CN106056114B - Contents of visiting cards recognition methods and device - Google Patents
Contents of visiting cards recognition methods and device Download PDFInfo
- Publication number
- CN106056114B CN106056114B CN201610347295.9A CN201610347295A CN106056114B CN 106056114 B CN106056114 B CN 106056114B CN 201610347295 A CN201610347295 A CN 201610347295A CN 106056114 B CN106056114 B CN 106056114B
- Authority
- CN
- China
- Prior art keywords
- image
- text
- text sequence
- sequence
- business card
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Character Input (AREA)
- Character Discrimination (AREA)
Abstract
The present invention relates to a kind of contents of visiting cards recognition methods and devices, which comprises obtains business card image；Detect the text sequence image in the business card image；To the text sequence image, the topography from head carries out text identification, obtains corresponding head text fragments；Text sequence content type is determined according to the head text fragments；When the text sequence content type is specified text sequence content type, then complete identification is carried out to the text sequence image and obtain corresponding text sequence.Contents of visiting cards recognition methods provided by the invention and device, adaptive ability is strong, and contents of visiting cards recognition efficiency can be improved.
Description
Technical field
The present invention relates to technical field of image processing, more particularly to a kind of business card identification method and device.
Background technique
Business card is a kind of important article in etiquette, passes through between stranger and exchanges visiting cards can quickly understand each other
Other side establishes social networks.Entity business card is traditional business card form, is at present still the business card form of mainstream.Entity business card can
Contents of visiting cards to be printed on paper card or plastic cards.Traditional business card usage mode is after receiving entity business card
Entity business card is covered up, the used time is needed manually to search, it is time-consuming and laborious.
Current eaily business card processing mode is to go out the content recognition in business card photo after shooting business card photo
Come and save, can quickly be searched by information retrieval technique when requiring to look up contents of visiting cards.Identify contents of visiting cards when need by
Business card photo upload to server, by server search database with the matched business card templates of business card photo, to utilize number
Contents of visiting cards identification is completed according to the marked content auxiliary of business card templates in library.
However, current contents of visiting cards identification method depends on artificial constructed business card templates database, and business card templates
It needs by manually marking, the mark of Database and business card templates requires artificial participative decision making, when not depositing in database
It will lead to discrimination in corresponding business card templates to be decreased obviously, adaptive ability is very poor.
Summary of the invention
Based on this, it is necessary to for the problem of current contents of visiting cards identification method adaptive ability difference, provide a kind of business card
Content identification method and device.
A kind of contents of visiting cards recognition methods, comprising:
Obtain business card image；
Detect the text sequence image in the business card image；
To the text sequence image, the topography from head carries out text identification, obtains corresponding head text piece
Section；
Text sequence content type is determined according to the head text fragments；
When the text sequence content type is specified text sequence content type, then to the text sequence image
It carries out complete identification and obtains corresponding text sequence.
A kind of contents of visiting cards identification device, comprising:
Text sequence detection module, for obtaining business card image；Detect the text sequence image in the business card image；
Text sequence pre-identification module, for carrying out text knowledge to topography of the text sequence image from head
Not, corresponding head text fragments are obtained；
Text sequence identification module, for determining text sequence content type according to the head text fragments；When described
When text sequence content type is specified text sequence content type, then text sequence image progress is completely identified
To corresponding text sequence.
Above-mentioned contents of visiting cards recognition methods and device detect text sequence image, by right after obtaining business card image
The text identification of text sequence image local image can determine corresponding text sequence content type, and then to required text
The corresponding text sequence image of sequence content type carries out complete identification and obtains corresponding text sequence.Using the hand of text identification
Section carries out contents of visiting cards identification, does not need manually to establish business card templates database and artificial mark, be adapted to various types of
The business card of type carries out content recognition, and adaptive ability is strong.And when text sequence content type is specified text sequence content
Complete identification is carried out to the text sequence image when type and obtains corresponding text sequence, contents of visiting cards identification effect can be improved
Rate.
Detailed description of the invention
Fig. 1 is the applied environment figure of namecard processing system in one embodiment；
Fig. 2 is the schematic diagram of internal structure of electronic equipment in one embodiment；
Fig. 3 is the flow diagram of contents of visiting cards recognition methods in one embodiment；
Fig. 4 is flow diagram the step of detecting the text sequence image in business card image in one embodiment；
Fig. 5 mentions for business card image, the business card image of binaryzation in one embodiment and from the business card image of binaryzation
The schematic diagram of the connected domain taken；
Fig. 6 is that the topography in one embodiment to text sequence image from head carries out text identification, obtains phase
The flow diagram of the step of head text fragments answered；
Fig. 7 is process signal the step of being syncopated as the sequence of individual character image from text sequence image in one embodiment
Figure；
Fig. 8 is the flow diagram of contents of visiting cards recognition methods in a concrete application scene；
Fig. 9 is the structural block diagram of contents of visiting cards identification device in one embodiment；
Figure 10 is the structural block diagram of text sequence detection module in one embodiment；
Figure 11 is the structural block diagram of text sequence pre-identification module in one embodiment；
Figure 12 is the structural block diagram of contents of visiting cards identification device in another embodiment.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
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.
As shown in Figure 1, in one embodiment, providing a kind of namecard processing system, including terminal 110 and server
120.Wherein terminal 110 can be personal computer, mobile terminal or wearable device, mobile terminal such as mobile phone, plate
Computer or personal digital assistant.Server 120 can be independent server or server cluster.Terminal 110 can be used for
It obtains business card image and is sent to server 120, server 120 can be used for receiving the business card image of the transmission of terminal 110；Detect name
Text sequence image in picture；To text sequence image, the topography from head carries out text identification, obtains corresponding
Head text fragments；Text sequence content type is determined according to head text fragments；When text sequence content type is specified
Text sequence content type when, then complete identification is carried out to text sequence image and obtains corresponding text sequence；Being also used to will
The text sequence recognized and corresponding text sequence content type are sent to terminal 110 as contents of visiting cards.Terminal 110 can be used
In the contents of visiting cards for receiving server feedback, the contents of visiting cards that can be also used for receive is shared.
As shown in Fig. 2, in one embodiment, providing a kind of electronic equipment, which be can be as shown in Figure 1
Terminal 110 or server 120.Electronic equipment include by system bus connect processor, non-volatile memory medium,
Built-in storage and network interface.When the electronic equipment is terminal 110, electronic equipment can also include display screen and input dress
It sets.Wherein, the non-volatile memory medium of electronic equipment is stored with operating system, further includes a kind of contents of visiting cards identification device,
The contents of visiting cards identification device is for realizing a kind of contents of visiting cards recognition methods.The processor of the electronic equipment is for providing calculating
And control ability, support the operation of electronic equipment.The built-in storage of electronic equipment is in the business card in non-volatile memory medium
The operation for holding identification device provides environment, can store computer-readable instruction in the built-in storage, the computer-readable instruction
When being executed by processor, processor may make to execute a kind of contents of visiting cards recognition methods.The network interface of electronic equipment is for connecting
Network is connected to be communicated.Display screen can be liquid crystal display or electric ink display screen etc., and input unit can be aobvious
The touch layer covered in display screen is also possible to the key being arranged on electronic equipment casing, trace ball or Trackpad, is also possible to outer
Keyboard, Trackpad or mouse for connecing etc..It will be understood by those skilled in the art that structure shown in Figure 2, only and the application
The block diagram of the relevant part-structure of scheme does not constitute the restriction for the electronic equipment being applied thereon to application scheme, tool
The electronic equipment of body may include perhaps combining certain components than more or fewer components as shown in the figure or having difference
Component layout.
As shown in figure 3, in one embodiment, providing a kind of contents of visiting cards recognition methods, this method can be used alone
110 side of terminal of namecard processing system in Fig. 1；Or 120 side of server can be applied individually to any；Or this method can one
Certain applications in 110 side of terminal and other parts are then applied to 120 side of server, by terminal 110 and server 120 interaction
Realize contents of visiting cards recognition methods.The present embodiment is applied to server 120 in this way to be come for example, this method specifically includes
Following steps:
Step 302, business card image is obtained.
Wherein, business card image refers to the image comprising contents of visiting cards, can be business card photo or business card scan part or
Electronic business card picture.Terminal can shoot entity business card by the camera of terminal and obtain business card image, or be swept by scanner
It retouches entity business card and obtains business card image, or receive the business card image that another terminal is sent.Terminal can send business card image
To server, which is received by server.In one embodiment, server can carry out fuzzy journey to business card image
Degree analysis, excludes the high business card image of fog-level, fog-level can be estimated according to gradient power；It can also exclude
The business card image of business card essential characteristic is not met, to weed out non-business card image.
Step 304, the text sequence image in business card image is detected.
Wherein, text sequence refers to the text-string that character arranged in sequence is formed.Text sequence can be line of text or
Person's text column, corresponding text sequence image then can be line of text image or text column image.Wherein line of text refers to word
The text sequence being substantially arranged in the horizontal direction is accorded with, text column is then the text sequence that character is substantially longitudinally arranged in.
Specifically, server can detect text sequence image according to the priori features of text sequence from business card image.
The priori features of text sequence such as line of text is perhaps inside the character pitch feature line of text or text column inside text column
The feature etc. of character center substantially point-blank.Character pitch inside line of text or text column is smaller, generally less than
The width or height of one or more characters.When the length of the text sequence image detected is more than preset length, can incite somebody to action
Text sequence image segmentation is that multiple text sequence images continue with.
Step 306, the topography to text sequence image from head carries out text identification, obtains corresponding head text
This segment.
Wherein, the head of text sequence image refers to the starting position according to the reading order of text sequence, such as text
The head of row image can be the left end of line of text image, and the head of also such as text column image can be text column image
Topmost.Topography can be the part figure of regular length or regular length accounting in text sequence image from head
Picture, wherein length accounting refers to that length of the topography along text sequence direction accounts for the ratio of text sequence image length.Service
Device can carry out text identification to topography, obtain the corresponding head text fragments of the topography.Head text fragments are phases
The a part for the text sequence answered.
Server can be used neural network model and carry out text identification, and CNN (Convolutional specifically can be used
Neural Networks, convolutional neural networks) model or FCNN (Fully Convolutional Neural
Networks, full convolutional neural networks) model.Wherein CNN model is very strong in visual field classification capacity, can accurately carry out list
Word identification.
Step 308, text sequence content type is determined according to head text fragments.
Wherein, text sequence content type refers to the type of content in the text sequence in text sequence image.Text sequence
Column content type such as telephone number-type, name type, e-mail address type, Business Name type or mailing address
Type etc..
In one embodiment, step 308 includes: to carry out keyword match and/or format match to head text fragments,
Determine corresponding text sequence content type.
Specifically, server can be collected in the head text fragments of text sequence sample in advance for identifying text sequence
The keyword of content type constitutes set of keywords, and records the corresponding text sequence content type of each keyword.Server exists
When executing step 308, can traverse set of keywords search with the current matched keyword of head text fragments, if finding
Text sequence content type is then determined as text sequence content type corresponding to matched keyword by the keyword matched.
Wherein, keyword can be the field name of mark text sequence content type, such as " phone ", " name ", " duty
The field names such as position ", " mailbox ", " company " or " mailing address ".Keyword is also possible to be counted text sequence head
One or more characters in can distinguish the content of text feature of text sequence content type, for example as surname " Lee ",
" king " perhaps individual characters such as " Nie " also such as "+86 ", " 136 " or " 139 " are expected someone's call prefix.
Format refers to the structural constraint of character combination in the character string of at least two characters composition.Server can prepare in advance
The corresponding format general formula of each text sequence content type, when executing step 308 by head text fragments and each format general formula
Compare, if it exists matched format general formula, then text sequence content type is determined as the corresponding text of matched format general formula
Sequence content type.Format general formula can be indicated with regular expression.
