CN109886934B - Carbonized bamboo chip defect detection method and system - Google Patents
Carbonized bamboo chip defect detection method and system Download PDFInfo
- Publication number
- CN109886934B CN109886934B CN201910079411.7A CN201910079411A CN109886934B CN 109886934 B CN109886934 B CN 109886934B CN 201910079411 A CN201910079411 A CN 201910079411A CN 109886934 B CN109886934 B CN 109886934B
- Authority
- CN
- China
- Prior art keywords
- carbonized bamboo
- defects
- bamboo chips
- historical
- image data
- 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
Abstract
The invention discloses a method and a system for detecting defects of carbonized bamboo chips. Wherein the method comprises the following steps: acquiring an image data sample of historical carbonized bamboo chips with defects, establishing a defect detection model based on the image data of the carbonized bamboo chips according to the acquired image data sample of the historical carbonized bamboo chips with the defects, carrying out defect detection on the current carbonized bamboo chips according to the established defect detection model based on the image data of the carbonized bamboo chips, and screening the carbonized bamboo chips with the defects in the current carbonized bamboo chips according to the detection result of the defect detection on the current carbonized bamboo chips. In this way, can realize need not the manual work and can carry out the defect detection to the carbonization bamboo chip automatically, improve detection efficiency and detection rate of accuracy, the quality of the carbonization bamboo chip after the defect detection can be ensured to improve the quality of bamboo product.
Description
Technical Field
The invention relates to the technical field of carbonized bamboos, in particular to a method and a system for detecting defects of carbonized bamboo chips.
Background
Bamboo is a branch of gramineae, is perennial, has various varieties, is distributed in tropical, subtropical and warm-warm areas, has the reputation of bamboo kingdom in China, and is rich in bamboo resources. According to statistics, the area of the bamboo forest in the world is about 2200 million hectares, while the area of the bamboo forest in China is 720 million hectares, which accounts for about one third, and is second in the world and only second in India. More than 70 genus and 1200 species of global bamboo plants; however, there are about 35 bamboo plants in China, nearly 400. The annual output of the bamboo forest all over the world is 1600 ten thousand tons, and the annual output of the bamboo forest in China reaches over 800 ten thousand tons and almost accounts for half of the world bamboo output; is the first place in the world. So in our country, bamboo is also called "second forest". The area distribution of the moso bamboo in the bamboo forest area in China is the largest, and the range is the widest. Wherein, the bamboo forest area of Fujian, Jiangxi and Zhejiang provinces occupies half of the whole country.
With the improvement of living standard, bamboo product industries such as bamboo sheet summer sleeping mat, bamboo sheet artistic engineering and bamboo sheet building are becoming hot points of public attention, however, when developing bamboo products, the problems of 'mildew, rot and moth damage' of bamboo materials, namely three-proofing treatment of mildew resistance, corrosion resistance and moth resistance, must be solved firstly. The bamboo material has a composition similar to wood, and the main components of bamboo material are cellulose, hemicellulose and lignin, and contain proteins, fats, various saccharides and a small amount of ash elements.
Carbonization, also known as dry distillation, carbonization, and coking, refers to a process of heating and decomposing a solid or organic substance in the absence of air or heating a solid substance to produce a liquid or gas, which is usually converted into a solid product. The carbonization process does not necessarily involve cracking or pyrolysis, and the product is collected after condensation. The carbonization process requires higher temperatures than usual distillation, with which liquid fuels can be extracted from charcoal or wood. Carbonization can also decompose mineral salts by pyrolysis, for example, dry distillation of sulfate can produce sulfur dioxide and sulfur trioxide, which can be dissolved in water to produce sulfuric acid; carbonizing coal to obtain coke, coal tar, coarse ammonia water and coal gas; carbonizing the bamboo chips to obtain the carbonized bamboo chips.
The principle of carbonizing the bamboo chips is that sugar in the bamboo chips is burnt off at high temperature, so that the processed bamboo chips are not easy to be bitten by insects, and the color, the natural color and the dark color are not different but are colored. The carbonized bamboo chips are not cracked after carbonization and dehydration, while the natural bamboo chips, namely the original bamboo, are cracked. The carbonized bamboo chips also have the same defect problems of 'mildew, rot, worm damage' and the like as natural color bamboo chips.
Carbonized bamboo chips must be detected for surface defects before processing of bamboo products on the next step, otherwise the quality of the bamboo products cannot be guaranteed, and the qualified rate is low.
The existing scheme for detecting the defects of the carbonized bamboo chips mainly depends on a mode of manual visual identification to screen the carbonized bamboo chips, the labor intensity is high, the screening efficiency is low, particularly, the human eyes carry out monotonous saccadic inspection for a long time, the visual fatigue is easy to generate, and the misjudgment and the omission inspection are increased more easily. The quality of the carbonized bamboo chips after manual screening is difficult to guarantee, the quality of bamboo products cannot be stably improved, and the rapid development of the bamboo product industry is greatly restricted.
However, the inventors found that at least the following problems exist in the prior art:
the scheme of current carbonization bamboo chip defect detection mainly relies on artifical naked eye discernment's mode to screen the carbonization bamboo chip, and intensity of labour is big, and screening efficiency is low, and easy erroneous judgement and hourglass are examined, and the quality of carbonization bamboo chip after artifical screening is difficult to obtain the guarantee, causes the unable stable improvement of bamboo product quality.
Disclosure of Invention
In view of this, the present invention provides a method and a system for detecting defects of carbonized bamboo chips, which can automatically detect defects of the carbonized bamboo chips without manual work, thereby improving detection efficiency and detection accuracy, and ensuring quality of the carbonized bamboo chips after the defects are detected, thereby improving quality of bamboo products.
According to an aspect of the present invention, there is provided a method for detecting defects in carbonized bamboo chips, comprising:
collecting image data samples of historical carbonized bamboo chips with defects; the image data sample of the historical carbonized bamboo chip with the defects comprises image information of a plurality of historical carbonized bamboo chips with the defects and corresponding defect type labels;
establishing a defect detection model based on the image data of the carbonized bamboo chips according to the acquired image data samples of the historical carbonized bamboo chips with defects;
detecting the defects of the current carbonized bamboo chips according to the established defect detection model based on the image data of the carbonized bamboo chips;
and screening the carbonized bamboo chips with the defects in the current carbonized bamboo chips according to the detection result of the defect detection of the current carbonized bamboo chips.
Wherein, according to the collected image data sample of the historical carbonized bamboo chips with defects, establishing a defect detection model based on the image data of the carbonized bamboo chips, comprising:
acquiring image information of a plurality of historical carbonized bamboo chips with defects and corresponding defect type labels in the acquired image data samples of the historical carbonized bamboo chips with the defects;
dividing image information of a plurality of historical carbonized bamboo strips with defects and corresponding defect type labels into N sections in the obtained image data sample of the historical carbonized bamboo strips with defects; wherein N is a natural number greater than 1;
extracting the image information of the plurality of historical carbonized bamboo chips with the defects after being divided into N sections and the time weighting characteristics of the corresponding defect type labels through a convolutional neural network;
obtaining image information of the plurality of historical carbonized bamboo chips which are divided into N sections and have the defects and multi-scale characteristics of corresponding defect type labels according to the extracted time weighting characteristics;
fusing image information of a plurality of historical carbonized bamboo chips with defects in the obtained image data samples of the N sections of historical carbonized bamboo chips with the defects and the multi-scale characteristics of corresponding defect type labels, and calculating a prediction score;
obtaining the final classification of the collected historical carbonized bamboo chip image data samples with defects according to the calculated prediction score;
obtaining training characteristics of the image data samples related to the collected historical carbonized bamboo chips with the defects according to the obtained classification of the image data samples related to the collected historical carbonized bamboo chips with the defects;
and performing model training according to the obtained training characteristics of the acquired image data samples related to the acquired historical carbonized bamboo chips with the defects, and establishing a defect detection model based on the image data of the carbonized bamboo chips.
Wherein, the defect detection of the current carbonized bamboo chips according to the established defect detection model based on the image data of the carbonized bamboo chips comprises the following steps:
and matching the training characteristics of the current carbonized bamboo chip image information from the established defect detection model based on the image data of the carbonized bamboo chips according to the established defect detection model based on the image data of the carbonized bamboo chips, and performing defect detection on the current carbonized bamboo chip image information by adopting a mode of training the current carbonized bamboo chip image information by using the matched training characteristics.
Wherein, according to the detection result of carrying out the defect detection to current carbonization bamboo chip, screen out the carbonization bamboo chip that has the defect in the current carbonization bamboo chip, include:
and prompting the detection result in an alarm mode according to the detection result of the defect detection of the current carbonized bamboo chips, and screening the carbonized bamboo chips with the defects in the current carbonized bamboo chips according to the prompted detection result.
Wherein, before the acquiring the image data sample of the historical carbonized bamboo chips with defects, the method further comprises the following steps:
after the detection process of the historical carbonized bamboo chips with the defects is completed, acquiring the image information of the historical carbonized bamboo chips with the defects, and generating a defect type label corresponding to the image information of the historical carbonized bamboo chips with the defects according to the defect type corresponding to the acquired image information of the historical carbonized bamboo chips with the defects.
According to another aspect of the present invention, there is provided a carbonized bamboo chip defect detecting system comprising:
the device comprises an acquisition unit, an establishing unit, a detection unit and a screening unit;
the acquisition unit is used for acquiring image data samples of the historical carbonized bamboo chips with defects; the image data sample of the historical carbonized bamboo chip with the defects comprises image information of a plurality of historical carbonized bamboo chips with the defects and corresponding defect type labels;
the establishing unit is used for establishing a defect detection model based on the image data of the carbonized bamboo chips according to the collected image data samples of the historical carbonized bamboo chips with defects;
the detection unit is used for detecting the defects of the current carbonized bamboo chips according to the established defect detection model based on the image data of the carbonized bamboo chips;
and the screening unit is used for screening the carbonized bamboo chips with defects in the current carbonized bamboo chips according to the detection result of the defect detection of the current carbonized bamboo chips.
Wherein, the establishing unit is specifically configured to:
acquiring image information of a plurality of historical carbonized bamboo chips with defects and corresponding defect type labels in the acquired image data samples of the historical carbonized bamboo chips with the defects;
dividing image information of a plurality of historical carbonized bamboo strips with defects and corresponding defect type labels into N sections in the obtained image data sample of the historical carbonized bamboo strips with defects; wherein N is a natural number greater than N;
extracting the image information of the plurality of historical carbonized bamboo chips with the defects after being divided into N sections and the time weighting characteristics of the corresponding defect type labels through a convolutional neural network;
obtaining image information of the plurality of historical carbonized bamboo chips which are divided into N sections and have the defects and multi-scale characteristics of corresponding defect type labels according to the extracted time weighting characteristics;
fusing image information of a plurality of historical carbonized bamboo chips with defects in the obtained image data samples of the N sections of historical carbonized bamboo chips with the defects and the multi-scale characteristics of corresponding defect type labels, and calculating a prediction score;
obtaining the final classification of the collected historical carbonized bamboo chip image data samples with defects according to the calculated prediction score;
obtaining training characteristics of the image data samples related to the collected historical carbonized bamboo chips with the defects according to the obtained classification of the image data samples related to the collected historical carbonized bamboo chips with the defects;
and performing model training according to the obtained training characteristics of the acquired image data samples related to the acquired historical carbonized bamboo chips with the defects, and establishing a defect detection model based on the image data of the carbonized bamboo chips.
Wherein, the detection unit is specifically configured to:
and matching the training characteristics of the current carbonized bamboo chip image information from the established defect detection model based on the image data of the carbonized bamboo chips according to the established defect detection model based on the image data of the carbonized bamboo chips, and performing defect detection on the current carbonized bamboo chip image information by adopting a mode of training the current carbonized bamboo chip image information by using the matched training characteristics.
Wherein, the screening unit is specifically configured to:
and prompting the detection result in an alarm mode according to the detection result of the defect detection of the current carbonized bamboo chips, and screening the carbonized bamboo chips with the defects in the current carbonized bamboo chips according to the prompted detection result.
Wherein, carbonization bamboo chip defect detecting system still includes:
the generating unit is used for acquiring the image information of the historical carbonized bamboo chips with the defects after the detection process of the historical carbonized bamboo chips with the defects is completed, and generating the defect type labels corresponding to the image information of the historical carbonized bamboo chips with the defects according to the defect types corresponding to the acquired image information of the historical carbonized bamboo chips with the defects.
It can be found that, according to the above scheme, the image data sample of the historical carbonized bamboo chips with defects can be collected, wherein the image data sample of the historical carbonized bamboo chips with defects comprises the image information of a plurality of historical carbonized bamboo chips with defects and corresponding defect type labels, and a defect detection model based on the image data of the carbonized bamboo chips is established according to the collected image data sample of the historical carbonized bamboo chips with defects, and the current carbonized bamboo chips are subjected to defect detection according to the established defect detection model based on the image data of the carbonized bamboo chips, and the carbonized bamboo chips with defects in the current carbonized bamboo chips are screened according to the detection result of the defect detection of the current carbonized bamboo chips, so that the defect detection of the carbonized bamboo chips can be automatically carried out without manual work, and the detection efficiency and the detection accuracy are improved, the quality of the carbonized bamboo chips after the defect detection can be guaranteed, so that the quality of the bamboo products is improved.
Further, according to the above scheme, the image information of a plurality of history carbonized bamboo chips with defects and corresponding defect type labels in the image data samples of the history carbonized bamboo chips with defects are obtained according to the collected image data samples of the history carbonized bamboo chips with defects, the image information of the history carbonized bamboo chips with defects and corresponding defect type labels in the obtained image data samples of the history carbonized bamboo chips with defects are divided into N sections, wherein N is a natural number greater than 1, the time weighting characteristics of the image information of the history carbonized bamboo chips with defects and corresponding defect type labels after the N sections are extracted through a convolutional neural network, and the multi-scale characteristics of the image information of the history carbonized bamboo chips with defects and corresponding defect type labels after the N sections are obtained according to the extracted time weighting characteristics, and fusing the image information of a plurality of historical carbonized bamboo chips with defects in the obtained image data samples of the N sections of historical carbonized bamboo chips with defects and the multi-scale characteristics of the corresponding defect type labels to calculate a prediction score, and obtaining a final classification of the collected image data samples related to the historical carbonized bamboo chips with defects according to the calculated prediction score, and obtaining training characteristics of the image data samples related to the collected historical carbonized bamboo chips with the defects according to the obtained classification of the image data samples related to the collected historical carbonized bamboo chips with the defects, and performing model training according to the obtained training characteristics of the acquired image data sample associated with the acquired historical carbonized bamboo chips with the defects, and establishing a defect detection model based on the image data of the carbonized bamboo chips, so that the modeling effect and accuracy of establishing the defect detection model based on the image data of the carbonized bamboo chips can be improved.
Further, according to the above scheme, the training characteristics of the current carbonized bamboo chip image information can be matched from the established defect detection model based on the image data of the carbonized bamboo chips, the defect detection can be performed on the current carbonized bamboo chip image information by adopting a mode of training the current carbonized bamboo chip image information by adopting the matched training characteristics, and the detection efficiency and accuracy of the detection result of the current carbonized bamboo chip image information can be effectively improved.
Further, above scheme can adopt the mode of reporting to the police to indicate this testing result according to this testing result that carries out the defect detection to current carbonization bamboo chip, according to the testing result of this suggestion, screens off the carbonization bamboo chip that has the defect in the current carbonization bamboo chip, can realize improving the automatic hourglass rate of examining that carries out the defect detection to the carbonization bamboo chip through the mode of reporting to the police, improves the quality guarantee of the carbonization bamboo chip after the defect detection to improve the quality of bamboo product.
Further, according to the scheme, after the detection process of the historical carbonized bamboo chips with the defects is completed, the image information of the historical carbonized bamboo chips with the defects can be obtained, the defect type labels corresponding to the image information of the historical carbonized bamboo chips with the defects are generated according to the defect types corresponding to the image information of the obtained historical carbonized bamboo chips with the defects, and the construction efficiency of establishing the defect detection model based on the image data of the carbonized bamboo chips can be effectively improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of an embodiment of a method for detecting defects in carbonized bamboo chips according to the present invention;
FIG. 2 is a schematic flow chart illustrating another embodiment of the method for detecting defects in carbonized bamboo chips according to the present invention;
FIG. 3 is a schematic structural diagram of an embodiment of a system for detecting defects in carbonized bamboo chips according to the present invention;
FIG. 4 is a schematic structural view of another embodiment of the carbonized bamboo chip defect detection system of the present invention;
fig. 5 is a schematic structural view of a carbonized bamboo chip defect detection system according to still another embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be noted that the following examples are only illustrative of the present invention, and do not limit the scope of the present invention. Similarly, the following examples are only some but not all examples of the present invention, and all other examples obtained by those skilled in the art without any inventive work are within the scope of the present invention.
The invention provides a method for detecting defects of carbonized bamboo chips, which can automatically detect the defects of the carbonized bamboo chips without manual work, improves the detection efficiency and the detection accuracy, and ensures the quality of the carbonized bamboo chips after the defects are detected, thereby improving the quality of bamboo products.
Referring to fig. 1, fig. 1 is a schematic flow chart of an embodiment of a method for detecting defects of carbonized bamboo chips according to the present invention. It should be noted that the method of the present invention is not limited to the flow sequence shown in fig. 1 if the results are substantially the same. As shown in fig. 1, the method comprises the steps of:
s101: collecting image data samples of historical carbonized bamboo chips with defects; the image data sample of the historical carbonized bamboo chips with the defects comprises image information of a plurality of historical carbonized bamboo chips with the defects and corresponding defect type labels.
Wherein, before the acquiring the image data sample of the historical carbonized bamboo strip with the defects, the method further comprises the following steps:
after the detection process of the historical carbonized bamboo chips with the defects is finished, acquiring image information of the historical carbonized bamboo chips with the defects;
and generating a defect type label corresponding to the image information of the historical carbonized bamboo chips with the defects according to the defect type corresponding to the acquired image information of the historical carbonized bamboo chips with the defects.
In this embodiment, the electronic device, such as a server, on which the carbonized bamboo chip defect detection method operates may collect image data samples of historical carbonized bamboo chips having defects from a terminal device with which the inspector logs in by a wired connection manner or a wireless connection manner.
In the present embodiment, the terminal device may be various electronic terminals including but not limited to a smart phone, a tablet computer, a laptop portable computer, a desktop computer, and the like, which have a camera and various sensors including but not limited to light-sensitive, distance, gravity, acceleration, magnetic induction, and the like.
In this embodiment, the electronic device may be a server providing various services, for example, a backend login server providing support for an image data login interface of the carbonized bamboo chips displayed on the terminal device, and the backend login server may analyze and perform processing on image data of the historical carbonized bamboo chips, image data of the current carbonized bamboo chips, and the like, and feed back a processing result, for example, suggestion information recommended to a detector for reference, to the terminal device.
In this embodiment, the examiner may use the terminal device to interact with an electronic device, such as a server, through a network to receive or send a message or the like. The terminal device can be provided with various client applications needing to verify the information of the detector, such as a carbonized bamboo strip application, an instant messaging tool, a mailbox client, carbonized bamboo strip platform software and the like.
S102: and establishing a defect detection model based on the image data of the carbonized bamboo chips according to the acquired image data samples of the historical carbonized bamboo chips with the defects.
Wherein, the establishing of the defect detection model based on the image data of the carbonized bamboo chips according to the collected image data samples of the historical carbonized bamboo chips with defects may include:
acquiring image information of a plurality of historical carbonized bamboo chips with defects and corresponding defect type labels in the acquired image data samples of the historical carbonized bamboo chips with the defects;
dividing image information of a plurality of historical carbonized bamboo chips with defects and corresponding defect type labels into N sections in the acquired image data sample of the historical carbonized bamboo chips with the defects; wherein N is a natural number greater than 1;
extracting image information of the plurality of historical carbonized bamboo chips with the defects after being divided into N sections and time weighting characteristics of corresponding defect type labels through a convolutional neural network;
obtaining image information of a plurality of historical carbonized bamboo chips which are divided into N sections and have defects and multi-scale characteristics of corresponding defect type labels according to the extracted time weighting characteristics;
fusing the image information of a plurality of historical carbonized bamboo chips with defects in the obtained image data samples of the N sections of historical carbonized bamboo chips with the defects and the multi-scale characteristics of the corresponding defect type labels, and calculating a prediction score;
obtaining a final classification of the collected historical carbonized bamboo chip image data samples with defects according to the calculated prediction score;
obtaining training characteristics of the image data samples related to the collected historical carbonized bamboo chips with the defects according to the obtained classification of the image data samples related to the collected historical carbonized bamboo chips with the defects;
and performing model training according to the obtained training characteristics of the acquired image data sample associated with the acquired historical carbonized bamboo chips with the defects, and establishing a defect detection model based on the image data of the carbonized bamboo chips.
In the present embodiment, the convolutional neural network is a kind of feedforward neural network that includes convolutional calculation and has a deep structure, and is one of the representative algorithms of deep learning.
In this embodiment, the convolutional neural network may include: at least one three-dimensional convolutional layer, at least one three-dimensional pooling layer, at least one fully-connected layer, and the like.
S103: and detecting the defects of the current carbonized bamboo chips according to the established defect detection model based on the image data of the carbonized bamboo chips.
The defect detection of the current carbonized bamboo chip according to the established defect detection model based on the image data of the carbonized bamboo chip may include:
and matching the training characteristics of the current carbonized bamboo chip image information from the established defect detection model based on the image data of the carbonized bamboo chips according to the established defect detection model based on the image data of the carbonized bamboo chips, and performing defect detection on the current carbonized bamboo chip image information by adopting a mode of training the current carbonized bamboo chip image information by adopting the matched training characteristics.
In this embodiment, the current carbonized bamboo chip image information may be image information of a current target carbonized bamboo chip, and the present invention is not limited thereto.
S104: and screening the carbonized bamboo chips with the defects in the current carbonized bamboo chips according to the detection result of the defect detection on the current carbonized bamboo chips.
Wherein, should screen the carbonization bamboo chip that has the defect in the present carbonization bamboo chip according to this detection result of carrying out the defect detection to current carbonization bamboo chip, can include:
and prompting the detection result in an alarm mode according to the detection result of the defect detection of the current carbonized bamboo chips, and screening the carbonized bamboo chips with the defects in the current carbonized bamboo chips according to the prompted detection result.
It can be found that, in this embodiment, an image data sample of a history carbonized bamboo chip with defects may be collected, where the image data sample of the history carbonized bamboo chip with defects includes image information of a plurality of history carbonized bamboo chips with defects and corresponding defect type labels, and a defect detection model based on the image data of the acquired history carbonized bamboo chips with defects is established according to the image data sample of the history carbonized bamboo chips with defects, and a defect detection is performed on a current carbonized bamboo chip according to the defect detection model based on the image data of the carbonized bamboo chip, and a carbonized bamboo chip with defects in the current carbonized bamboo chip is screened out according to a detection result of the defect detection on the current carbonized bamboo chip, so that the defect detection on the carbonized bamboo chip can be automatically performed without manual work, and the detection efficiency and the detection accuracy are improved, the quality of the carbonized bamboo chips after the defect detection can be guaranteed, so that the quality of the bamboo products is improved.
Further, in this embodiment, the image information of the plurality of history carbonized bamboo chips with defects and the corresponding defect type labels in the image data samples of the history carbonized bamboo chips with defects may be obtained according to the collected image data samples of the history carbonized bamboo chips with defects, and the image information of the plurality of history carbonized bamboo chips with defects and the corresponding defect type labels in the obtained image data samples of the history carbonized bamboo chips with defects are divided into N segments, where N is a natural number greater than 1, and the time weighting characteristics of the image information of the plurality of history carbonized bamboo chips with defects and the corresponding defect type labels after the N segments are extracted through a convolutional neural network, and the multi-scale characteristics of the image information of the plurality of history carbonized bamboo chips with defects and the corresponding defect type labels after the N segments are obtained according to the extracted time weighting characteristics, and fusing the image information of a plurality of historical carbonized bamboo chips with defects in the obtained image data samples of the N sections of historical carbonized bamboo chips with defects and the multi-scale characteristics of the corresponding defect type labels to calculate a prediction score, and obtaining a final classification of the collected image data samples related to the historical carbonized bamboo chips with defects according to the calculated prediction score, and obtaining training characteristics of the image data samples related to the collected historical carbonized bamboo chips with the defects according to the obtained classification of the image data samples related to the collected historical carbonized bamboo chips with the defects, and performing model training according to the obtained training characteristics of the acquired image data sample associated with the acquired historical carbonized bamboo chips with the defects, and establishing a defect detection model based on the image data of the carbonized bamboo chips, so that the modeling effect and accuracy of establishing the defect detection model based on the image data of the carbonized bamboo chips can be improved.
Further, in this embodiment, according to the established defect detection model based on the image data of the carbonized bamboo chips, the training features of the current image information of the carbonized bamboo chips may be matched from the established defect detection model based on the image data of the carbonized bamboo chips, and the defect detection may be performed on the current image information of the carbonized bamboo chips in a manner of training the current image information of the carbonized bamboo chips by using the matched training features, so as to effectively improve the detection efficiency and accuracy of the detection result of the current image information of the carbonized bamboo chips.
Further, in this embodiment, can adopt the mode of alarm to indicate this testing result according to this testing result of carrying out the defect detection to current carbonization bamboo chip, according to the testing result of this suggestion, screen the carbonization bamboo chip that has the defect in the current carbonization bamboo chip, can realize improving automatic hourglass rate of examining that carries out the defect detection to carbonization bamboo chip through the mode of alarm to improve the quality guarantee of carbonization bamboo chip after the defect detection, thereby improve the quality of bamboo product.
Referring to fig. 2, fig. 2 is a schematic flow chart of another embodiment of the method for detecting defects of carbonized bamboo chips according to the present invention. In this embodiment, the method includes the steps of:
s201: and after the detection process of the historical carbonized bamboo chips with the defects is finished, acquiring the image information of the historical carbonized bamboo chips with the defects, and generating a defect type label corresponding to the image information of the historical carbonized bamboo chips with the defects according to the defect type corresponding to the acquired image information of the historical carbonized bamboo chips with the defects.
S202: collecting image data samples of historical carbonized bamboo chips with defects; the image data sample of the historical carbonized bamboo chips with the defects comprises image information of a plurality of historical carbonized bamboo chips with the defects and corresponding defect type labels.
As described above in S101, further description is omitted here.
S203: and establishing a defect detection model based on the image data of the carbonized bamboo chips according to the acquired image data samples of the historical carbonized bamboo chips with the defects.
As described above in S102, further description is omitted here.
S204: and detecting the defects of the current carbonized bamboo chips according to the established defect detection model based on the image data of the carbonized bamboo chips.
As described above in S103, which is not described herein.
S205: and screening the carbonized bamboo chips with the defects in the current carbonized bamboo chips according to the detection result of the defect detection on the current carbonized bamboo chips.
As described above in S104, and will not be described herein.
It can be found that, in this embodiment, after the detection process of the history carbonized bamboo chips with the defects is completed, the image information of the history carbonized bamboo chips with the defects may be acquired, and the defect type labels corresponding to the image information of the history carbonized bamboo chips with the defects may be generated according to the defect types corresponding to the image information of the history carbonized bamboo chips with the defects, so that the efficiency of constructing the defect detection model based on the image data of the carbonized bamboo chips may be effectively improved.
The invention also provides a carbonized bamboo chip defect detection system, which can automatically detect the defects of the carbonized bamboo chips without manual work, improves the detection efficiency and the detection accuracy, and ensures the quality of the carbonized bamboo chips after the defect detection, thereby improving the quality of bamboo products.
Referring to fig. 3, fig. 3 is a schematic structural diagram of an embodiment of a carbonized bamboo chip defect detection system of the present invention. In this embodiment, the carbonized bamboo chip defect detection system 30 includes a collecting unit 31, an establishing unit 32, a detecting unit 33 and a screening unit 34.
The acquisition unit 31 is used for acquiring image data samples of the historical carbonized bamboo chips with defects; the image data sample of the historical carbonized bamboo chips with the defects comprises image information of a plurality of historical carbonized bamboo chips with the defects and corresponding defect type labels.
The establishing unit 32 is configured to establish a defect detection model based on the image data of the carbonized bamboo chips according to the collected image data samples of the historical carbonized bamboo chips with defects.
The detecting unit 33 is configured to perform defect detection on the current carbonized bamboo chips according to the established defect detection model based on the image data of the carbonized bamboo chips.
The screening unit 34 is configured to screen out the carbonized bamboo strips with defects from the current carbonized bamboo strips according to the detection result of the defect detection on the current carbonized bamboo strips.
Optionally, the establishing unit 32 may be specifically configured to:
acquiring image information of a plurality of historical carbonized bamboo chips with defects and corresponding defect type labels in the acquired image data samples of the historical carbonized bamboo chips with the defects;
dividing image information of a plurality of historical carbonized bamboo chips with defects and corresponding defect type labels into N sections in the acquired image data sample of the historical carbonized bamboo chips with the defects; wherein N is a natural number greater than 1;
extracting image information of the plurality of historical carbonized bamboo chips with the defects after being divided into N sections and time weighting characteristics of corresponding defect type labels through a convolutional neural network;
obtaining image information of a plurality of historical carbonized bamboo chips which are divided into N sections and have defects and multi-scale characteristics of corresponding defect type labels according to the extracted time weighting characteristics;
fusing the image information of a plurality of historical carbonized bamboo chips with defects in the obtained image data samples of the N sections of historical carbonized bamboo chips with the defects and the multi-scale characteristics of the corresponding defect type labels, and calculating a prediction score;
obtaining a final classification of the collected historical carbonized bamboo chip image data samples with defects according to the calculated prediction score;
obtaining training characteristics of the image data samples related to the collected historical carbonized bamboo chips with the defects according to the obtained classification of the image data samples related to the collected historical carbonized bamboo chips with the defects;
and performing model training according to the obtained training characteristics of the acquired image data sample associated with the acquired historical carbonized bamboo chips with the defects, and establishing a defect detection model based on the image data of the carbonized bamboo chips.
Optionally, the detecting unit 33 may be specifically configured to:
and matching the training characteristics of the current carbonized bamboo chip image information from the established defect detection model based on the image data of the carbonized bamboo chips according to the established defect detection model based on the image data of the carbonized bamboo chips, and performing defect detection on the current carbonized bamboo chip image information by adopting a mode of training the current carbonized bamboo chip image information by adopting the matched training characteristics.
Optionally, the screening unit 34 may be specifically configured to:
and prompting the detection result in an alarm mode according to the detection result of the defect detection of the current carbonized bamboo chips, and screening the carbonized bamboo chips with the defects in the current carbonized bamboo chips according to the prompted detection result.
Referring to fig. 4, fig. 4 is a schematic structural view of another embodiment of the carbonized bamboo chip defect detection system of the present invention. Different from the previous embodiment, the system 40 for detecting defects of carbonized bamboo chips in this embodiment further includes: the unit 41 is generated.
The generating unit 41 is configured to obtain the image information of the history carbonized bamboo chips with defects after the detection process of the history carbonized bamboo chips with defects is completed, and generate the defect type labels corresponding to the image information of the history carbonized bamboo chips with defects according to the defect types corresponding to the obtained image information of the history carbonized bamboo chips with defects.
Referring to fig. 5, fig. 5 is a schematic structural view of another embodiment of the carbonized bamboo chip defect detection system of the present invention. Each unit module of the carbonized bamboo chip defect detection system can respectively execute the corresponding steps in the method embodiment. For a detailed description of the above method, please refer to the above method, which is not repeated herein.
In this embodiment, the carbonized bamboo chip defect detection system includes: a processor 51, a memory 52 coupled to the processor 51, a detector 53, a filter 54.
The processor 51 is configured to obtain image information of a history carbonized bamboo chip with a defect after a detection process of the history carbonized bamboo chip with the defect is completed, generate a defect type label corresponding to the image information of the history carbonized bamboo chip with the defect according to a defect type corresponding to the obtained image information of the history carbonized bamboo chip with the defect, acquire an image data sample of the history carbonized bamboo chip with the defect, wherein the image data sample of the history carbonized bamboo chip with the defect comprises image information of a plurality of history carbonized bamboo chips with the defect and corresponding defect type labels, and establish a defect detection model based on the image data of the carbonized bamboo chips according to the acquired image data sample of the history carbonized bamboo chips with the defect.
The memory 52 is used for storing an operating system, instructions executed by the processor 51, and the like.
The detector 53 is configured to perform defect detection on the current carbonized bamboo chips according to the established defect detection model based on the image data of the carbonized bamboo chips.
The screening device 54 is configured to screen out the carbonized bamboo strips with defects from the current carbonized bamboo strips according to the detection result of the defect detection on the current carbonized bamboo strips.
Optionally, the processor 51 may be specifically configured to:
acquiring image information of a plurality of historical carbonized bamboo chips with defects and corresponding defect type labels in the acquired image data samples of the historical carbonized bamboo chips with the defects;
dividing image information of a plurality of historical carbonized bamboo chips with defects and corresponding defect type labels into N sections in the acquired image data sample of the historical carbonized bamboo chips with the defects; wherein N is a natural number greater than 1;
extracting image information of the plurality of historical carbonized bamboo chips with the defects after being divided into N sections and time weighting characteristics of corresponding defect type labels through a convolutional neural network;
obtaining image information of a plurality of historical carbonized bamboo chips which are divided into N sections and have defects and multi-scale characteristics of corresponding defect type labels according to the extracted time weighting characteristics;
fusing the image information of a plurality of historical carbonized bamboo chips with defects in the obtained image data samples of the N sections of historical carbonized bamboo chips with the defects and the multi-scale characteristics of the corresponding defect type labels, and calculating a prediction score;
obtaining a final classification of the collected historical carbonized bamboo chip image data samples with defects according to the calculated prediction score;
obtaining training characteristics of the image data samples related to the collected historical carbonized bamboo chips with the defects according to the obtained classification of the image data samples related to the collected historical carbonized bamboo chips with the defects;
and performing model training according to the obtained training characteristics of the acquired image data sample associated with the acquired historical carbonized bamboo chips with the defects, and establishing a defect detection model based on the image data of the carbonized bamboo chips.
Optionally, the detector 53 may be specifically configured to:
and matching the training characteristics of the current carbonized bamboo chip image information from the established defect detection model based on the image data of the carbonized bamboo chips according to the established defect detection model based on the image data of the carbonized bamboo chips, and performing defect detection on the current carbonized bamboo chip image information by adopting a mode of training the current carbonized bamboo chip image information by adopting the matched training characteristics.
Optionally, the filter 54 may be specifically configured to:
and prompting the detection result in an alarm mode according to the detection result of the defect detection of the current carbonized bamboo chips, and screening the carbonized bamboo chips with the defects in the current carbonized bamboo chips according to the prompted detection result.
It can be found that, according to the above scheme, the image data sample of the historical carbonized bamboo chips with defects can be collected, wherein the image data sample of the historical carbonized bamboo chips with defects comprises the image information of a plurality of historical carbonized bamboo chips with defects and corresponding defect type labels, and a defect detection model based on the image data of the carbonized bamboo chips is established according to the collected image data sample of the historical carbonized bamboo chips with defects, and the current carbonized bamboo chips are subjected to defect detection according to the established defect detection model based on the image data of the carbonized bamboo chips, and the carbonized bamboo chips with defects in the current carbonized bamboo chips are screened according to the detection result of the defect detection of the current carbonized bamboo chips, so that the defect detection of the carbonized bamboo chips can be automatically carried out without manual work, and the detection efficiency and the detection accuracy are improved, the quality of the carbonized bamboo chips after the defect detection can be guaranteed, so that the quality of the bamboo products is improved.
Further, according to the above scheme, the image information of a plurality of history carbonized bamboo chips with defects and corresponding defect type labels in the image data samples of the history carbonized bamboo chips with defects are obtained according to the collected image data samples of the history carbonized bamboo chips with defects, the image information of the history carbonized bamboo chips with defects and corresponding defect type labels in the obtained image data samples of the history carbonized bamboo chips with defects are divided into N sections, wherein N is a natural number greater than 1, the time weighting characteristics of the image information of the history carbonized bamboo chips with defects and corresponding defect type labels after the N sections are extracted through a convolutional neural network, and the multi-scale characteristics of the image information of the history carbonized bamboo chips with defects and corresponding defect type labels after the N sections are obtained according to the extracted time weighting characteristics, and fusing the image information of a plurality of historical carbonized bamboo chips with defects in the obtained image data samples of the N sections of historical carbonized bamboo chips with defects and the multi-scale characteristics of the corresponding defect type labels to calculate a prediction score, and obtaining a final classification of the collected image data samples related to the historical carbonized bamboo chips with defects according to the calculated prediction score, and obtaining training characteristics of the image data samples related to the collected historical carbonized bamboo chips with the defects according to the obtained classification of the image data samples related to the collected historical carbonized bamboo chips with the defects, and performing model training according to the obtained training characteristics of the acquired image data sample associated with the acquired historical carbonized bamboo chips with the defects, and establishing a defect detection model based on the image data of the carbonized bamboo chips, so that the modeling effect and accuracy of establishing the defect detection model based on the image data of the carbonized bamboo chips can be improved.
Further, according to the above scheme, the training characteristics of the current carbonized bamboo chip image information can be matched from the established defect detection model based on the image data of the carbonized bamboo chips, the defect detection can be performed on the current carbonized bamboo chip image information by adopting a mode of training the current carbonized bamboo chip image information by adopting the matched training characteristics, and the detection efficiency and accuracy of the detection result of the current carbonized bamboo chip image information can be effectively improved.
Further, above scheme can adopt the mode of reporting to the police to indicate this testing result according to this testing result that carries out the defect detection to current carbonization bamboo chip, according to the testing result of this suggestion, screens off the carbonization bamboo chip that has the defect in the current carbonization bamboo chip, can realize improving the automatic hourglass rate of examining that carries out the defect detection to the carbonization bamboo chip through the mode of reporting to the police, improves the quality guarantee of the carbonization bamboo chip after the defect detection to improve the quality of bamboo product.
Further, according to the scheme, after the detection process of the historical carbonized bamboo chips with the defects is completed, the image information of the historical carbonized bamboo chips with the defects can be obtained, the defect type labels corresponding to the image information of the historical carbonized bamboo chips with the defects are generated according to the defect types corresponding to the image information of the obtained historical carbonized bamboo chips with the defects, and the construction efficiency of establishing the defect detection model based on the image data of the carbonized bamboo chips can be effectively improved.
In the several embodiments provided in the present invention, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of a module or a unit is merely a logical division, and an actual implementation may have another division, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be substantially or partially implemented in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, a network device, or the like) or a processor (processor) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only a part of the embodiments of the present invention, and not intended to limit the scope of the present invention, and all equivalent devices or equivalent processes performed by the present invention through the contents of the specification and the drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (7)
1. A carbonized bamboo chip defect detection method is characterized by comprising the following steps:
collecting image data samples of historical carbonized bamboo chips with defects; the image data sample of the historical carbonized bamboo chip with the defects comprises image information of a plurality of historical carbonized bamboo chips with the defects and corresponding defect type labels;
establishing a defect detection model based on the image data of the carbonized bamboo chips according to the acquired image data samples of the historical carbonized bamboo chips with defects;
detecting the defects of the current carbonized bamboo chips according to the established defect detection model based on the image data of the carbonized bamboo chips;
screening out the carbonized bamboo chips with defects in the current carbonized bamboo chips according to the detection result of the defect detection on the current carbonized bamboo chips;
the establishing of the defect detection model based on the image data of the carbonized bamboo chips according to the collected image data samples of the historical carbonized bamboo chips with defects comprises the following steps:
acquiring image information of a plurality of historical carbonized bamboo chips with defects and corresponding defect type labels in the acquired image data samples of the historical carbonized bamboo chips with the defects;
dividing image information of a plurality of historical carbonized bamboo strips with defects and corresponding defect type labels into N sections in the obtained image data sample of the historical carbonized bamboo strips with defects; wherein N is a natural number greater than 1;
extracting the image information of the plurality of historical carbonized bamboo chips with the defects after being divided into N sections and the time weighting characteristics of the corresponding defect type labels through a convolutional neural network;
obtaining image information of the plurality of historical carbonized bamboo chips which are divided into N sections and have the defects and multi-scale characteristics of corresponding defect type labels according to the extracted time weighting characteristics;
fusing image information of a plurality of historical carbonized bamboo chips with defects in the obtained image data samples of the N sections of historical carbonized bamboo chips with the defects and the multi-scale characteristics of corresponding defect type labels, and calculating a prediction score;
obtaining the final classification of the collected historical carbonized bamboo chip image data samples with defects according to the calculated prediction score;
obtaining training characteristics of the image data samples related to the collected historical carbonized bamboo chips with the defects according to the obtained classification of the image data samples related to the collected historical carbonized bamboo chips with the defects;
and performing model training according to the obtained training characteristics of the acquired image data samples related to the acquired historical carbonized bamboo chips with the defects, and establishing a defect detection model based on the image data of the carbonized bamboo chips.
2. The carbonized bamboo chip defect detection method of claim 1, wherein the defect detection of the current carbonized bamboo chip according to the established defect detection model based on the image data of the carbonized bamboo chip comprises:
and matching the training characteristics of the current carbonized bamboo chip image information from the established defect detection model based on the image data of the carbonized bamboo chips according to the established defect detection model based on the image data of the carbonized bamboo chips, and performing defect detection on the current carbonized bamboo chip image information by adopting a mode of training the current carbonized bamboo chip image information by adopting the matched training characteristics.
3. The method for detecting defects of carbonized bamboo chips as claimed in claim 1, wherein said screening out the carbonized bamboo chips having defects from the current carbonized bamboo chips according to the detection result of the defect detection of the current carbonized bamboo chips comprises:
and prompting the detection result in an alarm mode according to the detection result of the defect detection of the current carbonized bamboo chips, and screening the carbonized bamboo chips with the defects in the current carbonized bamboo chips according to the prompted detection result.
4. The carbonized bamboo chip defect detection method of claim 1, wherein before the collecting the image data samples of the historical carbonized bamboo chips having the defects, further comprising: after the detection process of the historical carbonized bamboo chips with the defects is completed, the image information of the historical carbonized bamboo chips with the defects is obtained, and the defect type labels corresponding to the image information of the historical carbonized bamboo chips with the defects are generated according to the defect types corresponding to the obtained image information of the historical carbonized bamboo chips with the defects.
5. A carbonized bamboo chip defect detection system is characterized by comprising:
the device comprises an acquisition unit, an establishing unit, a detection unit and a screening unit;
the acquisition unit is used for acquiring image data samples of the historical carbonized bamboo chips with defects; the image data sample of the historical carbonized bamboo chip with the defects comprises image information of a plurality of historical carbonized bamboo chips with the defects and corresponding defect type labels;
the establishing unit is used for establishing a defect detection model based on the image data of the carbonized bamboo chips according to the collected image data samples of the historical carbonized bamboo chips with defects; the detection unit is used for detecting the defects of the current carbonized bamboo chips according to the established defect detection model based on the image data of the carbonized bamboo chips;
the screening unit is used for screening the carbonized bamboo chips with defects in the current carbonized bamboo chips according to the detection result of the defect detection on the current carbonized bamboo chips;
the established defect detection model based on the image data of the carbonized bamboo chips matches the training characteristics of the current image information of the carbonized bamboo chips from the established defect detection model based on the image data of the carbonized bamboo chips, and the defect detection is carried out on the current image information of the carbonized bamboo chips by adopting the mode of training the current image information of the carbonized bamboo chips by the matched training characteristics;
acquiring image information of a plurality of historical carbonized bamboo chips with defects and corresponding defect type labels in the acquired image data samples of the historical carbonized bamboo chips with the defects;
dividing image information of a plurality of historical carbonized bamboo strips with defects and corresponding defect type labels into N sections in the obtained image data sample of the historical carbonized bamboo strips with defects; wherein N is a natural number greater than 1;
extracting the image information of the plurality of historical carbonized bamboo chips with the defects after being divided into N sections and the time weighting characteristics of the corresponding defect type labels through a convolutional neural network;
obtaining image information of the plurality of historical carbonized bamboo chips which are divided into N sections and have the defects and multi-scale characteristics of corresponding defect type labels according to the extracted time weighting characteristics;
fusing image information of a plurality of historical carbonized bamboo chips with defects in the obtained image data samples of the N sections of historical carbonized bamboo chips with the defects and the multi-scale characteristics of corresponding defect type labels, and calculating a prediction score;
obtaining the final classification of the collected historical carbonized bamboo chip image data samples with defects according to the calculated prediction score;
obtaining training characteristics of the image data samples related to the collected historical carbonized bamboo chips with the defects according to the obtained classification of the image data samples related to the collected historical carbonized bamboo chips with the defects;
and performing model training according to the obtained training characteristics of the acquired image data samples related to the acquired historical carbonized bamboo chips with the defects, and establishing a defect detection model based on the image data of the carbonized bamboo chips.
6. The carbonized bamboo chip defect detection system of claim 5, wherein the screening unit is specifically configured to:
and prompting the detection result in an alarm mode according to the detection result of the defect detection of the current carbonized bamboo chips, and screening the carbonized bamboo chips with the defects in the current carbonized bamboo chips according to the prompted detection result.
7. The carbonized bamboo chip defect detection system of claim 5, further comprising:
and the generating unit is used for acquiring the image information of the historical carbonized bamboo chips with the defects after the detection process of the historical carbonized bamboo chips with the defects is completed, and generating the defect type labels corresponding to the image information of the historical carbonized bamboo chips with the defects according to the defect types corresponding to the acquired image information of the historical carbonized bamboo chips with the defects.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910079411.7A CN109886934B (en) | 2019-01-28 | 2019-01-28 | Carbonized bamboo chip defect detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910079411.7A CN109886934B (en) | 2019-01-28 | 2019-01-28 | Carbonized bamboo chip defect detection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109886934A CN109886934A (en) | 2019-06-14 |
| CN109886934B true CN109886934B (en) | 2020-12-18 |
Family
ID=66926945
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910079411.7A Active CN109886934B (en) | 2019-01-28 | 2019-01-28 | Carbonized bamboo chip defect detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109886934B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107256549A (en) * | 2017-06-06 | 2017-10-17 | 滁州市天达汽车部件有限公司 | A kind of bamboo strip defect detection method based on machine vision |
| CN108562589A (en) * | 2018-03-30 | 2018-09-21 | 慧泉智能科技（苏州）有限公司 | A method of magnetic circuit material surface defect is detected |
| CN108664989A (en) * | 2018-03-27 | 2018-10-16 | 北京达佳互联信息技术有限公司 | Image tag determines method, apparatus and terminal |
| CN109871455A (en) * | 2019-01-28 | 2019-06-11 | 厦门理工学院 | Be carbonized bamboo chip color separation method and system |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103954994B (en) * | 2014-04-17 | 2017-11-10 | 中国石油天然气集团公司 | Seismic signal Enhancement Method and device based on continuous wavelet transform |
| CN107564002A (en) * | 2017-09-14 | 2018-01-09 | 广东工业大学 | Plastic tube detection method of surface flaw, system and computer-readable recording medium |
| CN109064454A (en) * | 2018-07-12 | 2018-12-21 | 上海蝶鱼智能科技有限公司 | Product defects detection method and system |
| CN109242825A (en) * | 2018-07-26 | 2019-01-18 | 北京首钢自动化信息技术有限公司 | A kind of steel surface defect identification method and device based on depth learning technology |
-
2019
- 2019-01-28 CN CN201910079411.7A patent/CN109886934B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107256549A (en) * | 2017-06-06 | 2017-10-17 | 滁州市天达汽车部件有限公司 | A kind of bamboo strip defect detection method based on machine vision |
| CN108664989A (en) * | 2018-03-27 | 2018-10-16 | 北京达佳互联信息技术有限公司 | Image tag determines method, apparatus and terminal |
| CN108562589A (en) * | 2018-03-30 | 2018-09-21 | 慧泉智能科技（苏州）有限公司 | A method of magnetic circuit material surface defect is detected |
| CN109871455A (en) * | 2019-01-28 | 2019-06-11 | 厦门理工学院 | Be carbonized bamboo chip color separation method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109886934A (en) | 2019-06-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Grosjean et al. | Enumeration, measurement, and identification of net zooplankton samples using the ZOOSCAN digital imaging system | |
| CN108038843A (en) | A kind of method, apparatus and equipment for defects detection | |
| Clement et al. | The effect of call libraries and acoustic filters on the identification of bat echolocation | |
| CN111157698A (en) | Inversion method for obtaining total potassium content of black soil by using emissivity data | |
| Barbieri et al. | Alignment and proficiency of virgin olive oil sensory panels: The OLEUM approach | |
| Shao et al. | Feasibility study on hyperspectral LiDAR for ancient Huizhou-style architecture preservation | |
| Mann et al. | Automatic flower detection and phenology monitoring using time‐lapse cameras and deep learning | |
| CN109254959A (en) | A kind of data evaluation method, apparatus, terminal device and readable storage medium storing program for executing | |
| CN102998350B (en) | Method for distinguishing edible oil from swill-cooked dirty oil by electrochemical fingerprints | |
| CN105223140A (en) | The method for quickly identifying of homology material | |
| Rodríguez et al. | Fast and efficient food quality control using electronic noses: adulteration detection achieved by unfolded cluster analysis coupled with time-window selection | |
| CN109871455B (en) | Color separation method and system for carbonized bamboo chips | |
| Plankenbühler et al. | Image-based model for assessment of wood chip quality and mixture ratios | |
| Gislason et al. | Comparison between automated analysis of zooplankton using ZooImage and traditional methodology | |
| CN109886934B (en) | Carbonized bamboo chip defect detection method and system | |
| Silva et al. | Computer vision-based wood identification: A review | |
| Kaya et al. | An automatic identification method for the comparison of plant and honey pollen based on GLCM texture features and artificial neural network | |
| Zhang et al. | Research on the authenticity of mutton based on machine vision technology | |
| Lagorce‐Tachon et al. | Contribution of image processing for analyzing the cellular structure of cork | |
| CN108765391A (en) | A kind of plate glass foreign matter image analysis methods based on deep learning | |
| Wang | Recent advances in nondestructive evaluation of wood: in-forest wood quality assessments | |
| Ma et al. | Detection of defects in geomembranes using quasi-active infrared thermography | |
| Baigts-Allende et al. | Monitoring of the dehydration process of apple snacks with visual feature extraction and image processing techniques | |
| CN111898314B (en) | Lake water parameter inspection method and device, electronic equipment and storage medium | |
| Grandremy et al. | The ZooScan and the ZooCAM zooplankton imaging systems are intercomparable: A benchmark on the Bay of Biscay zooplankton |
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 | ||
| GR01 | Patent grant |