CN109544514B - Sawn timber identity identification method, device and equipment integrating apparent features - Google Patents
Sawn timber identity identification method, device and equipment integrating apparent features Download PDFInfo
- Publication number
- CN109544514B CN109544514B CN201811307821.4A CN201811307821A CN109544514B CN 109544514 B CN109544514 B CN 109544514B CN 201811307821 A CN201811307821 A CN 201811307821A CN 109544514 B CN109544514 B CN 109544514B
- Authority
- CN
- China
- Prior art keywords
- wood
- identified
- apparent
- image
- defect
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a sawn timber identity identification method, device and equipment fused with apparent characteristics, wherein the method comprises the following steps: extracting the apparent characteristics of all the wood, and storing the wood ID and the corresponding apparent characteristics of each wood into a database; wherein the apparent features include a color histogram of each wood and a defect location of each wood on a plurality of surfaces; acquiring a wood image of a wood to be identified conveyed on a conveyor belt; acquiring apparent characteristics of the wood to be identified according to the wood image; matching the defect positions of the wood to be identified on the plurality of surfaces with the defect positions of the wood in the database on the plurality of surfaces to obtain a wood ID set corresponding to the wood to be identified; the invention can effectively solve the problem of accurate and quick identification of wood, and promote the flexible and customized processing of a forest production line.
Description
Technical Field
The invention relates to the field of wood processing production and wood assembly, in particular to a sawn wood identity identification method, equipment and device integrating apparent characteristics.
Background
As is well known, although forest resources are abundant in China, the forest resources occupy a small number of people compared with other countries, and the demand of wood, especially the demand of solid wood is increasing. Therefore, it is becoming an urgent problem to increase the utilization rate of wood in the production and manufacturing processes.
Because the current forestry processing production investment of China is less and the mechanical automation level is low, the improvement of the utilization rate of wood is mainly developed by judging the defects of sawn wood. The traditional sawn timber defect detection is mainly completed by skilled workers, but the defect detection based on the visual observation can be subject to subjective difference to cause different detection results. In order to overcome the defects of the sawn timber by manual visual inspection, machine vision, ultrasonic waves, microwaves, nuclear magnetic resonance, X-ray density imaging and other technologies have been tried to be used for automatic detection of the sawn timber surface defects. Among them, the machine vision technology has been identified as one of effective technologies for the identification of surface defects of wood due to its high cost performance.
However, with the increasing situation of shortage of wood resources and the increasing price of raw wood materials year by year, the existing sawn timber utilization improvement method taking defect detection as a core has some defects. Secondly, the existing detection methods can only provide the basis of the quality of the current products generally, the sawn timber itself and sawn timbers in the same batch cannot be effectively identified, customized and flexible production and processing process optimization is difficult to realize, and the system integration is insufficient.
Disclosure of Invention
The invention discloses a sawn timber identity identification method, device and equipment integrating apparent characteristics, aiming at overcoming the defects that the sawn timber cannot effectively identify the sawn timber per se and sawn timber in the same batch, customized and flexible production and processing process optimization is difficult to realize, and system integration is insufficient.
The embodiment of the invention discloses a sawn timber identity identification method fused with apparent characteristics, which comprises the following steps: extracting the apparent characteristics of all the wood, and storing the wood ID and the corresponding apparent characteristics of each wood into a database; wherein the apparent features include a color histogram of each wood and a defect location of each wood on a plurality of surfaces;
acquiring a wood image of a wood to be identified conveyed on a conveyor belt;
acquiring apparent characteristics of the wood to be identified according to the wood image;
matching the defect positions of the wood to be identified on the plurality of surfaces with the defect positions of the wood in the database on the plurality of surfaces to obtain a wood ID set corresponding to the wood to be identified;
and when the number of the wood IDs in the wood ID set is judged to be not unique, matching the color histogram of the wood to be identified with the color histogram of the wood in the database to determine the final wood ID corresponding to the wood to be identified at present.
Preferably, the acquiring of the wood image of the wood to be identified, which is conveyed on the conveyor belt, specifically includes:
acquiring a transmission image shot by a line scanning camera;
judging whether wood exists according to the color brightness of the transmitted image, if the front part of the transmitted image is detected not to contain no wood and the rear part of the transmitted image contains wood, judging the transmitted image as a starting frame and marking; if the front part of the transmission image contains wood and the rear part does not contain wood, judging the transmission image as an end frame and marking;
and performing image splicing according to the starting frame, the ending frame and all the transmission images positioned between the starting frame and the ending frame to generate a wood image of the wood to be identified.
