CN104766082B - Image-recognizing method and device based on android system - Google Patents
Image-recognizing method and device based on android system Download PDFInfo
- Publication number
- CN104766082B CN104766082B CN201510124226.7A CN201510124226A CN104766082B CN 104766082 B CN104766082 B CN 104766082B CN 201510124226 A CN201510124226 A CN 201510124226A CN 104766082 B CN104766082 B CN 104766082B
- Authority
- CN
- China
- Prior art keywords
- image
- pixel
- feature
- information
- screen
- 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
Landscapes
- Image Analysis (AREA)
Abstract
A kind of image-recognizing method based on android system and device, described device carry out step S201:Image recognition order is received, the feature for the image that step S203 loads require to look up then is carried out;It then carries out step S205 and obtains current screen display information, the method that the acquisition current screen shows information is to access the internal storage data of current Android system, obtains Android system current screen image.Feature then based on displaying information on screen and the image required to look up carries out step S209 matching treatments;It finally carries out S211 outputs matching treatment result and passes through the above method, can screen data directly be obtained from memory, save previous memory and open load image file, parse the time of image data, so that whole image recognition time is greatly shortened, also search efficiency is made to be improved significantly.
Description
Technical field
The present invention relates to field of image recognition more particularly to a kind of image-recognizing methods based on android system.
Background technology
At present in Android device (operating system is the electronic equipments such as mobile phone, tablet computer, the TV of Android system)
Image recognition major way is to load different picture by Android applications to carry out point-by-point pixel comparison identification, or only
Sectional drawing can be carried out using the interface of itself for Android, point-by-point pixel comparison identification is carried out after then loading.With informationization
Deepen continuously, the data entrained by image are also increasing, and there are its following disadvantages for above-mentioned point-by-point pixel comparison recognition methods:
1) target and lookup image, which are required for reading, loads, and entire recognition time is made to greatly increase.2) Android can only be directed to apply certainly
It the interface of body, can not across different application carry out sectional drawing identification into the identification of Mobile state sectional drawing.
Invention content
For this reason, it may be necessary to provide a kind of technology across application identification image, saves to know and scheme the required time.It is above-mentioned to realize
Purpose inventor provides a kind of image-recognizing method based on android system, includes the following steps:
Image recognition order is received, the feature of the image required to look up is loaded;
It obtains current screen and shows information, the feature progress based on displaying information on screen and the image required to look up
With processing;
Export matching treatment result.
Specifically, described image recognition command includes path, similarity or the seeking scope of the image required to look up, it is described
The feature of image includes the length and width or Pixel Information of image.
Specifically, the matching treatment specifically includes:According to similarity calculation step-length, step width;
The Pixel Information for extracting vertex in the feature of image, the Pixel Information is matched point by point with displaying information on screen,
Obtain the first vertex pixel;
It is determined other three in displaying information on screen according to long and wide information in the feature of the first vertex pixel and image
A vertex pixel position simultaneously carries out matching judgment respectively;
Determine that target block, the target block are using the vertex pixel as the rectangle on vertex according to vertex pixel
The edge pixel point of the target block is chosen edge pixel sampled point, by edge picture by block of pixels according to step-length and step width
The feature of plain sampled point and image carries out matching judgment;
Target block sampled point is chosen according to step-length and step width in the target block, by the target block sampled point
Matching judgment is carried out with the feature of image, the first vertex pixel is re-searched for if any of the above-described matching judgment step mismatches
Otherwise point returns to successful match information.
Further, further include step:Initialization operation is carried out, the initialization operation includes obtaining Android system version
Originally, screen message.
Further, it further includes step to obtain after current screen shows information:The displaying information on screen is formatted.
A kind of pattern recognition device based on android system, including following module:Order receiver module, feature load mould
Block, screen message acquisition module and matching module;
The Order receiver module is for receiving image recognition order;The feature load-on module is required to look up for loading
Image feature;The screen message acquisition module shows that information, the matching module are used for base for obtaining current screen
Matching treatment is carried out in the feature of displaying information on screen and the image required to look up and exports matching treatment result.
Specifically, the image recognition order that the Order receiver module receives includes the path of the image required to look up, phase
Like degree or seeking scope, the feature of the image of the feature load-on module load includes the length and width or Pixel Information of image.
Specifically, the matching treatment that the matching module carries out specifically includes:According to similarity calculation step-length, step width;
The Pixel Information for extracting vertex in the feature of image, the Pixel Information is matched point by point with displaying information on screen,
Obtain the first vertex pixel;
It is determined other three in displaying information on screen according to long and wide information in the feature of the first vertex pixel and image
A vertex pixel position simultaneously carries out matching judgment respectively;
Determine that target block, the target block are using the vertex pixel as the rectangle on vertex according to vertex pixel
The edge pixel point of the target block is chosen edge pixel sampled point, by edge picture by block of pixels according to step-length and step width
The feature of plain sampled point and image carries out matching judgment;
Target block sampled point is chosen according to step-length and step width in the target block, by the target block sampled point
Matching judgment is carried out with the feature of image, the first vertex pixel is re-searched for if any of the above-described matching judgment step mismatches
Otherwise point returns to successful match information.
Further, further include initialization module:The initialization module is for carrying out initialization operation, the initialization
Operation includes obtaining Android system version, screen message.
Further, further include formatting module, the formatting module is for formatting the displaying information on screen.
It is different from the prior art, above-mentioned technical proposal removes opening loading figure by directly obtaining screen data from memory
As file, the time of image data is parsed, whole image recognition time is made to greatly shorten, while obtained step-length using similarity and searching
Rope image border reduces search time, also search efficiency is made to significantly improve.
Description of the drawings
Fig. 1 is the structural schematic diagram of screen picture identification device based on android system described in an embodiment of the present invention;
Fig. 2 is the flow chart of screen picture recognition methods based on android system described in an embodiment of the present invention.
Reference sign:
101, Order receiver module;
103, feature load-on module;
105, screen message acquisition module;
107, matching module;
109, initialization module;
111, formatting module.
Specific implementation mode
For the technology contents of technical solution, construction feature, the objects and the effects are described in detail, below in conjunction with specific reality
It applies example and attached drawing is coordinated to be explained in detail.
Referring to Fig. 1, for the flow chart of image-recognizing method based on android system described in an embodiment of the present invention, it should
Described method includes following steps for method:
Step S201:Image recognition order is received,
Step S203:Load the feature of the image required to look up;
Step S205:It obtains current screen and shows that information, the current screen that obtains show that the method for information is worked as to access
The internal storage data of preceding Android system obtains Android system current screen image.
Feature based on displaying information on screen and the image required to look up carries out step S209 matching treatments;
S211 exports matching treatment as a result, return to successful match information such as successful match if, otherwise return " search for less than
With image " information.
By the above method, can screen data directly be obtained from memory, save previous memory and open load image text
Part parses the time of image data, so that whole image recognition time is greatly shortened, also search efficiency is made to be improved significantly.
In certain specific embodiments based on the above method, described image recognition command includes the image required to look up
Path, similarity or seeking scope, wherein the path of the image required to look up be it is necessary, described device is carried according to above-mentioned path
The image required to look up is taken, extracts the feature of image, the feature of described image includes the length and width or Pixel Information of image, described
The information of all pixels point in Pixel Information, that is, image.Image recognition order can include similarity and seeking scope, the phase
It can be configured as needed with seeking scope like degree, user can be allowed voluntarily to input to Order receiver module, when image is known
Not Zhi Ling in do not contain similarity when, can give tacit consent to similarity be 1;Seeking scope information is not contained in image recognition instructs
When, it is screen picture using the upper left corner as starting point that can give tacit consent to seeking scope, and image length multiplies wide range.It is identified by refined image
Order and image feature information, and allow to need to be adjusted according to user, improve the practicability and identification effect of this method
Rate.
Specifically, the matching treatment specifically includes:According to value unit of account step-length, the unit step width of similarity;Wherein
One step is (1-S) * H roundings, unit step width is (1-S) * W roundings, and the unit of step-length and step width is (pixel);
The Pixel Information on any vertex in four vertex in the feature of image is then extracted, then the Pixel Information on the vertex
It is matched point by point with displaying information on screen, matching can be since displaying information on screen any direction, we are to extract the spy of image
In sign for the Pixel Information of left upper apex, from left to right, matched point by point in displaying information on screen from top to bottom, until
Find in displaying information on screen it is that certain puts match with vertex Pixel Information, by this in displaying information on screen o'clock as the
One vertex pixel, and determine the first vertex pixel position (cx,cy);
It is determined in displaying information on screen according to the information of (H) long in the feature of the first vertex pixel and image and wide (W)
The other three vertex pixel position { (cx+H,cy)、(cx,cy+ W) and (cx+H,cy+ W) } and respectively with it is another in the feature of image
The Pixel Information of outer three corresponding vertexs carries out matching judgment;Following step is continued to execute if judging to match.
Determine that target block, the target block are true as vertex using four vertex pixels according to vertex pixel
The edge pixel point of the target block is chosen edge pixel sampled point by fixed rectangular pixels block according to step-length and step width,
The information of corresponding points in the feature of edge pixel sampled point and image is subjected to edge matching judgement;Continue if being judged as matching
Carry out following step.
Target block sampled point is chosen according to step-length and step width in the target block, in some embodiments it is possible to
Sampled point is chosen every unit step width in target block the first row, then moves down unit one step row, is continued every unit step width
Choose sampled point.It is complete until choosing.By the Pixel Information of corresponding position in the feature of the target block sampled point and image
Carry out point-by-point matching judgment.The first vertex pixel is re-searched for if any of the above-described matching judgment step mismatches, is otherwise returned
Return successful match information.Pass through vertex matching, edge matching and point-by-point matched matching judgment step in matching treatment so that
With not only more efficient, and the adjustable matching judgment of precision can also be carried out according to similarity, user can be according to actual needs
Similarity is adjusted, this method is also improved and disclosure satisfy that more actual conditions.
Further, described device also carries out step S200:Initialization operation is carried out, the initialization operation includes obtaining
Android system version, screen message.The screen message is the screen message of fb_var_screeninfo structures.In certain tools
In the embodiment of body, in the executable file that the program finished write-in Android system is supported, described program is encoded for obtaining
The initialization informations such as Android system version, displaying information on screen.The executable file is executing we there are in Android system
When method, above-mentioned executable file is loaded and runs by the Shell instructions of Android system, the Shell instructions are Androids
The user interface of system provides user and interacts a kind of interface of operation with kernel.It receives order input by user simultaneously
It is sent into kernel to go to execute.After the executable file operation, carry out obtaining the initialization such as Android system version, screen message
Operation.Pass through above-mentioned initialization operation so that this method can be according to the more targeted acquisition memory of version of Android system
In displaying information on screen, improve the execution efficiency of this method.
Further, it further includes step S207 that described device, which obtains after current screen shows information,:The screen is shown
Show information format.In some specific embodiments, show that the image position (AP) of information will shield by the current screen of acquisition
Curtain shows the pixel-matrix of information, is converted into rgb format.Conversion regime is as follows:Pass through the transp knots in displaying information on screen
The value of offset and the value of the offset in red, green, blue structure, pass through formula in structure:
(Color>>offset)&0xFF
Obtain the value of R, G, B three-primary colours.Pass through formula again
Color=(R<<24)+(G<<16)+B
Obtain the pixel of rgb format.
Carrying out format conversion is advantageous in that convenient for identification, and rgb format is enabled to follow-up due to its higher universality
Pixel extraction, matching and etc. it is more convenient.
Further include pattern recognition device based on android system, structural schematic diagram such as Fig. 1 institutes in certain embodiment of the invention
Show, including following module:Order receiver module 101, feature load-on module 103, screen message acquisition module 105 and matching module
107;
The Order receiver module receives image recognition order for carrying out step S201;The feature load-on module is used for
Carry out the feature for the image that step S203 loads require to look up;The screen message acquisition module is for carrying out step S205 acquisitions
Current screen shows information, the matching module be used for the feature based on displaying information on screen and the image required to look up into
Row step S209 matching treatments and step S211 export matching treatment result.Be arranged by above-mentioned module, device can directly from
Memory obtains screen data, saves previous memory and opens load image file, parses the time of image data, make whole image
Recognition time greatly shortens, and also search efficiency is made to be improved significantly.
Specifically, the image recognition order that the Order receiver module receives includes the path of the image required to look up, phase
Like degree or seeking scope, the feature of the image of the feature load-on module load includes the length and width or Pixel Information of image.Pass through
Refined image recognition command and image feature information, and allow to need to be adjusted according to user, improve the practicality of the present apparatus
Property and recognition efficiency.
Specifically, the matching treatment that the matching module 107 carries out specifically includes:According to similarity calculation step-length, step width;
The Pixel Information for extracting vertex in the feature of image, the Pixel Information is matched point by point with displaying information on screen,
Obtain the first vertex pixel;
It is determined other three in displaying information on screen according to long and wide information in the feature of the first vertex pixel and image
A vertex pixel position simultaneously carries out matching judgment respectively;
Determine that target block, the target block are using the vertex pixel as the rectangle on vertex according to vertex pixel
The edge pixel point of the target block is chosen edge pixel sampled point, by edge picture by block of pixels according to step-length and step width
The feature of plain sampled point and image carries out matching judgment;
Target block sampled point is chosen according to step-length and step width in the target block, by the target block sampled point
Matching judgment is carried out with the feature of image, the first vertex pixel is re-searched for if any of the above-described matching judgment step mismatches
Otherwise point returns to successful match information.Pass through vertex matching, edge matching and point-by-point matched matching judgment step in matching treatment
Suddenly so that matching is not only more efficient, and can also carry out the adjustable matching judgment of precision according to similarity, and user can basis
Actual needs adjustment similarity, also improves the practicability of the present apparatus.
Further, further include initialization module 209:The initialization module is for carrying out step S200 initialization behaviour
Make, the initialization operation includes obtaining Android system version, screen message.The screen message is fb_var_
The screen message of screeninfo structures.Pass through above-mentioned initialization module 209 so that the present apparatus can be according to the version of Android system
This more targeted displaying information on screen obtained in memory, improves the execution efficiency of this method.
Further, further include formatting module 211, the formatting module is for carrying out step S207 by the screen
Show information format.Carrying out format conversion is advantageous in that rgb format, can due to its higher universality convenient for identification
So that later pixel extraction, matching and etc. it is more convenient.
It should be noted that herein, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that process, method, article or terminal device including a series of elements include not only those
Element, but also include other elements that are not explicitly listed, or further include for this process, method, article or end
The intrinsic element of end equipment.In the absence of more restrictions, being limited by sentence " including ... " or " including ... "
Element, it is not excluded that there is also other elements in process, method, article or the terminal device including the element.This
Outside, herein, " being more than ", " being less than ", " being more than " etc. are interpreted as not including this number;" more than ", " following ", " within " etc. understandings
It includes this number to be.
It should be understood by those skilled in the art that, the various embodiments described above can be provided as method, apparatus or computer program production
Product.Complete hardware embodiment, complete software embodiment or embodiment combining software and hardware aspects can be used in these embodiments
Form.All or part of step in the method that the various embodiments described above are related to can be instructed by program relevant hardware come
It completes, the program can be stored in the storage medium that computer equipment can be read, for executing the various embodiments described above side
All or part of step described in method.The computer equipment, including but not limited to:Personal computer, server, general-purpose computations
It is machine, special purpose computer, the network equipment, embedded device, programmable device, intelligent mobile terminal, smart home device, wearable
Smart machine, vehicle intelligent equipment etc.;The storage medium, including but not limited to:RAM, ROM, magnetic disc, tape, CD, sudden strain of a muscle
It deposits, USB flash disk, mobile hard disk, storage card, memory stick, webserver storage, network cloud storage etc..
The various embodiments described above are with reference to method, equipment (system) and the computer program product according to embodiment
Flowchart and/or the block diagram describes.It should be understood that can be realized by computer program instructions every in flowchart and/or the block diagram
The combination of flow and/or box in one flow and/or box and flowchart and/or the block diagram.These computers can be provided
Program instruction is to the processor of computer equipment to generate a machine so that the finger executed by the processor of computer equipment
It enables and generates to specify in one flow of flow chart or multiple flows and/or one box of block diagram or multiple boxes
The device of function.
These computer program instructions, which may also be stored in, can guide computer equipment computer operate in a specific manner to set
In standby readable memory so that the instruction generation being stored in the computer equipment readable memory includes the manufacture of command device
Product, command device realization refer in one flow of flow chart or multiple flows and/or one box of block diagram or multiple boxes
Fixed function.
These computer program instructions can be also loaded on computer equipment so that be executed on a computing device a series of
To generate computer implemented processing, the instruction to execute on a computing device is provided for realizing in flow operating procedure
The step of function of being specified in one flow of figure or multiple flows and/or one box of block diagram or multiple boxes.
Although the various embodiments described above are described, once a person skilled in the art knows basic wounds
The property made concept, then additional changes and modifications can be made to these embodiments, so example the above is only the implementation of the present invention,
It is not intended to limit the scope of patent protection of the present invention, it is every to utilize equivalent structure made by description of the invention and accompanying drawing content
Or equivalent process transformation, it is applied directly or indirectly in other relevant technical fields, the patent for being similarly included in the present invention
Within protection domain.
Claims (6)
1. a kind of image-recognizing method based on android system, which is characterized in that include the following steps:
Image recognition order is received, the feature of the image required to look up is loaded;
It obtains current screen and shows information, the method for obtaining current screen display information is the interior of the current Android system of access
Deposit data obtains Android system current screen image, based on the feature of displaying information on screen and the image required to look up into
Row matching treatment;
Export matching treatment result;
Described image recognition command includes path, similarity or the seeking scope of the image required to look up, the feature of described image
Length and width including image or Pixel Information;
The matching treatment specifically includes:According to similarity calculation step-length, step width;
The Pixel Information for extracting vertex in the feature of image, the Pixel Information is matched point by point with displaying information on screen, is obtained
First vertex pixel;
The other three top in displaying information on screen is determined according to long and wide information in the feature of the first vertex pixel and image
Point pixel position simultaneously carries out matching judgment respectively;
Determine that target block, the target block are using the vertex pixel as the rectangular pixels on vertex according to vertex pixel
The edge pixel point of the target block is chosen edge pixel sampled point according to step-length and step width, edge pixel is adopted by block
The feature of sampling point and image carries out matching judgment;
Target block sampled point is chosen according to step-length and step width in the target block, by the target block sampled point and figure
The feature of picture carries out matching judgment, and the first vertex pixel is re-searched for if any of the above-described matching judgment step mismatches, no
Then return to successful match information.
2. image-recognizing method based on android system according to claim 1, which is characterized in that further include step:Into
Row initialization operation, the initialization operation include obtaining Android system version, screen message.
3. image-recognizing method based on android system according to claim 1, which is characterized in that it is aobvious to obtain current screen
Show that information further includes later step:The displaying information on screen is formatted.
4. a kind of pattern recognition device based on android system, which is characterized in that including following module:Order receiver module, spy
Levy load-on module, screen message acquisition module and matching module;
The Order receiver module is for receiving image recognition order;The feature load-on module is for loading the figure required to look up
The feature of picture;The screen message acquisition module shows that information, the matching module are used for based on screen for obtaining current screen
Curtain shows that the feature of information and the image required to look up carries out matching treatment and exports matching treatment result;
The image recognition order that the Order receiver module receives includes path, similarity or the lookup model of the image required to look up
It encloses, the feature of the image of the feature load-on module load includes the length and width or Pixel Information of image;
The matching treatment that the matching module carries out specifically includes:According to similarity calculation step-length, step width;
The Pixel Information for extracting vertex in the feature of image, the Pixel Information is matched point by point with displaying information on screen, is obtained
First vertex pixel;
The other three top in displaying information on screen is determined according to long and wide information in the feature of the first vertex pixel and image
Point pixel position simultaneously carries out matching judgment respectively;
Determine that target block, the target block are using the vertex pixel as the rectangular pixels on vertex according to vertex pixel
The edge pixel point of the target block is chosen edge pixel sampled point according to step-length and step width, edge pixel is adopted by block
The feature of sampling point and image carries out matching judgment;
Target block sampled point is chosen according to step-length and step width in the target block, by the target block sampled point and figure
The feature of picture carries out matching judgment, and the first vertex pixel is re-searched for if any of the above-described matching judgment step mismatches, no
Then return to successful match information.
5. pattern recognition device based on android system according to claim 4, which is characterized in that further include initialization mould
Block:The initialization module includes obtaining Android system version, screen letter for carrying out initialization operation, the initialization operation
Breath.
6. pattern recognition device based on android system according to claim 4, which is characterized in that further include formatting mould
Block, the formatting module is for formatting the displaying information on screen.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510124226.7A CN104766082B (en) | 2015-03-20 | 2015-03-20 | Image-recognizing method and device based on android system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510124226.7A CN104766082B (en) | 2015-03-20 | 2015-03-20 | Image-recognizing method and device based on android system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104766082A CN104766082A (en) | 2015-07-08 |
CN104766082B true CN104766082B (en) | 2018-08-14 |
Family
ID=53647896
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510124226.7A Active CN104766082B (en) | 2015-03-20 | 2015-03-20 | Image-recognizing method and device based on android system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104766082B (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106327457B (en) * | 2016-08-23 | 2020-02-18 | 北京金山安全软件有限公司 | Picture processing method, device and equipment |
CN106375769B (en) * | 2016-08-31 | 2019-04-30 | 西安万像电子科技有限公司 | Characteristics of image searching method and device, storage medium and processor |
CN110245668B (en) * | 2018-03-09 | 2023-06-27 | 腾讯科技(深圳)有限公司 | Terminal information acquisition method, acquisition device and storage medium based on image recognition |
CN110533742B (en) * | 2019-09-03 | 2021-05-11 | 广州视源电子科技股份有限公司 | Image color filling method, device, equipment and storage medium |
US11321409B2 (en) * | 2020-01-21 | 2022-05-03 | International Business Machines Corporation | Performing a search based on position information |
CN111860385A (en) * | 2020-07-27 | 2020-10-30 | 珠海研果科技有限公司 | Target identification method and device |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101000623A (en) * | 2007-01-08 | 2007-07-18 | 深圳市宜搜科技发展有限公司 | Method for image identification search by mobile phone photographing and device using the method |
CN101276363A (en) * | 2007-03-30 | 2008-10-01 | 夏普株式会社 | Document image retrieval device and document image retrieval method |
CN101464951A (en) * | 2007-12-21 | 2009-06-24 | 北大方正集团有限公司 | Image recognition method and system |
CN103198317A (en) * | 2011-12-14 | 2013-07-10 | 韩国电子通信研究院 | Image processing device and image processing method |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP4366886B2 (en) * | 2001-05-24 | 2009-11-18 | コニカミノルタビジネステクノロジーズ株式会社 | Apparatus and method for image recognition |
-
2015
- 2015-03-20 CN CN201510124226.7A patent/CN104766082B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101000623A (en) * | 2007-01-08 | 2007-07-18 | 深圳市宜搜科技发展有限公司 | Method for image identification search by mobile phone photographing and device using the method |
CN101276363A (en) * | 2007-03-30 | 2008-10-01 | 夏普株式会社 | Document image retrieval device and document image retrieval method |
CN101464951A (en) * | 2007-12-21 | 2009-06-24 | 北大方正集团有限公司 | Image recognition method and system |
CN103198317A (en) * | 2011-12-14 | 2013-07-10 | 韩国电子通信研究院 | Image processing device and image processing method |
Non-Patent Citations (2)
Title |
---|
"Android系统上基于内容的图像检索研究";蒋晟;《中国优秀硕士学位论文全文数据库信息科技辑》;20131115(第11期);第1,11,25,26,29,34-36,41,43,45,51页 * |
"基于像素抽样的快速互相关图像匹配算法";曹炬 等;《宇航学报》;20040331;第25卷(第2期);第173-178页 * |
Also Published As
Publication number | Publication date |
---|---|
CN104766082A (en) | 2015-07-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104766082B (en) | Image-recognizing method and device based on android system | |
US9811894B2 (en) | Image processing method and apparatus | |
Chen et al. | Semantic segmentation of aerial images with shuffling convolutional neural networks | |
CN109255346A (en) | Reading method, device and electronic equipment | |
CN111275784B (en) | Method and device for generating image | |
CN110298413A (en) | Image characteristic extracting method, device, storage medium and electronic equipment | |
CN105184289B (en) | Character identifying method and device | |
Chu et al. | Image Retrieval Based on a Multi‐Integration Features Model | |
CN107368550B (en) | Information acquisition method, device, medium, electronic device, server and system | |
CN104866755B (en) | Setting method and device for background picture of application program unlocking interface and electronic equipment | |
CN107315824A (en) | Method and apparatus for generating thermodynamic chart | |
CN108734185A (en) | Image verification method and apparatus | |
CN113254683B (en) | Data processing method and device, and tag identification method and device | |
CN104978045B (en) | A kind of Chinese character input method and device | |
US20130283260A1 (en) | Image guided method for installing application software | |
CN112069341A (en) | Background picture generation and search result display method, device, equipment and medium | |
CN103871014B (en) | Change the method and device of color of image | |
CN106096043A (en) | A kind of photographic method and mobile terminal | |
Wang et al. | Multiple-environment Self-adaptive Network for Aerial-view Geo-localization | |
CN110580446A (en) | Behavior semantic subdivision understanding method, system, computer device and medium | |
CN110427915A (en) | Method and apparatus for output information | |
CN108985421A (en) | The generation method and recognition methods of encoded information | |
CN110533020A (en) | A kind of recognition methods of text information, device and storage medium | |
CN105913024B (en) | The Android mobile phone endpoint detection methods of resistance Replay Attack based on LAP operator | |
KR20200127928A (en) | Method and apparatus for recognizing object of image in electronic device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
EXSB | Decision made by sipo to initiate substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |