CN107357819A - A kind of input method, device, mobile terminal and storage medium for searching for content - Google Patents
A kind of input method, device, mobile terminal and storage medium for searching for content Download PDFInfo
- Publication number
- CN107357819A CN107357819A CN201710446426.3A CN201710446426A CN107357819A CN 107357819 A CN107357819 A CN 107357819A CN 201710446426 A CN201710446426 A CN 201710446426A CN 107357819 A CN107357819 A CN 107357819A
- Authority
- CN
- China
- Prior art keywords
- image
- searching
- probability
- identified
- preset range
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Library & Information Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Image Analysis (AREA)
Abstract
The applicable field of computer technology of the present invention, there is provided a kind of input method, device, mobile terminal and storage medium for searching for content, this method include：Search target of taking pictures is treated to be taken pictures, obtain target image, obtain the image in target image preset range, image in preset range is identified, obtain the first searching probability of corresponding first recognition result, by 180 ° of image rotation in preset range, postrotational image is identified, obtain the second searching probability of corresponding second recognition result, when the first searching probability is less than the second searching probability, target image is rotated 180 °, postrotational target image is identified, corresponding 3rd recognition result is arranged to content to be searched, content to be searched is input in corresponding search box, so as to improve the accuracy for obtaining search content, and then improve the efficiency for search of taking pictures.
Description
Technical field
The invention belongs to field of computer technology, more particularly to a kind of input method for searching for content, device, mobile terminal
And storage medium.
Background technology
At present, with the development for search of taking pictures, increasing online education APP, which is proposed to take pictures, searches topic.Take pictures and search topic
Be primarily referred to as " image of topic is obtained by way of taking pictures, is then scanned for the image of topic as the content of input,
The parsing of corresponding problem is obtained from cloud database or corresponding database " such a process.Existing search of taking pictures
Application program needs user to be shot manually to the topic searched for of needs, because user is when topic shoot, screen with
Literal line has certain angle, so just needs to correct literal line before topic is searched, and calculate by existing image
Method, it is difficult to judge whether word stands upside down, if the image after correction stands upside down, search success rate can be directly affected.
The content of the invention
It is an object of the invention to provide a kind of input method, device, mobile terminal and storage medium for searching for content, purport
Solving effectively to wait search target image processing method of taking pictures because prior art can not provide one kind, causing search content defeated
Enter the problem of inaccurate, search efficiency is low.
On the one hand, the invention provides a kind of input method for searching for content, methods described to comprise the steps：
Treat search target of taking pictures to be taken pictures, obtain target image；
The image in the target image preset range is obtained, the image in the preset range is identified, is obtained
First searching probability of corresponding first recognition result；
By 180 ° of image rotation in the preset range, the postrotational image is identified, obtains corresponding the
Second searching probability of two recognition results；
When first searching probability is less than second searching probability, the target image is rotated 180 °；
Postrotational target image is identified, corresponding 3rd recognition result is arranged to content to be searched, by described in
Content to be searched is input in corresponding search box.
On the other hand, the invention provides a kind of input unit for searching for content, described device to include：
First probability acquiring unit, for obtaining the image in the target image preset range, to the preset range
Interior image is identified, and obtains the first searching probability of corresponding first recognition result；
Second probability acquiring unit, for by 180 ° of image rotation in the preset range, to the postrotational figure
As being identified, the second searching probability of corresponding second recognition result is obtained；
First processing units, for when first searching probability is less than second searching probability, by the target
180 ° of image rotation；And
Content input unit, for postrotational target image to be identified, corresponding 3rd recognition result is arranged to
Content to be searched, the content to be searched is input in corresponding search box.
On the other hand, present invention also offers a kind of mobile terminal, including memory, processor and it is stored in described deposit
In reservoir and the computer program that can run on the processor, realized such as during computer program described in the computing device
The step of input method of the search content.
On the other hand, present invention also offers a kind of computer-readable recording medium, the computer-readable recording medium
Computer program is stored with, the step of the input method such as the search content is realized when the computer program is executed by processor
Suddenly.
The present invention treats search target of taking pictures and taken pictures, and obtains target image, obtains in target image preset range
Image, the image in preset range is identified, the first searching probability of corresponding first recognition result is obtained, by preset range
180 ° of interior image rotation, postrotational image is identified, and obtains the second searching probability of corresponding second recognition result, when
When first searching probability is less than the second searching probability, target image is rotated 180 °, postrotational target image is identified,
Corresponding 3rd recognition result is arranged to content to be searched, content to be searched is input in corresponding search box, so as to improve
The accuracy of search content is obtained, and then improves the efficiency for search of taking pictures.
Brief description of the drawings
Fig. 1 is the implementation process figure of the input method for the search content that the embodiment of the present invention one provides；
Fig. 2 is the implementation process figure of the input method for the search content that the embodiment of the present invention two provides；
Fig. 3 is the structural representation of the input unit for the search content that the embodiment of the present invention three provides；
Fig. 4 is the structural representation of the input unit for the search content that the embodiment of the present invention four provides；And
Fig. 5 is the structural representation for the mobile terminal that the embodiment of the present invention five provides.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
It is described in detail below in conjunction with specific implementation of the specific embodiment to the present invention：
Embodiment one：
Fig. 1 shows the implementation process of the input method for the search content that the embodiment of the present invention one provides, for the ease of saying
It is bright, the part related to the embodiment of the present invention is illustrate only, details are as follows：
In step S101, treat search target of taking pictures and taken pictures, obtain target image.
In embodiments of the present invention, when user needs to take pictures search, search target of taking pictures is treated first and is taken pictures, is obtained
Target image is taken, to obtain search content by treating to take pictures to search in a manner of target is taken pictures.
In step s 102, the image in target image preset range is obtained, the image in preset range is identified,
Obtain the first searching probability of corresponding first recognition result.
In embodiments of the present invention, the probability that searching probability is preset characters or keyword is searched, the first searching probability
For all characters that image in preset range is successfully identified in default searching character storehouse corresponding searching probability summation.Tool
Body, after target image is got, a zonule (i.e. preset range) is chosen in the target image, to the zonule
Image is identified, and obtains the first searching probability of the cell area image, so as to reduce identified amount, when reducing identification
Between.
In step s 103, by 180 ° of image rotation in preset range, postrotational image is identified, acquisition pair
Answer the second searching probability of the second recognition result.
In embodiments of the present invention, the second searching probability is the institute that is successfully identified after 180 ° of image rotation in preset range
There is character corresponding searching probability summation in default searching character storehouse.In order to judge whether the image obtained needs to be revolved
Turn and (rotate 180 °) processing, first 180 ° of the zonule image rotation to selection, be then identified again, and obtain and be somebody's turn to do
Second searching probability of cell area image, compared with the probability size for carrying out follow-up.
In step S104, when the first searching probability is less than the second searching probability, target image is rotated 180 °.
In embodiments of the present invention, the first searching probability and the second searching probability are compared, when the first searching probability
During less than the second searching probability, illustrate in the character that is successfully identified of cell area image before rotation rarely used word or not common character
More, common word (or commonly used word) is more in the character that postrotational cell area image is successfully identified, now, by target image
180 ° of rotation, to facilitate follow-up image recognition and search, so as to improve the treatment effect of target image.
In step S105, postrotational target image is identified, corresponding 3rd recognition result is arranged to wait to search
Rope content, content to be searched is input in corresponding search box.
In embodiments of the present invention, the target image after rotation processing is identified, the content for identifying to obtain is to wait to search
Rope content, therefore, it will identify that obtained content is input in corresponding search box, to carry out follow-up search.
In embodiments of the present invention, the first searching probability and postrotational second before being rotated by smaller area image
Searching probability, judge whether to carry out rotation processing to target image, then the target image after processing is identified, acquisition is treated
Content is searched for, to carry out follow-up search, so as to improve the accuracy for obtaining search content, and then improves the effect for search of taking pictures
Rate.
Embodiment two：
Fig. 2 shows the implementation process of the input method for the search content that the embodiment of the present invention two provides, for the ease of saying
It is bright, the part related to the embodiment of the present invention is illustrate only, details are as follows：
In step s 201, treat search target of taking pictures to be taken pictures, obtain target image.
In embodiments of the present invention, when user needs to take pictures search, search target of taking pictures is treated first and is taken pictures, is obtained
Target image is taken, to obtain search content by treating to take pictures to search in a manner of target is taken pictures.Preferably, target figure is being got
As after, the angle of inclination that target is searched in target image is obtained, line tilt is then entered to target image according to angle of inclination and rectified
Positive pretreatment, to improve follow-up target image recognition efficiency.
In step S202, the image in target image preset range is obtained, the image in preset range is identified,
Obtain the first searching probability of corresponding first recognition result.
In embodiments of the present invention, after target image is got, it is (i.e. pre- that a zonule is chosen in the target image
If scope), the image of the zonule is identified, and the first searching probability of the cell area image is obtained, so as to reduce
Identified amount, reduce recognition time.Preferably, when being identified in the image to the zonule, and obtaining the first searching probability,
Character recognition is carried out to the image of the zonule first, obtains the character recognized, then according to the character recognized default
Searching character storehouse in the probability that is identified to, obtain the first searching probability of the cell area image.
In step S203, postrotational image is identified 180 ° of image rotation in preset range, acquisition pair
Answer the second searching probability of the second recognition result.
In embodiments of the present invention, in order to judge whether the image obtained needs to carry out rotation processing, first to selection
180 ° of zonule image rotation, is then identified again, and obtains the second searching probability of the cell area image, after progress
Continuous probability size compares.
In step S204, judge whether the first searching probability is less than the second searching probability, be then to perform step S206,
Otherwise step S205 is performed.
In step S205, when the first searching probability is equal to the second searching probability, preset range is changed, and jump to step
Rapid S202.
In embodiments of the present invention, when the first searching probability is equal to the second searching probability, preset range, Ran Houchong are changed
The cell area image in target image preset range is obtained again, the cell area image of acquisition is identified, and obtains corresponding first
First searching probability of recognition result, to 180 ° of the zonule image rotation of selection, then it is identified again, and it is small to obtain this
Second searching probability of area image, until the first searching probability is not equal to the second searching probability.
In step S206, when the first searching probability is less than the second searching probability, target image is rotated 180 °.
In embodiments of the present invention, judge whether the first searching probability is less than the second searching probability, when the first searching probability
During less than the second searching probability, illustrate in the character that is successfully identified of cell area image before rotation rarely used word or not common character
More, common word (or commonly used word) is more in the character that postrotational cell area image is successfully identified, now, by target image
180 ° of rotation, to facilitate follow-up image recognition and search, so as to improve the treatment effect of target image.
In step S207, postrotational target image is identified, corresponding 3rd recognition result is arranged to wait to search
Rope content, content to be searched is input in corresponding search box.
In embodiments of the present invention, the first searching probability and postrotational second before being rotated by smaller area image
Searching probability, judge whether to carry out rotation processing to target image, then the target image after processing is identified, acquisition is treated
Content is searched for, to carry out follow-up search, so as to improve the accuracy for obtaining search content, and then improves the effect for search of taking pictures
Rate.
Embodiment three：
Fig. 3 shows the structure of the input unit for the search content that the embodiment of the present invention three provides, for convenience of description, only
The part related to the embodiment of the present invention is shown, including：
Image acquisition unit 31, taken pictures for treating search target of taking pictures, obtain target image.
First probability acquiring unit 32, for obtaining the image in target image preset range, to the figure in preset range
As being identified, the first searching probability of corresponding first recognition result is obtained.
In embodiments of the present invention, after target image is got, it is (i.e. pre- that a zonule is chosen in the target image
If scope), the image of the zonule is identified, and the first of the cell area image is obtained by the first probability acquiring unit
Searching probability, so as to reduce identified amount, reduce recognition time.
Second probability acquiring unit 33, for by 180 ° of image rotation in preset range, being carried out to postrotational image
Identification, obtain the second searching probability of corresponding second recognition result.
In embodiments of the present invention, in order to judge whether the image obtained needs to carry out rotation processing, first to selection
180 ° of zonule image rotation, is then identified again, and obtains the cell area image by the second probability acquiring unit
Second searching probability, compared with the probability size for carrying out follow-up.
First processing units 34, for when the first searching probability is less than the second searching probability, target image to be rotated
180°。
In embodiments of the present invention, the first searching probability and the second searching probability are compared, when the first searching probability
During less than the second searching probability, illustrate in the character that is successfully identified of cell area image before rotation rarely used word or not common character
More, common word (or commonly used word) is more in the character that postrotational cell area image is successfully identified, and now, the first processing is single
Target image is rotated 180 ° by member, to facilitate follow-up image recognition and search, so as to improve the treatment effect of target image.
Content input unit 35, for postrotational target image to be identified, corresponding 3rd recognition result is set
For content to be searched, content to be searched is input in corresponding search box.
In embodiments of the present invention, image acquisition unit is treated search target of taking pictures and taken pictures, and obtains target image, the
One probability acquiring unit obtains the image in target image preset range, and the image in preset range is identified, acquisition pair
Answer the first searching probability of the first recognition result, the second probability acquiring unit is by 180 ° of image rotation in preset range, to rotation
Image after turning is identified, and obtains the second searching probability of corresponding second recognition result, when the first searching probability is less than second
During searching probability, target image is rotated 180 ° by first processing units, and content input unit is carried out to postrotational target image
Identification, corresponding 3rd recognition result is arranged to content to be searched, content to be searched is input in corresponding search box, so as to
The treatment effect of target image is improved, improves the accuracy for obtaining search content, and then improve the efficiency for search of taking pictures.
In embodiments of the present invention, each unit for searching for the input unit of content can be real by corresponding hardware or software unit
Existing, each unit can be independent soft and hardware unit, can also be integrated into a soft and hardware unit, herein not limiting
Invention.
Example IV：
Fig. 4 shows the structure of the input unit for the search content that the embodiment of the present invention four provides, for convenience of description, only
The part related to the embodiment of the present invention is shown, including：
Image acquisition unit 41, taken pictures for treating search target of taking pictures, obtain target image.
In embodiments of the present invention, when user needs to take pictures search, search target of taking pictures is treated first and is taken pictures, is led to
Cross image acquisition unit and obtain target image, to obtain search content by treating to take pictures to search in a manner of target is taken pictures.
Image pre-processing unit 42, for carrying out Slant Rectify pretreatment to target image using preset algorithm.
In embodiments of the present invention, after target image is got, image pre-processing unit obtains target image first
The angle of inclination of middle search target, then carries out Slant Rectify pretreatment according to angle of inclination to target image, follow-up to improve
Target image recognition efficiency.
First probability acquiring unit 43, for obtaining the image in target image preset range, to the figure in preset range
As being identified, the first searching probability of corresponding first recognition result is obtained.
In embodiments of the present invention, after target image is got, it is (i.e. pre- that a zonule is chosen in the target image
If scope), the image of the zonule is identified, and the first of the cell area image is obtained by the first probability acquiring unit
Searching probability, so as to reduce identified amount, reduce recognition time.Preferably, it is identified in the image to the zonule, and
When obtaining the first searching probability, character recognition is carried out to the image of the zonule first, obtains the character recognized, then basis
The probability that the character recognized is identified in default searching character storehouse, the first search for obtaining the cell area image are general
Rate.
Second probability acquiring unit 44, for by 180 ° of image rotation in preset range, being carried out to postrotational image
Identification, obtain the second searching probability of corresponding second recognition result.
In embodiments of the present invention, in order to judge whether the image obtained needs to carry out rotation processing, first to selection
180 ° of zonule image rotation, is then identified again, and obtains the cell area image by the second probability acquiring unit
Second searching probability, compared with the probability size for carrying out follow-up.
First processing units 45, for when the first searching probability is less than the second searching probability, target image to be rotated
180°。
In embodiments of the present invention, the first searching probability and the second searching probability are compared, when the first searching probability
During less than the second searching probability, illustrate in the character that is successfully identified of cell area image before rotation rarely used word or not common character
More, common word (or commonly used word) is more in the character that postrotational cell area image is successfully identified, and now, the first processing is single
Target image is rotated 180 ° by member, to facilitate follow-up image recognition and search, so as to improve the treatment effect of target image.
Comparing unit 46 is circulated, for when the first searching probability is equal to the second searching probability, changing preset range, and again
The secondary image obtained in target image preset range, the image in preset range is identified.
In embodiments of the present invention, when the first searching probability is equal to the second searching probability, circulation comparing unit presets model
Enclose, then repeat to obtain the cell area image in target image preset range, the cell area image of acquisition is identified, obtain
First searching probability of corresponding first recognition result, to 180 ° of the zonule image rotation of selection, is then identified again, and
The second searching probability of the cell area image is obtained, until the first searching probability is not equal to the second searching probability.
Content input unit 47, for postrotational target image to be identified, corresponding 3rd recognition result is set
For content to be searched, content to be searched is input in corresponding search box.
In embodiments of the present invention, the target image after rotation processing is identified, the content for identifying to obtain is to wait to search
Rope content, therefore, content input unit will identify that obtained content is input in corresponding search box, to carry out follow-up search
Rope.
It is therefore preferred that the first probability acquiring unit 43 includes：
Character recognition unit 431, for carrying out character recognition to the image in preset range, obtain the character recognized；
And
First obtains subelement 432, for what is be identified to according to the character recognized in default searching character storehouse
Probability, obtain the first searching probability of image in preset range.
In embodiments of the present invention, each unit for searching for the input unit of content can be real by corresponding hardware or software unit
Existing, each unit can be independent soft and hardware unit, can also be integrated into a soft and hardware unit, herein not limiting
Invention.
Embodiment five：
Fig. 5 shows the structure for the mobile terminal that the embodiment of the present invention five provides, and for convenience of description, illustrate only and this
The related part of inventive embodiments.
The mobile terminal 5 of the embodiment of the present invention includes processor 50, memory 51 and is stored in memory 51 and can
The computer program 52 run on processor 50.The processor 50 realizes above-mentioned each search when performing computer program 52
Step in the input method embodiment of content, such as step S101 to the step S201 shown in S104, Fig. 2 shown in Fig. 1 is extremely
S207.Or the function of each unit in above-mentioned each device embodiment is realized during the execution computer program 52 of processor 50, such as scheme
The function of unit 31 to 35 shown in 3, unit 41 to 47 shown in Fig. 4.
In embodiments of the present invention, the control that above-mentioned each screen wakes up is realized when the processor 50 performs computer program 52
During step in embodiment of the method processed, treat search target of taking pictures and taken pictures, obtain target image, obtain target image and preset
In the range of image, the image in preset range is identified, obtains the first searching probability of corresponding first recognition result, will
180 ° of image rotation in preset range, postrotational image is identified, and obtain corresponding second recognition result second is searched
Rope probability, when the first searching probability is less than the second searching probability, target image is rotated 180 °, to postrotational target image
It is identified, corresponding 3rd recognition result is arranged to content to be searched, content to be searched is input in corresponding search box.
The mobile terminal of the embodiment of the present invention can be mobile phone, tablet personal computer, learning machine.Processor in the mobile terminal 5
50 specifically refer to the description of method in embodiment one and embodiment two the step of realization when performing computer program 52, herein
Repeat no more.
Embodiment six：
In embodiments of the present invention, there is provided a kind of computer-readable recording medium, the computer-readable recording medium are deposited
Computer program is contained, the computer program realizes the input method embodiment of above-mentioned each search content when being executed by processor
In step, for example, the step S101 to the step S201 to S207 shown in S104, Fig. 2 shown in Fig. 1.Or the computer journey
The function of each unit in above-mentioned each device embodiment, such as unit 31 to 35 shown in Fig. 3, Fig. 4 are realized when sequence is executed by processor
The function of shown unit 41 to 47.
In embodiments of the present invention, treat search target of taking pictures to be taken pictures, obtain target image, it is pre- to obtain target image
If the image in scope, the image in preset range is identified, the first searching probability of corresponding first recognition result is obtained,
By 180 ° of image rotation in preset range, postrotational image is identified, obtains the second of corresponding second recognition result
Searching probability, when the first searching probability is less than the second searching probability, target image is rotated 180 °, to postrotational target figure
As being identified, corresponding 3rd recognition result is arranged to content to be searched, content to be searched is input to corresponding search box
In.The input method for the search content that the computer program is realized when being executed by processor further refers to preceding method implementation
The description of step, will not be repeated here in example.
The computer-readable recording medium of the embodiment of the present invention can include that any of computer program code can be carried
Entity or device, recording medium, for example, the memory such as ROM/RAM, disk, CD, flash memory.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
All any modification, equivalent and improvement made within refreshing and principle etc., should be included in the scope of the protection.
Claims (10)
1. a kind of input method for searching for content, it is characterised in that methods described comprises the steps：
Treat search target of taking pictures to be taken pictures, obtain target image；
The image in the target image preset range is obtained, the image in the preset range is identified, is obtained corresponding
First searching probability of the first recognition result；
By 180 ° of image rotation in the preset range, the postrotational image is identified, corresponding second is obtained and knows
Second searching probability of other result；
When first searching probability is less than second searching probability, the target image is rotated 180 °；
Postrotational target image is identified, corresponding 3rd recognition result is arranged to content to be searched, waits to search by described
Rope content is input in corresponding search box.
2. the method as described in claim 1, it is characterised in that after the step of obtaining target image, obtain the target figure
Before the step of image in preset range, methods described also includes：
Slant Rectify pretreatment is carried out to the target image using preset algorithm.
3. the method as described in claim 1, it is characterised in that the image in the preset range is identified, acquisition pair
The step of answering the first searching probability of the first recognition result, including：
Character recognition is carried out to the image in the preset range, obtains the character being successfully identified；
According to each character being successfully identified in default searching character storehouse corresponding searched probability, described in calculating
First searching probability of the character being successfully identified.
4. the method as described in claim 1, it is characterised in that methods described also includes：
When first searching probability is equal to second searching probability, the preset range is changed, and jumps to and obtains institute
The image in target image preset range is stated, the step of the image in the preset range is identified.
5. a kind of input unit for searching for content, it is characterised in that described device includes：
Image acquisition unit, taken pictures for treating search target of taking pictures, obtain target image；
First probability acquiring unit, for obtaining the image in the target image preset range, in the preset range
Image is identified, and obtains the first searching probability of corresponding first recognition result；
Second probability acquiring unit, for by 180 ° of image rotation in the preset range, entering to the postrotational image
Row identification, obtain the second searching probability of corresponding second recognition result；
First processing units, for when first searching probability is less than second searching probability, by the target image
180 ° of rotation；And
Content input unit, for postrotational target image to be identified, corresponding 3rd recognition result is arranged to wait to search
Rope content, the content to be searched is input in corresponding search box.
6. device as claimed in claim 5, it is characterised in that described device also includes：
Image pre-processing unit, for carrying out Slant Rectify pretreatment to the target image using preset algorithm.
7. device as claimed in claim 5, it is characterised in that the first probability acquiring unit includes：
Character recognition unit, for carrying out character recognition to the image in the preset range, obtain the character being successfully identified；
And
First obtains subelement, for according to each character for being successfully identified in default searching character storehouse corresponding to
It is searched probability, the first searching probability of the character being successfully identified described in calculating.
8. device as claimed in claim 5, it is characterised in that described device also includes：
Comparing unit is circulated, for when first searching probability is equal to second searching probability, changing the default model
Enclose, and obtain the image in the target image preset range again, the image in the preset range is identified.
9. a kind of mobile terminal, including memory, processor and it is stored in the memory and can be on the processor
The computer program of operation, it is characterised in that realize such as Claims 1-4 described in the computing device during computer program
The step of any one methods described.
10. a kind of computer-readable recording medium, the computer-readable recording medium storage has computer program, and its feature exists
In when the computer program is executed by processor the step of realization such as any one of Claims 1-4 methods described.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710446426.3A CN107357819A (en) | 2017-06-14 | 2017-06-14 | A kind of input method, device, mobile terminal and storage medium for searching for content |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710446426.3A CN107357819A (en) | 2017-06-14 | 2017-06-14 | A kind of input method, device, mobile terminal and storage medium for searching for content |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107357819A true CN107357819A (en) | 2017-11-17 |
Family
ID=60272872
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710446426.3A Pending CN107357819A (en) | 2017-06-14 | 2017-06-14 | A kind of input method, device, mobile terminal and storage medium for searching for content |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107357819A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108062370A (en) * | 2017-12-11 | 2018-05-22 | 维沃移动通信有限公司 | A kind of application program searching method and mobile terminal |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1542656A (en) * | 2003-04-30 | 2004-11-03 | ������������ʽ���� | Information processing apparatus, method, storage medium and program |
| US20110320463A1 (en) * | 2009-03-06 | 2011-12-29 | Panasonic Corporation | Image search device and image search method |
| CN102890783A (en) * | 2011-07-20 | 2013-01-23 | 富士通株式会社 | Method and device for recognizing direction of character in image block |
| CN106326406A (en) * | 2016-08-22 | 2017-01-11 | 广东小天才科技有限公司 | Question searching method and device applied to electronic terminal |
-
2017
- 2017-06-14 CN CN201710446426.3A patent/CN107357819A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1542656A (en) * | 2003-04-30 | 2004-11-03 | ������������ʽ���� | Information processing apparatus, method, storage medium and program |
| US20110320463A1 (en) * | 2009-03-06 | 2011-12-29 | Panasonic Corporation | Image search device and image search method |
| CN102890783A (en) * | 2011-07-20 | 2013-01-23 | 富士通株式会社 | Method and device for recognizing direction of character in image block |
| CN106326406A (en) * | 2016-08-22 | 2017-01-11 | 广东小天才科技有限公司 | Question searching method and device applied to electronic terminal |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108062370A (en) * | 2017-12-11 | 2018-05-22 | 维沃移动通信有限公司 | A kind of application program searching method and mobile terminal |
| CN108062370B (en) * | 2017-12-11 | 2020-11-03 | 维沃移动通信有限公司 | Application program searching method and mobile terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11860976B2 (en) | Data processing method and device, classifier training method and system, and storage medium | |
| TWI690919B (en) | Method and device for recognizing speech keyword, terminal, server, computer readable storage medium, and computer program product | |
| US11361585B2 (en) | Method and system for face recognition via deep learning | |
| CN110826530B (en) | Face detection using machine learning | |
| WO2020155766A1 (en) | Method, device and apparatus for identification rejection in intention identification, and storage medium | |
| CN110390269A (en) | PDF document table extracting method, device, equipment and computer readable storage medium | |
| WO2022042123A1 (en) | Image recognition model generation method and apparatus, computer device and storage medium | |
| CN109583325A (en) | Face samples pictures mask method, device, computer equipment and storage medium | |
| US20180158449A1 (en) | Method and device for waking up via speech based on artificial intelligence | |
| CN107506350B (en) | Method and equipment for identifying information | |
| CN104766077B (en) | Method and device for recognizing characters in picture | |
| CN109885828A (en) | Word error correction method, device, computer equipment and medium based on language model | |
| CN105320945A (en) | Image classification method and apparatus | |
| CN111242273B (en) | Neural network model training method and electronic equipment | |
| CN112949649B (en) | Text image identification method and device and computing equipment | |
| CN110909665B (en) | Multitask image processing method and device, electronic equipment and storage medium | |
| CN105825164A (en) | Fingerprint identification method and electronic equipment | |
| CN107423306A (en) | A kind of image search method and device | |
| CN109712617A (en) | Voice control method and device, storage medium and air conditioner | |
| RU2014117521A (en) | RECOGNITION OF DYNAMIC GESTURES USING PROPERTIES RECEIVED FROM SEVERAL INTERVALS | |
| CN109859314A (en) | Three-dimensional rebuilding method, device, electronic equipment and storage medium | |
| CN108345612A (en) | A kind of question processing method and device, a kind of device for issue handling | |
| TWI749349B (en) | Text restoration method, device, electronic equipment and computer readable storage medium | |
| CN106469186A (en) | A kind of method and device of character string comparison | |
| JP7429307B2 (en) | Character string recognition method, device, equipment and medium based on computer vision |
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: 20171117 |