CN108304843A - A kind of image measures and procedures for the examination and approval and examination ＆ approval device - Google Patents
A kind of image measures and procedures for the examination and approval and examination ＆ approval device Download PDFInfo
- Publication number
- CN108304843A CN108304843A CN201711418984.5A CN201711418984A CN108304843A CN 108304843 A CN108304843 A CN 108304843A CN 201711418984 A CN201711418984 A CN 201711418984A CN 108304843 A CN108304843 A CN 108304843A
- Authority
- CN
- China
- Prior art keywords
- hot
- word
- zone
- examination
- approval
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
- G06V10/225—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition based on a marking or identifier characterising the area
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
Abstract
The present invention provides a kind of image measures and procedures for the examination and approval and examination ＆ approval devices, including, obtain at least one pending image that user sends；For each described pending image at least one pending image, at least one hot-zone in the pending image is determined；For each described hot-zone at least one hot-zone, the hot-zone information in the hot-zone is identified；Each the described hot-zone information identified is analyzed, and exports analysis result；According to the analysis result, determine whether the examination ＆ approval of the pending image pass through.This programme can improve the examination ＆ approval efficiency of image.
Description
Technical field
The present invention relates to field of computer technology, more particularly to a kind of image measures and procedures for the examination and approval and examination ＆ approval device.
Background technology
With the development of Internet technology, each enterprises and institutions actively establish operational line and handle platform, to meet the masses
The demand of " not meeting examination ＆ approval ", " i.e. to do ".
Currently, staff needs staff when handling user and handling the image that platform is submitted by operational line
It first checks the content in the image document that user submits, then determines whether the image that user submits passes through examination ＆ approval.But work people
Member needs word for word to go to check in the content in examining image, so staff's a large amount of time can be expended, and staff
The time to work daily is fixed, therefore the examination ＆ approval efficiency of image can be caused low.
Invention content
An embodiment of the present invention provides a kind of image measures and procedures for the examination and approval and examination ＆ approval devices, can improve the examination ＆ approval efficiency of image.
In a first aspect, an embodiment of the present invention provides a kind of image measures and procedures for the examination and approval, including：
Obtain at least one pending image that user sends；
For each described pending image at least one pending image, the pending image is determined
In at least one hot-zone；
For each described hot-zone at least one hot-zone, the hot-zone information in the hot-zone is identified；
Each the described hot-zone information identified is analyzed, and exports analysis result；
According to the analysis result, determine whether the examination ＆ approval of the pending image pass through.
Preferably, further comprise before at least one hot-zone in the determination pending image：
Pre-set at least one template chart；
For each described template chart at least one template chart, store every in the template chart
One template hot-zone；
At least one pending image for obtaining user and sending, including：
Obtain the pending image that user uploads according to each template chart；
At least one hot-zone in the determination pending image, including：
The pending image is compared with template chart described in each respectively, is determined and the pending image
Corresponding specified template chart；
According to each described template hot-zone in the specified template chart of storage, determine in the pending image
Hot-zone.
Preferably, the hot-zone information in the identification hot-zone, including：
Adjust the gray value of each pixel in the pending image；
It is preset to determine whether the corresponding pixel value of the pixel after each adjusts gray value is more than or equal to respectively
Threshold value；
If so, determining that the pixel after adjusting gray value is characterized pixel；
Determine the hot-zone information being made of feature pixel described in each, wherein the hot-zone information, including text envelope
Breath and/or geometric figure.
Preferably, each described hot-zone information for being identified is analyzed described, and before exporting analysis result, further
Including：
Store at least one mark word, wherein the mark word includes any one in Chinese character, letter and number
Or it is multiple；
For each described mark word of storage, the corresponding at least one identification information of the mark word is determined；
It is described to analyze each the described hot-zone information identified, and analysis result is exported, including：
When the hot-zone information is text message,
Determine the corresponding at least one characteristic information of the word to be identified of each in the text message；
For word to be identified described in each, each corresponding described characteristic information of the word to be identified is distinguished
It is compared with each corresponding described identification information of word is identified described in each；
For the designated identification word identified described in each in word, when each corresponding institute of the word to be identified
The matching degree for stating characteristic information each designated identification information corresponding with the designated identification word is more than or equal to preset
When with value, determine that the word to be identified is identical as the designated identification word；
Determine that each described word to be identified identical with the designated identification word is copending word；
Semantic analysis carried out to copending word described in each, and by each copending word and corresponding language
Justice is exported as analysis result.
Preferably, described to determine whether the examination ＆ approval of the pending image pass through according to the analysis result, including：
The analysis result is compared with preset examination ＆ approval rule, wherein the examination ＆ approval rule includes name, registration
It is any one or more in fund, Business Name, residence and approval notice lot number；
When the analysis result with it is described examination ＆ approval rule matching degree be more than or equal to preset examination ＆ approval value when, determine described in wait for
Processing image examination ＆ approval pass through.
Second aspect, an embodiment of the present invention provides a kind of image analysis apparatus, including：
Image processing unit, at least one pending image for obtaining user's transmission；It at least one is waited for for described
Each described pending image in image is handled, determines at least one hot-zone in the pending image；
Hot-zone information process unit, for every at least one hot-zone for the determination of described image processing unit
One hot-zone identifies the hot-zone information in the hot-zone；Each the described hot-zone information identified is analyzed, and exports and divides
Analyse result；
Processing unit is examined, for the analysis result that export according to the hot-zone information process unit, described in determination
Whether the examination ＆ approval of pending image pass through.
Preferably, described image processing unit, for pre-setting at least one template chart；For described at least one
Each described template chart in template chart, stores each template hot-zone in the template chart；Obtain user's root
The pending image uploaded according to each template chart；By the pending image respectively with template chart described in each into
Row compares, and determines specified template chart corresponding with the pending image；According in the specified template chart of storage
Each described template hot-zone, determine hot-zone in the pending image.
Preferably, the hot-zone information process unit, the ash for adjusting each pixel in the pending image
Angle value；Determine whether the corresponding pixel value of the pixel after each adjusts gray value is more than or equal to preset threshold respectively
Value；If so, determining that the pixel after adjusting gray value is characterized pixel；It determines by feature pixel described in each
The hot-zone information of composition, wherein the hot-zone information, including text message and/or geometric figure.
Preferably, the hot-zone information process unit, including：Storage unit, determination unit and analytic unit；
The storage unit, for storing at least one mark word, wherein the mark word includes Chinese character, letter
With it is any one or more in number；
The determination unit determines the mark for each described mark word for storage unit storage
Know the corresponding at least one identification information of word；When the hot-zone information is text message, determine every in the text message
The corresponding at least one characteristic information of one word to be identified；
The analytic unit, for the designated identification in the mark word for each described storage Anyuan storage
Word, the characteristic information when each corresponding determination unit determination of the word to be identified and the designated identification
When the matching degree of each corresponding designated identification information of word is more than or equal to preset matching value, the word to be identified is determined
It is identical as the designated identification word；Determine that each described word to be identified identical with the designated identification word is pending
Certification word；Semantic analysis carried out to copending word described in each, and by each copending word and corresponding language
Justice is exported as analysis result.
Preferably, the examination ＆ approval processing unit, for the analysis result to be compared with preset examination ＆ approval rule,
In, it is described examination ＆ approval rule include name, registered capital, Business Name, residence and check and approve notice lot number in any one or
It is multiple；When the analysis result with it is described examination ＆ approval rule matching degree be more than or equal to preset examination ＆ approval value when, determine described in wait locating
Reason image examination ＆ approval pass through.
Description of the drawings
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is the present invention
Some embodiments for those of ordinary skill in the art without creative efforts, can also basis
These attached drawings obtain other attached drawings.
Fig. 1 is a kind of flow chart for image measures and procedures for the examination and approval that one embodiment of the invention provides；
Fig. 2 is the flow chart for another image measures and procedures for the examination and approval that one embodiment of the invention provides；
Fig. 3 is a kind of structural schematic diagram for image examination ＆ approval device that one embodiment of the invention provides；
Fig. 4 is the structural schematic diagram for another image examination ＆ approval device that one embodiment of the invention provides.
Specific implementation mode
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments, based on the embodiments of the present invention, those of ordinary skill in the art
The every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
As shown in Figure 1, an embodiment of the present invention provides a kind of image measures and procedures for the examination and approval, including：
Step 101：Obtain at least one pending image that user sends；
Step 102：For each described pending image at least one pending image, waited for described in determination
Handle at least one hot-zone in image；
Step 103：For each described hot-zone at least one hot-zone, the hot-zone letter in the hot-zone is identified
Breath；
Step 104：Each the described hot-zone information identified is analyzed, and exports analysis result；
Step 105：According to the analysis result, determine whether the examination ＆ approval of the pending image pass through.
In embodiments of the present invention, user need to only send pending image, you can hot-zone processing is carried out to pending image,
And identify the hot-zone information in hot-zone, it can determine that pending image is finally by being analyzed the hot-zone information identified
No examination ＆ approval pass through, and the content checked in image is taken a substantial amount of time without staff, so as to improve examining for image
Criticize efficiency.
In an embodiment of the present invention, in the determination pending image before at least one hot-zone, further
Including：
Pre-set at least one template chart；
For each described template chart at least one template chart, store every in the template chart
One template hot-zone；
At least one pending image for obtaining user and sending, including：
Obtain the pending image that user uploads according to each template chart；
At least one hot-zone in the determination pending image, including：
The pending image is compared with template chart described in each respectively, is determined and the pending image
Corresponding specified template chart；
According to each described template hot-zone in the specified template chart of storage, determine in the pending image
Hot-zone.
In embodiments of the present invention, by pre-setting multiple template chart, and the mould on each template chart is stored
Plate hot-zone is submitted after user can be made to fill in related content in template chart as pending figure, then by pending figure
As being compared with each template chart, you can the template hot-zone corresponding to corresponding template chart determines pending figure
Each hot-zone as in, consequently facilitating the hot-zone information in identification hot-zone.
In an embodiment of the present invention, the hot-zone information in the identification hot-zone, including：
Adjust the gray value of each pixel in the pending image；
It is preset to determine whether the corresponding pixel value of the pixel after each adjusts gray value is more than or equal to respectively
Threshold value；
If so, determining that the pixel after adjusting gray value is characterized pixel；
Determine the hot-zone information being made of feature pixel described in each, wherein the hot-zone information, including text envelope
Breath and/or geometric figure.
In embodiments of the present invention, by adjusting the gray value of pending image, it is black can so that pending image is presented
The hot-zone information area in the image background of pending image and pending image is separated, then will adjust gray scale by color and white
The pixel value corresponding to pixel after value is compared with preset threshold value, you can determine the hot-zone information in hot-zone, and nothing
It needs staff to expend the excessive time and checks content in pending image, so as to improve the examination ＆ approval effect of pending image
Rate.
In an embodiment of the present invention, in described each described hot-zone information analyzed and identified, and analysis knot is exported
Before fruit, further comprise：
Store at least one mark word, wherein the mark word includes any one in Chinese character, letter and number
Or it is multiple；
For each described mark word of storage, the corresponding at least one identification information of the mark word is determined；
It is described to analyze each the described hot-zone information identified, and analysis result is exported, including：
When the hot-zone information is text message,
Determine the corresponding at least one characteristic information of the word to be identified of each in the text message；
For word to be identified described in each, each corresponding described characteristic information of the word to be identified is distinguished
It is compared with each corresponding described identification information of word is identified described in each；
For the designated identification word identified described in each in word, when each corresponding institute of the word to be identified
The matching degree for stating characteristic information each designated identification information corresponding with the designated identification word is more than or equal to preset
When with value, determine that the word to be identified is identical as the designated identification word；
Determine that each described word to be identified identical with the designated identification word is copending word；
Semantic analysis carried out to copending word described in each, and by each copending word and corresponding language
Justice is exported as analysis result.
In embodiments of the present invention, since each word has character pair information, when the hot-zone letter in hot-zone
When breath is text message, by the corresponding characteristic information of each word to be identified mark corresponding with word is identified in text message
Know information to be compared, you can identify that word to be identified, then the word to be identified to identifying carry out semantic analysis, that is, determine
Word to be identified belongs to noun, verb, comb, English or Chinese, you can completes the identification work of hot-zone information, and is identifying
During hot-zone information and semantic analysis without human intervention, it thus may be implemented to examine movable intelligent processing.
Specifically, multiple geometric figures can also be stored, and determine the corresponding identification information of each geometric figure, and are worked as
When hot-zone information in hot-zone is pending figure, according to the geometric figure pair of pending figure corresponding characteristic information and storage
The identification information answered is compared, and then determines pending figure.
For example, prestore mark word " in " and " day "；
Identify word " in " identification information be " mouth " and " Shu "；
Identify word " day " identification information be " one ", " one ", " Pie " and
Pending word " in " characteristic information be " mouth " and " Shu "；
By pending word " in " identification information respectively with mark word " in " and the characteristic information in " day " be compared,
Determine pending word " in " with mark word " in " matching degree reach 100%, it is thus determined that pending word " in " be mark
Know information " in ", and determine pending word " in " semantic analysis be Chinese.
In an embodiment of the present invention, described according to the analysis result, determine the pending image examination ＆ approval whether
Pass through, including：
The analysis result is compared with preset examination ＆ approval rule, wherein the examination ＆ approval rule includes name, registration
It is any one or more in fund, Business Name, residence and approval notice lot number；
When the analysis result with it is described examination ＆ approval rule matching degree be more than or equal to preset examination ＆ approval value when, determine described in wait for
Processing image examination ＆ approval pass through.
In embodiments of the present invention, after the analysis result for obtaining hot-zone information, analysis result and examination ＆ approval rule are determined
Whether matching degree is more than or equal to preset examination ＆ approval value, and the matching degree and if only if analysis result and examination ＆ approval rule is more than or equal to examination ＆ approval
When value, determine that the examination ＆ approval of pending image pass through, and determine pending image examination ＆ approval whether by process without staff's consumption
Take excessive time participation, therefore the error rate of artificial treatment can be reduced, and can also avoid manually examining pending figure
As when expend the excessive time caused by pending image examine inefficiency the drawbacks of.
In order to more clearly illustrate technical scheme of the present invention and advantage, with pre-set template chart a and template
For chart b, a kind of image measures and procedures for the examination and approval provided in an embodiment of the present invention are described in detail, as shown in Fig. 2, specifically can be with
Include the following steps：
Step 201：Template chart a and template chart b are pre-set, and stores template chart a and template chart b is right respectively
Each the hot-zone shape answered.
Specifically, template chart is pre-set, and determines the hot-zone of template chart, user can be made to be filled out according to template chart
Corresponding information is write, and will fill in the template chart after information and upload to approving authority as pending image, and according to template
Hot-zone in chart can determine the hot-zone in pending image, therefore can reduce the difficulty for determining the hot-zone in pending image
Degree, and improve the precision for determining pending image hot-zone.
For example, template chart a is as follows：
Step 202：At least one mark word is stored, and determines the corresponding at least one mark letter of each mark word
Breath.
Specifically, since there are corresponding characteristic informations for each word, thus by prestore mark word and
Corresponding identification information can, when receiving the pending image of user's transmission, to be identified according to the identification information of storage
Content in pending image.
For example, it prestores and identifies word " text ", " six ", " o " and " z ",
The identification information for identifying word " text " is " Dian ", "×" and " one "；
The identification information for identifying word " six " is " Dian ", " Dian ", " one " and " Pie "；
The identification information for identifying word " o " is " o "；
Identify the identification information Wei " Ya of word " z " " and " one ".
Step 203：Receive the pending image that user uploads according to template chart a and template chart b.
Specifically, user selects required template chart according to actual demand from template chart a and template chart b,
It is filled in manually after direct fill message or download in the graph, it can be as pending figure after having filled in relevant information
As being sent to associated mechanisms.
Step 204：Pending image is compared with template chart a and template chart b, is determined and pending image phase
Corresponding specified template chart.
Specifically, the pending image that user sends is compared with each template chart of storage, you can find
Specified template chart corresponding with pending image, and when what is do not sent with user in the template chart of storage waits locating
When managing the corresponding specified template chart of image, the information of aphalangia solid plate can be sent to user.
Step 205：According to each corresponding template hot-zone of specified template chart, the hot-zone in pending image is determined.
Specifically, due to each template chart corresponding templates hot-zone, so corresponding specified according to pending image
Template hot-zone corresponding to template chart, you can determine the hot-zone in pending image.
Step 206：Adjust the gray value of each pixel in pending image.
Specifically, it in the pending image for receiving user's transmission, when pending image is colored, then needs to adjust and wait for
The gray value of image is handled, so as to be black and white by pending Image Adjusting, convenient in difference background information and pending image
Content.
Step 207：It is preset to determine whether the corresponding pixel value of pixel after each adjusts gray value is more than or equal to
Otherwise threshold value, executes step 217 if so, executing step 208.
Specifically, the pixel value in pending image is compared with preset threshold value, you can determine corresponding pixel
Point is the content in background or pending image.
Step 208：Determine that the pixel after adjusting gray value is characterized pixel.
Specifically, when the corresponding pixel value of pixel is more than or equal to preset threshold value, it is determined that in pending image
Information.
Step 209：Determine the hot-zone information being made of each feature pixel.
Specifically, according to the corresponding coordinate points of each feature pixel, you can determine the hot-zone information in pending image.
Step 210：When hot-zone information is text message, the word difference to be identified of each in text message is determined respectively
Each corresponding characteristic information.
Specifically, it when the hot-zone information being made of feature pixel is text message, needs first to carry out text message
It is split as each word, then the thickness to determining strokes of characters, break pen, adhesion, the characteristic informations such as rotation.
Step 211：For each word to be identified, the corresponding characteristic information of word to be identified is marked with each respectively
Know the corresponding identification information of word to be compared.
Specifically, when identifying word to be identified, the number according to the corresponding stroke endpoint of word to be identified, crosspoint is needed
Amount and position or stroke section characteristic information are compared with the identification information of each mark word, and then determine text to be identified
Word.
Step 212：When the corresponding characteristic information of word to be identified designated identification information corresponding with designated identification word
When matching degree is more than or equal to preset matching value, determine that word to be identified is identical as designated identification word.
Specifically, when preset matching value is 100%, then it needs to be determined that the corresponding characteristic information of word to be identified and mark
The corresponding identification information of designated identification word known in word exactly matches, then it is assumed that word to be identified and designated identification word phase
Together.
Step 213：Semantic analysis is carried out to each word to be identified identical with designated identification word, and exports semanteme
Analysis result.
Specifically, semantic analysis is carried out to word to be identified, can identifies that word to be identified belongs to noun, verb, number
The word of word, English or Chinese, even negative feeling or active mood, so as to be carried out further according to preset examination ＆ approval rule
Comparison passes through to determine whether pending image is examined.
Step 214：Determine whether semantic analysis result and the matching degree of preset examination ＆ approval rule are more than or equal to preset examine
Value is criticized, if so, step 215 is executed, it is no to then follow the steps 216.
Specifically, can be the regulation to the content in each pending image, the language of word to be identified during examination ＆ approval are regular
When adopted analysis result is in examination ＆ approval rule, then it can determine that pending image examination ＆ approval pass through, and send examination ＆ approval to user and pass through,
Otherwise, it needs to send to examine to user not pass through.
Step 215：Determine that pending image examination ＆ approval pass through.
Specifically, when the analysis result of word to be identified is consistent with examination ＆ approval rule, determine that pending image is examined
It criticizes and passes through.
Step 216：Determine that pending image examination ＆ approval do not pass through.
Specifically, the analysis result of word to be identified with examination ＆ approval rule by operation relatively after, determine analysis result with
When the matching degree of examination ＆ approval rule is not up to examination ＆ approval value, it is determined that pending image examination ＆ approval do not pass through.
Step 217：Determine that the pixel after adjusting gray value is background.
Specifically, when the corresponding pixel value of pixel is less than preset threshold value, it is determined that for the back of the body in pending image
Scape.
As shown in figure 3, an embodiment of the present invention provides a kind of images to examine device, including：
Image processing unit 301, at least one pending image for obtaining user's transmission；For described at least one
Each described pending image in pending image, determines at least one hot-zone in the pending image；
Hot-zone information process unit 302, at least one hot-zone for being determined for described image processing unit 301
In each described hot-zone, identify the hot-zone information in the hot-zone；Each the described hot-zone information identified is analyzed, and
Export analysis result；
Processing unit 303 is examined, the analysis result for being exported according to the hot-zone information process unit 302, really
Whether the examination ＆ approval of the fixed pending image pass through.
In the embodiment of the present invention, user need to only send pending image, you can by image processing unit to pending figure
The hot-zone information in hot-zone is identified as carrying out hot-zone processing, and by hot-zone information process unit, it is single finally by examination ＆ approval processing
Member, which analyzes the hot-zone information that hot-zone information process unit identifies, can determine whether pending image is examined and passes through, and
The content checked in image is taken a substantial amount of time without staff, so as to improve the examination ＆ approval efficiency of image.
In an embodiment of the present invention, described image processing unit, for pre-setting at least one template chart；For
Each described template chart at least one template chart stores each template heat in the template chart
Area；Obtain the pending image that user uploads according to each template chart；By the pending image respectively with each
The template chart is compared, and determines specified template chart corresponding with the pending image；According to storage
Each described template hot-zone in specified template chart, determines hot-zone in the pending image.
In an embodiment of the present invention, the hot-zone information process unit, it is each in the pending image for adjusting
The gray value of a pixel；Determine whether the corresponding pixel value of the pixel after each adjusts gray value is more than respectively
In preset threshold value；If so, determining that the pixel after adjusting gray value is characterized pixel；It determines described in each
The hot-zone information of feature pixel composition, wherein the hot-zone information, including text message and/or geometric figure.
Device is examined based on a kind of image shown in Fig. 3, as shown in figure 4, the hot-zone information process unit 302, including：
Storage unit 3021, determination unit 3022 and analytic unit 3023；
The storage unit 3021, for storing at least one mark word, wherein the mark word include Chinese character,
It is any one or more in letter and number；
The determination unit 3022, each described mark word for being stored for the storage unit 3021, really
Determine the corresponding at least one identification information of the mark word；When the hot-zone information is text message, the text is determined
The corresponding at least one characteristic information of the word to be identified of each in information；
The analytic unit 3023, in the mark word for the storage of each described storage unit 3021
Designated identification word, when the characteristic information that corresponding each the described determination unit 3022 of the word to be identified determines with
When the matching degree of each corresponding designated identification information of the designated identification word is more than or equal to preset matching value, institute is determined
It is identical as the designated identification word to state word to be identified；Determine that each waits knowing described in identical with the designated identification word
Other word is copending word；Semantic analysis carried out to copending word described in each, and by each pending certification
Word and corresponding semanteme are exported as analysis result.
In an embodiment of the present invention, the examination ＆ approval processing unit, for advising the analysis result and preset examination ＆ approval
It is then compared, wherein the examination ＆ approval rule includes name, registered capital, Business Name, residence and checks and approves in notice lot number
It is any one or more；When the matching degree of the analysis result and the examination ＆ approval rule is more than or equal to preset examination ＆ approval value,
Determine that the pending image examination ＆ approval pass through.
The each embodiment of the present invention at least has the advantages that：
1, in one embodiment of the invention, user need to only send pending image, you can carry out hot-zone to pending image
Processing, and identifies the hot-zone information in hot-zone, finally by the hot-zone information identified is analyzed can determine it is pending
Whether image, which is examined, passes through, and the content checked in image is taken a substantial amount of time without staff, so as to improve figure
The examination ＆ approval efficiency of picture.
2, it in one embodiment of the invention, by pre-setting multiple template chart, and stores on each template chart
Template hot-zone, submitted as pending figure after user can be made to fill in related content in template chart, then will wait locating
Reason image is compared with each template chart, you can the template hot-zone corresponding to corresponding template chart, which determines, to be waited locating
Each hot-zone in image is managed, consequently facilitating the hot-zone information in identification hot-zone.
3, in one embodiment of the invention, by adjusting the gray value of pending image, it can so that pending image is in
Existing black and white, i.e., separate the hot-zone information area in the image background of pending image and pending image, then will adjust
The pixel value corresponding to pixel after gray value is compared with preset threshold value, you can determine the hot-zone information in hot-zone,
The excessive time is expended without staff and checks content in pending image, so as to improve examining for pending image
Criticize efficiency.
4, in one embodiment of the invention, since each word has character pair information, the heat in hot-zone
It is when area's information is text message, the corresponding characteristic information of each word to be identified in text message is corresponding with word is identified
Identification information compared, you can identify word to be identified, then the word to be identified to identifying carries out semantic analysis, i.e.,
Determine that word to be identified belongs to noun, verb, comb, English or Chinese, you can the identification work of completion hot-zone information, and
It identifies during hot-zone information and semantic analysis without human intervention, thus may be implemented to examine movable intelligent processing.
5, in one embodiment of the invention, after the analysis result for obtaining hot-zone information, determine that analysis result is advised with examination ＆ approval
Whether matching degree then is more than or equal to preset examination ＆ approval value, and the matching degree and if only if analysis result and examination ＆ approval rule is more than or equal to
When examination ＆ approval value, determine that the examination ＆ approval of pending image pass through, and determine pending image examination ＆ approval whether by process be not necessarily to work people
Member expends excessive time participation, therefore can reduce the error rate of artificial treatment, and can also avoid manually examining and wait locating
Caused by the excessive time being expended when managing image the drawbacks of pending image examination ＆ approval inefficiency.
It should be noted that herein, such as first and second etc relational terms are used merely to an entity
Or operation is distinguished with another entity or operation, is existed without necessarily requiring or implying between these entities or operation
Any actual relationship or order.Moreover, the terms "include", "comprise" or its any other variant be intended to it is non-
It is exclusive to include, so that the process, method, article or equipment including a series of elements includes not only those elements,
But also include other elements that are not explicitly listed, or further include solid by this process, method, article or equipment
Some elements.In the absence of more restrictions, the element limited by sentence " including a 〃 〃 ", it is not excluded that
There is also other identical factors in the process, method, article or apparatus that includes the element.
Finally, it should be noted that：The foregoing is merely presently preferred embodiments of the present invention, is merely to illustrate the skill of the present invention
Art scheme, is not intended to limit the scope of the present invention.Any modification for being made all within the spirits and principles of the present invention,
Equivalent replacement, improvement etc., are included within the scope of protection of the present invention.
Claims (10)
1. a kind of image measures and procedures for the examination and approval, which is characterized in that including：
Obtain at least one pending image that user sends；
For each described pending image at least one pending image, determine in the pending image extremely
A few hot-zone；
For each described hot-zone at least one hot-zone, the hot-zone information in the hot-zone is identified；
Each the described hot-zone information identified is analyzed, and exports analysis result；
According to the analysis result, determine whether the examination ＆ approval of the pending image pass through.
2. the measures and procedures for the examination and approval according to claim 1, which is characterized in that
In the determination pending image before at least one hot-zone, further comprise：
Pre-set at least one template chart；
For each described template chart at least one template chart, each in the template chart is stored
Template hot-zone；
At least one pending image for obtaining user and sending, including：
Obtain the pending image that user uploads according to each template chart；
At least one hot-zone in the determination pending image, including：
The pending image is compared with template chart described in each respectively, determination is opposite with the pending image
The specified template chart answered；
According to each described template hot-zone in the specified template chart of storage, determine hot in the pending image
Area.
3. the measures and procedures for the examination and approval according to claim 1, which is characterized in that
Hot-zone information in the identification hot-zone, including：
Adjust the gray value of each pixel in the pending image；
Determine whether the corresponding pixel value of the pixel after each adjusts gray value is more than or equal to preset threshold value respectively；
If so, determining that the pixel after adjusting gray value is characterized pixel；
Determine the hot-zone information being made of feature pixel described in each, wherein the hot-zone information, including text message
And/or geometric figure.
4. the measures and procedures for the examination and approval according to claim 3, which is characterized in that
Each described hot-zone information for being identified is analyzed described, and before exporting analysis result, further comprised：
Store at least one mark word, wherein it is described mark word include in Chinese character, letter and number any one or it is more
It is a；
For each described mark word of storage, the corresponding at least one identification information of the mark word is determined；
It is described to analyze each the described hot-zone information identified, and analysis result is exported, including：
When the hot-zone information is text message,
Determine the corresponding at least one characteristic information of the word to be identified of each in the text message；
For word to be identified described in each, by each corresponding described characteristic information of the word to be identified respectively with often
Each corresponding described identification information of one mark word is compared；
For the designated identification word identified described in each in word, as each corresponding described spy of the word to be identified
The matching degree that reference ceases each designated identification information corresponding with the designated identification word is more than or equal to preset matching value
When, determine that the word to be identified is identical as the designated identification word；
Determine that each described word to be identified identical with the designated identification word is copending word；
Semantic analysis is carried out to copending word described in each, and each described copending word and corresponding semanteme are made
It is exported for analysis result.
5. according to any measures and procedures for the examination and approval in Claims 1-4, which is characterized in that
It is described to determine whether the examination ＆ approval of the pending image pass through according to the analysis result, including：
The analysis result is compared with preset examination ＆ approval rule, wherein the examination ＆ approval rule includes name, registration money
It is any one or more in gold, Business Name, residence and approval notice lot number；
When the matching degree of the analysis result and the examination ＆ approval rule is more than or equal to preset examination ＆ approval value, determine described pending
Image examination ＆ approval pass through.
6. a kind of image examines device, which is characterized in that including：
Image processing unit, at least one pending image for obtaining user's transmission；For described at least one pending
Each described pending image in image, determines at least one hot-zone in the pending image；
Hot-zone information process unit, for each at least one hot-zone for the determination of described image processing unit
The hot-zone identifies the hot-zone information in the hot-zone；Each the described hot-zone information identified is analyzed, and exports analysis knot
Fruit；
Processing unit is examined, for the analysis result that export according to the hot-zone information process unit, waits locating described in determination
Whether the examination ＆ approval of reason image pass through.