Preferably, the scanning frequency of the line scanning camera coincides with the conveying frequency of the conveyor belt.
Preferably, whether wood grain exists in each line on the transmission image is judged according to the color brightness on the transmission image, and then whether wood exists in the transmission image is determined.
Preferably, the extracting the apparent features of all the woods and storing the wood ID and the corresponding apparent feature of each wood into the database specifically comprises:
traversing the surface of each wood in the wood image, and selecting a region with a defect outline area larger than M pixel values on each surface to obtain a candidate local defect region to be selected;
acquiring a circumscribed rectangle of the candidate local defect area, and taking a Y coordinate value of a center point of the circumscribed rectangle from a shortest end point as a defect position of the wood on the corresponding surface;
acquiring the color histogram characteristics of each wood image according to the statistical pixel value range A of all the woods;
an apparent feature of each wood is generated from the defect location on each surface and the color histogram feature, and the wood ID and corresponding apparent feature of each wood are stored in a database.
Preferably, the value of M is 4000 and the A range is 7-120.
Preferably, the matching the defect positions of the wood to be identified on the plurality of surfaces with the defect positions of the wood in the database on the plurality of surfaces, and the obtaining of the wood ID set corresponding to the wood to be identified specifically includes:
comparing the defect positions of the wood to be identified on the plurality of surfaces with the defect positions of the wood in the database on the plurality of surfaces, and adding the corresponding wood ID to the wood ID set corresponding to the wood to be identified when the distance between the two defect positions is less than N.
Preferably, when it is determined that the number of wood IDs in the wood ID set is not unique, the color histogram of the wood to be identified and the color histogram of the wood in the database are matched to determine that the final wood ID corresponding to the target wood to be identified specifically is:
when the number of the wood IDs in the wood ID set is judged to be not unique, calculating Euclidean distances between the color histogram features of each surface of the wood to be identified and the color histogram features of each surface of the wood in the database, sequencing the obtained numerical values from small to large, reserving the first X numbers, and obtaining a wood ID set of each surface;
and counting the wood IDs with the highest occurrence times in the wood ID sets of the multiple surfaces, namely determining the final ID of the wood to be searched corresponding to the wood to be identified.
The embodiment of the invention also provides a sawn timber identity recognition device fused with the apparent characteristics, which comprises:
the apparent characteristic extraction unit is used for extracting the apparent characteristics of all the wood and storing the wood ID and the corresponding apparent characteristics of each wood into a database; wherein the apparent features include a color histogram of each wood and a defect location of each wood on a plurality of surfaces;
a wood image acquisition unit that acquires a wood image of a wood to be identified conveyed on a conveyor belt;
the apparent characteristic recognition unit acquires the apparent characteristic of the wood to be recognized according to the wood image;
the defect matching unit is used for matching the defect positions of the wood to be identified on the plurality of surfaces with the defect positions of the wood in the database on the plurality of surfaces to acquire a wood ID set corresponding to the wood to be identified;
and the color histogram matching unit is used for matching the color histogram of the wood to be identified with the color histogram of the wood in the database to determine the final wood ID corresponding to the wood to be identified at present when the number of the wood IDs in the wood ID set is judged to be not unique.
The embodiment of the invention also provides sawn timber identification equipment fused with the apparent characteristics, which comprises a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the sawn timber identification equipment fused with the apparent characteristics realizes the sawn timber identification method fused with the apparent characteristics.
Based on the sawn timber identity identification method, equipment and device fusing the apparent features, the apparent features of the timbers to be identified are obtained through the line scanning camera, the timber ID of each timber and the corresponding apparent features are stored in the database, and the final ID of the timber to be identified is determined through matching the defect position and the color histogram features on the timber image to be identified, so that the problems of insufficient utilization rate and system integrity of the timber are effectively solved, and the flexible and customized processing of a forest work production line is promoted.
Drawings
Fig. 1 is a schematic flow chart of a sawn timber identification method with integrated apparent features according to a first embodiment of the present invention;
fig. 2 is a block diagram of a sawn timber identification device incorporating apparent features according to a second embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings of the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention. Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
Referring to fig. 1, the embodiment of the present invention discloses a sawn timber identification method with fused apparent features, which can be performed by sawn timber identification equipment with fused apparent features (hereinafter referred to as sawn timber identification equipment), and includes:
s101, extracting the apparent characteristics of all the wood, and storing the wood I D of each wood and the corresponding apparent characteristics into a database; wherein the apparent features include a color histogram of each wood and a defect location of each wood on a plurality of surfaces.
In this embodiment, the sawn timber identification device may be a computer, a terminal with an operation processing capability, a server, or the like, and the present invention is not limited in particular.
In this embodiment, the sawn timber identification device may first extract the apparent features of the entire batch of timber offline, where the apparent features may include the color histogram features of each timber and the defect locations of each timber on multiple surfaces (typically four surfaces). And after the apparent features are extracted, storing the wood ID and the corresponding apparent features of each wood into a database to form a feature library.
S102, acquiring a wood image of the wood to be identified, which is conveyed on a conveyor belt.
In particular, in this embodiment, the wood flowing on the conveyor belt may be photographed using a line scanning camera from which the sawn timber identification device acquires an image of the wood flowing.
In consideration of the fact that the length of wood is often long, the images shot by the line scanning camera need to be spliced to obtain a complete wood image. Specifically, step S102 may include:
s1021, a transmission image captured by the line scan camera is acquired.
The line scanning camera forms a small image by 400 lines of pixels of each line scanning, the small image is used as an alternative splicing frame, and in order to ensure that the splicing frames are not interfered with each other, a cache storage image is distributed for each frame in the memory.
S1022, judging whether wood exists according to the color brightness of the transmitted image, if the front part of the transmitted image does not contain wood or not and the rear part of the transmitted image contains wood, judging the transmitted image as a starting frame and marking; if it is detected that the front part of the transmission image contains wood and the rear part does not contain wood, the transmission image is judged to be an end frame and marked.
And S1023, performing image splicing according to the starting frame, the ending frame and all the transmission images positioned between the starting frame and the ending frame to generate a wood image of the wood to be identified.
S103, acquiring the apparent characteristics of the wood to be identified according to the wood image.
In this embodiment, after the wood image is acquired, the color histogram features of the wood image and the defect positions of the wood on the plurality of surfaces are acquired.
Wherein, the defect position can be extracted by the following method:
firstly, traversing four surfaces of each wood in the wood image, and selecting a region with a defect outline area larger than M pixel values on each surface to obtain a candidate local defect region to be selected; then, acquiring a circumscribed rectangle of the candidate local defect area, and taking the Y coordinate value of the center point of the circumscribed rectangle from the shortest end point as the defect position of the wood on the corresponding surface.
In the present embodiment, M is preferably 4000. It should be noted that, in other embodiments of the present invention, the value of M may be adjusted according to actual needs, for example, the value is 3500 or 5000, and these schemes are all within the protection scope of the present invention. In addition, it should be noted that, when the defect position is selected, the X coordinate value of the shortest end point from the center point of the circumscribed rectangle may also be used as the defect position of the wood on the corresponding surface, or other setting methods, which is not specifically limited in the present invention.
The color histogram feature of the wood image can be obtained by:
and acquiring the color histogram characteristics of each wood image according to the statistical pixel value range A of all the woods.
Wherein the range a is gray scale values of 7-120. Of course, it should be noted that the range of a can be adjusted according to actual needs, for example, the range a can be adjusted according to different wood species, and these schemes are within the protection scope of the present invention.
S104, matching the defect positions of the wood to be identified on the plurality of surfaces with the defect positions of the wood in the database on the plurality of surfaces, and acquiring a wood ID set corresponding to the wood to be identified.
Specifically, if the timber to be searched currently has defects, the first defect position of the first surface of the four surfaces of the timber acquired in real time is compared with the defect positions of the surfaces of all the timbers in the database one by one, as long as the difference between the two numerical values is within N, the two defects are tentatively determined to be approximately consistent in position, the timber image in the database is kept as an alternative, and the database is traversed to complete the first screening, so that a timber surface set C1 which accords with the first defect position is obtained.
Then, according to the first screening result, the second defect position of the first surface of the current wood image is compared and screened again in the set C1 to obtain a smaller set D1, and by analogy, the candidate surface set S1 of the first surface is obtained, and the other three surfaces are processed in the same way to obtain four sets { S1, S2, S3 and S4 }.
And finally, each surface in the four sets corresponds to a unique wood ID, and the wood IDs corresponding to all the surfaces in the four sets are counted, namely the wood ID set A corresponding to the wood to be identified is obtained through defect screening.