In one embodiment, keyword match and format match, which can separate, is used alone, and can also be applied in combination.Group
Close in use, such as can find with the matched keyword of head text fragments, and exist with head text fragments it is matched
Format general formula, and matched keyword and matched format general formula correspond to identical text sequence content type, then by text sequence
Column content type is determined as the identical text sequence content type.
Step 310, when text sequence content type is specified text sequence content type, then to text sequence image
It carries out complete identification and obtains corresponding text sequence.
Wherein, specified text sequence content type is preparatory or this executes to specify when contents of visiting cards identifies and needs to identify
Text sequence content type out.Specified text sequence content type can be one or more.When text sequence content class
When type is specified text sequence content type, illustrate that corresponding text sequence is contents of visiting cards needed for contents of visiting cards identification,
Required text sequence can be obtained by carrying out complete identification to text sequence image.If text sequence content type can not be determined
Complete identification can be carried out to text sequence image as needed and obtain text sequence, then confirm whether text sequence is required text
This sequence；Or corresponding text sequence image can be abandoned.If it is determined that text sequence content type be not specified text
Sequence content type then can directly abandon corresponding text sequence image, no longer be identified.
In one embodiment, server can also verify the text sequence content type and root of the text sequence identified
Whether the text sequence content type determined according to head text fragments is consistent, verifies and passes through if consistent, retains the text identified
This sequence and corresponding text sequence content type；The text sequence that can will be determined according to head text fragments if inconsistent
Content type is changed to the text sequence content type of the text sequence identified.It can guarantee contents of visiting cards recognition result in this way
Accuracy.
Above-mentioned contents of visiting cards recognition methods detects text sequence image after obtaining business card image, by text sequence
The text identification of column image local image can determine corresponding text sequence content type, and then in required text sequence
Hold the corresponding complete identification of text sequence image progress of type and obtains corresponding text sequence.Using the means of text identification come into
The identification of row contents of visiting cards does not need manually to establish business card templates database and artificial mark, is adapted to various types of names
Piece carries out content recognition, and adaptive ability is strong.And when text sequence content type is specified text sequence content type
Complete identification is carried out to text sequence image and obtains corresponding text sequence, contents of visiting cards recognition efficiency can be improved.
As shown in figure 4, in one embodiment, step 304 specifically comprises the following steps:
Step 402, the connected domain in business card image is extracted.
Specifically, server can carry out connected domain analysis by business card image binaryzation, and by the business card image after binaryzation
Connected domain is extracted, adjacent connected domain can also be merged.Smooth (the Run Length of stroke can be used in service implement body
Smooth Algorithm, is abbreviated as RLSA) algorithm carries out connected domain analysis and merging, the algorithm can be by adjacent connected domains
Pixel be connected, form the region of monolith, relatively due to the distance between each connected domain of one text interior sequences,
So the connected domain in same text sequence can form a complete connected domain.
As shown in figure 5, part of sensitive information hides for protection privacy purpose shown in business card image such as Fig. 5 (a)
Lid processing.The image as shown in Fig. 5 (b) will be obtained after business card image binaryzation shown in Fig. 5 (a), then passes through connected domain analysis
The connected domain of each white as shown in Fig. 5 (c) is obtained with merging.
Step 404, corresponding text sequence image is determined according to connected domain.
Specifically, the outer profile for multiple connected domains that server can will be approximately on same straight line is determined as text sequence
The position of image and record, with the corresponding text sequence image of determination.When text sequence image is indicated with rectangle, text sequence
The position of image can be indicated with a vertex of the text sequence image of rectangle and rectangle are wide with rectangle height.Server
It can be using each connected domain as independent text sequence image procossing.
Step 406, the inclination angle of each connected domain is determined.
Wherein, inclination angle refers to the angle for deviateing reference direction, and reference direction can be consistent with the direction of text sequence, than
Such as line of text, inclination angle can be the angle for deviateing horizontal direction, and also such as text column, inclination angle can be deviation
The angle of vertical direction.Specifically, each connected domain can indicate that server can calculate the rectangular profile with its rectangular profile
Inclination angle of the inclination angle as corresponding connected domain.
In one embodiment, server can project to the pixel of connected domain on straight line, so that the straight line
On projection variance it is maximum, and then using the inclination angle of the straight line as the inclination angle of corresponding connected domain.Service implement body can be used
Principal component analysis (Principal Component Analysis, PCA) algorithm or least square regression algorithm scheduling algorithm come
Obtain the inclination angle of the projection maximum straight line of variance.
Step 408, the inclination angle of business card image is determined according to the inclination angle of each connected domain.
Specifically, server can be using the arithmetic mean of instantaneous value at the inclination angle of each connected domain or weighted average as business card
The inclination angle of image.
Step 410, direction correction is carried out to business card image according to the inclination angle of business card image, what acquisition was corrected by direction
Each text sequence image.
Specifically, server can rotate business card image towards the direction for reducing inclination angle according to the inclination angle of business card image
Equal to the angle at inclination angle, the direction of business card image is corrected to realize.After business card image has integrally carried out direction correction, name
Each text sequence image in picture has also been correspondingly made available direction correction.
In one embodiment, step 404 can delete, and step 410 could alternatively be: according to the inclination of business card image
Angle carries out direction correction to business card image, determines corresponding text sequence according to each connected domain in the business card image through overcorrection
Column image.
In the present embodiment, by the connected domain extracted from business card image, corresponding text sequence can be not only determined
Image can also correct the direction correction realized to each text sequence image by the direction of business card image entirety.In foundation
Connected domain can realize detection and the direction of text sequence image using connected domain during detecting text sequence image
Correction does not need to carry out direction correction individually for each text sequence image, improves computational efficiency.
As shown in fig. 6, in one embodiment, step 306 specifically comprises the following steps:
Step 602, the sequence of individual character image is syncopated as from text sequence image.
Wherein, individual character image is the rectangular image for including single character, and server is syncopated as one from text sequence image
Each and every one individual character image, these individual character images constitute the sequence of individual character image according to the sequence in text sequence image.Service
Implement body can be according to priori knowledges such as text sequence pitch characteristics, character length feature and character ratio consistency from text sequence
The sequence of individual character image is syncopated as in column image.Text sequence image can pass through image enhancement before being split, for example increase figure
Image contrast.
In one embodiment, each pixel value therein can will be projected to text after text sequence image binaryzation by server
Accumulated value is obtained in this sequence image longitudinal direction, local maxima accumulated value is searched out or Local Minimum accumulated value is cut
Point, to obtain the sequence of individual character image.If wherein indicating after text sequence image binaryzation, the pixel color of character is white,
Then find Local Minimum accumulated value；If the pixel color for indicating character after text sequence image binaryzation is black, searching office
Portion's maximum accumulated value.
Step 604, text identification is carried out to the continuous individual character image in part in the sequence of individual character image from head, obtained
Corresponding head text fragments.
Specifically, server is chosen from the individual character image of the sequence whole of individual character image from the sequence of individual character image
The continuous individual character image in part that head is risen, and then text identification is carried out to the continuous individual character image in the part of selection, it obtains corresponding
Head text fragments.The continuous individual character image in part wherein in the sequence of individual character image from head, specifically can be individual character figure
The continuous individual character image of fixed quantity in the sequence of picture from head or the continuous individual character image of default accounting.It is default to account for
Continuous individual character image than can be selection accounts for the ratio of individual character total number of images in the sequence of individual character image.
In the present embodiment, to obtaining the sequence of individual character image after text sequence image cutting, to the sequence of individual character image into
The identification of row part obtains head text fragments, can conveniently and efficiently determine head text fragments.
In one embodiment, complete identification is carried out to text sequence image in step 310 and obtains corresponding text sequence
It comprises determining that and removes the remaining individual character image of the continuous individual character image in part from head in the sequence of individual character image；To surplus
Remaining individual character image carries out text identification, obtains corresponding remaining local segment；According to remaining local segment and head part piece
Section obtains text sequence corresponding with text sequence image.
Specifically, server, which first determines the sequence of individual character image and locally identifies, obtains head text fragments, when according to head
When portion's text fragments determine that the text sequence in text sequence image is specified text sequence content type, then continue to individual character
Remaining individual character image carries out text identification in the sequence of image, remaining local segment is obtained, by remaining local segment and head
Local segment combination can obtain complete text sequence.
It, can be efficiently to text after server can be required contents of visiting cards determining text sequence in the present embodiment
Sequence image carries out complete identification and obtains corresponding text sequence, improves contents of visiting cards recognition efficiency.
As shown in fig. 7, in one embodiment, step 602 specifically comprises the following steps:
Step 702, the long side in text sequence image along text sequence image is according to the short side than text sequence image
Short spacing takes candidate cut-off.
Specifically, text sequence image is rectangle, the width of character in the short side of text sequence image substantially text sequence
Or it is high, long side is then about the length of text sequence in text sequence image, and server is chosen according to the spacing shorter than short side
Candidate cut-off, the quantity of the candidate cut-off selected in this way are greater than the quantity of actual cut-off.Choose candidate cut-off
Spacing can specifically be less than or equal to text sequence image short side half or one third or a quarter.It waits
Selecting cut-off is candidate dicing position, can distance with coordinate or apart from text sequence picture headers starting point indicate.
In one embodiment, all text sequence images can be kept length-width ratio to carry out short side normalization by server,
So that it is equal by the normalized each text sequence image bond length of short side, short side normalizing is being passed through by server again later
Candidate cut-off is taken according to the spacing shorter than its short side along its long side in the text sequence image of change.Such as it can be by all texts
Row image keeps length-width ratio scaling, so that the height of the line of text image after scaling is 120 pixels, according still further to 30 pixels
Spacing take candidate cut-off from the line of text image after scaling.
Step 704, the cutting confidence level of each candidate cut-off is obtained.
Here two classification problems are converted by cutting problems, that is, judges whether candidate cut-off is actual cutting
Point, cutting confidence level be corresponding candidate cut-off be actual cut-off probability quantized value.Servicing implement body can be by
It is syncopated as corresponding picture according to candidate cut-off, will be sequentially inputted to after the picture being syncopated as extraction characteristics of image trained
In classifier, the cutting confidence level of corresponding candidate cut-off is exported.Random forest grader can be used in classifier.
The characteristics of image of extraction can use HOG (Histogram of Oriented Gradient, direction gradient histogram
Figure) feature.In the case where business card image is relatively fuzzyyer, can be sticked together between character, without obvious spacing；It is wrapped in character
Contained symbol for example " (" etc., the ratios of these symbols and Chinese character and number are all different, here using HOG feature, between character
Apparently difference is very big for the corresponding region of cut-off and the region of character inner, and HOG feature can give expression to accordingly well
The robustness of cutting can be improved using HOG feature for feature.The characteristics of image of extraction can also use LBP (Local Binary
Patterns, local binary patterns) other features such as feature.
Step 706, cut-off is determined according to cutting confidence level.
Specifically, server can be determined as reality if being higher than preset threshold by cutting confidence level compared with preset threshold
Cut-off.In one embodiment, server can exclude the time of cutting confidence level local maximum from each candidate cut-off
The candidate cut-off that cut-off is adjacent is selected, cut-off is determined according to remaining candidate cut-off.Wherein cutting confidence level local pole
Big candidate cut-off refers to that the cutting confidence level of candidate's cut-off is higher than the cutting confidence level of adjacent candidate cut-off.It examines
The quantity for considering candidate cut-off is less than the quantity of actual cut-off, even if the cutting confidence of two adjacent candidate's cut-offs
Degree is all very high, wherein also only having one is actual cut-off, after excluding impossible candidate cut-off in this way, remaining time
Select cut-off can be all or according to above-mentioned preset threshold selectively as actual cut-off, the cutting that selects in this way
Point is more accurate.
Step 708, the sequence of individual character image is syncopated as from text sequence image according to determining cut-off.Specifically,
Cutting is carried out at the server cut-off that everywhere determines in text sequence image, obtains individual character image one by one, is constituted single
The sequence of word image.
It, can be by densely selecting candidate cut-off in text sequence image in the present embodiment, and utilize each candidate
The cutting confidence level of cut-off carrys out cutting text sequence image and obtains the sequence of individual character image, may be implemented to text sequence image
Accurate cutting, improve contents of visiting cards discrimination.
In one embodiment, electronic equipment (such as terminal) is being got in the text sequence and text sequence identified
After holding type, it can be shown in the designated position at specified interface according to text sequence content type classification.For example electronic equipment can be
The field name of each text sequence content type is shown in the interface at specified interface, so that corresponding each field name shows phase
The text sequence answered.
In one embodiment, electronic equipment (such as terminal) can also receive typing instruction, instructed and obtained according to typing
The contents of visiting cards of typing, and the contents of visiting cards of typing is saved together with text sequence and text sequence content type.This implementation
In example, user can not only identify contents of visiting cards, can also mark the new contents of visiting cards not having in the text sequence identified,
And saved together with the contents of visiting cards identified, contents of visiting cards can be further enriched, business card ease of use is improved.Terminal is being protected
Server can be stored in locally or is saved in when depositing.
In one embodiment, electronic equipment (such as terminal) can also obtain business card sharing instruction；Shared according to business card
It instructs and determines recipient's mark；Text sequence is shared with corresponding text sequence content type to recipient and identifies corresponding end
End.Electronic equipment can also divide the new contents of visiting cards of typing together with text sequence and corresponding text sequence content type
It enjoys to recipient and identifies corresponding terminal.Recipient identifies the user identifier that can be social good friend.User identifier can be marked uniquely
Know user out, such as user account.
It, can be by text after obtaining the text sequence identified and corresponding text sequence content type in the present embodiment
Sequence is shared with corresponding text sequence content type to specified recipient, convenient for will be in the business card after entity business card electronization
That holds is shared, and recipient does not need typing business card again, improves operation ease.
As shown in figure 8, in a concrete application scene, server can advanced style of writing current row detection, then carry out line of text
Pre-identification finally carries out line of text content recognition and extraction.Server is when carrying out line of text detection, first by business card image two-value
Change, then extract connected domain and merge, to extract line of text image, estimates line of text quantity and inclination angle, utilize text
Current row quantity and tilt angle calculation go out the inclination angle of business card image, to be carried out according to the inclination angle of business card image to business card image
General direction correction, to reach the result for carrying out direction correction to line of text image.Server can with ambiguous estimation degree,
Without identification if fog-level is higher than fog-level threshold value.
Further, server carries out image enhancement to line of text image when carrying out line of text pre-identification, and then to text
Current row image carries out individual character cutting and laggard this pre-identification of style of writing of the individual character image binaryzation being syncopated as is obtained corresponding head
Portion's text fragments.Then, server closes head text fragments during carrying out line of text content recognition and extracting
The matching of key word, again completely identifies corresponding line of text image if being matched to keyword, and verify recognition result, finally
The contents of visiting cards recognized is exported.
As shown in figure 9, in one embodiment, providing a kind of contents of visiting cards identification device 900, including text sequence inspection
Survey module 901, text sequence pre-identification module 902 and text sequence identification module 903.
Text sequence detection module 901, for obtaining business card image；Detect the text sequence image in business card image.
Text sequence pre-identification module 902, for carrying out text knowledge to topography of the text sequence image from head
Not, corresponding head text fragments are obtained.
Text sequence identification module 903, for determining text sequence content type according to head text fragments；When text sequence
When column content type is specified text sequence content type, then complete identification is carried out to text sequence image and obtain corresponding text
This sequence.
Above-mentioned contents of visiting cards identification device 900 detects text sequence image, by text after obtaining business card image
The text identification of this sequence image topography can determine corresponding text sequence content type, and then to required text sequence
The corresponding text sequence image of column content type carries out complete identification and obtains corresponding text sequence.Using the means of text identification
Contents of visiting cards identification is carried out, does not need manually to establish business card templates databases and artificial mark, is adapted to various types
Business card carry out content recognition, adaptive ability is strong.And when text sequence content type is specified text sequence content class
Complete identification is carried out to text sequence image when type and obtains corresponding text sequence, contents of visiting cards recognition efficiency can be improved.
As shown in Figure 10, in one embodiment, text sequence detection module 901 include: connected domain extraction module 901a,
Text sequence image determining module 901b and direction rectification module 901c.
Connected domain extraction module 901a, for extracting the connected domain in business card image.
Text sequence image determining module 901b, for determining corresponding text sequence image according to connected domain.
Direction rectification module 901c, for determining the inclination angle of each connected domain；Inclination angle according to each connected domain is true
Name the inclination angle of picture；Direction correction is carried out to business card image according to the inclination angle of business card image, obtains and is rectified by direction
Positive each text sequence image.
In the present embodiment, by the connected domain extracted from business card image, corresponding text sequence can be not only determined
Image can also correct the direction correction realized to each text sequence image by the direction of business card image entirety.In foundation
Connected domain can realize detection and the direction of text sequence image using connected domain during detecting text sequence image
Correction does not need to carry out direction correction individually for each text sequence image, improves computational efficiency.
In one embodiment, text sequence identification module 903 is also used to carry out keyword match to head text fragments
And/or format match, determine corresponding text sequence content type.
As shown in figure 11, in one embodiment, text sequence pre-identification module 902 includes: individual character cutting module 902a
With text head pre-identification module 902b.
Individual character cutting module 902a, for being syncopated as the sequence of individual character image from text sequence image.
Text head pre-identification module 902b, for the continuous individual character image in part in the sequence to individual character image from head
Text identification is carried out, corresponding head text fragments are obtained.
In the present embodiment, to obtaining the sequence of individual character image after text sequence image cutting, to the sequence of individual character image into
The identification of row part obtains head text fragments, can conveniently and efficiently determine head text fragments.
In one embodiment, from the beginning text sequence identification module 903 is also used to determine removes in the sequence of individual character image
The remaining individual character image of the continuous individual character image in part that portion rises；Text identification is carried out to remaining individual character image, is obtained corresponding
Remaining local segment；Text sequence corresponding with text sequence image is obtained according to remaining local segment and head local segment
Column.
It, can be efficiently to text after server can be required contents of visiting cards determining text sequence in the present embodiment
Sequence image carries out complete identification and obtains corresponding text sequence, improves contents of visiting cards recognition efficiency.
In one embodiment, individual character cutting module 902a is also used in text sequence image along text sequence image
Long side takes candidate cut-off according to the short spacing of the short side than text sequence image；Obtain the cutting confidence of each candidate cut-off
Degree；Cut-off is determined according to cutting confidence level；Individual character image is syncopated as from text sequence image according to determining cut-off
Sequence.
It, can be by densely selecting candidate cut-off in text sequence image in the present embodiment, and utilize each candidate
The cutting confidence level of cut-off carrys out cutting text sequence image and obtains the sequence of individual character image, may be implemented to text sequence image
Accurate cutting, improve contents of visiting cards discrimination.
In one embodiment, individual character cutting module 902a is also used to exclude cutting confidence level from each candidate cut-off
The adjacent candidate cut-off of the candidate cut-off of local maximum determines cut-off according to remaining candidate cut-off.
As shown in figure 12, in one embodiment, contents of visiting cards identification device 900 further includes business card sharing module 904, is used
Share instruction in obtaining business card；Shared to instruct according to business card and determines recipient's mark；By text sequence and corresponding text sequence
Content type, which is shared to recipient, identifies corresponding terminal.
It, can be by text after obtaining the text sequence identified and corresponding text sequence content type in the present embodiment
Sequence is shared with corresponding text sequence content type to specified recipient, convenient for will be in the business card after entity business card electronization
That holds is shared, and recipient does not need typing business card again, improves operation ease.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, which can be stored in a computer-readable storage and be situated between
In matter, the program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, storage medium above-mentioned can be
The non-volatile memory mediums such as magnetic disk, CD, read-only memory (Read-Only Memory, ROM) or random storage note
Recall body (Random Access Memory, RAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
Only several embodiments of the present invention are expressed for above embodiments, and the description thereof is more specific and detailed, but can not
Therefore it is construed as limiting the scope of the patent.It should be pointed out that for those of ordinary skill in the art,
Under the premise of not departing from present inventive concept, various modifications and improvements can be made, and these are all within the scope of protection of the present invention.
Therefore, the scope of protection of the patent of the invention shall be subject to the appended claims.
Claims (14)
1. a kind of contents of visiting cards recognition methods, comprising:
Obtain business card image；
Detect the text sequence image in the business card image；
The sequence of individual character image is syncopated as from the text sequence image；
Text identification is carried out to the continuous individual character image in part in the sequence of the individual character image from head, obtains corresponding head
Portion's text fragments；
Text sequence content type is determined according to the head text fragments；
When the text sequence content type is specified text sequence content type, then
The individual character image remaining to the removing continuous individual character image in part from head in the sequence of the individual character image
Text identification is carried out, corresponding remaining local segment is obtained；It is obtained according to the remaining local segment and the head text fragments
To text sequence corresponding with the text sequence image.
2. the method according to claim 1, wherein the text sequence image in the detection business card image
Include:
Extract the connected domain in the business card image；
Corresponding text sequence image is determined according to the connected domain；
Determine the inclination angle of each connected domain；
The inclination angle of the business card image is determined according to the inclination angle of each connected domain；
Direction correction is carried out to the business card image according to the inclination angle of the business card image, obtains each institute corrected by direction
State text sequence image.
3. the method according to claim 1, wherein described determine text sequence according to the head text fragments
Content type includes:
Keyword match and/or format match are carried out to the head text fragments, determine corresponding text sequence content type.
4. the method according to claim 1, wherein described be syncopated as individual character figure from the text sequence image
The sequence of picture includes:
Long side in the text sequence image along the text sequence image is according to the short side than the text sequence image
Short spacing takes candidate cut-off；
Obtain the cutting confidence level of each candidate cut-off；
Cut-off is determined according to the cutting confidence level；
The sequence of individual character image is syncopated as from the text sequence image according to determining cut-off.
5. according to the method described in claim 4, it is characterized in that, described determine cut-off packet according to the cutting confidence level
It includes:
The adjacent candidate cut-off of the candidate cut-off of cutting confidence level local maximum is excluded from each candidate cut-off, according to
Remaining candidate's cut-off determines cut-off.
6. the method according to claim 1, wherein further include:
It obtains business card and shares instruction；
Shared to instruct according to the business card and determines recipient's mark；
The text sequence is shared with the corresponding text sequence content type to the recipient and identifies corresponding terminal.
7. a kind of contents of visiting cards identification device characterized by comprising
Text sequence detection module, for obtaining business card image；Detect the text sequence image in the business card image；
Text sequence pre-identification module, for being syncopated as the sequence of individual character image from the text sequence image；To the list
The continuous individual character image in part in the sequence of word image from head carries out text identification, obtains corresponding head text fragments；
Text sequence identification module, for determining text sequence content type according to the head text fragments；When the text
It is when sequence content type is specified text sequence content type, then described from head to being removed in the sequence of the individual character image
The remaining individual character image of the continuous individual character image in part risen carries out text identification, obtains corresponding remaining local segment；According to
The residue local segment and the head text fragments obtain text sequence corresponding with the text sequence image.
8. device according to claim 7, which is characterized in that the text sequence detection module includes:
Connected domain extraction module, for extracting the connected domain in the business card image；
Text sequence image determining module, for determining corresponding text sequence image according to the connected domain；
Direction rectification module, for determining the inclination angle of each connected domain；The name is determined according to the inclination angle of each connected domain
The inclination angle of picture；Direction correction is carried out to the business card image according to the inclination angle of the business card image, obtains process side
To each text sequence image of correction.
9. device according to claim 7, which is characterized in that the text sequence identification module is also used to the head
Text fragments carry out keyword match and/or format match, determine corresponding text sequence content type.
10. device according to claim 7, which is characterized in that the individual character cutting module is also used in the text sequence
Candidate is taken to cut according to the spacing shorter than the short side of the text sequence image along the long side of the text sequence image in column image
Branch；Obtain the cutting confidence level of each candidate cut-off；Cut-off is determined according to the cutting confidence level；According to determining cutting
Point is syncopated as the sequence of individual character image from the text sequence image.
11. device according to claim 10, which is characterized in that the individual character cutting module is also used to from each candidate cutting
The adjacent candidate cut-off of the candidate cut-off of cutting confidence level local maximum is excluded in point, according to remaining candidate cut-off
Determine cut-off.
12. device according to claim 7, which is characterized in that further include:
Business card sharing module shares instruction for obtaining business card；Shared to instruct according to the business card and determines recipient's mark；By institute
It states text sequence and shares terminal corresponding to recipient mark with the corresponding text sequence content type.
13. a kind of computer readable storage medium is stored with computer program, when the computer program is executed by processor,
So that the processor is executed such as the step of any one of claims 1 to 6 the method.
14. a kind of computer equipment, including memory and processor, the memory is stored with computer program, the calculating
When machine program is executed by the processor, so that the processor executes the step such as any one of claims 1 to 6 the method
Suddenly.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610347295.9A CN106056114B (en) | 2016-05-24 | 2016-05-24 | Contents of visiting cards recognition methods and device |
| PCT/CN2017/084625 WO2017202232A1 (en) | 2016-05-24 | 2017-05-17 | Business card content identification method, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610347295.9A CN106056114B (en) | 2016-05-24 | 2016-05-24 | Contents of visiting cards recognition methods and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106056114A CN106056114A (en) | 2016-10-26 |
| CN106056114B true CN106056114B (en) | 2019-07-05 |
Family
ID=57175176
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610347295.9A Active CN106056114B (en) | 2016-05-24 | 2016-05-24 | Contents of visiting cards recognition methods and device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN106056114B (en) |
| WO (1) | WO2017202232A1 (en) |
Families Citing this family (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106056114B (en) * | 2016-05-24 | 2019-07-05 | 腾讯科技（深圳）有限公司 | Contents of visiting cards recognition methods and device |
| CN106815561A (en) * | 2016-12-22 | 2017-06-09 | 北京五八信息技术有限公司 | Business license printed page analysis method and device |
| CN107067005A (en) * | 2017-04-10 | 2017-08-18 | 深圳爱拼信息科技有限公司 | A kind of method and device of Sino-British mixing OCR Character segmentations |
| CN109389115B (en) * | 2017-08-11 | 2023-05-23 | 腾讯科技（上海）有限公司 | Text recognition method, device, storage medium and computer equipment |
| CN107871232A (en) * | 2017-10-19 | 2018-04-03 | 中国平安人寿保险股份有限公司 | A kind of generation method and its terminal of customer visit plan |
| CN107832756B (en) * | 2017-10-24 | 2021-09-07 | 讯飞智元信息科技有限公司 | Express bill information extraction method and device, storage medium and electronic equipment |
| CN108229299B (en) * | 2017-10-31 | 2021-02-26 | 北京市商汤科技开发有限公司 | Certificate identification method and device, electronic equipment and computer storage medium |
| CN108038504B (en) * | 2017-12-11 | 2019-12-27 | 深圳房讯通信息技术有限公司 | Method for analyzing content of house property certificate photo |
| CN108875721A (en) * | 2017-12-18 | 2018-11-23 | 南通艾思达智能科技有限公司 | A kind of more specification text cooperatives positioning and extracting method |
| CN108596181B (en) * | 2018-04-16 | 2022-02-25 | 腾讯科技（深圳）有限公司 | Text recognition method, system, machine device and computer-readable storage medium |
| CN110569835B (en) * | 2018-06-06 | 2024-03-05 | 北京搜狗科技发展有限公司 | Image recognition method and device and electronic equipment |
| CN113961900A (en) * | 2018-07-16 | 2022-01-21 | 创新先进技术有限公司 | Identity authentication method and device |
| CN109740548B (en) * | 2019-01-08 | 2020-12-08 | 北京易道博识科技有限公司 | Reimbursement bill image segmentation method and system |
| CN110175610B (en) * | 2019-05-23 | 2023-09-05 | 上海交通大学 | Bill image text recognition method supporting privacy protection |
| CN110489622B (en) * | 2019-07-10 | 2024-02-06 | 平安科技（深圳）有限公司 | Sharing method and device of object information, computer equipment and storage medium |
| CN111181835B (en) * | 2019-10-17 | 2021-07-27 | 腾讯科技（深圳）有限公司 | Message monitoring method, system and server |
| CN111178347B (en) * | 2019-11-22 | 2023-12-08 | 京东科技控股股份有限公司 | Ambiguity detection method, ambiguity detection device, ambiguity detection equipment and ambiguity detection storage medium for certificate image |
| CN110969154A (en) * | 2019-11-29 | 2020-04-07 | 上海眼控科技股份有限公司 | Text recognition method and device, computer equipment and storage medium |
| CN111339910B (en) * | 2020-02-24 | 2023-11-28 | 支付宝实验室(新加坡)有限公司 | Text processing and text classification model training method and device |
| CN111553364B (en) * | 2020-04-28 | 2022-10-11 | 支付宝(杭州)信息技术有限公司 | Picture processing method and device |
| CN111626383B (en) * | 2020-05-29 | 2023-11-07 | Oppo广东移动通信有限公司 | Font identification method and device, electronic equipment and storage medium |
| CN113657369B (en) * | 2021-08-26 | 2024-05-24 | 北京有竹居网络技术有限公司 | Character recognition method and related equipment thereof |
| CN113887484B (en) * | 2021-10-20 | 2022-11-04 | 前锦网络信息技术(上海)有限公司 | Card type file image identification method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1632821A (en) * | 2004-12-30 | 2005-06-29 | 北京中星微电子有限公司 | Automatic searching and determining method for key words information in name card identification |
| CN101520851A (en) * | 2008-02-29 | 2009-09-02 | 富士通株式会社 | Character information identification device and method |
| CN102750552A (en) * | 2012-06-18 | 2012-10-24 | 北京捷通华声语音技术有限公司 | Handwriting recognition method and system as well as handwriting recognition terminal |
| CN103093224A (en) * | 2011-11-08 | 2013-05-08 | 佳能株式会社 | Method and device for determining average character width and method and equipment of character segmentation |
| CN103679117A (en) * | 2012-09-07 | 2014-03-26 | 北京蒙恬科技有限公司 | Business card identification method and device |
| CN104966097A (en) * | 2015-06-12 | 2015-10-07 | 成都数联铭品科技有限公司 | Complex character recognition method based on deep learning |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1532768A (en) * | 2003-03-26 | 2004-09-29 | 摩托罗拉公司 | Method and device for classifying digital image field types |
| US9916514B2 (en) * | 2012-06-11 | 2018-03-13 | Amazon Technologies, Inc. | Text recognition driven functionality |
| KR20140090371A (en) * | 2013-01-08 | 2014-07-17 | 주식회사 협신 | Post-it type business card set |
| CN106056114B (en) * | 2016-05-24 | 2019-07-05 | 腾讯科技（深圳）有限公司 | Contents of visiting cards recognition methods and device |
-
2016
- 2016-05-24 CN CN201610347295.9A patent/CN106056114B/en active Active
-
2017
- 2017-05-17 WO PCT/CN2017/084625 patent/WO2017202232A1/en active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1632821A (en) * | 2004-12-30 | 2005-06-29 | 北京中星微电子有限公司 | Automatic searching and determining method for key words information in name card identification |
| CN101520851A (en) * | 2008-02-29 | 2009-09-02 | 富士通株式会社 | Character information identification device and method |
| CN103093224A (en) * | 2011-11-08 | 2013-05-08 | 佳能株式会社 | Method and device for determining average character width and method and equipment of character segmentation |
| CN102750552A (en) * | 2012-06-18 | 2012-10-24 | 北京捷通华声语音技术有限公司 | Handwriting recognition method and system as well as handwriting recognition terminal |
| CN103679117A (en) * | 2012-09-07 | 2014-03-26 | 北京蒙恬科技有限公司 | Business card identification method and device |
| CN104966097A (en) * | 2015-06-12 | 2015-10-07 | 成都数联铭品科技有限公司 | Complex character recognition method based on deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106056114A (en) | 2016-10-26 |
| WO2017202232A1 (en) | 2017-11-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106056114B (en) | Contents of visiting cards recognition methods and device | |
| CN110163198B (en) | Table identification reconstruction method and device and storage medium | |
| US10867171B1 (en) | Systems and methods for machine learning based content extraction from document images | |
| Yanikoglu et al. | Pink Panther: a complete environment for ground-truthing and benchmarking document page segmentation | |
| Lee et al. | Object detection with sliding window in images including multiple similar objects | |
| US8391615B2 (en) | Image recognition algorithm, method of identifying a target image using same, and method of selecting data for transmission to a portable electronic device | |
| US9189700B2 (en) | Device and method for analyzing the correlation between an image and another image or between an image and a video | |
| Laine et al. | A standalone OCR system for mobile cameraphones | |
| Lee et al. | Photographic composition classification and dominant geometric element detection for outdoor scenes | |
| CN107832756B (en) | Express bill information extraction method and device, storage medium and electronic equipment | |
| CN105630915A (en) | Method and device for classifying and storing pictures in mobile terminals | |
| Vanetti et al. | Gas meter reading from real world images using a multi-net system | |
| EP1631933A1 (en) | Human figure contour outlining in images | |
| RU2697649C1 (en) | Methods and systems of document segmentation | |
| CN109389115A (en) | Text recognition method, device, storage medium and computer equipment | |
| EP1300779A2 (en) | Form recognition system, form recognition method, program and storage medium | |
| WO2016086877A1 (en) | Text detection method and device | |
| CN106575280A (en) | System and methods for analysis of user-associated images to generate non-user generated labels and utilization of the generated labels | |
| CN109190615B (en) | Shape-near word recognition determination method, device, computer device and storage medium | |
| CN110119460A (en) | Image search method, device and electronic equipment | |
| CN106919326A (en) | A kind of image searching method and device | |
| CN110781195B (en) | System, method and device for updating point of interest information | |
| Ngoc et al. | Document detection in videos captured by smartphones using a saliency-based method | |
| CN110245570A (en) | Scan text segmentation method, device, computer equipment and storage medium | |
| US9378428B2 (en) | Incomplete patterns |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | 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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210922 Address after: 518057 Tencent Building, No. 1 High-tech Zone, Nanshan District, Shenzhen City, Guangdong Province, 35 floors Patentee after: TENCENT TECHNOLOGY (SHENZHEN) Co.,Ltd. Patentee after: TENCENT CLOUD COMPUTING (BEIJING) Co.,Ltd. Address before: 2, 518000, East 403 room, SEG science and Technology Park, Zhenxing Road, Shenzhen, Guangdong, Futian District Patentee before: TENCENT TECHNOLOGY (SHENZHEN) Co.,Ltd. |
|
| TR01 | Transfer of patent right |