7. examination ＆ approval device according to claim 6, which is characterized in that
Described image processing unit, for pre-setting at least one template chart；For at least one template chart
Each described template chart, store each template hot-zone in the template chart；User is obtained according to each described
The pending image that template chart uploads；The pending image is compared with template chart described in each respectively, really
Fixed specified template chart corresponding with the pending image；According to each institute in the specified template chart of storage
Template hot-zone is stated, determines hot-zone in the pending image.
8. examination ＆ approval device according to claim 6, which is characterized in that
The hot-zone information process unit, the gray value for adjusting each pixel in the pending image；It is true respectively
Whether the corresponding pixel value of the pixel after each fixed adjusting gray value is more than or equal to preset threshold value；If so, really
The pixel after saving gray value of setting the tone is characterized pixel；It determines and is believed by the hot-zone that feature pixel described in each forms
Breath, wherein the hot-zone information, including text message and/or geometric figure.
9. examination ＆ approval device according to claim 6, which is characterized in that the hot-zone information process unit, including：Storage is single
Member, determination unit and analytic unit；
The storage unit, for storing at least one mark word, wherein the mark word includes Chinese character, alphabetical sum number
It is any one or more in word；
The determination unit determines the mark text for each described mark word for storage unit storage
The corresponding at least one identification information of word；When the hot-zone information is text message, each in the text message is determined
The corresponding at least one characteristic information of word to be identified；
The analytic unit, for the designated identification text in the mark word for each storage unit storage
Word, when the characteristic information and designated identification text of each corresponding determination unit determination of the word to be identified
The matching degree of each corresponding designated identification information of word be more than or equal to preset matching value when, determine the word to be identified with
The designated identification word is identical；Determine that each described word to be identified identical with the designated identification word is copending
Word；Semantic analysis carried out to copending word described in each, and by each copending word and corresponding semanteme
It is exported as analysis result.
10. according to any examination ＆ approval device in claim 6 to 9, which is characterized in that
The examination ＆ approval processing unit, for the analysis result to be compared with preset examination ＆ approval rule, wherein the examination ＆ approval
Rule includes name, registered capital, Business Name, residence and checks and approves any one or more in notice lot number；When described
When the matching degree of analysis result and the examination ＆ approval rule is more than or equal to preset examination ＆ approval value, determine that the pending image examination ＆ approval are logical
It crosses.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711418984.5A CN108304843B (en) | 2017-12-25 | 2017-12-25 | Image approval method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711418984.5A CN108304843B (en) | 2017-12-25 | 2017-12-25 | Image approval method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108304843A true CN108304843A (en) | 2018-07-20 |
| CN108304843B CN108304843B (en) | 2022-02-22 |
Family
ID=62870827
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711418984.5A Active CN108304843B (en) | 2017-12-25 | 2017-12-25 | Image approval method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108304843B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111914820A (en) * | 2019-05-09 | 2020-11-10 | 百度在线网络技术（北京）有限公司 | Qualification auditing method and device |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102098332A (en) * | 2010-12-30 | 2011-06-15 | 北京新媒传信科技有限公司 | Method and device for examining and verifying contents |
| CN104008401A (en) * | 2014-05-07 | 2014-08-27 | 中国科学院信息工程研究所 | Method and device for image character recognition |
| CN104751194A (en) * | 2015-04-27 | 2015-07-01 | 陈包容 | Processing method and processing device for financial expense reimbursement |
| CN104966047A (en) * | 2015-05-22 | 2015-10-07 | 浪潮电子信息产业股份有限公司 | Method and device for identifying vehicle license |
| CN105095842A (en) * | 2014-05-22 | 2015-11-25 | 阿里巴巴集团控股有限公司 | Method and device for identifying information of bill |
| CN105761052A (en) * | 2016-02-05 | 2016-07-13 | 北京金和网络股份有限公司 | Business examination and approval mobile terminal, business examination and approval system with business examination and approval mobile terminal and business examination and approval method |
| CN106407919A (en) * | 2016-09-05 | 2017-02-15 | 珠海赛纳打印科技股份有限公司 | Image processing-based text separation method, device and image forming device |
| CN106529380A (en) * | 2015-09-15 | 2017-03-22 | 阿里巴巴集团控股有限公司 | Image identification method and device |
| CN106886776A (en) * | 2017-02-23 | 2017-06-23 | 山东浪潮云服务信息科技有限公司 | The application model of license electronization is realized in a kind of utilization image recognition |
| CN107122806A (en) * | 2017-05-16 | 2017-09-01 | 北京京东尚科信息技术有限公司 | A kind of nude picture detection method and device |
| CN107133571A (en) * | 2017-04-11 | 2017-09-05 | 上海众开信息科技有限公司 | A kind of system and method that paper invoice is automatically generated to financial statement |
| WO2017179129A1 (en) * | 2016-04-12 | 2017-10-19 | 義和 東 | Content requesting system |
| CN107423731A (en) * | 2017-04-06 | 2017-12-01 | 云南小鹰科技有限公司 | The data processing method and system of aviation document |
-
2017
- 2017-12-25 CN CN201711418984.5A patent/CN108304843B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102098332A (en) * | 2010-12-30 | 2011-06-15 | 北京新媒传信科技有限公司 | Method and device for examining and verifying contents |
| CN104008401A (en) * | 2014-05-07 | 2014-08-27 | 中国科学院信息工程研究所 | Method and device for image character recognition |
| CN105095842A (en) * | 2014-05-22 | 2015-11-25 | 阿里巴巴集团控股有限公司 | Method and device for identifying information of bill |
| CN104751194A (en) * | 2015-04-27 | 2015-07-01 | 陈包容 | Processing method and processing device for financial expense reimbursement |
| CN104966047A (en) * | 2015-05-22 | 2015-10-07 | 浪潮电子信息产业股份有限公司 | Method and device for identifying vehicle license |
| CN106529380A (en) * | 2015-09-15 | 2017-03-22 | 阿里巴巴集团控股有限公司 | Image identification method and device |
| CN105761052A (en) * | 2016-02-05 | 2016-07-13 | 北京金和网络股份有限公司 | Business examination and approval mobile terminal, business examination and approval system with business examination and approval mobile terminal and business examination and approval method |
| WO2017179129A1 (en) * | 2016-04-12 | 2017-10-19 | 義和 東 | Content requesting system |
| CN106407919A (en) * | 2016-09-05 | 2017-02-15 | 珠海赛纳打印科技股份有限公司 | Image processing-based text separation method, device and image forming device |
| CN106886776A (en) * | 2017-02-23 | 2017-06-23 | 山东浪潮云服务信息科技有限公司 | The application model of license electronization is realized in a kind of utilization image recognition |
| CN107423731A (en) * | 2017-04-06 | 2017-12-01 | 云南小鹰科技有限公司 | The data processing method and system of aviation document |
| CN107133571A (en) * | 2017-04-11 | 2017-09-05 | 上海众开信息科技有限公司 | A kind of system and method that paper invoice is automatically generated to financial statement |
| CN107122806A (en) * | 2017-05-16 | 2017-09-01 | 北京京东尚科信息技术有限公司 | A kind of nude picture detection method and device |
Non-Patent Citations (3)
| Title |
|---|
| LIU SHUFENG等: "Research on Chinese characters recognition in complex background images", 《2017 2ND INTERNATIONAL CONFERENCE ON IMAGE, VISION AND COMPUTING (ICIVC)》 * |
| 俞丽颖: "基于规则的医保智能审核系统的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 马雪莲: "基于规则引擎的某企业业务审批系统的设计与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111914820A (en) * | 2019-05-09 | 2020-11-10 | 百度在线网络技术（北京）有限公司 | Qualification auditing method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108304843B (en) | 2022-02-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10068128B2 (en) | Face key point positioning method and terminal | |
| KR102385463B1 (en) | Facial feature extraction model training method, facial feature extraction method, apparatus, device and storage medium | |
| WO2019218451A1 (en) | Method and device for generating medical report | |
| CN109599187A (en) | A kind of online interrogation point examines method, server, terminal, equipment and medium | |
| CN109241513A (en) | A kind of method and device based on big data crowdsourcing model data mark | |
| CN111008971B (en) | Aesthetic quality evaluation method of group photo image and real-time shooting guidance system | |
| WO2021042842A1 (en) | Interview method and apparatus based on ai interview system, and computer device | |
| WO2019142127A1 (en) | Method and system of creating multiple expression emoticons | |
| CN114565602A (en) | Image identification method and device based on multi-channel fusion and storage medium | |
| CN104091173A (en) | Gender recognition method and device based on network camera | |
| JP6916849B2 (en) | Information processing equipment, information processing methods and information processing programs | |
| WO2023273247A1 (en) | Face image processing method and device, computer readable storage medium, terminal | |
| CN108304843A (en) | A kind of image measures and procedures for the examination and approval and examination ＆ approval device | |
| CN103049754B (en) | The picture recommendation method of social networks and device | |
| CN110503101A (en) | Font evaluation method, device, equipment and computer readable storage medium | |
| CN110377201A (en) | Terminal equipment control method, device, computer installation and readable storage medium storing program for executing | |
| CN107424125A (en) | A kind of image weakening method and terminal | |
| CN109003264B (en) | Retinopathy image type identification method and device and storage medium | |
| CN110135391A (en) | System is matched using the program and spectacle-frame of computer apolegamy spectacle-frame | |
| RU2768797C1 (en) | Method and system for determining synthetically modified face images on video | |
| TWM618756U (en) | Image recognition system | |
| WO2021073150A1 (en) | Data detection method and apparatus, and computer device and storage medium | |
| Tao et al. | QoE-oriented multimedia assessment: A facial expression recognition approach | |
| Wang et al. | A bayesian approach to automated creation of tactile facial images | |
| KR102543461B1 (en) | Image adjustment method that selectively changes specific properties using deep learning |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |