CN108681735A - Optical character recognition method based on convolutional neural networks deep learning model - Google Patents
Optical character recognition method based on convolutional neural networks deep learning model Download PDFInfo
- Publication number
- CN108681735A CN108681735A CN201810270374.3A CN201810270374A CN108681735A CN 108681735 A CN108681735 A CN 108681735A CN 201810270374 A CN201810270374 A CN 201810270374A CN 108681735 A CN108681735 A CN 108681735A
- Authority
- CN
- China
- Prior art keywords
- model
- deep learning
- optical character
- neural networks
- convolutional neural
- 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
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/285—Selection of pattern recognition techniques, e.g. of classifiers in a multi-classifier system
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Abstract
The present invention discloses a kind of optical character recognition method based on convolutional neural networks deep learning model.This approach includes the following steps：The Chinese characters in common use and 10 Arabic numerals of collection different fonts and 26 English alphabet data sets are simultaneously converted into picture format；Slight distortion and rotation are carried out to enhance the robustness of model to picture, generate model training database；Establish the deep learning model of optical character identification；Training set image input model is continued to optimize into object function using convolutional neural networks model by the method for supervised learning, learns a multi-categorizer；For new test sample, feature extraction is carried out to it based on model obtained in the previous step and application model grader obtains final classification result.The present invention proposes new model and method to application of the deep learning based on convolutional neural networks in optical character identification, this method can be applied in general pattern classification task, especially text identification problem, the optical character identification model proposed by the present invention based on deep learning can significantly improve the recognition correct rate of character recognition.
Description
Technical field
The present invention relates to computer vision, pattern-recognition, the technical fields such as natural scene feature recognition, especially a kind of bases
In the optical character recognition method of convolutional neural networks deep learning model.
Background technology
Optical character identification is because it in real-life practicability has obtained the extensive concern of domestic and foreign scholars, base at present
It is concentrated mainly on scanned document character recognition in the application of optical character identification.Optical character identification streetscape identifier identify,
The foreground of being widely applied also is used in bank's ID card information identification, classroom blackboard-writing identification etc..Optical character identification has height
The advantages of effect property and convenience.There is a large amount of research effort just constantly promoting the development of field of optical character recognition at present.
A usual character recognition system is acquired by character, Character segmentation, feature extraction, several step structures such as characteristic matching
At.Wherein feature extraction has most important influence for the accuracy of character recognition.When the feature using most identification
When matching is compared to character, better discrimination can be usually obtained, it is on the contrary then will be greatly reduced character recognition system
Accuracy.And the research of character recognition is also concentrated mainly in the method for character feature extraction, it is based on convolutional neural networks
Deep learning method in detection feature automatically and extract characteristic aspect and have big advantage.
In recent years, the deep learning model based on convolutional neural networks is prominent in numerous computer vision problems because of it
Go out performance and obtains great concern.Its basic thought is to carry an original image automatically behind multilayer convolution sum pond
Take wherein most representational feature.Deep learning is all obtained in character recognition, image classification, natural language processing etc. in fields
Obtained howling success.And with the development of technology, how to learn to suitable for particular problem (such as be used for image classification, character
Identification) model become scholars' focus of attention.
Using the method for deep learning, a weight matrix with identification can be obtained by study and is biased towards
Amount.Weight vector and biasing constitute a grader, and classification knot will be can be obtained after character input grader to be tested
Fruit.Research under this theoretical frame is mainly concentrated in so that the model learnt has differentiation performance more outstanding.
However, in character recognition problem under practical application scene, it is not usually to mark that we, which can be obtained character picture,
Accurate character picture.Due to intensity of illumination, the factors such as placement position, character picture usually has a degree of rotation or torsion
It is bent.If the character picture of standard is directly used in above-mentioned model, is had in the model acquired and greatly represent judgement index
Weaker requires character picture very stringent information, then the recognition correct rate of model can substantially reduce.And if it is intended to obtaining
Obtain good recognition effect, it usually needs the additional capacity for increasing character training set is to expand its coverage area.
For deep learning model have the characteristics that good ability in feature extraction this, it is proposed that existing optics word
Symbol identification model is improved, and learns a grader under deep learning frame to complete the identification to character.In this way in reality
It, can be in a unification from the identification of the input character picture of non-standard (including but not limited to) to the end under the application environment of border
Frame in be resolved.
Invention content
(1) technical problems to be solved
The problem of for input picture in character recognition problem under actual environment may be non-standard image, the present invention propose
Character feature extraction and character recognition are placed on by a kind of optical character recognition method based on neural network deep learning model
It is resolved under one unified frame so that it is correct that the interaction of above-mentioned two step improves final character recognition jointly
Rate.
(2) technical solution
A kind of technical solution of optical character recognition method based on neural network deep learning model proposed by the present invention
It is as follows：
Step S1 collects the Chinese character of common different fonts, 10 Arabic numerals and 26 English alphabets and generates figure
The data set of piece format.
Step S2, training set and test set sample to acquisition suitably carry out slight rotation and distortion.
Step S3, each layer weight matrix parameter W and biasing b of the grader of Optimization Learning training set, passes through stochastic gradient
The optimal way of descent method (SGD) minimizes object function, study optimum classifier parameter W and b.
Step S4 carries out a propagated forward, calculates the probability value of its affiliated each classification, obtains the classification of test character
As a result.
Beneficial effects of the present invention：The present invention is directed to the character recognition problem under actual application environment, can directly input
Non-standard character image carries out character recognition.It is placed on a unified model frame by expressing character feature, with character recognition
It is solved under frame, it is hereby achieved that higher discrimination, enhances the robustness of algorithm.
Description of the drawings
Fig. 1 is the system flow chart of the optical character recognition method based on neural network deep learning model.
Specific implementation mode
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with specific example, and with reference to detailed
Thin attached drawing, the present invention is described in more detail.But described embodiment is intended merely to facilitate the understanding of the present invention, and right
It does not play any restriction effect.
Fig. 1 is flow chart of the method for the present invention, as shown in Figure 1, proposed by the present invention a kind of based on neural network depth
The optical character recognition method for practising model includes following steps：
Step S1 collects the Chinese character of common different fonts, 26 English alphabets of 10 Arabic numerals and English alphabet
And generate the data set of picture format.
Step S2, training set and test set sample to acquisition suitably carry out slight rotation and distortion.
Step S3, each layer weight matrix parameter W of the grader of Optimization Learning training set, passes through stochastic gradient descent method
(SGD) optimal way minimizes object function, study optimum classifier parameter W and b.
S31 initializes weights square for multiple convolution kernels of each convolutional layer in training set by Gaussian Profile
Battle array.Next, entering alternately error propagated forward and gradient back-propagation process, each of which volume is provided simultaneously by SGD algorithms
The weights of product core.S32 and S33 is recycled until restraining or reaching iterations requirement.
This is the object function of a typical classification problem, and the optimization for completing this object function can be in the hope of one group
Sorting parameter W and b.
S32, the value of propagated forward counting loss function：
S33, the Grad of backpropagation counting loss function pair parameters.
Wherein, f is hidden layer.
Step S4 carries out a propagated forward, calculates the probability value of its affiliated each classification.
Wherein, s=g (xi；W, b).
Case study on implementation：
For the specific implementation mode and verification effectiveness of the invention that the present invention will be described in detail, we propose the present invention
Method be applied to the database that forms of picture generated by Chinese characters in common use, 10 Arabic numerals and 26 letters.The data
Library is included in the image that rotation in various degree and distortion obtain.In our embodiment, we extract every in image first
A character.Using the single character after extraction as the input feature vector of training and test.
According to the step S3 in the technical detail introduced before, we first carry out all training set data input models
Training, wherein training parameter W are set as Gaussian Profile, mean value 0, standard deviation 0.01.Next according to step S31, S32 and
S33 completes the training to model.Grader is inputted to obtain final classification results by step S4 to new test image.
Particular embodiments described above has carried out further in detail the purpose of the present invention, technical solution and advantageous effect
It describes in detail bright, it should be understood that the above is only a specific embodiment of the present invention, is not intended to restrict the invention, it is all
Within the spirit and principles in the present invention, any modification, equivalent substitution, improvement and etc. done should be included in the guarantor of the present invention
Within the scope of shield.
Claims (6)
1. a kind of optical character recognition method based on convolutional neural networks deep learning model, which is characterized in that this method
Specific steps include：
Step S1 collects the Chinese character of common different fonts, 10 Arabic numerals and 26 English alphabets and generates picture lattice
The data set of formula.
Step S2, training set and test set sample to acquisition suitably carry out slight rotation and distortion processing.
Step S3, each layer weight matrix parameter W and biasing b of the grader of Optimization Learning training set, passes through stochastic gradient descent
The optimal way of method (SGD) minimizes object function, study optimum classifier parameter W and b.
2. the optical character recognition method according to claim 1 based on convolutional neural networks deep learning model, special
Sign is, in the step S1, collects the Chinese characters in common use and 10 Arabic numerals and 26 that all identity cards are related to
English alphabet.
3. the optical character recognition method according to claim 1 based on convolutional neural networks deep learning model, special
Sign is, in step s 2, to training set and test set sample differ mild distortion and the rotation of degree, after processing
Image as input feature vector.
4. the optical character recognition method according to claim 1 based on convolutional neural networks deep learning model, special
Sign is that in step s3, the optimization of deep learning model needs to complete by stochastic gradient descent method iteration optimization strategy,
Specific process is summarized as follows：
S31 initializes weight matrix for multiple convolution kernels of each convolutional layer in training set by Gaussian Profile.It connects
Get off, into alternately error propagated forward and gradient back-propagation process, each of which convolution kernel is provided by SGD algorithms simultaneously
Weights.S32 and S33 is recycled until restraining or reaching iterations requirement.
S32, the value of propagated forward counting loss function：
This is the object function of a typical classification problem, and the optimization for completing this object function can be in the hope of one group of classification
Parameter W and b.
S33, the Grad of backpropagation counting loss function pair parameters.
Wherein, f is hidden layer.
5. the optical character recognition method according to claim 1 based on convolutional neural networks deep learning model, special
Sign is, in step s3, after model training, for a new test sample ytest, depth is acquired currently
It practises in model and predicts its value.Its concrete operation step is as follows：
S4 carries out a propagated forward, calculates the probability value of its affiliated each classification.
Wherein, si=g (xi；W, b), i=1,2 ... m.
6. the optical character recognition method according to claim 5 based on convolutional neural networks deep learning model, special
Sign is, in steps of 5, after the probability value for calculating all categories, last classification results is determined according to the size of probability value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810270374.3A CN108681735A (en) | 2018-03-28 | 2018-03-28 | Optical character recognition method based on convolutional neural networks deep learning model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810270374.3A CN108681735A (en) | 2018-03-28 | 2018-03-28 | Optical character recognition method based on convolutional neural networks deep learning model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108681735A true CN108681735A (en) | 2018-10-19 |
Family
ID=63800544
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810270374.3A Pending CN108681735A (en) | 2018-03-28 | 2018-03-28 | Optical character recognition method based on convolutional neural networks deep learning model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108681735A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109598270A (en) * | 2018-12-04 | 2019-04-09 | 龙马智芯（珠海横琴）科技有限公司 | Distort recognition methods and the device, storage medium and processor of text |
| CN109858305A (en) * | 2019-01-17 | 2019-06-07 | 柳州康云互联科技有限公司 | A kind of two dimensional code positioning identification system and method based on deep learning |
| CN110059705A (en) * | 2019-04-22 | 2019-07-26 | 厦门商集网络科技有限责任公司 | A kind of OCR recognition result decision method and equipment based on modeling |
| CN110956133A (en) * | 2019-11-29 | 2020-04-03 | 上海眼控科技股份有限公司 | Training method of single character text normalization model, text recognition method and device |
| CN111797908A (en) * | 2020-06-18 | 2020-10-20 | 浪潮金融信息技术有限公司 | Training set generation method of deep learning model for print character recognition |
| CN112580657A (en) * | 2020-12-23 | 2021-03-30 | 陕西天诚软件有限公司 | Self-learning character recognition method |
| CN113191251A (en) * | 2021-04-28 | 2021-07-30 | 北京有竹居网络技术有限公司 | Method and device for detecting stroke order, electronic equipment and storage medium |
| US11295155B2 (en) | 2020-04-08 | 2022-04-05 | Konica Minolta Business Solutions U.S.A., Inc. | Online training data generation for optical character recognition |
| CN117173716A (en) * | 2023-09-01 | 2023-12-05 | 湖南天桥嘉成智能科技有限公司 | Deep learning-based high-temperature slab ID character recognition method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0784828A2 (en) * | 1994-10-05 | 1997-07-23 | United Parcel Service Of America, Inc. | Method of and apparatus for segmenting foreground and background information for optical character recognition of labels employing single layer recurrent neural network |
| 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 |
| CN105184312A (en) * | 2015-08-24 | 2015-12-23 | 中国科学院自动化研究所 | Character detection method and device based on deep learning |
| CN107273897A (en) * | 2017-07-04 | 2017-10-20 | 华中科技大学 | A kind of character recognition method based on deep learning |
-
2018
- 2018-03-28 CN CN201810270374.3A patent/CN108681735A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0784828A2 (en) * | 1994-10-05 | 1997-07-23 | United Parcel Service Of America, Inc. | Method of and apparatus for segmenting foreground and background information for optical character recognition of labels employing single layer recurrent neural network |
| 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 |
| CN105184312A (en) * | 2015-08-24 | 2015-12-23 | 中国科学院自动化研究所 | Character detection method and device based on deep learning |
| CN107273897A (en) * | 2017-07-04 | 2017-10-20 | 华中科技大学 | A kind of character recognition method based on deep learning |
Non-Patent Citations (1)
| Title |
|---|
| 张超群: ""基于深度学习的字符识别"", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109598270B (en) * | 2018-12-04 | 2020-05-05 | 龙马智芯（珠海横琴）科技有限公司 | Method and device for identifying distorted characters, storage medium and processor |
| CN109598270A (en) * | 2018-12-04 | 2019-04-09 | 龙马智芯（珠海横琴）科技有限公司 | Distort recognition methods and the device, storage medium and processor of text |
| CN109858305A (en) * | 2019-01-17 | 2019-06-07 | 柳州康云互联科技有限公司 | A kind of two dimensional code positioning identification system and method based on deep learning |
| CN110059705A (en) * | 2019-04-22 | 2019-07-26 | 厦门商集网络科技有限责任公司 | A kind of OCR recognition result decision method and equipment based on modeling |
| CN110956133A (en) * | 2019-11-29 | 2020-04-03 | 上海眼控科技股份有限公司 | Training method of single character text normalization model, text recognition method and device |
| US11295155B2 (en) | 2020-04-08 | 2022-04-05 | Konica Minolta Business Solutions U.S.A., Inc. | Online training data generation for optical character recognition |
| CN111797908B (en) * | 2020-06-18 | 2022-08-09 | 浪潮金融信息技术有限公司 | Training set generation method of deep learning model for print character recognition |
| CN111797908A (en) * | 2020-06-18 | 2020-10-20 | 浪潮金融信息技术有限公司 | Training set generation method of deep learning model for print character recognition |
| CN112580657A (en) * | 2020-12-23 | 2021-03-30 | 陕西天诚软件有限公司 | Self-learning character recognition method |
| CN112580657B (en) * | 2020-12-23 | 2022-11-01 | 陕西天诚软件有限公司 | Self-learning character recognition method |
| CN113191251A (en) * | 2021-04-28 | 2021-07-30 | 北京有竹居网络技术有限公司 | Method and device for detecting stroke order, electronic equipment and storage medium |
| CN117173716A (en) * | 2023-09-01 | 2023-12-05 | 湖南天桥嘉成智能科技有限公司 | Deep learning-based high-temperature slab ID character recognition method and system |
| CN117173716B (en) * | 2023-09-01 | 2024-03-26 | 湖南天桥嘉成智能科技有限公司 | Deep learning-based high-temperature slab ID character recognition method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108681735A (en) | Optical character recognition method based on convolutional neural networks deep learning model | |
| CN111325203B (en) | American license plate recognition method and system based on image correction | |
| CN107368831B (en) | English words and digit recognition method in a kind of natural scene image | |
| CN110490081B (en) | Remote sensing object interpretation method based on focusing weight matrix and variable-scale semantic segmentation neural network | |
| WO2017016240A1 (en) | Banknote serial number identification method | |
| CN106096602A (en) | A kind of Chinese licence plate recognition method based on convolutional neural networks | |
| CN109117885B (en) | Stamp identification method based on deep learning | |
| JP2022532177A (en) | Forged face recognition methods, devices, and non-temporary computer-readable storage media | |
| CN106228166B (en) | The recognition methods of character picture | |
| CN106372624B (en) | Face recognition method and system | |
| CN103544504B (en) | Scene character recognition method based on multi-scale map matching core | |
| CN104951781B (en) | Character recognition device and recognition function generation method | |
| CN109886161A (en) | A kind of road traffic index identification method based on possibility cluster and convolutional neural networks | |
| CN112307919B (en) | Improved YOLOv 3-based digital information area identification method in document image | |
| CN112069900A (en) | Bill character recognition method and system based on convolutional neural network | |
| CN108364037A (en) | Method, system and the equipment of Handwritten Chinese Character Recognition | |
| Hossain et al. | Recognition and solution for handwritten equation using convolutional neural network | |
| He et al. | Aggregating local context for accurate scene text detection | |
| Kobchaisawat et al. | Thai text localization in natural scene images using convolutional neural network | |
| Harizi et al. | Convolutional neural network with joint stepwise character/word modeling based system for scene text recognition | |
| Liu et al. | Scene text recognition with high performance CNN classifier and efficient word inference | |
| Yildirim et al. | Text recognition in natural images using multiclass hough forests | |
| Wicht et al. | Camera-based sudoku recognition with deep belief network | |
| CN110766001B (en) | Bank card number positioning and end-to-end identification method based on CNN and RNN | |
| Zuo et al. | An intelligent knowledge extraction framework for recognizing identification information from real-world ID card images |
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: 20181019 |
|
| RJ01 | Rejection of invention patent application after publication |