S105, when the number of the wood IDs in the wood ID set is judged to be not unique, matching the color histogram of the wood to be identified with the color histogram of the wood in the database to determine the final wood ID corresponding to the wood to be identified at present.
Specifically, if the wood ID in the set a is not unique (for example, the wood itself has no defect or there is a wood with a very similar defect location), it indicates that the current wood cannot be identified, and further identification judgment is required.
At this time, further judgment can be made according to the color histogram features of the four faces of the wood to be identified, which are obtained by the previous calculation.
Specifically, similarity detection is performed by using the color histogram feature of the first surface and the histogram features of all the surfaces of all the wood in the set a, that is, euclidean distances between the color histogram feature of the first surface and the histogram features of all the surfaces of all the wood in the set a are calculated, obtained values are sorted from small to large, and the front X surfaces are retained to obtain a surface set. The same procedure calculates the other three surfaces to obtain another three surface sets, and for each set, the wood ID of each surface is counted to obtain a set of four wood IDs { W1, W2, W3, W4}, and then the wood ID with the highest occurrence frequency in the four sets is counted, and the ID is the final ID of the wood to be identified.
Wherein the value of X is set according to the size of the database, wherein the value of X takes 20. The first embodiment of the invention can effectively realize the combination optimization of the sawn timber of the same batch, effectively identify the sawn timber of the same batch, solve the problems of insufficient utilization rate and system integration of the timber and promote the flexible and customized processing of the forest work production line.
The embodiment of the invention also provides a sawn timber identity recognition device fused with the apparent characteristics, which comprises:
an apparent feature extraction unit 10 for extracting the apparent features of all the woods and storing the wood ID and the corresponding apparent features of each wood into a database; wherein the apparent features include a color histogram of each wood and a defect location of each wood on a plurality of surfaces;
a wood image acquiring unit 20 that acquires a wood image of the wood to be identified conveyed on the conveyor belt;
an apparent feature recognition unit 30 which acquires an apparent feature of the wood to be recognized from the wood image;
the defect matching unit 40 is used for matching the defect positions of the wood to be identified on the plurality of surfaces with the defect positions of the wood in the database on the plurality of surfaces to acquire a wood ID set corresponding to the wood to be identified;
and a color histogram matching unit 50, when the number of wood IDs in the wood ID set is determined to be not unique, matching the color histogram of the wood to be identified with the color histogram of the wood in the database to determine a final wood ID currently corresponding to the wood to be identified.
Preferably, the wood image acquiring unit 20 specifically includes:
a transmission image acquisition module for acquiring a transmission image photographed by the line scanning camera;
judging whether wood exists according to the color brightness of the transmitted image, if the front part of the transmitted image is detected not to contain no wood and the rear part of the transmitted image contains wood, judging the transmitted image as a starting frame and marking; if the front part of the transmission image contains wood and the rear part does not contain wood, judging the transmission image as an end frame and marking;
and performing image splicing according to the starting frame, the ending frame and all the transmission images positioned between the starting frame and the ending frame to generate a wood image of the wood to be identified.
Preferably, the apparent feature recognition unit 30 is configured to recognize an apparent feature in the wood image of the wood to be recognized generated by the transmitted image acquisition module, where the apparent feature includes a wood image color histogram feature of the wood to be recognized and a wood image defect position of the wood to be recognized.
Preferably, the defect matching unit 40 specifically includes:
defect position comparison module: the wood identification method comprises the steps of comparing defect positions of the wood to be identified on a plurality of surfaces with defect positions of the wood in the database on a plurality of surfaces, and adding corresponding wood IDs to wood ID sets corresponding to the wood to be identified when the distance between the two defect positions is smaller than N.
Preferably, the value of N is taken to be 100 here.
Preferably, the color histogram matching unit 50 specifically includes:
wood ID quantity judgment module: for determining whether the wood ID numbers in the wood ID set are unique.
A color histogram feature matching module: when the wood ID quantity judging module judges that the quantity of the wood IDs in the wood ID set is not unique, calculating Euclidean distances between the color histogram features of each surface of the wood to be identified and the color histogram features of each surface of the wood in the database, sequencing the obtained numerical values from small to large, reserving the first X numbers, and obtaining the wood ID set of each surface;
wood ID statistics module: and counting the wood ID with the highest occurrence frequency in the wood ID sets of the multiple surfaces, namely determining the final ID of the wood to be searched corresponding to the wood to be identified.
