CN110171140A - A kind of 3D biometric print machine of the control printing distance based on image procossing - Google Patents
A kind of 3D biometric print machine of the control printing distance based on image procossing Download PDFInfo
- Publication number
- CN110171140A CN110171140A CN201910390764.9A CN201910390764A CN110171140A CN 110171140 A CN110171140 A CN 110171140A CN 201910390764 A CN201910390764 A CN 201910390764A CN 110171140 A CN110171140 A CN 110171140A
- Authority
- CN
- China
- Prior art keywords
- image
- printing
- spray head
- distance
- layer
- 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.)
- Pending
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
- B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
- B29C64/00—Additive manufacturing, i.e. manufacturing of three-dimensional [3D] objects by additive deposition, additive agglomeration or additive layering, e.g. by 3D printing, stereolithography or selective laser sintering
- B29C64/30—Auxiliary operations or equipment
- B29C64/386—Data acquisition or data processing for additive manufacturing
- B29C64/393—Data acquisition or data processing for additive manufacturing for controlling or regulating additive manufacturing processes
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B33—ADDITIVE MANUFACTURING TECHNOLOGY
- B33Y—ADDITIVE MANUFACTURING, i.e. MANUFACTURING OF THREE-DIMENSIONAL [3-D] OBJECTS BY ADDITIVE DEPOSITION, ADDITIVE AGGLOMERATION OR ADDITIVE LAYERING, e.g. BY 3-D PRINTING, STEREOLITHOGRAPHY OR SELECTIVE LASER SINTERING
- B33Y50/00—Data acquisition or data processing for additive manufacturing
- B33Y50/02—Data acquisition or data processing for additive manufacturing for controlling or regulating additive manufacturing processes
Abstract
The 3D biometric print machine for the control printing distance based on image procossing that the invention discloses a kind of, including PC host computer and 3D printing slave computer, the PC host computer includes control module, image processing module, display module, the 3D printing slave computer includes printer body, and it is set to stepper motor, guide rail, spray head pedestal, spray head, forming workbench and camera in printer body, the camera is connect with image processing module；Image processing module handles the image of acquisition, the distance between the destination organization for obtaining spray head and printing, and sends the distance to upper computer software processing；The data real-time display that PC upper computer software will receive, and 3D printing slave computer is controlled, adjustment printing distance.The printing function is maintained at the distance between spray head and biological tissue between 200 to 300 microns, the problems such as to overcome printing precision not high.
Description
Technical field
A kind of 3D biometric print machine of the control printing distance based on image procossing of the present invention, belongs to bioengineered tissue art
Field.
Background technique
3D printing, that is, rapid prototyping technology one kind, it is one kind based on digital model file, with powdered gold
Belong to or the adhesive materials such as plastics, constructs the technology of object by layer-by-layer printing.Organizational project merged engineering science,
The subjects such as life science and material science, the process formed by imitating human tissue organ, can construct and cultivate in vitro
Biologically active structural body.Among these, 3D printing technique is tied because multiple material can be used to form the three-dimensional of any complexity for it
Structure becomes the most strong research means of field of tissue engineering technology.The principle of 3D printing technique is exactly Layered manufacturing, is accumulated layer by layer.
3D biometric print technology is gradually developed based on 3D printing technique.The technology is to use Computer-aided
Additive Manufacturing technology accurately controls biomaterial, biological cell, growth factor, in whole 3D structure
Position, in conjunction with, utilize mutually, with bioactivity, and be able to achieve it is close with destination organization or biologic-organ, it is identical,
Even more superior function.The realization of the technology depends on 3D biometric print machine.3D biometric print and traditional 3D printing technique
Still it makes a big difference, other than the core technology of traditional 3D printing is utilized, the manufacturing process of all 3D biometric prints
The standard of biology is had to comply with, cell activity, function of organization should be can guarantee, also to meet Medicine standard.Currently, raw in 3D
In object printing equipment, there is the low technological deficiencies of cell printing precision.Cause the technical reason of the defect very much, one of them
Important influence factor is spray head and the distance between the biological tissue printed, if printing precision is lower apart from excessive,
It is easy error, and then influences print speed；If spray head may stick together with the biological tissue printed, root apart from too small
Originally it can not print.And there are no the technologies being efficiently modified for this defect currently on the market.
Summary of the invention
The present invention is in order to overcome the deficiencies of the prior art, it is therefore an objective to provide a kind of control printing distance based on image procossing
3D biometric print machine, the printing function are maintained at the distance between spray head and biological tissue between 200 to 300 microns, with gram
Take the problems such as printing precision is not high.
The invention is realized by the following technical scheme:
A kind of 3D biometric print machine of the control printing distance based on image procossing, including PC host computer and 3D printing bottom
Machine, the PC host computer are carried out data transmission with 3D printing slave computer by Ethernet interface；
The PC host computer includes control module, image processing module, display module, and user is realized by upper computer software
The various parameters of 3D printing are arranged, and the various parameters that 3D printing slave computer is run are shown on the display module；User is certainly
The distance between biological tissue row setting printing head and printed, or using the default setting of 3D printing slave computer, control
Printing head is 200 to 300 microns with the distance between the biological tissue printed；
The 3D printing slave computer includes printer body, and the stepper motor, the guide rail, spray that are set in printer body
Head pedestal, spray head, forming workbench and camera, the printer body vertical direction are arranged guide rail, install on the guide rail
Spray head is arranged in stepper motor and spray head pedestal, the spray head base bottom, and the spray head is directed at forming worktable, the camera
It is mounted on the top on the right side of the printer body, the camera is connect with image processing module, for obtaining spray head in real time
Locate image, and sends image processing module to；
Image processing module handles the image of acquisition, obtain spray head between the destination organization that prints away from
From, and send the distance to upper computer software processing；PC upper computer software is real by the data received from image processing module
When display on the display module, when the distance deviate from user setting, control 3D printing slave computer, the distance is adjusted automatically
It is whole to 200 to 300 microns.
The image processing process of described image processing module includes the following steps:
1) high-definition camera focal length is adjusted, its picture is made to be shown as the most clear；
2) gray processing processing is carried out to image；
3) to gray processing treated image segmentation, only retain the figure of spray head and forming workbench and the biological tissue on platform
Picture, remaining image are divided away；
4) image after segmentation is normalized；
5) edge extracting is carried out using BP neural network:
It is extracted using 3 layers of neural network, the three-layer neural network is respectively input layer, output layer, middle layer, institute
It states input layer and corresponds to original image, output layer corresponding edge image, middle layer neuron takes activation primitive Sigmoid function g
(z):
Wherein, z is the product that this layer of weight θ matrix and upper one layer of node activate value matrix, z=θTX, θ are neuron
Weight matrix, θTFor the transposition of θ matrix, the input value matrix that x is upper one layer；
For middle layer neuron number under the premise of guaranteeing image quality requirements, selection makes cost function J (θ) fitting degree
Highest function:
Wherein, m is training sample number, and K is the number of output, and k indicates k-th of input layer output, and L is neural net layer
Number, l are l layers of neural network, and λ indicates that iotazation constant, i are i-th of training sample, ykIt is exported for k-th of sample, yk (i)For
K-th of sample output corresponding with i-th of training sample, h (x(i)) it is hypothesis function corresponding to i-th of training sample, Sl
For l layers of neuron number, θji (l)For the weight of value corresponding to j-th of feature of i-th of training sample in l layers.
6) average value is calculated to the gray value of whole image, is then made with the value in the neighborhood of the average value or the average value
For threshold value, binary conversion treatment is then carried out, grayscale image is converted into black and white binary image, obtains clearly edge wheel profile；
7) the distance between the biological tissue for calculating spray head and printing:
Spray head point M, the contact point of spinneret and the biological tissue printed are found in image after binary conversion treatment
N, two endpoints D, the E on the longer side of forming workbench, then；
Then coordinate system is established on image after treatment, spray head can be obtained in image between the biological tissue printed
Image pixel distance LMNWith the image pixel distance L of forming workbench long side in imageDEIt is respectively as follows:
Wherein, xM, yMIndicate the coordinate of spray head M point, xN, yNIndicate spinneret and the contact point N's for the biological tissue printed
Coordinate；
Wherein, xD, yDIndicate the coordinate of forming workbench long side side endpoint, xE, yEIndicate that forming workbench long side is another
The coordinate of side point；
Further, LBCIndicate the long back gauge of the actual forming workbench of printer,
Then under a proportional relationship, it can obtain:
Due to LMN, LDE, LBCAll it is known quantity, acquires the actual spray head of 3D biometric print machine to the biological tissue printed
The distance between LAO；
Host computer is by LAOIt shows and is adjusted according to this result, control 3D printing slave computer, by spray head and beat
The distance between destination organization printed off is maintained between 200 to 300 microns.
Compared with prior art, the invention has the following beneficial effects:
It is of the present invention it is a kind of based on image procossing can distance between adjust automatically spray head and the biological tissue printed
3D biometric print machine.Can by image procossing obtain spray head between the biological tissue printed at a distance from, make distance keep
In OK range, so as to improve printing precision；Using the technological means of automatic adjustment in print procedure, 3D biology is improved
The degree of automation of printer；Due to improving precision and the degree of automation, the probability of printing error is reduced, is also indirectly mentioned
High print speed.
Detailed description of the invention
Fig. 1 is 3D printing slave computer structural schematic diagram；
Fig. 2 is printer work flow diagram of the present invention.
In figure, stepper motor 1, printer body 2, guide rail 3, spray head pedestal 4, spray head 5, forming workbench 6, camera 7.
Specific embodiment
The present invention is described in further detail combined with specific embodiments below, but protection scope of the present invention is not
Be limited to these embodiments, it is all without departing substantially from the change of present inventive concept or equivalent substitute be included in protection scope of the present invention it
It is interior.
A kind of 3D biometric print machine of the control printing distance based on image procossing, including PC host computer and 3D printing bottom
Machine, the PC host computer are carried out data transmission with 3D printing slave computer by Ethernet interface；
The PC host computer includes control module, image processing module, display module, and user is realized by upper computer software
The various parameters of 3D printing are arranged, and the various parameters that 3D printing slave computer is run are shown on the display module；User is certainly
The distance between biological tissue row setting printing head and printed, or using the default setting of 3D printing slave computer, control
Printing head is 200 to 300 microns with the distance between the biological tissue printed；
The 3D printing slave computer includes printer body 2, and the stepper motor 1, the guide rail that are set in printer body 2
3, spray head pedestal 4, spray head 5, forming workbench 6 and camera 7, guide rail 3 is arranged in 2 vertical direction of printer body, described
Stepper motor 1 and spray head pedestal 4 are installed, spray head 5, the alignment of spray head 5 molding is arranged in 4 bottom of spray head pedestal on guide rail 3
Workbench 6, the camera 7 are mounted on the top on 2 right side of printer body, the camera 7 and image processing module
Connection for obtaining image at spray head in real time, and sends image processing module to；
Image processing module handles the image of acquisition, obtain spray head between the destination organization that prints away from
From, and send the distance to upper computer software processing；PC upper computer software is real by the data received from image processing module
When display on the display module, when the distance deviate from user setting, control 3D printing slave computer, the distance is adjusted automatically
It is whole to 200 to 300 microns.
The PC host computer by the image real-time display taken on the display module.User can remotely check printing
When state, if discovery spray head wire drawing or blocking, the biological tissue of printing is unqualified can to stop printing at any time.
The image processing process of described image processing module includes the following steps:
1) high-definition camera focal length is adjusted, its picture is made to be shown as the most clear；
2) gray processing processing is carried out to image；
It 3) is mind after mitigating since the image range that camera obtains is too big to gray processing treated image segmentation
Difficulty through network processes, only retains the image near spray head and forming workbench, and remaining image is divided away；
4) image after segmentation is normalized；
5) edge extracting is carried out using BP neural network:
Firstly, considering with how many layers of neural network to carry out Image Edge-Detection, however, it would be possible to which use is comprising in multiple
The BP neural network of interbed, simple and effective, function convergence speed is fast to make to handle, and extracts side using 3 layers of BP neural network
Edge, the three-layer neural network are respectively input layer, output layer, middle layer, and the input layer corresponds to original image, output layer pair
Answer edge image；
Then, planned network, the input layer of network is corresponding with gray level image, and output layer is corresponding with edge image,
Middle layer neuron takes activation primitive Sigmoid function g (z):
Wherein, z is the product that this layer of weight θ matrix and upper one layer of node activate value matrix, z=θTX, θ are neuron
Weight matrix, θTFor the transposition of θ matrix, the input value matrix that x is upper one layer；
Middle layer neuron number, under the premise of guaranteeing image quality requirements, selection makes cost function J (θ) to be fitted journey
Spend highest function:
Wherein, m is training sample number, and K is the number of output, and k indicates k-th of input layer output, and L is neural net layer
Number, l are l layers of neural network, and λ indicates that iotazation constant, i are i-th of training sample, ykIt is exported for k-th of sample, yk (i)For
K-th of sample output corresponding with i-th of training sample, h (x(i)) it is hypothesis function corresponding to i-th of training sample, Sl
For l layers of neuron number, θji (l)For the weight of value corresponding to j-th of feature of i-th of training sample in l layers.
Then, sample is trained, the training sample in network is original image, and teacher signal is original image by adding
Work treated edge image.Since Sigmoid function has preferable processing capacity to the data between [0,1], so
When carrying out edge detection to image, it is necessary first to be normalized, prevent absolute because what is inputted only to the gray level image of input
It is worth excessive and makes neuron output saturation.
After forward-propagating is handled, it is compared, takes out total with corresponding teacher's column vector signal in output end
Mean square error signal, according to set error requirements, the reversed connection weight for adjusting neuron so that neural network reach compared with
Good capability of fitting, can be completed training mission.
6) average value is calculated to the gray value of whole image, is then made with the value in the neighborhood of the average value or the average value
For threshold value, binary conversion treatment is then carried out, grayscale image is converted into black and white binary image, obtains clearly edge wheel profile；
7) the distance between the biological tissue for calculating spray head and printing:
Spray head point M, the contact point of spinneret and the biological tissue printed are found in image after binary conversion treatment
N, two endpoints D, the E on the longer side of forming workbench, then；
Then coordinate system is established on image after treatment, spray head can be obtained in image between the biological tissue printed
Image pixel distance LMNWith the image pixel distance L of forming workbench long side in imageDEIt is respectively as follows:
Wherein, xM, yMIndicate the coordinate of spray head M point, xN, yNIndicate spinneret and the contact point N's for the biological tissue printed
Coordinate；
Wherein, xD, yDIndicate the coordinate of forming workbench long side side endpoint, xE, yEIndicate that forming workbench long side is another
The coordinate of side point；
Further, LBCIndicate the long back gauge of the actual forming workbench of printer, and this is a known quantity, the distance is logical
Measurement is crossed to obtain.
Then under a proportional relationship, it can obtain:
Due to LMN, LDE, LBCAll it is known quantity, acquires the actual spray head of 3D biometric print machine to the biological tissue printed
The distance between LAO；
Host computer is by LAOIt shows and is adjusted according to this result, control 3D printing slave computer, by spray head and beat
The distance between destination organization printed off is maintained between 200 to 300 microns, and spray head will not both glued with the biological tissue printed
Together, printing precision is in turn ensured.
As shown in Fig. 2, printer needs first to set parameters before starting to work, wherein spray head and print biological group
Distance between knitting is set between 200 to 300 microns；Then start to print biological tissue, high-definition camera, which starts simultaneously at, to be adopted
Collect image, and by the image processing module of image transmitting to host computer；Image processing module to obtained after image procossing spray head with
Distance between the biological tissue printed；After upper computer software obtains spacing, compared with set interval, if in set interval,
Then continue to print；Deviation if it exists then automatically adjusts spacing, remains at it within setting range, continues to print later.
It is constantly recycled from the workflow after acquisition image, realizes the real-time monitoring to distance between spray head and the biological tissue printed
With adjusting.
The present invention is not limited by embodiment illustrated herein, and is to fit to and principles disclosed herein and novelty
The consistent widest range of feature.
Claims (3)
1. a kind of 3D biometric print machine of the control printing distance based on image procossing, including PC host computer and 3D printing bottom
Machine, which is characterized in that the PC host computer is carried out data transmission with 3D printing slave computer by Ethernet interface；
The PC host computer includes control module, image processing module, display module, and user realizes that 3D is beaten by upper computer software
The various parameters of print are arranged, and the various parameters that 3D printing slave computer is run are shown on the display module；User voluntarily sets
The distance between the biological tissue for determining printing head and printing, or using the default setting of 3D printing slave computer, control printing
Spray head is 200 to 300 microns with the distance between the biological tissue printed；
The 3D printing slave computer includes printer body, and the stepper motor, the guide rail, spray head bottom that are set in printer body
Seat, spray head, forming workbench and camera, the printer body vertical direction are arranged guide rail, install stepping on the guide rail
Spray head is arranged in motor and spray head pedestal, the spray head base bottom, and the spray head is directed at forming worktable, the camera installation
Top on the right side of the printer body, the camera are connect with image processing module, for obtaining figure at spray head in real time
Picture, and send image processing module to；
Image processing module handles the image of acquisition, the distance between the destination organization for obtaining spray head and printing, and
Send the distance to upper computer software processing；The data real-time display that PC upper computer software will be received from image processing module
On the display module, when the distance deviates from user's setting, the distance is automatically adjusted to by control 3D printing slave computer
200 to 300 microns.
2. a kind of 3D biometric print machine of control printing distance based on image procossing according to claim 1, feature
It is, the image processing process of described image processing module includes the following steps:
1) high-definition camera focal length is adjusted, its picture is made to be shown as the most clear；
2) gray processing processing is carried out to image；
3) to gray processing treated image segmentation, only retain the image of spray head and forming workbench and the biological tissue on platform,
Remaining image is divided away；
4) image after segmentation is normalized；
5) edge extracting is carried out using BP neural network:
6) average value is calculated to the gray value of whole image, then using the value in the neighborhood of the average value or the average value as threshold
Value, then carries out binary conversion treatment, grayscale image is converted to black and white binary image, obtain clearly edge wheel profile；
7) the distance between the biological tissue for calculating spray head and printing:
Spray head point M, the contact point N of spinneret and the biological tissue printed are found in image after binary conversion treatment, at
Two endpoints D, the E on the longer side of shape workbench, then；
Then coordinate system is established on image after treatment, spray head can be obtained in image to the image between the biological tissue printed
Pixel distance LMNWith the image pixel distance L of forming workbench long side in imageDEIt is respectively as follows:
Wherein, xM, yMIndicate the coordinate of spray head M point, xN, yNIndicate the coordinate of spinneret with the contact point N for the biological tissue printed；
Wherein, xD, yDIndicate the coordinate of forming workbench long side side endpoint, xE, yEIndicate another side of forming workbench long side
The coordinate of point；
Further, LBCIndicate the long back gauge of the actual forming workbench of printer,
Then under a proportional relationship, it can obtain:
Due to LMN, LDE, LBCAll it is known quantity, acquires the actual spray head of 3D biometric print machine between the biological tissue printed
Distance LAO；
Host computer is by LAOShow and be adjusted according to this result, control 3D printing slave computer, by spray head with print
The distance between destination organization be maintained between 200 to 300 microns.
3. according to a kind of 3D biometric print machine of the control printing distance based on image procossing of claim 2, which is characterized in that institute
It states and carries out edge extracting using BP neural network, extracted using 3 layers of neural network, the three-layer neural network is respectively defeated
Enter layer, output layer, middle layer, the input layer corresponds to original image, output layer corresponding edge image, and middle layer neuron is taken
Activation primitive Sigmoid function g (z):
Wherein, z is the product that this layer of weight θ matrix and upper one layer of node activate value matrix, z=θTX, θ are the weight square of neuron
Battle array, θTFor the transposition of θ matrix, the input value matrix that x is upper one layer；
For middle layer neuron number under the premise of guaranteeing image quality requirements, selection makes cost function J (θ) fitting degree highest
Function:
Wherein, m is training sample number, and K is the number of output, and k indicates k-th of input layer output, and L is the neural network number of plies, l
For l layers of neural network, λ indicates that iotazation constant, i are i-th of training sample, ykIt is exported for k-th of sample, yk (i)For with i-th
Corresponding k-th of sample output of a training sample, h (x(i)) it is hypothesis function corresponding to i-th of training sample, SlFor l
The neuron number of layer, θji (l)For the weight of value corresponding to j-th of feature of i-th of training sample in l layers.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910390764.9A CN110171140A (en) | 2019-05-10 | 2019-05-10 | A kind of 3D biometric print machine of the control printing distance based on image procossing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910390764.9A CN110171140A (en) | 2019-05-10 | 2019-05-10 | A kind of 3D biometric print machine of the control printing distance based on image procossing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110171140A true CN110171140A (en) | 2019-08-27 |
Family
ID=67690891
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910390764.9A Pending CN110171140A (en) | 2019-05-10 | 2019-05-10 | A kind of 3D biometric print machine of the control printing distance based on image procossing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110171140A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112030368A (en) * | 2020-09-25 | 2020-12-04 | 信泰(福建)科技有限公司 | Production line and production line equipment of melt-blown fabric |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104802402A (en) * | 2014-01-29 | 2015-07-29 | 施乐公司 | System for controlling material drop volume in three dimensional object printing |
| CN206085687U (en) * | 2016-10-19 | 2017-04-12 | 泉州装备制造研究所 | 3D printing device's shower nozzle mechanism |
| CN107901398A (en) * | 2017-12-22 | 2018-04-13 | 南通矢量生物膜技术有限公司 | A kind of 3D printing method of nanofiber dry type facial mask |
| CN109308707A (en) * | 2018-11-09 | 2019-02-05 | 河北工业大学 | Aluminium ingot thickness non-contact type on-line measurement method |
-
2019
- 2019-05-10 CN CN201910390764.9A patent/CN110171140A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104802402A (en) * | 2014-01-29 | 2015-07-29 | 施乐公司 | System for controlling material drop volume in three dimensional object printing |
| CN206085687U (en) * | 2016-10-19 | 2017-04-12 | 泉州装备制造研究所 | 3D printing device's shower nozzle mechanism |
| CN107901398A (en) * | 2017-12-22 | 2018-04-13 | 南通矢量生物膜技术有限公司 | A kind of 3D printing method of nanofiber dry type facial mask |
| CN109308707A (en) * | 2018-11-09 | 2019-02-05 | 河北工业大学 | Aluminium ingot thickness non-contact type on-line measurement method |
Non-Patent Citations (7)
| Title |
|---|
| CSDN博客: "[机器学习] Coursera ML笔记 - 神经网络（Learning）", 《CSDN博客》 * |
| CSDN博客: "斯坦福机器学习公开课笔记(六)--神经网络的学习", 《CSDN博客》 * |
| 姚炜等: "《人工智能与机械臂》", 30 September 2018, 苏州大学出版社 * |
| 张习民等: "BP神经网络在图像边缘检测中的应用", 《计算机工程与设计》 * |
| 文少波等: "《新能源汽车及其智能化技术》", 30 September 2017, 东南大学出版社 * |
| 范永勇: "Machine Learning-神经网络（Neural Network）", 《范永勇》 * |
| 郭文强等: "《数字图像处理》", 31 May 2009, 西安电子科技大学出版社 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112030368A (en) * | 2020-09-25 | 2020-12-04 | 信泰(福建)科技有限公司 | Production line and production line equipment of melt-blown fabric |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105894045B (en) | A kind of model recognizing method of the depth network model based on spatial pyramid pond | |
| CN107610123A (en) | A kind of image aesthetic quality evaluation method based on depth convolutional neural networks | |
| CN105050247B (en) | Light intelligent regulating system and its method based on expression Model Identification | |
| CN110321923A (en) | Object detection method, system and the medium of different scale receptive field Feature-level fusion | |
| WO2020007363A1 (en) | Method and apparatus for identifying number of targets, and computer-readable storage medium | |
| CN110059741A (en) | Image-recognizing method based on semantic capsule converged network | |
| CN110109457A (en) | A kind of intelligent sound blind-guidance robot control method and control system | |
| CN108921049A (en) | Tumour cell pattern recognition device and equipment based on quantum gate transmission line neural network | |
| CN107066934A (en) | Tumor stomach cell image recognition decision maker, method and tumor stomach section identification decision equipment | |
| CN106845327B (en) | Training method, face alignment method and the device of face alignment model | |
| CN109919831A (en) | A kind of method for migrating retinal fundus images in different images domain, electronic equipment and computer readable storage medium | |
| CN101751689A (en) | Three-dimensional facial reconstruction method | |
| CN105534534A (en) | Emotion recognition method, device and system based on real-time functional magnetic resonance | |
| CN108688142A (en) | Three-dimensional printing method and its system | |
| CN105965886A (en) | Error control self-learning 3D printer and control method thereof | |
| CN110171140A (en) | A kind of 3D biometric print machine of the control printing distance based on image procossing | |
| CN107164305A (en) | A kind of external class brain tissue and its construction method | |
| CN110394422A (en) | A kind of sand mold print procedure on-line monitoring device and method | |
| CN205620835U (en) | Dimming control system is cultivateed to self -adaptation plant based on machine vision | |
| CN106725341A (en) | A kind of enhanced lingual diagnosis system | |
| CN108573232A (en) | Human motion recognition method based on convolutional neural networks | |
| CN110119768A (en) | Visual information emerging system and method for vehicle location | |
| CN105719276A (en) | Liver parenchymal segmentation method based on CT images | |
| CN111626969A (en) | Attention mechanism-based corn disease image processing method | |
| CN114938556A (en) | Automatic adjusting method and device for light of desk lamp, electronic equipment and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190827 |