CN108090488A - A kind of artificial intelligence labour union Message Entry System based on big data OCR Internet of Things - Google Patents
A kind of artificial intelligence labour union Message Entry System based on big data OCR Internet of Things Download PDFInfo
- Publication number
- CN108090488A CN108090488A CN201711361209.0A CN201711361209A CN108090488A CN 108090488 A CN108090488 A CN 108090488A CN 201711361209 A CN201711361209 A CN 201711361209A CN 108090488 A CN108090488 A CN 108090488A
- Authority
- CN
- China
- Prior art keywords
- ocr
- image
- value
- gray
- things
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Character Input (AREA)
Abstract
The present invention relates to OCR scanning techniques field, especially a kind of artificial intelligence labour union Message Entry System based on big data OCR Internet of Things, wherein typing step is：Pass through mobile phone photograph identity card or the papery data of acquisition；It is uploaded to OCR integrated systems；The content of photo of the OCR integrated systems to taking pictures is identified；Information in photo is converted into text information；To text information acquisition, typing.Advantageous effect of the present invention：The combination of photographing function of mobile phone and OCR technique of the present invention, it will quickly solve the problems, such as that the member of a trade union gathers typing, system integration OCR technique, pass through OCR technique, realize that the content of the photo to taking pictures is identified, information in photo is converted into text information, so as to fulfill quick information gathering, typing.
Description
Technical field
The present invention relates to OCR scanning techniques field, especially a kind of artificial intelligence work based on big data OCR Internet of Things
It can Message Entry System.
Background technology
At present, the typing on member of a trade union's information still more relies on traditional artificial acquisition typing mode, so leads
Cause acquisition efficiency of inputting slower, typing error rate height, therefore, it is necessary to by a kind of new technology, can quickly realize the member of a trade union
The acquisition and typing of information；Acquisition on the member of a trade union at present, there are no correlation technique applications.
Therefore, for the above problem, it is necessary to propose a kind of artificial intelligence labour union information based on big data OCR Internet of Things
Input system.
The content of the invention
The present invention seeks to overcome deficiency of the prior art, a kind of people based on big data OCR Internet of Things is provided
Work intelligence labour union Message Entry System.
In order to solve the above-mentioned technical problem, the present invention is to be achieved through the following technical solutions：
A kind of artificial intelligence labour union Message Entry System based on big data OCR Internet of Things, wherein typing step are：Step
Rapid one：Pass through mobile phone photograph identity card or the papery data of acquisition；Step 2：It is uploaded to OCR integrated systems；Step 3：OCR
The content of photo of the integrated system to taking pictures is identified；Step 4：Information in photo is converted into text information；Step 5：
To text information acquisition, typing.
Preferably, wherein OCR integrated systems include generation image module, image processing module, Text region module, text
Word editor module and date reminding module.
Preferably, wherein generation image module is with the camera opened on mobile phone, by user to various certificates, letter
Breath form is taken pictures, and obtains picture to be treated or by existing picture in mobile phone, figure to be processed needed for acquisition
Piece.
Preferably, wherein Text region module is special by pictograph conversion, the cutting of the binaryzation of image, individual character, word
Sign extraction, matching identification and manual synchronizing, finally export recognition result.
Preferably, the wherein binaryzation of image is according to each coordinate value of pixel and pair of gray-scale value in gray level image
It should be related to, a width gray level image can be expressed as two-dimensional function f (x, y), wherein, x, y are pixel coordinate value；F (x, y) is the picture
Plain gray value；
It is assumed that the value range of the gray-scale value of pixel is 0~Mf in a width gray level image, it is desirable to be able to more prominent figure
Word segment as in, inhibits those and uninterested gray areas, and the word in usual image is all black, in gray scale
Gray value is smaller in image, here g by extend intensity value ranges (0, a) dark-coloured area and the light tone area of (b, Mf), compression
The scope in gray value (a, b) section makes the character area more prominent method using piecewise linear transform in image, number
Learn expression formula such as formula：
The appropriate broken line corner position i.e. value of (a, b, c, d) is set, the slope of segmented linear is controlled, to gray space 0
~a and b~Mf are extended, and the gray space of a~b is compressed, and after gray scale adjusts, set some threshold value, ash
Angle value is replaced more than the pixel of threshold value with 255, is expressed as the point of white；Pixel less than threshold value is replaced with 0,
Be expressed as black to get to binary map.
Preferably, wherein individual character cutting includes row cutting and character segmentation.
Preferably, the method for wherein character segmentation is：
(1) first Li=1 Σ f (i, j)=0 is calculated in the range of ja≤j≤ja+wm (L is often capable height)
Point, is set to jb, so as to cut out the single character image between ja~jb；
If there is no such points, (5) step is gone to.
(2) if ja-jb<δ (δ is by empirically determined), i.e., character minimum less than one is wide, then is noise jamming, disregards,
Turn (3).Otherwise turn (4).
(3) point of first Li=1 Σ f (i, j)=0 is calculated in the range of jb≤j≤ja+wm, jb is set to, so as to cut
Go out the single character image between ja~jb.If such point is not present,
Then go to (5) step；
(4) the above-mentioned image being cut into is matched with dictionary, if successful match, writes down jb, turned (6)；Otherwise turn
(3)；
(5) it is obtained in the range of ja+wm-d≤j≤ja+wm so that the point that Li=1 Σ f (i, j) are minimized, is denoted as
jb。
(6) be as vertical line from jb word line of demarcation (right margin), the width of jth word is ja~jb.
(7) since jb, Li=1 Σ f (i, j) are calculated, j ' a, and ja ' are set to as Li=1 Σ f (i, j) ≠ 0>Jb,
Then ja ' is the left margin of+1 word of jth, repeats above step.
Preferably, wherein row cutting is usually constructed with certain white space between the row and row of word, is utilized in text
This white space sets the i-th row in character image into every trade cutting, and the pixel value of jth row is f (i, j)；
Then then, the integral projection in the i-th row horizontal direction is Lj=1 Σ f (i, j) to f (i, j)=0 figure viewed from behind, 1 word,
Middle L is the length of row.
Advantageous effect of the present invention：The combination of photographing function of mobile phone and OCR technique of the present invention, will quickly solve labour union
Member gathers the problem of typing, and system integration OCR technique by OCR technique, realizes that the content of the photo to taking pictures carries out
It identifies, the information in photo is converted into text information, so as to fulfill quick information gathering, typing.
The technique effect of the design of the present invention, concrete structure and generation is described further below with reference to attached drawing, with
It is fully understood from the purpose of the present invention, feature and effect.
Description of the drawings
Fig. 1 is flow chart of the method for the present invention.
Specific embodiment
The embodiment of the present invention is described in detail below in conjunction with attached drawing, but the present invention can be limited by claim
Fixed and covering multitude of different ways is implemented.
As shown in Figure 1, a kind of artificial intelligence labour union Message Entry System based on big data OCR Internet of Things, wherein typing
Step is：Step 1：Pass through mobile phone photograph identity card or the papery data of acquisition；Step 2：It is uploaded to OCR integrated systems；Step
Rapid three：The content of photo of the OCR integrated systems to taking pictures is identified；Step 4：Information in photo is converted into word letter
Breath；Step 5：To text information acquisition, typing.
Wherein OCR integrated systems include generation image module, image processing module, Text region module, copy editor's mould
Block and date reminding module.
Wherein generate image module with open mobile phone on camera, by user to various certificates, information form into
Row is taken pictures, and obtains picture to be treated or by existing picture in mobile phone, picture to be processed needed for acquisition.
Wherein Text region module is cut by pictograph conversion, the binaryzation of image, individual character, character features extract,
Matching identification and manual synchronizing, finally export recognition result.
The wherein binaryzation of image according to each coordinate value of pixel and the correspondence of gray-scale value in gray level image,
One width gray level image can be expressed as two-dimensional function f (x, y), wherein, x, y are pixel coordinate value；F (x, y) is the pixel grey scale
Value；
It is assumed that the value range of the gray-scale value of pixel is 0~Mf in a width gray level image, it is desirable to be able to more prominent figure
Word segment as in, inhibits those and uninterested gray areas, and the word in usual image is all black, in gray scale
Gray value is smaller in image, here g by extend intensity value ranges (0, a) dark-coloured area and the light tone area of (b, Mf), compression
The scope in gray value (a, b) section makes the character area more prominent method using piecewise linear transform in image, number
Learn expression formula such as formula：
The appropriate broken line corner position i.e. value of (a, b, c, d) is set, the slope of segmented linear is controlled, to gray space 0
~a and b~Mf are extended, and the gray space of a~b is compressed, and after gray scale adjusts, set some threshold value, ash
Angle value is replaced more than the pixel of threshold value with 255, is expressed as the point of white；Pixel less than threshold value is replaced with 0,
Be expressed as black to get to binary map.
Wherein individual character cutting includes row cutting and character segmentation.
The method of wherein character segmentation is：
(1) first Li=1 Σ f (i, j)=0 is calculated in the range of ja≤j≤ja+wm (L is often capable height)
Point, is set to jb, so as to cut out the single character image between ja~jb；
If there is no such points, (5) step is gone to.
(2) if ja-jb<δ (δ is by empirically determined), i.e., character minimum less than one is wide, then is noise jamming, disregards,
Turn (3).Otherwise turn (4).
(3) point of first Li=1 Σ f (i, j)=0 is calculated in the range of jb≤j≤ja+wm, jb is set to, so as to cut
Go out the single character image between ja~jb.If such point is not present,
Then go to (5) step；
(4) the above-mentioned image being cut into is matched with dictionary, if successful match, writes down jb, turned (6)；Otherwise turn
(3)；
(5) it is obtained in the range of ja+wm-d≤j≤ja+wm so that the point that Li=1 Σ f (i, j) are minimized, is denoted as
jb。
(6) be as vertical line from jb word line of demarcation (right margin), the width of jth word is ja~jb.
(7) since jb, Li=1 Σ f (i, j) are calculated, j ' a, and ja ' are set to as Li=1 Σ f (i, j) ≠ 0>Jb,
Then ja ' is the left margin of+1 word of jth, repeats above step.
Wherein row cutting is usually constructed with certain white space between the row and row of word, this sky is utilized in text
White gap sets the i-th row in character image into every trade cutting, and the pixel value of jth row is f (i, j)；Then 1 text of f (i, j)=0 figure viewed from behind
Then, the integral projection in the i-th row horizontal direction is Lj=1 Σ f (i, j) to word, and wherein L is the length of row.
The combination of photographing function of mobile phone and OCR technique of the present invention will quickly solve the member of a trade union and gather asking for typing
Topic, system integration OCR technique, by OCR technique, realizes that the content of the photo to taking pictures is identified, the information in photo
Text information is converted into, so as to fulfill quick information gathering, typing.
OCR identifying systems are built in member of a trade union's information management system, by mobile terminal member of a trade union's information system
APP is taken pictures or upload information form is, it can be achieved that real-time conversion, acquisition and the typing of pictorial information.Based on mobile terminal and master
Machine shares uniform data information bank, realizes that real-time membership information is synchronous, the system brought because data are asynchronous application is avoided to ask
Topic.OCR identifying systems are built in existing membership information system, membership information system application in mobile terminal realizes that collection information turns
Change, data acquisition, data inputting and data change function in one automatically, compared with other collecting devices, reduce hardware
The dependence of side, and data acquisition, data inputting and data modification can be carried out in real time, data acquisition efficiency is greatly improved, is carried
Data inputting efficiency has been risen, has reduced the manpower and materials cost of acquisition typing.
The preferred embodiment of the present invention described in detail above.It should be appreciated that those of ordinary skill in the art without
Creative work is needed according to the present invention can to conceive and makes many modifications and variations.Therefore, all technologies in the art
Personnel can be obtained under this invention's idea by logical analysis, reasoning, or a limited experiment on the basis of existing technology
Technical solution, all should be in the protection domain being defined in the patent claims.
Claims (8)
1. a kind of artificial intelligence labour union Message Entry System based on big data OCR Internet of Things, it is characterised in that：Wherein typing walks
Suddenly it is：
Step 1：Pass through mobile phone photograph identity card or the papery data of acquisition；
Step 2：It is uploaded to OCR integrated systems；
Step 3：The content of photo of the OCR integrated systems to taking pictures is identified；
Step 4：Information in photo is converted into text information；
Step 5：To text information acquisition, typing.
2. a kind of artificial intelligence labour union Message Entry System based on big data OCR Internet of Things as described in claim 1, special
Sign is：Wherein OCR integrated systems include generation image module, image processing module, Text region module, copy editor's module
With date reminding module.
3. a kind of artificial intelligence labour union Message Entry System based on big data OCR Internet of Things as described in claim 1, special
Sign is：Image module is wherein generated with the camera opened on mobile phone, various certificates, information form are carried out by user
It takes pictures, obtains picture to be treated or by existing picture in mobile phone, picture to be processed needed for acquisition.
4. a kind of artificial intelligence labour union Message Entry System based on big data OCR Internet of Things as claimed in claim 2, special
Sign is：Wherein Text region module is by pictograph conversion, the cutting of the binaryzation of image, individual character, character features extraction, ratio
To identification and Intelligent calibration, finally recognition result is exported.
5. a kind of artificial intelligence labour union Message Entry System based on big data OCR Internet of Things as claimed in claim 4, special
Sign is：Wherein the binaryzation of image is according to the coordinate value of each pixel in gray level image and gray-scale value
Correspondence, a width gray level image can be expressed as two-dimensional function f (x, y), wherein, x, y are pixel coordinate value；F (x, y) is
The grey scale pixel value；
It is assumed that the value range of the gray-scale value of pixel is 0~Mf in a width gray level image, it is desirable to be able in more prominent image
Word segment, inhibit those and uninterested gray areas, the word in usual image is all black, in gray level image
Gray value is smaller, here g by extend intensity value ranges (0, a) dark-coloured area and the light tone area of (b, Mf), compression gray value (a,
B) scope in section makes the character area more prominent method using piecewise linear transform in image, and mathematic(al) representation is such as
Formula：
Set the appropriate broken line corner position i.e. value of (a, b, c, d), control the slope of segmented linear, to 0~a of gray space and
B~Mf is extended, and the gray space of a~b is compressed, and after gray scale adjusts, sets some threshold value, gray value is big
It is replaced in the pixel of threshold value with 255, is expressed as the point of white；Pixel less than threshold value is replaced with 0, is expressed as black
Color to get to binary map.
6. a kind of artificial intelligence labour union Message Entry System based on big data OCR Internet of Things as claimed in claim 4, special
Sign is：Wherein individual character cutting includes row cutting and character segmentation.
7. a kind of artificial intelligence labour union Message Entry System based on big data OCR Internet of Things as claimed in claim 4, special
Sign is：The method of wherein character segmentation is：
(1) point of first Li=1 Σ f (i, j)=0 (L is often capable height) is calculated in the range of ja≤j≤ja+wm, is set to
Jb, so as to cut out the single character image between ja~jb；
If there is no such points, (5) step is gone to；
(2) if ja-jb<δ (δ is by empirically determined), i.e., character minimum less than one is wide, then is noise jamming, disregards, and turns (3)；
Otherwise turn (4)；
(3) in the range of jb≤j≤ja+wm calculate first Li=1 Σ f (i, j)=0 point, be set to jb, so as to cut out ja~
Single character image between jb if there is no such points, goes to (5) step；
(4) the above-mentioned image being cut into is matched with dictionary, if successful match, writes down jb, turned (6)；Otherwise turn (3)；
(5) it is obtained in the range of ja+wm-d≤j≤ja+wm so that the point that Li=1 Σ f (i, j) are minimized, is denoted as jb；
(6) be as vertical line from jb word line of demarcation (right margin), the width of jth word is ja~jb；
(7) since jb, Li=1 Σ f (i, j) are calculated, j ' a, and ja ' are set to as Li=1 Σ f (i, j) ≠ 0>Jb, then ja '
For the left margin of+1 word of jth, above step is repeated.
8. a kind of artificial intelligence labour union Message Entry System based on big data OCR Internet of Things as claimed in claim 4, special
Sign is：Wherein row cutting is usually constructed with certain white space between the row and row of word, this blank is utilized in text
Gap sets the i-th row in character image into every trade cutting, and the pixel value of jth row is f (i, j)；
Then then, the integral projection in the i-th row horizontal direction is Lj=1 Σ f (i, j) to f (i, j)=0 figure viewed from behind, 1 word, and wherein L is
Capable length.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711361209.0A CN108090488A (en) | 2017-12-18 | 2017-12-18 | A kind of artificial intelligence labour union Message Entry System based on big data OCR Internet of Things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711361209.0A CN108090488A (en) | 2017-12-18 | 2017-12-18 | A kind of artificial intelligence labour union Message Entry System based on big data OCR Internet of Things |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108090488A true CN108090488A (en) | 2018-05-29 |
Family
ID=62176860
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711361209.0A Pending CN108090488A (en) | 2017-12-18 | 2017-12-18 | A kind of artificial intelligence labour union Message Entry System based on big data OCR Internet of Things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108090488A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109979547A (en) * | 2019-04-08 | 2019-07-05 | 皮敏 | A kind of novel clinical case data collection system and acquisition method |
| CN110191285A (en) * | 2019-06-12 | 2019-08-30 | 深圳前海微众银行股份有限公司 | A kind of method and device commenced business |
| CN111104853A (en) * | 2019-11-11 | 2020-05-05 | 中国建设银行股份有限公司 | Image information input method and device, electronic equipment and storage medium |
| CN112749700A (en) * | 2021-01-15 | 2021-05-04 | 杭州盈嘉网络科技有限公司 | Workshop information input method based on big data OCR Internet of things |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1734467A (en) * | 2004-12-24 | 2006-02-15 | 康佳集团股份有限公司 | Mobile phone capable of inputting text by taking pictures and inputting method thereof |
| CN1877598A (en) * | 2005-06-06 | 2006-12-13 | 英华达(上海)电子有限公司 | Method for gathering and recording business card information in mobile phone by using image recognition |
| CN101339618A (en) * | 2007-07-06 | 2009-01-07 | 上海思必得通讯技术有限公司 | Mobile phones name card recognition device |
| CN102222289A (en) * | 2011-08-02 | 2011-10-19 | 浙江大学 | Optical character recognition (OCR)-based mobile phone financial management method and system |
| CN102759987A (en) * | 2012-06-13 | 2012-10-31 | 胡锦云 | Information inputting method |
-
2017
- 2017-12-18 CN CN201711361209.0A patent/CN108090488A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1734467A (en) * | 2004-12-24 | 2006-02-15 | 康佳集团股份有限公司 | Mobile phone capable of inputting text by taking pictures and inputting method thereof |
| CN1877598A (en) * | 2005-06-06 | 2006-12-13 | 英华达(上海)电子有限公司 | Method for gathering and recording business card information in mobile phone by using image recognition |
| CN101339618A (en) * | 2007-07-06 | 2009-01-07 | 上海思必得通讯技术有限公司 | Mobile phones name card recognition device |
| CN102222289A (en) * | 2011-08-02 | 2011-10-19 | 浙江大学 | Optical character recognition (OCR)-based mobile phone financial management method and system |
| CN102759987A (en) * | 2012-06-13 | 2012-10-31 | 胡锦云 | Information inputting method |
Non-Patent Citations (1)
| Title |
|---|
| 孙刘杰主编: "《印刷图像处理》", 28 February 2013 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109979547A (en) * | 2019-04-08 | 2019-07-05 | 皮敏 | A kind of novel clinical case data collection system and acquisition method |
| CN110191285A (en) * | 2019-06-12 | 2019-08-30 | 深圳前海微众银行股份有限公司 | A kind of method and device commenced business |
| CN111104853A (en) * | 2019-11-11 | 2020-05-05 | 中国建设银行股份有限公司 | Image information input method and device, electronic equipment and storage medium |
| CN112749700A (en) * | 2021-01-15 | 2021-05-04 | 杭州盈嘉网络科技有限公司 | Workshop information input method based on big data OCR Internet of things |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108090488A (en) | A kind of artificial intelligence labour union Message Entry System based on big data OCR Internet of Things | |
| Raj et al. | Face recognition based smart attendance system | |
| Bussa et al. | Smart attendance system using OPENCV based on facial recognition | |
| CN111695392B (en) | Face recognition method and system based on cascade deep convolutional neural network | |
| CN105528601A (en) | Identity card image acquisition and recognition system as well as acquisition and recognition method based on contact type sensor | |
| CN110163111A (en) | Method, apparatus of calling out the numbers, electronic equipment and storage medium based on recognition of face | |
| CN108446699A (en) | Identity card pictorial information identifying system under a kind of complex scene | |
| CN109858480A (en) | Digital instrument identification method | |
| CN104143091B (en) | Based on the single sample face recognition method for improving mLBP | |
| CN110222572A (en) | Tracking, device, electronic equipment and storage medium | |
| Hezil et al. | Signature recognition using binary features and KNN | |
| CN111428710A (en) | File classification collaboration robot and image character recognition method based on same | |
| CN111967319A (en) | Infrared and visible light based in-vivo detection method, device, equipment and storage medium | |
| CN104361357A (en) | Photo set classification system and method based on picture content analysis | |
| Edward V | Support vector machine based automatic electric meter reading system | |
| Cai et al. | Perception preserving decolorization | |
| Nayak et al. | Automatic number plate recognition | |
| D RAJ et al. | British sign language recognition using HOG | |
| Ovodov | Optical Braille recognition using object detection CNN | |
| Subur et al. | Braille character recognition using find contour method | |
| Brahmankar et al. | Indian sign language recognition using canny edge detection | |
| CN114581922A (en) | Chinese handwritten signature recognition method and system based on deep learning | |
| CN114882582A (en) | Gait recognition model training method and system based on federal learning mode | |
| Ajao et al. | Yoruba handwriting word recognition quality evaluation of preprocessing attributes using information theory approach | |
| Aji et al. | Sign Language Translator Based on Raspberry Pi Camera Using The Haar Cascade Classifier Method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180529 |
|
| RJ01 | Rejection of invention patent application after publication |