Preferably, the value of X here takes 20.
The embodiment of the invention also provides sawn timber identification equipment fused with the apparent characteristics, which comprises a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the sawn timber identification equipment fused with the apparent characteristics realizes the sawn timber identification method fused with the apparent characteristics.
According to the sawn timber identity identification method, equipment and device fusing the apparent features, the apparent features of the timbers to be identified are obtained through the line scanning camera, the timber ID and the corresponding apparent features of each timber are stored in the database, the final ID of the timber to be identified is determined through matching of the defect position and the color histogram features on the timber image to be identified, the problems of insufficient timber utilization rate and system integrity are effectively solved, and flexible and customized processing of a forest worker production line is promoted.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A sawn timber identity identification method fused with apparent characteristics is characterized by comprising the following steps:
extracting the apparent characteristics of all the wood, and storing the wood ID and the corresponding apparent characteristics of each wood into a database; wherein the apparent features include a color histogram of each wood and a defect location of each wood on a plurality of surfaces;
acquiring a wood image of a wood to be identified conveyed on a conveyor belt;
acquiring apparent characteristics of the wood to be identified according to the wood image;
matching the defect positions of the wood to be identified on the plurality of surfaces with the defect positions of the wood in the database on the plurality of surfaces to obtain a wood ID set corresponding to the wood to be identified;
and when the number of the wood IDs in the wood ID set is judged to be not unique, matching the color histogram of the wood to be identified with the color histogram of the wood in the database to determine a final wood ID corresponding to the wood to be identified.
2. The sawn timber identification method with fused apparent characteristics as claimed in claim 1,
the acquiring of the wood image of the wood to be identified conveyed on the conveyor belt specifically comprises:
acquiring a transmission image shot by a line scanning camera;
judging whether wood exists according to the color brightness of the transmitted image, if the front part of the transmitted image is detected not to contain no wood and the rear part of the transmitted image contains wood, judging the transmitted image as a starting frame and marking; if the front part of the transmission image contains wood and the rear part does not contain wood, judging the transmission image as an end frame and marking;
and performing image splicing according to the starting frame, the ending frame and all the transmission images positioned between the starting frame and the ending frame to generate a wood image of the wood to be identified.
3. The sawn timber identification method fused with the appearance characteristics as claimed in claim 2, wherein the scanning frequency of the line scanning camera is consistent with the conveying frequency of the conveyor belt.
4. The sawn timber identification method with fused appearance characteristics as claimed in claim 2,
and judging whether wood grains exist in each line on the transmission image according to the color brightness on the transmission image, and further determining whether wood exists in the transmission image.
5. The method for identifying sawn timber identity fused with apparent features according to claim 1, wherein the steps of extracting the apparent features of all the timbers and storing the timber ID and the corresponding apparent features of each timbers into a database specifically comprise:
traversing the surface of each wood in the wood image, and selecting a region with the defect outline area larger than M pixel values on each surface to obtain a candidate local defect region;
acquiring a circumscribed rectangle of the candidate local defect area, and taking a Y coordinate value of a center point of the circumscribed rectangle from a shortest end point as a defect position of the wood on the corresponding surface;
acquiring the color histogram characteristics of each wood image according to the statistical pixel value range A of all the woods;
an apparent feature of each wood is generated from the defect location on each surface and the color histogram feature, and the wood ID and corresponding apparent feature of each wood are stored in a database.
6. The sawn timber identification method with the fused apparent characteristics as claimed in claim 5, wherein the value of M is 4000, and the range of A is 7-120.
7. The method for identifying sawn timber with fused apparent features as claimed in claim 1, wherein the matching of the defect positions of the timber to be identified on a plurality of surfaces with the defect positions of the timber in the database on a plurality of surfaces to obtain the timber ID set corresponding to the timber to be identified specifically comprises:
comparing the defect positions of the wood to be identified on the plurality of surfaces with the defect positions of the wood in the database on the plurality of surfaces, and adding the corresponding wood ID to the wood ID set corresponding to the wood to be identified when the distance between the two defect positions is less than N.
8. The method according to claim 1, wherein when it is determined that the number of wood IDs in the wood ID set is not unique, the color histogram of the wood to be identified and the color histogram of the wood in the database are matched to determine a final wood ID corresponding to the target wood to be identified specifically as:
when the number of the wood IDs in the wood ID set is judged to be not unique, calculating Euclidean distances between the color histogram features of each surface of the wood to be identified and the color histogram features of each surface of the wood in the database, sequencing the obtained numerical values from small to large, reserving the first X numbers, and obtaining a wood ID set of each surface;
and counting the wood IDs with the highest occurrence times in the wood ID sets of the multiple surfaces, namely determining the final ID of the wood to be searched corresponding to the wood to be identified.
9. A sawn timber identification device fused with apparent characteristics is characterized by comprising:
the apparent characteristic extraction unit is used for extracting the apparent characteristics of all the wood and storing the wood ID and the corresponding apparent characteristics of each wood into a database; wherein the apparent features include a color histogram of each wood and a defect location of each wood on a plurality of surfaces;
a wood image acquisition unit that acquires a wood image of a wood to be identified conveyed on a conveyor belt;
the apparent characteristic recognition unit acquires the apparent characteristic of the wood to be recognized according to the wood image;
the defect matching unit is used for matching the defect positions of the wood to be identified on the plurality of surfaces with the defect positions of the wood in the database on the plurality of surfaces to acquire a wood ID set corresponding to the wood to be identified;
and the color histogram matching unit is used for matching the color histogram of the wood to be identified and the color histogram of the wood in the database to determine the final wood ID corresponding to the wood to be identified when the number of the wood IDs in the wood ID set is judged to be not unique.
10. A sawn timber identification device fused with apparent characteristics, which comprises a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to realize the sawn timber identification method fused with apparent characteristics according to any one of claims 1 to 8.
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 CN109544514A (en) | 2019-03-29 |
| CN109544514B true 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) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN112129773B (en) * | 2020-08-20 | 2022-06-14 | 湖南大学 | Wood surface defect detection method, device, equipment, system and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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***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 |
Family Cites Families (1)
| 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 |
-
2018
- 2018-11-05 CN CN201811307821.4A patent/CN109544514B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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***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 |
|---|
| 坤甸木在潮州广济桥修复工程中的应用;李旭伟等;《建筑监督检测与造价》;20090331;第2卷(第3期);第42-46页 * |
| 基于应力波和支持向量机的木材缺陷识别分类方法;王再超等;《 南京林业大学学报(自然科学版)》;20150531;第39卷(第3期);第130-136页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109544514A (en) | 2019-03-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109829914B (en) | Method and device for detecting product defects | |
| CN111951237B (en) | Visual appearance detection method | |
| CN102393397B (en) | System and method for detecting surface defects of magnetic shoe | |
| CN113095438B (en) | Wafer defect classification method, device and system thereof, electronic equipment and storage medium | |
| CN110705405A (en) | Target labeling method and device | |
| WO2012074361A1 (en) | Method of image segmentation using intensity and depth information | |
| CN114994061B (en) | Machine vision-based steel rail intelligent detection method and system | |
| CN109544514B (en) | Sawn timber identity identification method, device and equipment integrating apparent features | |
| CN110728269B (en) | High-speed rail contact net support pole number plate identification method based on C2 detection data | |
| CN116703911A (en) | LED lamp production quality detecting system | |
| CN115937101A (en) | Quality detection method, device, equipment and storage medium | |
| CN117455917B (en) | Establishment of false alarm library of etched lead frame and false alarm on-line judging and screening method | |
| JP2018081629A (en) | Determination device, method for determination, and determination program | |
| CN112967224A (en) | Electronic circuit board detection system, method and medium based on artificial intelligence | |
| CN117351472A (en) | Tobacco leaf information detection method and device and electronic equipment | |
| CN112883213B (en) | Picture archiving method and device and electronic equipment | |
| CN116071335A (en) | Wall surface acceptance method, device, equipment and storage medium | |
| CN107403429B (en) | Method for quickly and automatically acquiring parameters of periodic sequence image model | |
| CN109584212A (en) | A kind of SLM powder bed powder laying image scratch defect identification method based on MATLAB | |
| CN110807453A (en) | OCR-based product character online detection method, device and system | |
| CN115511902A (en) | Angular point feature extraction method and system | |
| CN115082449A (en) | Electronic component defect detection method | |
| CN110189301B (en) | Foreign matter detection method for generator stator core steel sheet stacking platform | |
| CN111402341A (en) | Camera parameter determination method and device, electronic equipment and readable storage medium | |
| CN112613754B (en) | Management method, system, device and storage medium for cloth production |
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 | ||
| 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 |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |