CN110097139B - Intelligent rice washing method and device based on convolutional neural network - Google Patents
Intelligent rice washing method and device based on convolutional neural network Download PDFInfo
- Publication number
- CN110097139B CN110097139B CN201910393635.5A CN201910393635A CN110097139B CN 110097139 B CN110097139 B CN 110097139B CN 201910393635 A CN201910393635 A CN 201910393635A CN 110097139 B CN110097139 B CN 110097139B
- Authority
- CN
- China
- Prior art keywords
- rice
- model
- water
- insects
- training
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47J—KITCHEN EQUIPMENT; COFFEE MILLS; SPICE MILLS; APPARATUS FOR MAKING BEVERAGES
- A47J43/00—Implements for preparing or holding food, not provided for in other groups of this subclass
- A47J43/04—Machines for domestic use not covered elsewhere, e.g. for grinding, mixing, stirring, kneading, emulsifying, whipping or beating foodstuffs, e.g. power-driven
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Food Science & Technology (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Mechanical Engineering (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Image Analysis (AREA)
- Adjustment And Processing Of Grains (AREA)
Abstract
The invention discloses an intelligent rice washing method and device based on a convolutional neural network, which belong to the field of artificial intelligence, and solve the technical problem of how to utilize the convolutional neural network to replace people to select and remove insects by naked eyes to realize intelligent rice washing, and the technical scheme is as follows: (1) the method comprises the steps that whether insects exist in rice or not is detected by two different models, namely a water-model and a rice-model, aiming at the two situations of a horizontal plane of the rice soaked by water and a rice plane laid on the horizontal plane, and when the water-model and the rice-model judge that no insects exist, the rice is determined to be clean; otherwise, the operation is repeated until both the water-model and the rice-model make a judgment that there are no worms. (2) The device comprises a server, a camera, a water injection pumping tool, a picture processing module and a rice washing machine, wherein the server is respectively connected with the camera, the picture processing module and the rice washing machine, and the rice washing machine is communicated with the water injection pumping tool.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to an intelligent rice washing method and device based on a convolutional neural network.
Background
With the development shift of productive lifestyles and the advancement of artificial intelligence technology, many boring and repetitive lifestyles in life can be replaced by artificial intelligence. Among the various deep neural network structures, convolutional neural networks are the most widely used one, proposed by LeCun in 1989. Convolutional neural networks were successfully applied to handwritten character image recognition at an early stage. The AlexNet network in the deeper layer of 2012 is successful, and the convolutional neural network is developed vigorously, is widely used in various fields, and achieves the best performance in many problems. Convolutional neural networks achieve the best current results in machine vision and many other problems. The convolutional neural network automatically learns the features of the image at various levels through convolution and pooling operations, which is consistent with the common knowledge that we understand the image.
The existing life style mainly adopts manual work, but the artificial intelligence technology is greatly improved. The artificial intelligence can provide more services and lives, and people can enjoy higher life quality by saving the time for doing life. Activities like rice washing, which are necessary but cumbersome in life, should be solved more by means of artificial intelligence. The rice is the indispensable staple food of people in the life, but has a vexation, and after weather is warm, always there are many bugs in a heap of rice, must wash rice repeatedly before eating at every turn just edible, but this process is boring and lengthy, and people can only select the rejection through the naked eye, and is comparatively time-consuming, and the rejection is unclean moreover. Therefore, how to use the convolutional neural network to replace the situation that people select and remove insects by naked eyes to realize intelligent rice washing is a technical problem which is continuously solved in the prior art at present.
Disclosure of Invention
The invention provides an intelligent rice washing method and device based on a convolutional neural network, and aims to solve the problem of how to utilize the convolutional neural network to replace people to select and remove insects by naked eyes so as to realize intelligent rice washing.
The technical task of the invention is realized in the following way, the intelligent rice washing method based on the convolutional neural network detects whether insects exist in rice or not by utilizing two different models, namely a water-model and a rice-model, aiming at the two conditions of the horizontal plane of the rice soaked by water and the rice plane spread on the plane, and when the two models are judged to have no insects, the rice is determined to be clean; otherwise, repeating the operation until the water-model and the rice-model both make judgment that no worm exists; the method comprises the following specific steps:
s1, training a model: including water-model training and rice-model training;
s2, performing rice washing work by using the trained water-model and rice-model: two different models of convolutional neural networks, namely a water-model and a rice-model, are obtained through training, the two models are put into a raspberry pie, the raspberry pie and a camera are embedded into a rice washing machine capable of automatically injecting water for pumping, and rice is washed by the rice washing machine.
Preferably, the specific steps of the water-model training in step S1 are as follows:
s1-11, pouring rice with equal volume into a rice utensil, and pouring water to enable insects in a rice pile with the insects to float;
s1-12, taking a picture of a horizontal plane, observing whether insects exist on the horizontal plane through naked eyes, and meanwhile, marking the picture with a label, wherein the content of the label is whether the insects exist;
s1-13, repeating the operation of the step S1-12 for a plurality of times under different light environments;
s1-14, selectively cutting, rotating, magnifying and reducing the existing photos, and making all the photos with labels into a horizontal plane data set which is divided into a horizontal plane training set and a horizontal plane testing set
S1-15, putting a water-model (namely a convolutional neural network model modified based on an ssd model) into a processed horizontal plane data set, and training by using a server;
s1-16, putting the trained water-model into a horizontal plane test data set for testing, and judging whether the test result achieves a preset effect:
and if the preset effect is not achieved, the data set training is re-taken or the water-model is finely adjusted until the water-model is fitted.
Preferably, the specific steps of the rice-model training in step S1 are as follows:
s1-21, spreading the rice soaked with water and not treated in the steps S1-11 to S1-16 on a flat plate, wherein the size of the selected flat plate is just enough to cover one layer of rice in order to prevent insects from being covered in the rice layer;
s1-22, identifying whether insects exist in the rice on the plane plate by naked eyes, shooting the rice in the plane plate into a picture by a camera, and marking the picture with a label, wherein the content of the label is whether the insects exist;
s1-23, repeating the operation of the step S1-22 for a plurality of times under different light environments;
s1-24, selectively cutting, rotating, amplifying and reducing the existing photos, and making all the photos with labels into a flat rice surface data set which is divided into a training set and a testing set;
s1-25, putting the rice-model (namely, a convolutional neural network model modified based on an ssd model) into a processed and flattened rice flour training data set, and training by using a server;
s1-26, putting the trained rice-model into a flat rice flour test data set for testing, and judging whether the test result achieves a preset effect:
and if the preset effect is not achieved, the data set training is re-acquired or the rice-model is subjected to fine adjustment until the rice-model is fitted.
Preferably, the mouth and the planar plate of the rice appliance are rectangular.
Preferably, the step S2 of performing rice washing by using the trained water-model and rice-model includes the following steps:
s201, pouring the rice into a rice washing machine, wherein the rice washing machine selects the rice with fixed capacity to pour into an alternative rice space in the rice washing machine;
s202, starting automatic water injection until the rice is completely covered, and taking a picture of a horizontal plane by using a camera;
s203, transmitting the photo in the step S203 to a water-model in a raspberry pie for judgment:
(1) if the water-model obtains that the insects exist, executing the step S204;
(2) if the water-model has no bugs, jumping to step S205;
s204, automatically pumping out all the water, pumping out all the insects on the surface of the horizontal plane while pumping water, and repeating the operations of the step S202 and the step S203 until the water-model judges that no insects exist;
s205, in order to prevent that partial insects may not float out of the water surface, the insects in the rice are thoroughly removed, the rice and the water are automatically separated according to the particle size, the water permeates into another space, the remaining rice is flatly spread at the bottom of the rectangular cylinder, the rice on the bottom surface is photographed into a picture by a camera, the picture is transmitted into a raspberry group, and whether the insects exist is judged by using a rice-model:
(1) if the insects exist, water is injected again, and the operation of the step S202 and the operation of the step S203 are carried out again;
(2) if no insects exist, the rice is determined to be clean and is placed into a clean rice space;
s206, the remaining rice in the rice washing machine is subjected to the operations of the steps S201 to S205 until each part of the rice is clean, i.e., the rice washing operation is completed.
Preferably, the space for selecting rice in the rice washing machine is in a rectangular cylinder structure.
The utility model provides an intelligence device of washing rice based on convolutional neural network, the device includes server, camera, water injection pumping tool, picture processing module and the machine of washing rice, and the camera is connected respectively to the server, picture processing module and the machine of washing rice, and the machine of washing rice is linked together with water injection pumping tool.
Preferably, the server is used for training models, and the models comprise water-model and rice-model;
a camera for taking pictures; the picture processing module is used for processing the pictures shot by the camera by utilizing the raspberry pi, and comprises the steps of cutting, rotating, amplifying and reducing the pictures;
the rice washing machine is used for performing rice washing work by using two trained models, namely a water-model and a rice-model, obtaining two different models, namely the water-model and the rice-model, of a convolutional neural network through training, putting the two models into a raspberry pie, embedding the raspberry pie and a camera into an automatic injection water pumping rice washing machine, and performing rice washing by using the rice washing machine;
the water injection pumping tool is used for automatic pumping and water injection of the rice washing machine.
The intelligent rice washing method and device based on the convolutional neural network have the following advantages:
the method has the advantages that the problem that whether insects exist in the rice is identified by using the currently most popular convolutional neural network in the field of artificial intelligence computer vision, and the insects in the rice are thoroughly removed according to a certain flow, so that intelligent rice washing is realized;
secondly, the invention relates to a binary classification method for judging whether insects exist in a pile of rice based on a convolutional neural network, and water is injected or pumped according to a judgment result, so that the insects are removed, and the aim of cleaning the rice is fulfilled; in order to eliminate the bugs completely, the rice washing process is decomposed, and whether the bugs exist is judged by using a model trained based on a convolutional neural network under the conditions of water existence and water absence respectively; only in both cases when there are no bugs can it be determined that the rice heap is clean.
Drawings
The invention is further described below with reference to the accompanying drawings.
FIG. 1 is a flow chart of an intelligent rice washing method based on a convolutional neural network;
FIG. 2 is a schematic view of a model structure.
Detailed Description
The intelligent rice washing method and device based on the convolutional neural network of the present invention are described in detail with reference to the attached drawings and specific embodiments.
Example 1:
the invention relates to an intelligent rice washing method based on a convolutional neural network, which utilizes two different models, namely a water-model and a rice-model, to respectively detect whether insects exist in rice aiming at the two conditions of a horizontal plane of the rice soaked by water and a rice plane spread on the plane, and when the two models of the water-model and the rice-model judge that no insects exist, the rice is determined to be clean; otherwise, repeating the operation until the water-model and the rice-model both make judgment that no worm exists; the method comprises the following specific steps:
s1, training a model: including water-model training and rice-model training; the specific steps of water-model training are as follows:
s1-11, pouring rice with equal volume into a rice utensil, and pouring water to enable insects in a rice pile with the insects to float;
s1-12, taking a picture of a horizontal plane, observing whether insects exist on the horizontal plane through naked eyes, and meanwhile, marking the picture with a label, wherein the content of the label is whether the insects exist;
s1-13, repeating the operation of the step S1-12 for a plurality of times under different light environments;
s1-14, selectively cutting, rotating, magnifying and reducing the existing photos, and making all the photos with labels into a horizontal plane data set which is divided into a horizontal plane training set and a horizontal plane testing set
S1-15, putting a water-model (namely a convolutional neural network model, modified based on an ssd model, and the model structure shown in the attached figure 2) into a processed horizontal plane data set, and training by using a server;
s1-16, putting the trained water-model into a horizontal plane test data set for testing, and judging whether a test result achieves a preset effect:
and if the preset effect is not achieved, the data set training is re-taken or the water-model is finely adjusted until the water-model is fitted.
The concrete steps of rice-model training are as follows:
s1-21, spreading the rice soaked with water and not treated in the steps S1-11 to S1-16 on a flat plate, wherein the size of the selected flat plate is just enough to cover one layer of rice in order to prevent insects from being covered in the rice layer;
s1-22, identifying whether insects exist in rice on a flat plate by naked eyes, taking a picture of the rice in the flat plate by using a camera, and marking the picture with a label, wherein the content of the label is whether the insects exist;
s1-23, repeating the operation of the step S1-22 for a plurality of times under different light environments;
s1-24, selectively cutting, rotating, amplifying and reducing the existing photos, and making all the photos with labels into a flat rice flour data set which is divided into a training set and a testing set;
s1-25, putting the rice-model (namely, a convolutional neural network model, modified based on an ssd model, and with the model structure shown in the attached figure 2) into a processed and flattened rice flour training data set, and training by using a server;
s1-26, putting the trained rice-model into a flat rice flour test data set for testing, and judging whether the test result achieves a preset effect:
and if the preset effect is not achieved, the data set training is re-acquired or the rice-model is subjected to fine adjustment until the rice-model is fitted.
S2, performing rice washing work by using the trained water-model and rice-model models: obtaining two different convolution neural network models, namely a water-model and a rice-model, through training, putting the two models into a raspberry pie, embedding the raspberry pie and a camera into a rice washing machine capable of automatically pumping water, and washing rice by using the rice washing machine; as shown in the attached figure 1, the method comprises the following specific steps:
s201, pouring the rice into a rice washing machine, wherein the rice washing machine selects the rice with fixed capacity to pour into an alternative rice space in the rice washing machine;
s202, starting automatic water injection until the rice is completely covered, and taking a picture of a horizontal plane by using a camera;
s203, transmitting the photo in the step S203 to a water-model in a raspberry pie for judgment:
(1) if the result obtained by the water-model is that the insects exist, executing the step S204;
(2) if the water-model has no bugs, jumping to step S205;
s204, automatically pumping out all the water, pumping out all the insects on the surface of the horizontal plane while pumping water, and repeating the operations of the step S202 and the step S203 until the water-model judges that no insects exist;
s205, in order to prevent that partial insects may not float out of the water surface, the insects in the rice are thoroughly removed, the rice and the water are automatically separated according to the particle size, the water permeates into another space, the remaining rice is flatly spread at the bottom of the rectangular cylinder, the rice on the bottom surface is photographed into a picture by a camera, the picture is transmitted into a raspberry group, and whether the insects exist is judged by using a rice-model:
(1) if insects exist, water is injected again, and the operations of the step S202 and the step S203 are carried out again;
(2) if no insects exist, the rice is determined to be clean and is placed into a clean rice space;
s206, the operations of step S201 to step S205 are performed on the remaining rice in the rice washing machine until each part of the rice is clean, i.e., the rice washing operation is completed.
Wherein, the mouth and the plane plate of the rice appliance are both rectangular. The space for selecting rice in the rice washing machine is in a rectangular column structure.
Example 2:
the invention discloses an intelligent rice washing device based on a convolutional neural network, which comprises a server, a camera, a water injection and water pumping tool, a picture processing module and a rice washing machine, wherein the server is respectively connected with the camera, the picture processing module and the rice washing machine, and the rice washing machine is communicated with the water injection and water pumping tool. The server is used for training models, and the models comprise water-models and rice-models; a camera for taking pictures; the picture processing module is used for processing the pictures shot by the camera by utilizing the raspberry pi, and comprises the steps of cutting, rotating, amplifying and reducing the pictures; the rice washing machine is used for performing rice washing work by using two trained models, namely a water-model and a rice-model, two different models, namely the water-model and the rice-model, of a convolutional neural network are obtained through training, the two models are placed into a raspberry pie, the raspberry pie and a camera are embedded into the rice washing machine which automatically injects water for pumping, and rice washing is performed by using the rice washing machine; the water injection pumping tool is used for automatic pumping and water injection of the rice washing machine.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (6)
1. An intelligent rice washing method based on a convolutional neural network is characterized in that whether insects exist in rice is detected by using two different models, namely a water-model and a rice-model, aiming at the two conditions of a horizontal plane of the rice soaked by water and a rice plane laid on the plane, and when the two models are judged to have no insects, the rice is determined to be clean; otherwise, repeating the operation until the water-model and the rice-model both make judgment that no worm exists; the method comprises the following specific steps:
s1, training a model: including water-model training and rice-model training; the water-model training method comprises the following specific steps:
s1-11, pouring rice with equal volume into a rice utensil, and pouring water to enable insects in a rice pile with the insects to float;
s1-12, taking a picture of a horizontal plane, observing whether insects exist on the horizontal plane through naked eyes, and meanwhile labeling the picture, wherein the content of the label is whether the insects exist;
s1-13, repeating the operation of the step S1-12 for a plurality of times under different light environments;
s1-14, selectively cutting, rotating, amplifying and reducing the existing photos, and making all the photos with labels into a horizontal plane data set which is divided into a horizontal plane training set and a horizontal plane testing set;
s1-15, putting the water-model into the processed horizontal plane data set, and training by using a server;
s1-16, putting the trained water-model into a horizontal plane test data set for testing, and judging whether the test result achieves a preset effect:
if the preset effect is not achieved, the data set is re-taken for training or the water-model is finely adjusted until the water-model is fitted;
s2, performing rice washing work by using the trained water-model and rice-model: two different models of convolutional neural networks, namely a water-model and a rice-model, are obtained through training, the two models are put into a raspberry pie, the raspberry pie and a camera are embedded into a rice washing machine which automatically pumps water, and rice is washed by the rice washing machine.
2. The intelligent rice washing method based on the convolutional neural network as claimed in claim 1, wherein the specific steps of rice-model training in step S1 are as follows:
s1-21, spreading the rice soaked with water and not treated in the steps S1-11 to S1-16 on a flat plate, wherein the size of the selected flat plate is just enough to cover one layer of rice in order to prevent insects from being covered in the rice layer;
s1-22, identifying whether insects exist in rice on a flat plate by naked eyes, taking a picture of the rice in the flat plate by using a camera, and marking the picture with a label, wherein the content of the label is whether the insects exist;
s1-23, repeating the operation of the step S1-22 for a plurality of times under different light environments;
s1-24, selectively cutting, rotating, amplifying and reducing the existing photos, and making all the photos with labels into a flat rice flour data set which is divided into a training set and a testing set;
s1-25, putting the rice-model into a processed and spread rice noodle training data set, and training by using a server;
s1-26, putting the trained rice-model into a flat rice flour test data set for testing, and judging whether the test result achieves a preset effect:
and if the preset effect is not achieved, the data set training is re-acquired or the rice-model is subjected to fine adjustment until the rice-model is fitted.
3. The intelligent rice washing method based on the convolutional neural network as claimed in claim 1 or 2, wherein the mouth of the rice appliance and the plane plate are rectangular.
4. The convolutional neural network-based intelligent rice washing method as claimed in claim 1, wherein the step S2 of performing rice washing by using two models, namely a water-model and a rice-model, comprises the following steps:
s201, pouring the rice into a rice washing machine, wherein the rice washing machine selects the rice with fixed capacity to pour into an alternative rice space in the rice washing machine;
s202, automatically filling water until the rice is completely covered, and taking a picture of the horizontal plane by using a camera;
s203, transmitting the photo in the step S203 to a water-model in a raspberry pie for judgment:
(1) if the result obtained by the water-model is that the insects exist, executing the step S204;
(2) if the water-model has no bugs, jumping to step S205;
s204, automatically pumping out all the water, pumping out all the insects on the surface of the horizontal plane while pumping water, and repeating the operations of the step S202 and the step S203 until the water-model judges that no insects exist;
s205, in order to prevent that partial insects may not float out of the water surface, the insects in the rice are thoroughly removed, the rice and the water are automatically separated according to the particle size, the water permeates into another space, the remaining rice is flatly spread at the bottom of the rectangular cylinder, the rice on the bottom surface is photographed into a picture by a camera, the picture is transmitted into a raspberry group, and whether the insects exist is judged by using a rice-model:
(1) if insects exist, water is injected again, and the operations of the step S202 and the step S203 are carried out again;
(2) if no insects exist, the rice is determined to be clean and is placed into a clean rice space;
and S206, performing the operations from the step S201 to the step S205 on the remaining rice in the rice washing machine until each part of the rice is clean, namely finishing the rice washing operation.
5. The intelligent rice washing method based on the convolutional neural network as claimed in claim 4, wherein the space of the alternative rice in the rice washing machine is a rectangular cylinder structure.
6. An intelligent rice washing device based on a convolutional neural network is characterized by comprising a server, a camera, a water injection and water pumping tool, a picture processing module and a rice washing machine, wherein the server is respectively connected with the camera, the picture processing module and the rice washing machine, and the rice washing machine is communicated with the water injection and water pumping tool;
the server is used for training models, and the models comprise water-model and rice-model; the specific steps of water-model training are as follows:
s1-11, pouring rice with equal volume into a rice utensil, and pouring water to enable insects in a rice pile with the insects to float;
s1-12, taking a picture of a horizontal plane, observing whether insects exist on the horizontal plane through naked eyes, and meanwhile, marking the picture with a label, wherein the content of the label is whether the insects exist;
s1-13, repeating the operation of the step S1-12 for a plurality of times under different light environments;
s1-14, selectively cutting, rotating, amplifying and reducing the existing photos, and making all the photos with labels into a horizontal plane data set which is divided into a horizontal plane training set and a horizontal plane testing set;
s1-15, putting the water-model into the processed horizontal plane data set, and training by using a server;
s1-16, putting the trained water-model into a horizontal plane test data set for testing, and judging whether the test result achieves a preset effect:
if the preset effect is not achieved, the data set is re-taken for training or the water-model is finely adjusted until the water-model is fitted;
a camera for taking pictures; the picture processing module is used for processing the pictures shot by the camera by utilizing the raspberry pi, and comprises the steps of cutting, rotating, amplifying and reducing the pictures;
the rice washing machine is used for performing rice washing work by using two trained models, namely a water-model and a rice-model, obtaining two different models, namely the water-model and the rice-model, of a convolutional neural network through training, putting the two models into a raspberry pie, embedding the raspberry pie and a camera into an automatic injection water pumping rice washing machine, and performing rice washing by using the rice washing machine;
the water injection pumping tool is used for automatic pumping and water injection of the rice washing machine.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910393635.5A CN110097139B (en) | 2019-05-13 | 2019-05-13 | Intelligent rice washing method and device based on convolutional neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910393635.5A CN110097139B (en) | 2019-05-13 | 2019-05-13 | Intelligent rice washing method and device based on convolutional neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110097139A CN110097139A (en) | 2019-08-06 |
| CN110097139B true CN110097139B (en) | 2022-12-13 |
Family
ID=67447854
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910393635.5A Active CN110097139B (en) | 2019-05-13 | 2019-05-13 | Intelligent rice washing method and device based on convolutional neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110097139B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113837049B (en) * | 2021-09-17 | 2023-06-20 | 山东浪潮科学研究院有限公司 | Intelligent pavement cleaning method based on convolutional neural network and genetic algorithm |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016195496A2 (en) * | 2015-06-05 | 2016-12-08 | Universiteit Van Amsterdam | Deep receptive field networks |
| CN109740560A (en) * | 2019-01-11 | 2019-05-10 | 济南浪潮高新科技投资发展有限公司 | Human cellular protein automatic identifying method and system based on convolutional neural networks |
-
2019
- 2019-05-13 CN CN201910393635.5A patent/CN110097139B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016195496A2 (en) * | 2015-06-05 | 2016-12-08 | Universiteit Van Amsterdam | Deep receptive field networks |
| CN109740560A (en) * | 2019-01-11 | 2019-05-10 | 济南浪潮高新科技投资发展有限公司 | Human cellular protein automatic identifying method and system based on convolutional neural networks |
Non-Patent Citations (1)
| Title |
|---|
| TensorFlow在图像识别系统中的应用;邢艳芳等;《计算机技术与发展》;20181221(第05期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110097139A (en) | 2019-08-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111860533B (en) | Image recognition method and device, storage medium and electronic device | |
| CN111414971B (en) | Convolutional neural network-based finished tea variety and grade identification method | |
| CN104867144B (en) | IC element welding point defect detection methods based on mixed Gauss model | |
| CN108596338A (en) | A kind of acquisition methods and its system of neural metwork training collection | |
| CN108108767A (en) | A kind of cereal recognition methods, device and computer storage media | |
| CN106295789A (en) | A kind of crop seed method of counting based on image procossing | |
| CN110097139B (en) | Intelligent rice washing method and device based on convolutional neural network | |
| CN101123677B (en) | Method, device and integrated circuit for improving image acuteness | |
| CN111986183B (en) | Chromosome scattered image automatic segmentation and identification system and device | |
| CN1700238A (en) | Method for dividing human body skin area from color digital images and video graphs | |
| CN108109133B (en) | Silkworm egg automatic counting method based on digital image processing technology | |
| CN102110294A (en) | Method and system for processing image of diseased fish body | |
| CN111524144A (en) | Intelligent pulmonary nodule diagnosis method based on GAN and Unet network | |
| CN109740721A (en) | Wheat head method of counting and device | |
| Huang et al. | The prototype of a smart underwater surveillance system for shrimp farming | |
| CN110084792A (en) | A kind of method for detecting abnormality of mariculture cage netting | |
| CN110866915A (en) | Circular inkstone quality detection method based on metric learning | |
| CN109886170A (en) | A kind of identification of oncomelania intelligent measurement and statistical system | |
| CN108734708A (en) | Gastric cancer recognition methods, device and storage medium | |
| CN108090518A (en) | A kind of cereal recognition methods, device and computer storage media | |
| CN104615163B (en) | Automatic PCB agent adding method | |
| CN112115873A (en) | Diatom automatic detection method and system based on deep learning | |
| CN104050676B (en) | A kind of backlight image detecting method and device based on Logistic regression models | |
| Cao et al. | Research on counting algorithm of residual feeds in aquaculture based on machine vision | |
| CN106846312B (en) | A method of the monitoring sludge system hydraulics variation based on color space |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20221121 Address after: 250100 building S02, No. 1036, Langchao Road, high tech Zone, Jinan City, Shandong Province Applicant after: Shandong Inspur Scientific Research Institute Co.,Ltd. Address before: 250100 First Floor of R&D Building 2877 Kehang Road, Sun Village Town, Jinan High-tech Zone, Shandong Province Applicant before: JINAN INSPUR HIGH-TECH TECHNOLOGY DEVELOPMENT Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |