CN109345468A - Data processing method and device - Google Patents
Data processing method and device Download PDFInfo
- Publication number
- CN109345468A CN109345468A CN201810995761.3A CN201810995761A CN109345468A CN 109345468 A CN109345468 A CN 109345468A CN 201810995761 A CN201810995761 A CN 201810995761A CN 109345468 A CN109345468 A CN 109345468A
- Authority
- CN
- China
- Prior art keywords
- picture
- class
- tool
- designated pictures
- noisy
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 11
- 238000000034 method Methods 0.000 claims abstract description 38
- 244000025254 Cannabis sativa Species 0.000 claims description 9
- 238000005520 cutting process Methods 0.000 claims description 8
- 239000002689 soil Substances 0.000 claims description 8
- 239000003814 drug Substances 0.000 claims description 6
- 239000000428 dust Substances 0.000 claims description 6
- 239000000049 pigment Substances 0.000 claims description 6
- 230000000903 blocking effect Effects 0.000 claims description 5
- 230000009286 beneficial effect Effects 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 6
- 230000000875 corresponding effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Classifications
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
Abstract
This application discloses a kind of data processing method and device, this method comprises: obtaining an at least chaff interferent picture;According to preset noise jamming method, the chaff interferent picture is added in designated pictures, to generate at least one noisy picture of tool;The designated pictures and the noisy picture of tool are stored, it can make designated pictures by the above method and have the data acquisition system more diversity that noisy picture is constituted, and then be conducive to make the robustness of data acquisition system stronger, and when carrying out picture recognition by designated pictures and the noisy picture of tool, it is also beneficial to improve the accuracy rate of recognition result.
Description
Technical field
This application involves field of computer technology, in particular to a kind of data processing method and device.
Background technique
In the prior art, usually one image of acquisition is stored in image library as standard picture, then utilizes the mark
Quasi- image carries out image recognition to the image of the same object of subsequent acquisition, but the surface of the object can be over time
It changes, which can form noise to the image of subsequent acquisition, so that the result accuracy rate of image recognition is lower, or
Person compares image without correlated noise since standard picture has noise.For example, when the face image that the standard picture is ox
When, the living environment as locating for ox is more complicated, and after ox movable a period of time, face can be stained with grass cuttings and/or soil
Equal chaff interferents, above-mentioned chaff interferent can impact the face of ox, after the face image for getting the ox again at this time, face figure
There are noise jamming as in, the face image for not interfering with object influence got before utilization is to current collected face
When image is identified, the lower problem of recognition result accuracy rate will cause.
Summary of the invention
The main purpose of the application is to provide a kind of data processing method and device, to improve the accurate of image recognition
Rate.
To achieve the goals above, this application provides a kind of data processing methods, which comprises
Obtain an at least chaff interferent picture;
According to preset noise jamming method, the chaff interferent picture is added in designated pictures, to generate at least one
Open the noisy picture of tool;
The designated pictures and the noisy picture of tool are stored.
Optionally, the chaff interferent in the chaff interferent picture includes:
Soil class, dust class, grass cuttings class, feed class, excrement class, fence class, class balustrade, sundries class, pigment class, medicament
Class, uneven light class, bright spot, the blocking of hand, clothes class.
Optionally, according to preset noise jamming method, the chaff interferent picture is added in designated pictures, to generate
At least one noisy picture of tool includes:
The chaff interferent picture is arranged to the Target Photo of at least one size;
The Target Photo is added in the designated pictures, to generate at least one noisy picture of tool.
Optionally, the Target Photo is added in the designated pictures, to generate at least one noisy figure of tool
Piece includes:
The Target Photo is added at least one predeterminated position in the designated pictures, to generate at least one
Has noisy picture.
Optionally, the method also includes:
Image knowledge is carried out to the picture to be identified got using the noisy picture of the tool and the designated pictures
Not;And/or
Image training is carried out to picture using the noisy picture of the tool and the designated pictures as training set of images.
To achieve the goals above, this application provides a kind of data processing equipment, described device includes:
Acquiring unit, for obtaining an at least chaff interferent picture;
Adding unit, for according to preset noise jamming method, the chaff interferent picture to be added in designated pictures,
To generate at least one noisy picture of tool;
Storage unit, for being stored to the designated pictures and the noisy picture of tool.
Optionally, the chaff interferent in the chaff interferent picture includes:
Soil class, dust class, grass cuttings class, feed class, excrement class, fence class, class balustrade, sundries class, pigment class, medicament
Class, uneven light class, bright spot, the blocking of hand, clothes class.
Optionally, it is used to be added the chaff interferent picture according to preset noise jamming method in the adding unit
Into designated pictures, when generating at least one noisy picture of tool, it is used for:
The chaff interferent picture is arranged to the Target Photo of at least one size;
The Target Photo is added in the designated pictures, to generate at least one noisy picture of tool.
Optionally, it is used to for the Target Photo being added in the designated pictures in the adding unit, to generate extremely
When a few noisy picture of tool, it is used for:
The Target Photo is added at least one predeterminated position in the designated pictures, to generate at least one
Has noisy picture.
Optionally, described device further include:
Recognition unit, for using the noisy picture of the tool and the designated pictures to the figure to be identified got
Piece carries out image recognition;And/or
Training unit, for using the noisy picture of the tool and the designated pictures as training set of images to picture into
The training of row image.
The technical solution that embodiments herein provides can include the following benefits:
It in this application,, will be described according to preset noise jamming method after getting an at least chaff interferent picture
Chaff interferent picture is added in designated pictures, to generate at least one noisy picture of tool, then to the designated pictures and
The noisy picture of tool is stored, wherein the chaff interferent in chaff interferent picture can be according to the interference in actual scene
Object is set, and noise jamming method can also be set according to actual scene, so as to simulate in true environment
The case where being likely encountered, and then the noisy picture of tool generated can be made and obtained when encountering chaff interferent in true environment
Picture more close to so that designated pictures and have the data acquisition system more diversity that noisy picture is constituted, into
And be conducive to make the robustness of data acquisition system stronger, and carrying out picture recognition by designated pictures and the noisy picture of tool
When, it is also beneficial to improve the accuracy rate of recognition result.
Detailed description of the invention
The attached drawing constituted part of this application is used to provide further understanding of the present application, so that the application's is other
Feature, objects and advantages become more apparent upon.The illustrative examples attached drawing and its explanation of the application is for explaining the application, not
Constitute the improper restriction to the application.In the accompanying drawings:
Fig. 1 is a kind of flow diagram of data processing method provided by the present application;
Fig. 2 is the flow diagram of another data processing method provided by the present application;
Fig. 3 is a kind of structural schematic diagram of data processing equipment provided by the present application;
Fig. 4 is the structural schematic diagram of another data processing equipment provided by the present application.
Specific embodiment
In order to make those skilled in the art more fully understand application scheme, below in conjunction in the embodiment of the present application
Attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is only
The embodiment of the application a part, instead of all the embodiments.Based on the embodiment in the application, ordinary skill people
Member's every other embodiment obtained without making creative work, all should belong to the model of the application protection
It encloses.
It should be noted that the description and claims of this application and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this way
Data be interchangeable under appropriate circumstances, so as to embodiments herein described herein.In addition, term " includes " and " tool
Have " and their any deformation, it is intended that cover it is non-exclusive include, for example, containing a series of steps or units
Process, method, system, product or equipment those of are not necessarily limited to be clearly listed step or unit, but may include without clear
Other step or units listing to Chu or intrinsic for these process, methods, product or equipment.
In this application, term " on ", "lower", "left", "right", "front", "rear", "top", "bottom", "inner", "outside",
" in ", "vertical", "horizontal", " transverse direction ", the orientation or positional relationship of the instructions such as " longitudinal direction " be orientation based on the figure or
Positional relationship.These terms are not intended to limit indicated dress primarily to better describe the application and embodiment
Set, element or component must have particular orientation, or constructed and operated with particular orientation.
Also, above-mentioned part term is other than it can be used to indicate that orientation or positional relationship, it is also possible to for indicating it
His meaning, such as term " on " also are likely used for indicating certain relations of dependence or connection relationship in some cases.For ability
For the those of ordinary skill of domain, the concrete meaning of these terms in this application can be understood as the case may be.
In addition, term " installation ", " setting ", " being equipped with ", " connection ", " connected ", " socket " shall be understood in a broad sense.For example,
It may be a fixed connection, be detachably connected or monolithic construction;It can be mechanical connection, or electrical connection;It can be direct phase
It even, or indirectly connected through an intermediary, or is two connections internal between device, element or component.
For those of ordinary skills, the concrete meaning of above-mentioned term in this application can be understood as the case may be.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 be a kind of flow diagram of data processing method provided by the present application, as shown in Figure 1, this method include with
Lower step:
101, an at least chaff interferent picture is obtained.
It should be noted that chaff interferent can be the objects such as grass cuttings and mud, the type of the chaff interferent in chaff interferent picture
It can be set with quantity, be not specifically limited herein according to actual needs.
102, according to preset noise jamming method, the chaff interferent picture is added in designated pictures, to generate extremely
The noisy picture of a few tool.
Specifically, preset noise jamming method can be set according to the actual situation, for example, by chaff interferent picture
When being added in designated pictures, can be according to can actually occur the case where, chaff interferent picture is added to certain of designated pictures
It on one position, and is to be added to chaff interferent picture in the designated pictures with specified area coverage, about specific noise
Interference method can be set according to actual needs, be not specifically limited herein.
After generating the noisy picture of tool using the above method, it can to have in the picture and real scene of noise
The picture got is more close to having in the noise and real scene in noisy picture chaff interferent in designated pictures
It is influenced relatively caused by object, to be conducive to improve the validity for having noisy picture.
It should be noted that designated pictures can be for there is no the pictures of influence of noise, about the specific pattern of designated pictures
It can be set, be not specifically limited herein according to actual needs.
103, the designated pictures and the noisy picture of tool are stored.
It in this application,, will be described according to preset noise jamming method after getting an at least chaff interferent picture
Chaff interferent picture is added in designated pictures, to generate at least one noisy picture of tool, then to the designated pictures and
The noisy picture of tool is stored, wherein the chaff interferent in chaff interferent picture can be according to the interference in actual scene
Object is set, and noise jamming method can also be set according to actual scene, so as to simulate in true environment
The case where being likely encountered, and then the noisy picture of tool generated can be made and obtained when encountering chaff interferent in true environment
Picture more close to so that designated pictures and have the data acquisition system more diversity that noisy picture is constituted, into
And be conducive to make the robustness of data acquisition system stronger, and carrying out picture recognition by designated pictures and the noisy picture of tool
When, it is also beneficial to improve the accuracy rate of recognition result.
In a feasible embodiment, the chaff interferent in the chaff interferent picture includes: soil class, dust class, grass
Consider the screening of class, feed class, excrement class, fence class, class balustrade, sundries class, pigment class, medicament class, uneven light class, bright spot, hand to be worth doing
Gear, clothes class.
Specifically, only including a kind of interference in each chaff interferent picture to improve the authenticity for having noisy picture
Object, when obtaining chaff interferent picture, the chaff interferent picture of available variety classes chaff interferent, and by way of permutation and combination
The chaff interferent picture of at least one chaff interferent is added in designated pictures, to be conducive to improve the true of simulation of real scenes
Degree, thus be conducive to improve have noisy picture picture corresponding with real scene close to degree.
It should be noted that above-mentioned chaff interferent is only the illustrative explanation that the application provides, the application is not constituted
Limit, wherein above-mentioned chaff interferent can also be finely divided according to the actual situation, such as: soil class can be subdivided into yellow mud bar and
Black mud etc., grass cuttings class can be subdivided into green herbage fines and tame hay fines etc., can be according to reality about specific chaff interferent
Border scene is set, and is not specifically limited herein, still, all to block to the object formation in designated pictures, from
And after the picture for obtaining the object, the guarantor of the application is belonged to the chaff interferent that the object in designated pictures forms influence of noise
Protect range.
In a feasible embodiment, Fig. 2 is the process signal of another data processing method provided by the present application
Figure, as shown in Fig. 2, can be realized by following steps when executing step 102:
201, the chaff interferent picture is arranged to the Target Photo of at least one size.
202, the Target Photo is added in the designated pictures, to generate at least one noisy picture of tool.
Specifically, chaff interferent might have a variety of feelings to the area coverage of the object in designated pictures in actual scene
Condition, in order to improve the noisy picture of tool picture corresponding with real scene close to degree, chaff interferent picture can be arranged
At the Target Photo of at least one size, after Target Photo is added in designated pictures, true field can be simulated
Jing Zhong, the area coverage that chaff interferent is likely to occur the object in designated pictures, for example, chaff interferent picture can be arranged to
1cm2、2cm2、3cm2And 4cm2The Target Photo of homalographic size, and the Target Photo of above-mentioned area is respectively added to specify
In picture, has noisy picture to generate.
It should be noted that the specific area and quantity about Target Photo can be set according to actual needs,
This is not specifically limited.
In a feasible embodiment, when executing step 202, the Target Photo can be added to the finger
Determine at least one predeterminated position in picture, to generate at least one noisy picture of tool.
Specifically, chaff interferent is likely to appear on multiple positions due in actual scene, and each chaff interferent
Area coverage is also a variety of, therefore after the Target Photo for determining to have different area coverages, by different area coverages
Target Photo is added on the position being likely to occur in actual scene (i.e. predeterminated position), i.e., different area coverages, different
In predeterminated position and chaff interferent picture the type of chaff interferent generated by the way of permutation and combination corresponding number tool it is noisy
Picture, so that the noisy picture of tool generated can cover all possibility situations in actual scene as far as possible, thus favorably
In the diversity of enhancing designated pictures and the data acquisition system for having noisy picture composition, and then be conducive to improve data acquisition system
Robustness.
In a feasible embodiment, after executing the step 103, can use the noisy picture of the tool and
The designated pictures carry out image recognition to the picture to be identified got;And/or have noisy picture and institute for described
Designated pictures are stated as training set of images, image training is carried out to picture.
Specifically, since the diversity of data acquisition system obtained above is higher, so as to allow model learning to really
Feature, thus can use above-mentioned data acquisition system to picture to be identified carry out image recognition when, image recognition can be improved
Accuracy, also, due to that can learn to real feature, so when using designated pictures and having noisy picture as figure
It is as training set carries out image training to picture, relevant feature can be learnt by deep learning algorithm, to be conducive to enhance
The anti-jamming effectiveness of data acquisition system.
Fig. 3 is a kind of structural schematic diagram of data processing equipment provided by the present application, as shown in figure 3, described device includes:
Acquiring unit 31, for obtaining an at least chaff interferent picture;
Adding unit 32, for according to preset noise jamming method, the chaff interferent picture to be added to designated pictures
In, to generate at least one noisy picture of tool;
Storage unit 33, for being stored to the designated pictures and the noisy picture of tool.
In a feasible embodiment, the chaff interferent in the chaff interferent picture includes:
Soil class, dust class, grass cuttings class, feed class, excrement class, fence class, class balustrade, sundries class, pigment class, medicament
Class, uneven light class, bright spot, the blocking of hand, clothes class.
In a feasible embodiment, it is used in the adding unit 32 according to preset noise jamming method, it will
The chaff interferent picture is added in designated pictures, when generating at least one noisy picture of tool, is used for:
The chaff interferent picture is arranged to the Target Photo of at least one size;
The Target Photo is added in the designated pictures, to generate at least one noisy picture of tool.
In a feasible embodiment, it is used to the Target Photo being added to the finger in the adding unit 32
Determine in picture, when generating at least one noisy picture of tool, be used for:
The Target Photo is added at least one predeterminated position in the designated pictures, to generate at least one
Has noisy picture.
In a feasible embodiment, Fig. 4 is the structural representation of another data processing equipment provided by the present application
Figure, as shown in figure 4, described device further include:
Recognition unit 34, for be identified to what is got using the noisy picture of the tool and the designated pictures
Picture carries out image recognition;And/or
Training unit 35 is used for using the noisy picture of the tool and the designated pictures as training set of images to picture
Carry out image training.
The concrete mode of execution operation about each unit in above-described embodiment is in the embodiment in relation to this method
In be described in detail, no detailed explanation will be given here.
It in this application,, will be described according to preset noise jamming method after getting an at least chaff interferent picture
Chaff interferent picture is added in designated pictures, to generate at least one noisy picture of tool, then to the designated pictures and
The noisy picture of tool is stored, wherein the chaff interferent in chaff interferent picture can be according to the interference in actual scene
Object is set, and noise jamming method can also be set according to actual scene, so as to simulate in true environment
The case where being likely encountered, and then the noisy picture of tool generated can be made and obtained when encountering chaff interferent in true environment
Picture more close to so that designated pictures and have the data acquisition system more diversity that noisy picture is constituted, into
And be conducive to make the robustness of data acquisition system stronger, and carrying out picture recognition by designated pictures and the noisy picture of tool
When, it is also beneficial to improve the accuracy rate of recognition result.
The foregoing is merely preferred embodiment of the present application, are not intended to limit this application, for the skill of this field
For art personnel, various changes and changes are possible in this application.Within the spirit and principles of this application, made any to repair
Change, equivalent replacement, improvement etc., should be included within the scope of protection of this application.
Claims (10)
1. a kind of data processing method, which is characterized in that the described method includes:
Obtain an at least chaff interferent picture;
According to preset noise jamming method, the chaff interferent picture is added in designated pictures, to generate at least one tool
Noisy picture;
The designated pictures and the noisy picture of tool are stored.
2. the method as described in claim 1, which is characterized in that the chaff interferent in the chaff interferent picture includes:
Soil class, dust class, grass cuttings class, feed class, excrement class, fence class, class balustrade, sundries class, pigment class, medicament class, no
Uniform light class, bright spot, the blocking of hand, clothes class.
3. the method as described in claim 1, which is characterized in that according to preset noise jamming method, by the chaff interferent figure
Piece is added in designated pictures, includes: to generate at least one noisy picture of tool
The chaff interferent picture is arranged to the Target Photo of at least one size;
The Target Photo is added in the designated pictures, to generate at least one noisy picture of tool.
4. method as claimed in claim 3, which is characterized in that the Target Photo is added in the designated pictures, with
Generating at least one noisy picture of tool includes:
The Target Photo is added at least one predeterminated position in the designated pictures, is had to generate at least one
The picture of noise.
5. the method as described in claim 1, which is characterized in that the method also includes:
Image recognition is carried out to the picture to be identified got using the noisy picture of the tool and the designated pictures;
And/or
Image training is carried out to picture using the noisy picture of the tool and the designated pictures as training set of images.
6. a kind of data processing equipment, which is characterized in that described device includes:
Acquiring unit, for obtaining an at least chaff interferent picture;
Adding unit, for the chaff interferent picture being added in designated pictures, with life according to preset noise jamming method
At at least one noisy picture of tool;
Storage unit, for being stored to the designated pictures and the noisy picture of tool.
7. device as claimed in claim 6, which is characterized in that the chaff interferent in the chaff interferent picture includes:
Soil class, dust class, grass cuttings class, feed class, excrement class, fence class, class balustrade, sundries class, pigment class, medicament class, no
Uniform light class, bright spot, the blocking of hand, clothes class.
8. device as claimed in claim 6, which is characterized in that be used in the adding unit according to preset noise jamming side
The chaff interferent picture is added in designated pictures by method, when generating at least one noisy picture of tool, is used for:
The chaff interferent picture is arranged to the Target Photo of at least one size;
The Target Photo is added in the designated pictures, to generate at least one noisy picture of tool.
9. device as claimed in claim 8, which is characterized in that be used to for the Target Photo being added in the adding unit
In the designated pictures, when generating at least one noisy picture of tool, it is used for:
The Target Photo is added at least one predeterminated position in the designated pictures, is had to generate at least one
The picture of noise.
10. device as claimed in claim 6, which is characterized in that described device further include:
Recognition unit, for using the noisy picture of the tool and the designated pictures to the picture to be identified got into
Row image recognition;And/or
Training unit, for carrying out figure to picture using the noisy picture of the tool and the designated pictures as training set of images
As training.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810995761.3A CN109345468A (en) | 2018-08-29 | 2018-08-29 | Data processing method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810995761.3A CN109345468A (en) | 2018-08-29 | 2018-08-29 | Data processing method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109345468A true CN109345468A (en) | 2019-02-15 |
Family
ID=65291890
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810995761.3A Pending CN109345468A (en) | 2018-08-29 | 2018-08-29 | Data processing method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109345468A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110292774A (en) * | 2019-06-28 | 2019-10-01 | 广州华多网络科技有限公司 | One kind is found fault picture materials processing method, device, equipment and storage medium |
CN110933353A (en) * | 2019-12-17 | 2020-03-27 | 中国科学院长春光学精密机械与物理研究所 | Video interference injection generator |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120294525A1 (en) * | 2011-05-19 | 2012-11-22 | Foveon, Inc. | Methods for suppressing structured noise in a digital image |
CN104966097A (en) * | 2015-06-12 | 2015-10-07 | 成都数联铭品科技有限公司 | Complex character recognition method based on deep learning |
CN105139337A (en) * | 2015-09-10 | 2015-12-09 | 北京金山安全软件有限公司 | Picture generation method and device |
CN105976345A (en) * | 2016-04-27 | 2016-09-28 | 北京航空航天大学 | Visible light remote sensing image synthesis method |
CN107292886A (en) * | 2017-08-11 | 2017-10-24 | 厦门市美亚柏科信息股份有限公司 | Object intrusion detection method and device based on mesh generation and neutral net |
CN107784316A (en) * | 2016-08-26 | 2018-03-09 | 阿里巴巴集团控股有限公司 | A kind of image-recognizing method, device, system and computing device |
CN108236784A (en) * | 2018-01-22 | 2018-07-03 | 腾讯科技(深圳)有限公司 | The training method and device of model, storage medium, electronic device |
CN108460414A (en) * | 2018-02-27 | 2018-08-28 | 北京三快在线科技有限公司 | Generation method, device and the electronic equipment of training sample image |
-
2018
- 2018-08-29 CN CN201810995761.3A patent/CN109345468A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120294525A1 (en) * | 2011-05-19 | 2012-11-22 | Foveon, Inc. | Methods for suppressing structured noise in a digital image |
CN104966097A (en) * | 2015-06-12 | 2015-10-07 | 成都数联铭品科技有限公司 | Complex character recognition method based on deep learning |
CN105139337A (en) * | 2015-09-10 | 2015-12-09 | 北京金山安全软件有限公司 | Picture generation method and device |
CN105976345A (en) * | 2016-04-27 | 2016-09-28 | 北京航空航天大学 | Visible light remote sensing image synthesis method |
CN107784316A (en) * | 2016-08-26 | 2018-03-09 | 阿里巴巴集团控股有限公司 | A kind of image-recognizing method, device, system and computing device |
CN107292886A (en) * | 2017-08-11 | 2017-10-24 | 厦门市美亚柏科信息股份有限公司 | Object intrusion detection method and device based on mesh generation and neutral net |
CN108236784A (en) * | 2018-01-22 | 2018-07-03 | 腾讯科技(深圳)有限公司 | The training method and device of model, storage medium, electronic device |
CN108460414A (en) * | 2018-02-27 | 2018-08-28 | 北京三快在线科技有限公司 | Generation method, device and the electronic equipment of training sample image |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110292774A (en) * | 2019-06-28 | 2019-10-01 | 广州华多网络科技有限公司 | One kind is found fault picture materials processing method, device, equipment and storage medium |
CN110933353A (en) * | 2019-12-17 | 2020-03-27 | 中国科学院长春光学精密机械与物理研究所 | Video interference injection generator |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Liu et al. | Reflection backdoor: A natural backdoor attack on deep neural networks | |
CN108492281B (en) | Bridge crack image obstacle detection and removal method based on generation type countermeasure network | |
Yu et al. | Learning a discriminative feature network for semantic segmentation | |
CN105184778B (en) | A kind of detection method and device | |
CN109360232B (en) | Indoor scene layout estimation method and device based on condition generation countermeasure network | |
Carpin et al. | Quantitative assessments of USARSim accuracy | |
CN103699908B (en) | Video multi-target tracking based on associating reasoning | |
CN102844768B (en) | The shielding of image template | |
EP1872334A2 (en) | Method and system for the detection and the classification of events during motion actions | |
CN101883209B (en) | Method for integrating background model and three-frame difference to detect video background | |
CN102028482A (en) | Human body detection image processing method and human body detection apparatus | |
CN107688345A (en) | Screen state automatic detection machine people, method and computer-readable recording medium | |
CN103955950B (en) | Image tracking method utilizing key point feature matching | |
CN108230355A (en) | Target following and neural network training method, device, storage medium and electronic equipment | |
CN108854069A (en) | Source of sound determines method and apparatus, storage medium and electronic device | |
CN109345468A (en) | Data processing method and device | |
CN109635740A (en) | Video object detection method, device and image processing equipment | |
CN110348434A (en) | Camera source discrimination method, system, storage medium and calculating equipment | |
Kim et al. | Sanity simulations for saliency methods | |
CN106327531A (en) | Panorama video identification method and device, and video playing method and device | |
CN106331848A (en) | Panoramic video identification method and device, and video playing method and device | |
CN105070094A (en) | Machine vision based parking space detection system and parking space detection method | |
CN101833760A (en) | Background modeling method and device based on image blocks | |
Skinner et al. | The probabilistic object detection challenge | |
Afzali et al. | Foreground and background feature fusion using a convex hull based center prior for salient object detection |
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: 20190215 |