangements characterised by the use of optical techniques for measuring diameters internal diameters
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
- G01J3/46—Measurement of colour; Colour measuring devices, e.g. colorimeters
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N3/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N3/40—Investigating hardness or rebound hardness
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2203/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N2203/0058—Kind of property studied
- G01N2203/0076—Hardness, compressibility or resistance to crushing
Abstract
A kind of log detection method, apparatus of present invention offer and equipment, the method includes：According to the tactful automatically grinding timber of polishing；Acquire the image data after the timber polishing；Show that the testing result of the timber, the testing result are obtained based on the image data after the polishing.The log detection process that the present invention automates, both saves manpower, is convenient for the use of commonly used person, while can realize that the real-time, type to timber fast and automatically is detected.
Description
Technical field
The present invention relates to wood processing technique fields, more particularly, to a kind of log detection method, apparatus and equipment.
Background technology
As China's imported timber quantity gradually increases, the timber kind of import is increasing, is related to pine, China fir, red
The different cultivars such as wood.The material and price of variety classes timber have differences, therefore are detected to the type of timber real in turn
Now classification is the generally operation in lumber-trade field.Some businessmans must declare at customs port simultaneously can have unreal problem, example
Such as timber in imminent danger other timber that disguise oneself as of forbidding cutting down of some unauthorized thefts are smuggled.Therefore, it is necessary to reliably, rapidly
Timber kind is detected and then is realized and differentiates or classifies.
Way traditional at present is to carry out polishing sampling to timber, is analyzed the sample after polishing using microscope.
If polishing is in place, the type of timber can be analyzed according to timber aperture information under microscopical observation.If polishing less than
Position, then be unable to get the clear image in timber aperture, the type of timber can not be accurately identified in the detection in later stage.Conventional method
It is not only time-consuming and laborious, but also testing result cannot be obtained in real time.
Therefore, it is necessary to a kind of method or equipment can in real time, the type to timber fast and automatically is detected.
Invention content
A kind of log detection method, apparatus of offer of the embodiment of the present invention and equipment, to provide customs inspection, consumer checks
Etc. the detection of timber kind in real time, fast and automatically is provided under scenes.
To solve the above-mentioned problems, a kind of log detection method, apparatus of present invention offer and equipment, the method includes：
According to the tactful automatically grinding timber of polishing；
Acquire the image data after the timber polishing；
Show that the testing result of the timber, the testing result are obtained based on the image data after the polishing.
Optionally, the polishing strategy includes one in polishing time, the polishing component of at least one precision, polishing track
A or multiple, the polishing component includes polishing consumptive material and its parameter.
Optionally, the polishing strategy includes the polishing strategy of acquiescence.
Optionally, before the strategy polishing timber according to polishing, further include：Acquire the raw image data of timber；
The polishing strategy is obtained based on the raw image data.
Optionally, the polishing strategy includes and the associated polishing strategy of polishing characteristic parameter, the polishing characteristic parameter
It is obtained based on image processing techniques and the raw image data.
Optionally, the polishing characteristic parameter includes：One or more of roughness, flatness, hardness and color.
Optionally, the testing result is obtained based on shown detection characteristic parameter, and the detection characteristic parameter is based on
What the image data after image processing techniques and the polishing obtained.
Optionally, the detection characteristic parameter includes：The one or more of aperture information, texture information.
Optionally, the testing result is obtained the image data after the polishing as the input of machine learning algorithm
, the machine learning algorithm is the model of the image data training after the polishing largely marked.
Optionally, the polishing strategy is according to the updated polishing strategy of the testing result.
Optionally, the method further includes：Display alarm information, the prompting message include：Polishing consumptive material uses the longevity
Life is reminded.
Optionally, the method further includes：Caution signal is exported when the timber is illegal timber.
To solve the above-mentioned problems, the present invention provides a kind of wood detection equipment, and described device includes：
Polishing module, for according to timber described in the tactful automatically grinding of polishing；
Image data acquiring module, for acquiring the image data after the timber is polished；
Display module, the testing result for showing the timber, the testing result are based on the figure after the polishing
As data obtain.
Optionally, the polishing strategy includes one in polishing time, the polishing component of at least one precision, polishing track
A or multiple, the polishing component includes polishing consumptive material and its parameter.
Optionally, the polishing strategy includes the polishing strategy of acquiescence.
Optionally, described image acquisition module is additionally operable to the raw image data of acquisition timber；The polishing strategy is base
It is obtained in the raw image data.
Optionally, the polishing strategy includes and the associated polishing strategy of polishing characteristic parameter, the polishing characteristic parameter
It is obtained based on image processing techniques and the raw image data.
Optionally, the polishing characteristic parameter includes：One or more of roughness, flatness, hardness and color.
Optionally, the testing result is obtained based on shown detection characteristic parameter, and the detection characteristic parameter is based on
What the image data after image processing techniques and the polishing obtained.
Optionally, the detection characteristic parameter includes：The one or more of aperture information, texture information.
Optionally, the testing result is obtained the image data after the polishing as the input of machine learning algorithm
, the machine learning algorithm is the model of the image data training after the polishing largely marked.
Optionally, the polishing strategy is according to the updated polishing strategy of the testing result.
Optionally, the display module is additionally operable to display alarm information, and the prompting message includes：The use of polishing consumptive material
Service life reminds.
Optionally, described device further includes alert module, for exporting caution signal when the timber is illegal timber.
To solve the above-mentioned problems, the present invention provides a kind of hand-held log detection equipment, and the equipment includes：Image sensing
Device, polishing module, display module, handle arrangement, memory and one or more processors；Wherein, described image sensor, beat
Mill module, display module are connect with the memory and one or more of processor communications, are stored in the memory
The instruction that can be executed by one or more of processors, described instruction are executed by one or more of processors, so that institute
Method described in any one of the above embodiments can be realized by stating one or more processors.
In the present embodiment, the hand-held log detection equipment of integrated polishing module does further timber according to polishing strategy
Polishing obtains the image data after timber polishing after polishing, and the detection of timber is determined according to the image data after polishing
As a result.The log detection process of automation, both saves manpower, is convenient for the use of commonly used person, while can realize real-time, fast
Speed is automatically detected the type of timber.
Description of the drawings
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention
Fig. 1 is a kind of log detection method flow diagram according to an embodiment of the present invention；
Fig. 2 is the exterior view of a wood sample to be detected；
Fig. 3 is a kind of wood detection equipment structure chart according to an embodiment of the present invention；
Fig. 4 is the hand-held log detection equipment schematic diagram according to an embodiment of the present invention.
Specific implementation mode
In order to make the invention's purpose, features and advantages of the invention more obvious and easy to understand, below in conjunction with the present invention
Attached drawing in embodiment, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described reality
It is only a part of the embodiment of the present invention to apply mode, and not all embodiments.Based on the embodiments of the present invention, art technology
The every other embodiment that personnel are obtained without making creative work, shall fall within the protection scope of the present invention.
It is set it will be understood by those skilled in the art that the terms such as " first ", " second " in the present invention are only used for difference difference
Standby, module or parameter etc. neither represent any particular technology meaning, also do not indicate that the inevitable logical order between them.
As shown in Figure 1, a kind of log detection method flow diagram of an embodiment of the present invention, is applied to hand-held log detection
Equipment, the equipment include imaging sensor, polishing module, handle arrangement and display module.The handle arrangement is used to support
Modular structure, while convenient for the operation of user.Specifically, this method includes：
Step S11, according to timber described in the tactful automatically grinding of polishing.
Wood surface to be detected is mostly without polishing in actual scene, the raw image data directly to timber acquisition
Often barely satisfactory, Limited information is not enough to therefrom judge the type of timber.In addition, some retailers, which have, is intended to wood surface
Apply certain cover-ups, such as coating, and then influences testing result.Fig. 2 is the exterior view of a wood sample to be detected.
Wherein, Fig. 2 (a) is image of the sample without polishing, can be seen that end face is fuzzy from image, aperture is blocked, and is unable to get
Effective aperture information or other can judge the information of type；Fig. 2 (b) is image of the sample after polishing, from image
It can be seen that end face is clear, aperture is apparent, can obtain effective aperture information, and then the kind of timber is detected based on aperture information
Class.And each timber is because of self-characteristic, the polishing process being applicable in is not fully identical, while being detected in actual scene
Personnel also are intended to use quick polishing process.Therefore, the polishing module for holding log detection equipment is tactful to wood according to polishing
Material is polished.Here polishing module is driven polishing consumptive material to do the mechanical movement of high speed, and then right by the electric drive of power supply
Timber is polished, and the present invention not grind, justify the forms such as mill, belt sander by the side of limitation.
The polishing component of different accuracy may be this hair because polishing consumptive material difference and/or the parameter of polishing consumptive material are different
It is bright not to be restricted.The execution of polishing strategy namely starts used in order and each polishing surface on different polishing surfaces
Time.Polishing track can be predefined track or track input by user etc..In one embodiment, polishing component
Endless all standing holds the bottom surface of grinding apparatus, and to realize the polishing of all standing, predefined polishing track includes in Fig. 4 (b)
Arrow direction.In addition to this, polishing track can also include the track vertical with previous direction；If the polishing component is round
Cylindricality, polishing track can also include rotation.May include one or more polishing stages in one polishing strategy, it is each to polish
Polishing time, polishing consumptive material and parameter selected by stage can be entirely different, can also be partly different, and the present invention does not limit
System.In one embodiment, polishing module is installed on the front of imaging sensor, and when not actuated polishing module allows timber
Image is acquired in image sensing sensor.Hand-held log detection equipment can also include scrap-removing apparatus, utilize jet or air-breathing
Mode removal polishing generates in bruting process or after the completion of polishing sawdust or dust, and then reduce sawdust or dust for
The influence of subsequent detection result.
Step S12 acquires the image data after the timber polishing.
By the image data of imaging sensor acquisition timber after the completion of polishing, the image data after being polished, this
Image data includes more abundant characteristic information compared with the raw image data of timber.Imaging sensor includes：Infrared light figure
As one or more in sensor, visible light image sensor or radioscopic image sensor.In view of detection method is for figure
As the demand of fineness, enlarging lens can also be increased before imaging sensor, to realize amplification or micro-imaging.Before enlarging lens
The components such as holder can also be increased, sample surfaces are located at the focuses of enlarging lens when detecting to realize.Hand-held log detection is set
It can also increase light source in standby, make up the problem of luminance shortage in actual scene and image quality difference.Here the image after polishing
Data can be by the pretreated image of image processing module, and pretreatment processing includes denoising, segmentation, binaryzation, coding
Compression, enhancing recovery etc..Image processing module can be integrated in imaging sensor, or be integrated in a server, the clothes
It is engaged in carrying out data exchange by wired or wireless mode between device and imaging sensor, the present invention is not restricted.
Step S13 shows that the testing result of the timber, the testing result are based on the image data after the polishing
It obtains.
Detection module can obtain the testing result of timber based on the image data after polishing, and display module shows this
As a result it is presented to the user.If detection module cannot obtain the testing result of timber based on the image data after polishing, will return
Step S11 continues to polish, and so cycle is until obtain the testing result of timber.Detection module can be integrated in hand-held timber
In detection device, either it is integrated between independent server and hand-held log detection equipment through wired or wireless parties
Formula carries out data exchange, and the present invention is not restricted.
In the present embodiment, the hand-held log detection equipment of integrated polishing module does further timber according to polishing strategy
Polishing obtains the image data after timber polishing after polishing, and the detection of timber is determined according to the image data after polishing
As a result.The log detection process of automation, both saves manpower, is convenient for the use of commonly used person, while can realize real-time, fast
Speed is automatically detected the type of timber.
In one embodiment, the polishing strategy includes the polishing strategy of acquiescence.It is special in view of the material of certain timber
Sign, the polishing strategy of acquiescence can select bastard file.For batch log detection, the polishing strategy of the acquiescence can be with
Be before detection, set by the user with certain polishing experience, and detection process kind or after any time period
The polishing strategy of the acquiescence can be changed.Further, the polishing strategy of the acquiescence includes rough polish strategy.Timber is beaten
Mill is usually to take by slightly getting to the mode carefully beaten, therefore the polishing strategy given tacit consent to may be configured as rough polish strategy, if beaten
Wear away material be sand paper, then rough polish strategy be polishing mesh number at least and polishing time shortest strategy.Assembly 100 can be used
The grinding apparatus of mesh, 300 mesh or 500 mesh sand paper slightly breaks timber, then reuses 1000 mesh of assembly, 2000 mesh, 3000
The grinding apparatus of mesh or 5000 mesh sand paper carries out timber.In specific implementation process, by slightly get to the process carefully beaten be by
Several sand paper follow the ascending various combination of mesh number, and a combination thereof mode is by strategy decision of polishing accordingly.
In one embodiment, before the strategy polishing timber according to polishing, further include：
Step S10 acquires the raw image data of timber.
The raw image data that timber is acquired using imaging sensor determines polishing plan based on the raw image data
Slightly.Realize the polishing strategy selection of this step is polishing policy module, it can be integrated in hand-held log detection equipment, also may be used
To be located at same server with detection module, or an independent server can be located at, which examines with hand-held timber
Data exchange is carried out by wired or wireless mode between measurement equipment, the present invention is not restricted.
In one embodiment, the polishing strategy is using the raw image data as the defeated of machine learning algorithm
Enter, the machine learning algorithm is the model by the raw image data training largely marked.Utilize timber image
Have regularity and machine learning algorithm excellent performance, polishing strategy selection before can advance training pattern, training
Sample is the raw image data by manually marking, and this model is deployed in polishing policy module.Here engineering
Practising algorithm includes：Neural network (Neural Networks, be abbreviated as NN), convolutional neural networks (CNN), deep neural network
(DNN), one kind or several in decision forest, nearest neighbor algorithm (KNN), hard clustering algorithm (K-means) or support vector machines (SVM)
Kind combination.
In one embodiment, the polishing strategy includes tactful with the associated polishing of polishing characteristic parameter, described to beat
Mill characteristic parameter is obtained based on image processing techniques and the raw image data.The polishing characteristic parameter includes：Slightly
Rugosity, flatness, hardness, the one or more of color.Ripe timber workers processing has the polishing of timber a large amount of
Experience accumulation can quickly determine appropriate polishing strategy.Therefore, can be based on practical experience establish polishing characteristic parameter with
The associated polishing policy database of polishing strategy.After image data after being polished can root image processing techniques obtain timber
Polishing characteristic parameter, finally obtain tactful with the associated polishing of polishing characteristic parameter.If a certain polishing being calculated is special
Sign parameter is not present in polishing policy database, selects the polishing strategy of acquiescence at this time.
Further, the polishing strategy is according to the updated polishing strategy of the testing result.If polishing strategy
What module was chosen is acquiescence polishing strategy, by this polishing strategy, finally successfully obtains the testing result of timber, can be with
The relevance of polishing characteristic parameter and this polishing strategy before timber is polished is stored in polishing policy data, in order under
The quick polishing and detection of secondary similar timber.If what polishing policy module was chosen is acquiescence polishing strategy, pass through this polishing
Strategy finally successfully obtains the testing result of timber, by the parameter of the polishing consumptive material of this polishing strategy or can beat
Fine tuning, the number of fine tuning are not intended to limit downwards for time consuming.The purpose of fine tuning is to shorten polishing while ensureing testing result
It takes and consumes, give the better use feeling of user.If the polishing characteristic parameter handled raw image data is F3,
There is no an associated polishing strategy S3 of F3 in polishing policy database, policy module priority of polishing has chosen different twice associated
Polish strategy S1 (F1), S2 (F2), and wherein F is the corresponding polishing characteristic parameter of polishing strategy, finally successfully obtains timber
Testing result, can by this, strategy S1, S2 does certain merging treatment twice, obtain new associated polishing strategy S3.Such as
When fruit appearance polishing characteristic parameter is the similar timber of F3, associated polishing strategy S3 is directly chosen.If in a kind of embodiment party
Consumptive material of polishing in formula is sand paper, and M1 indicates that polishing strategy S1 uses the mesh number set of sand paper, M2 to indicate that polishing strategy S2 uses sand
The set of the mesh number of paper, M3 indicate that polishing strategy S3 using the set of the mesh number of sand paper, then has such relation of equal quantity：M3=
M1∪M2.T1 indicates the set of time used in polishing strategy S1 different meshes；T2 indicates polishing strategy S2 different meshes institute's used times
Between set；T3 indicates the set pair of time used in polishing strategy S3 different meshes, to arbitrary t1, t2, the t3 of identical mesh number,
, then there is such relation of equal quantity in middle t1 ∈ T1, t2 ∈ T2, t3 ∈ T3：T3=t1+t2.
In one embodiment, the testing result is using the image data after the polishing as machine learning algorithm
Input obtain, the machine learning algorithm be after the polishing largely marked image data training model.Utilize wood
Material image have regularity and machine learning algorithm excellent performance, before detection can advance training pattern, training sample
For the image data after the polishing after the polishing manually marked, and this model is deployed in detection module.Here machine
Device learning algorithm includes：Neural network (Neural Networks, be abbreviated as NN), convolutional neural networks (CNN), depth nerve
One kind in network (DNN), decision forest, nearest neighbor algorithm (KNN), hard clustering algorithm (K-means) or support vector machines (SVM)
Or several combinations.
In one embodiment, the testing result is the specific packet obtained based on the image data after the polishing
It includes：The testing result is obtained based on shown detection characteristic parameter, and the detection characteristic parameter is based on image processing techniques
It is obtained with the image data after the polishing.Detection module is obtained by image processing techniques from the image data after polishing
Characteristic parameter is detected, then testing result is determined based on detection characteristic parameter.The detection characteristic parameter includes：Aperture information, line
Manage the one or more of information.Aperture information includes pore size and porosity.The same grain of wood is as axis in timber body
To the form of expression of molecule (such as wood-fibred, tracheid, conduit) orientation, there is certain characteristic, can be used for the inspection of type
It surveys.Even certain detection characteristic parameters have uniqueness, and the type of timber can be directly judged when detecting this feature.
In one embodiment, the method further includes：Caution signal is exported when the timber is illegal timber.It is logical
Said in popular meaning, the timber for originating from sustainable forest is referred to as green timber, it means that consumption and the use of these timber is pair
Environmental benefits.And illegal timber or illegal timber are on the contrary, it represents irreversible forest deterioration, or even meeting
Lead to even more serious political crisis and group's violence.Legal timber should have following important document：First, fell the main body of timber
Legal, i.e., whether the producer has the right and this felling behavior is engaged in license, such as national self-employed tree cultivator authorities issue Lin Zhuzi
Cross-examination.Second, the right for carrying out this behavior should be had by implementing the movable staff of the related forest such as forest harvesting or felling,
Such as cutting license book, the forest practitioner's certificate that National Forest department issues.Third fells means or the side of timber
Method should meet in forest law about the regulation to fell trees.4th, following process, transport or outlet of the timber after felling
Etc. links should abide by concerned countries make laws and participate in international treaties.5th, the timber felled is not included in state guarantee
Within the scope of species or wild protection species in imminent danger.In log detection, in contrast detect the exact type difficulty bigger of timber,
Algorithm more complicated requirement higher for hardware device can be inclined in practical application and transfer to the server in high in the clouds to do the process
Processing, required time are relatively also just longer.If can quickly be screened to illegal timber, especially legal timber important document
In the 4th, the 5th point, when detecting illegal timber export caution signal will greatly improve detection efficiency.Here it is possible to
Prestore the image data or image feature data of illegal timber, is conducive to the polishing that image processing techniques acquires imaging sensor
Image afterwards is handled, and judges whether timber to be detected is illegal timber, such as protection timber or the timber of embargo.This
The identification of the illegal timber of step can be completed by detection module, can also be independent processor completion, such as graphics process
Device (GPU), it might even be possible to be that the server connected between hand-held log detection equipment is completed.In contrast, illegal timber
Recognizer is easier to, the requirement for hardware device is not especially high, in order to provide recognition result faster, this step 1
As be to be completed by hand-held log detection equipment.Also, in order to pursue faster detection speed, when imaging sensor collects polishing
In image data afterwards, hand-held detection device can transmit the data to cloud server, and the detection of timber kind is completed by it,
The detection of illegal timber itself is completed simultaneously.If detect illegal timber, caution signal is exported, caution signal can be single
Only display module, acousto-optic module, the display module that can also be integrated in hand-held detection device, i.e. one in display module
Point, the present invention does not limit.
In one embodiment, the method further includes：Display alarm information, the prompting message include：Polishing consumption
The service life of material is reminded.In bruting process, for polishing consumptive material because abrasion needs irregularly to be replaced, polishing consumptive material uses note
The time for the polishing that each polishing consumptive material uses in record module record polishing strategy simultaneously carries out cumulative calculation, and polishing consumptive material uses note
Record module is by the time duration for wearing away material and beats service life duration and is compared.When polishing consumptive material is accumulative close to the time limit using duration
When, it prompts to replace.In another embodiment, polishing consumptive material usage record module is subtracted with the service life duration of each polishing consumptive material
The time duration spent is gone, in obtained Difference Storage to time storage device.Before automatically grinding next time, polishing
When consumptive material usage record module uses the duration in strategy of polishing and polishing consumptive material in corresponding time storage device remaining
Length is compared.If the duration in time storage device is less than the duration in polishing strategy, pass through display module presentation user
Prompt, such as " the polishing consumptive material cannot disposably complete the polishing task, and intermediate demand replaces polishing consumptive material ".Display module is also
It can show that the failure of hand-held log detection equipment is reminded.Fault detection module can timely find hand-held log detection equipment
Failure, and failure is informed by user by display module in time.In general fault detection module is integrated in hand-held timber inspection
Measurement equipment, naturally it is also possible to be integrated in a server being connect with hand-held log detection equipment.
As shown in figure 3, the present invention provides a kind of wood detection equipment, it is applied to hand-held log detection equipment, the equipment
Including imaging sensor, polishing module, handle arrangement and display module.The handle arrangement is used to support modular structure, simultaneously
Convenient for the operation of user.Specifically, described device includes：
Polishing module 31, for according to timber described in the tactful automatically grinding of polishing；
Image data acquiring module 32, for acquiring the image data after the timber is polished；
Display module 33, the testing result for showing the timber, the testing result are based on after the polishing
What image data obtained.
Optionally, the polishing strategy includes one in polishing time, the polishing component of at least one precision, polishing track
A or multiple, the polishing component includes polishing consumptive material and its parameter.
Optionally, the polishing strategy includes the polishing strategy of acquiescence.
Optionally, described image acquisition module is additionally operable to the raw image data of acquisition timber；The polishing strategy is base
It is obtained in the raw image data.
Optionally, the polishing strategy includes and the associated polishing strategy of polishing characteristic parameter, the polishing characteristic parameter
It is obtained based on image processing techniques and the raw image data.
Optionally, the polishing characteristic parameter includes：Roughness, flatness, hardness, the one or more of color.
Optionally, the testing result is obtained based on shown detection characteristic parameter, and the detection characteristic parameter is based on
What the image data after image processing techniques and the polishing obtained.
Optionally, the detection characteristic parameter includes：The one or more of aperture information, texture information.
Optionally, the testing result is obtained the image data after the polishing as the input of machine learning algorithm
, the machine learning algorithm is the model of the image data training after the polishing largely marked.
Optionally, the polishing strategy is according to the updated polishing strategy of the testing result.
Optionally, the display module is additionally operable to display alarm information, and the prompting message includes：The use of polishing consumptive material
Service life reminds.
Optionally, described device further includes alert module, for exporting caution signal when the timber is illegal timber.
It is the hand-held log detection equipment schematic diagram of one embodiment of the present invention, wherein Fig. 4 (a) is hand-held with reference to figure 4
The bottom surface upward view of log detection equipment, Fig. 4 (b) are the front views of hand-held log detection equipment.As shown in figure 4, the equipment packet
It includes：
One or more processors 41, imaging sensor 42, memory 43, polishing module 44, display module 46, handle knot
Structure 47.In not actuated polishing module, imaging sensor can acquire the timber for being positioned over hand-held log detection equipment bottom surface
Image data.
Wherein, described image sensor 42, polishing module 44, display module 46 and the memory 43 and it is one or
Multiple processors 41 communicate to connect, and the instruction that can be executed by one or more of processors is stored in the memory 43,
Described instruction is executed by one or more of processors 41, so that one or more of processors 41 execute：
According to the tactful automatically grinding timber of polishing；
Acquire the image data after the timber polishing；
Show that the testing result of the timber, the testing result are obtained based on the image data after the polishing.
Optionally, the polishing strategy includes one in polishing time, the polishing component of at least one precision, polishing track
A or multiple, the polishing component includes polishing consumptive material and its parameter.
Optionally, the polishing strategy includes the polishing strategy of acquiescence.
Optionally, before the strategy polishing timber according to polishing, further include：Acquire the raw image data of timber；
The polishing strategy is obtained based on the raw image data.
Optionally, the polishing strategy includes and the associated polishing strategy of polishing characteristic parameter, the polishing characteristic parameter
It is obtained based on image processing techniques and the raw image data.
Optionally, the polishing characteristic parameter includes：Roughness, flatness, hardness, the one or more of color.
Optionally, the testing result is obtained based on shown detection characteristic parameter, and the detection characteristic parameter is based on
What the image data after image processing techniques and the polishing obtained.
Optionally, the detection characteristic parameter includes：The one or more of aperture information, texture information.
Optionally, the testing result is obtained the image data after the polishing as the input of machine learning algorithm
, the machine learning algorithm is the model of the image data training after the polishing largely marked.
Optionally, the polishing strategy is according to the updated polishing strategy of the testing result.
Optionally, the method further includes：Display alarm information, the prompting message include：Polishing consumptive material uses the longevity
Life is reminded.
Optionally, the method further includes：Caution signal is exported when the timber is illegal timber.
In one embodiment, polishing module 44 includes the polishing component of multiple precision, the first precision polishing component
441, the second precision polishing component 442, third precision polishing component 443, the polishing component of different accuracy may be because of polishing
Consumptive material difference and/or the parameter of polishing consumptive material are different, and the present invention is not restricted.When not actuated polish member storage in equipment simultaneously
And do not touch the bottom surface of equipment；Start specific polishing component by modes such as flexible, pop-ups according to polishing strategy, and makes the component
Touch the bottom surface of equipment.The equipment includes at least one motor.Since polishing 44 endless all standing of component holds grinding apparatus
Bottom surface, to realize that the polishing of all standing, polishing track include arrow direction in Fig. 4 (b), which is the first track, by
First motor 451 drives.In addition to this, polishing track can also include driving the second track by the second motor 452, and the second track can
To be the track vertical with the first track；If the polishing component is cylindrical, the second track can also be rotation.
It should be understood by those skilled in the art that, the embodiment of the present invention can be provided as method, system or computer program
Product.Therefore, the shape of hardware embodiment, software implementation or embodiment combining software and hardware aspects can be used in the present invention
Formula.Moreover, the present invention can be used can use storage in the computer that one or more wherein includes computer usable program code
The form for the computer program product implemented on medium (including but not limited to magnetic disk storage and optical memory etc.).
The present invention be with reference to according to the method for the embodiment of the present invention, the flow of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that can be realized by computer program instructions every first-class in flowchart and/or the block diagram
The combination of flow and/or box in journey and/or box and flowchart and/or the block diagram.These computer programs can be provided
Instruct the processor of all-purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine so that the instruction executed by computer or the processor of other programmable data processing devices is generated for real
The device for the function of being specified in present one flow of flow chart or one box of multiple flows and/or block diagram or multiple boxes.
These computer program instructions, which may also be stored in, can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that instruction generation stored in the computer readable memory includes referring to
Enable the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one box of block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device so that count
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, in computer or
The instruction executed 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 a box or multiple boxes.
The foregoing is only a preferred embodiment of the present invention, is not intended to limit the scope of the present invention.
Claims (10)
1. a kind of log detection method, which is characterized in that the method includes：
According to the tactful automatically grinding timber of polishing；
Acquire the image data after the timber polishing；
Show that the testing result of the timber, the testing result are obtained based on the image data after the polishing.
2. according to the method described in claim 1, the polishing portion of the polishing strategy including polishing time, at least one precision
One or more of part, polishing track, the polishing component includes polishing consumptive material and its parameter.
3. according to the method described in claim 1, before the strategy polishing timber according to polishing, further include：
Acquire the raw image data of timber；The polishing strategy is obtained based on the raw image data.
4. according to the method described in claim 3, the polishing strategy includes and the associated polishing strategy of polishing characteristic parameter, institute
Polishing characteristic parameter is stated to obtain based on image processing techniques and the raw image data.
5. according to the method described in claim 1, the testing result is obtained based on shown detection characteristic parameter, the inspection
Survey what characteristic parameter was obtained based on the image data after image processing techniques and the polishing.
6. according to the method described in claim 1, the testing result is using the image data after the polishing as engineering
What the input of habit algorithm obtained, the machine learning algorithm is the mould of the image data training after the polishing largely marked
Type.
7. a kind of wood detection equipment, which is characterized in that described device includes：
Polishing module, for according to timber described in the tactful automatically grinding of polishing；
Image data acquiring module, for acquiring the image data after the timber is polished；
Display module, the testing result for showing the timber, the testing result are based on the picture number after the polishing
According to what is obtained.
8. device according to claim 7, described image acquisition module is additionally operable to the raw image data of acquisition timber；Institute
Polishing strategy is stated to obtain based on the raw image data.
9. device according to claim 7, the testing result is using the image data after the polishing as engineering
What the input of habit algorithm obtained, the machine learning algorithm is the mould of the image data training after the polishing largely marked
Type.
10. a kind of hand-held log detection equipment, which is characterized in that including：Imaging sensor, polishing module, display module, handle
Structure, memory and one or more processors；
Wherein, described image sensor, polishing module, display module and the memory and one or more of processors are logical
Letter connects, and is stored with the instruction that can be executed by one or more of processors in the memory, described instruction is by described one
A or multiple processors execute, so that one or more of processors can be realized as described in any one of claim 1-6
Method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711335528.4A CN108375353B (en) | 2017-12-14 | Wood detection method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711335528.4A CN108375353B (en) | 2017-12-14 | Wood detection method, device and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108375353A true CN108375353A (en) | 2018-08-07 |
| CN108375353B CN108375353B (en) | 2024-04-19 |
Family
ID=
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109886302A (en) * | 2019-01-21 | 2019-06-14 | 河北新兴铸管有限公司 | Caliber judgment method and terminal device based on machine learning |
| CN110726584A (en) * | 2019-11-26 | 2020-01-24 | 上海市建筑科学研究院有限公司 | On-site micro-damage sampling detection method for tree species identification |
| CN111791103A (en) * | 2020-06-30 | 2020-10-20 | 北京百度网讯科技有限公司 | Filter debugging method and device, electronic equipment and readable storage medium |
| CN113177908A (en) * | 2021-04-01 | 2021-07-27 | 柳城县迪森人造板有限公司 | Identification method and device for solid wood ecological plate |
| CN114161262A (en) * | 2021-12-03 | 2022-03-11 | 四川兴事发木业有限公司 | Timber edging system for polishing |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1800838A (en) * | 2004-12-30 | 2006-07-12 | 戚大伟 | Non-destructive test device for wood |
| CN101669023A (en) * | 2007-04-20 | 2010-03-10 | 株式会社名南制作所 | Lumber inspection method, device and program |
| US20110223417A1 (en) * | 2008-09-23 | 2011-09-15 | Upm-Kymmene Wood Oy | Wood-metal composite structure |
| CN103278113A (en) * | 2013-02-27 | 2013-09-04 | 中国林业科学研究院木材工业研究所 | Method for rapidly measuring surface roughness of timber in non-contact manner |
| CN104180767A (en) * | 2013-05-24 | 2014-12-03 | 武汉铁路局武汉大型养路机械运用检修段 | steel-rail wear measurement device based on machine vision and grinding strategy method thereof |
| CN105486684A (en) * | 2016-01-13 | 2016-04-13 | 广东产品质量监督检验研究院 | Non-destructive testing method for mahogany furniture wood varieties based on network platform |
| US20160274022A1 (en) * | 2015-03-18 | 2016-09-22 | CENTRE DE RECHERCHE INDUSTRIELLE DU QUéBEC | Optical method and apparatus for identifying wood species of a raw wooden log |
| CN106153624A (en) * | 2016-06-23 | 2016-11-23 | 四川农业大学 | The grain of wood and the assay method of surface characteristic feature coverage rate |
| CN106780489A (en) * | 2017-01-19 | 2017-05-31 | 中国科学院新疆生态与地理研究所 | A kind of tree ring half-tone information analysis method and device |
| CN107392896A (en) * | 2017-07-14 | 2017-11-24 | 佛山市南海区广工大数控装备协同创新研究院 | A kind of Wood Defects Testing method and system based on deep learning |
| CN107437094A (en) * | 2017-07-12 | 2017-12-05 | 北京木业邦科技有限公司 | Plank method for sorting and system based on machine learning |
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1800838A (en) * | 2004-12-30 | 2006-07-12 | 戚大伟 | Non-destructive test device for wood |
| CN101669023A (en) * | 2007-04-20 | 2010-03-10 | 株式会社名南制作所 | Lumber inspection method, device and program |
| US20110223417A1 (en) * | 2008-09-23 | 2011-09-15 | Upm-Kymmene Wood Oy | Wood-metal composite structure |
| CN103278113A (en) * | 2013-02-27 | 2013-09-04 | 中国林业科学研究院木材工业研究所 | Method for rapidly measuring surface roughness of timber in non-contact manner |
| CN104180767A (en) * | 2013-05-24 | 2014-12-03 | 武汉铁路局武汉大型养路机械运用检修段 | steel-rail wear measurement device based on machine vision and grinding strategy method thereof |
| US20160274022A1 (en) * | 2015-03-18 | 2016-09-22 | CENTRE DE RECHERCHE INDUSTRIELLE DU QUéBEC | Optical method and apparatus for identifying wood species of a raw wooden log |
| CN105486684A (en) * | 2016-01-13 | 2016-04-13 | 广东产品质量监督检验研究院 | Non-destructive testing method for mahogany furniture wood varieties based on network platform |
| CN106153624A (en) * | 2016-06-23 | 2016-11-23 | 四川农业大学 | The grain of wood and the assay method of surface characteristic feature coverage rate |
| CN106780489A (en) * | 2017-01-19 | 2017-05-31 | 中国科学院新疆生态与地理研究所 | A kind of tree ring half-tone information analysis method and device |
| CN107437094A (en) * | 2017-07-12 | 2017-12-05 | 北京木业邦科技有限公司 | Plank method for sorting and system based on machine learning |
| CN107392896A (en) * | 2017-07-14 | 2017-11-24 | 佛山市南海区广工大数控装备协同创新研究院 | A kind of Wood Defects Testing method and system based on deep learning |
Non-Patent Citations (1)
| Title |
|---|
| 任洪娥;高洁;马岩;: "我国木材材种识别技术的新进展", 木材加工机械, no. 04 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109886302A (en) * | 2019-01-21 | 2019-06-14 | 河北新兴铸管有限公司 | Caliber judgment method and terminal device based on machine learning |
| CN110726584A (en) * | 2019-11-26 | 2020-01-24 | 上海市建筑科学研究院有限公司 | On-site micro-damage sampling detection method for tree species identification |
| CN111791103A (en) * | 2020-06-30 | 2020-10-20 | 北京百度网讯科技有限公司 | Filter debugging method and device, electronic equipment and readable storage medium |
| CN111791103B (en) * | 2020-06-30 | 2022-04-29 | 北京百度网讯科技有限公司 | Filter debugging method and device, electronic equipment and readable storage medium |
| US11469975B2 (en) | 2020-06-30 | 2022-10-11 | Beijing Baidu Netcom Science & Technology Co., Ltd | Filter debugging method, device, electronic apparatus and readable storage medium |
| CN113177908A (en) * | 2021-04-01 | 2021-07-27 | 柳城县迪森人造板有限公司 | Identification method and device for solid wood ecological plate |
| CN113177908B (en) * | 2021-04-01 | 2022-11-25 | 柳城县迪森人造板有限公司 | Identification method and device for solid wood ecological plate |
| CN114161262A (en) * | 2021-12-03 | 2022-03-11 | 四川兴事发木业有限公司 | Timber edging system for polishing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11232553B2 (en) | System, method and computer program product for security analysis of jewelry items | |
| CN104866862B (en) | A kind of method of belt steel surface area-type defect recognition classification | |
| Fernández et al. | Evaluation of robustness against rotation of LBP, CCR and ILBP features in granite texture classification | |
| CN109977983A (en) | Obtain the method and device of training image | |
| CN107045641A (en) | A kind of identification of pallets method based on image recognition technology | |
| CN102095731A (en) | System and method for recognizing different defect types in paper defect visual detection | |
| CN105973148A (en) | Pen point appearance size standardization detection system based on machine vision | |
| US20190012865A1 (en) | Coin recognition system and method | |
| CA3166347A1 (en) | Video generation method and apparatus, and computer system | |
| CN105205673B (en) | A kind of false proof trace-back technique using in bar cigarette stamp feature | |
| CN114359235A (en) | Wood surface defect detection method based on improved YOLOv5l network | |
| CN108288274A (en) | Mold detection method, device and electronic equipment | |
| CN111062861A (en) | Method and device for generating display image samples | |
| US20200019776A1 (en) | Currency verification and transaction validation system | |
| EP1739616A1 (en) | Process for verifying, labeling and rating diamonds and other gemstones from mine to market | |
| JP5780791B2 (en) | Cell tracking method | |
| CN110097603A (en) | A kind of fashion images dominant hue analytic method | |
| CN108375353A (en) | A kind of log detection method, apparatus and equipment | |
| CN109492445A (en) | A kind of anti-fake method for preventing goods from altering based on sequential information code image recognition | |
| CN103472064B (en) | A kind of method of justifying the qualification of bright cut jewel cut | |
| CN115240031B (en) | Board surface defect generation method and system based on generation countermeasure network | |
| TWM550465U (en) | Semiconductor wafer analyzing system | |
| CN110017998A (en) | Vehicle checking method, device and equipment | |
| US20230044043A1 (en) | Method and system for automated grading and trading of numismatics and trading cards | |
| CN115731198A (en) | Intelligent detection system for leather surface defects |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |