CN113159015A - Seal identification method based on transfer learning - Google Patents
Seal identification method based on transfer learning Download PDFInfo
- Publication number
- CN113159015A CN113159015A CN202110494953.8A CN202110494953A CN113159015A CN 113159015 A CN113159015 A CN 113159015A CN 202110494953 A CN202110494953 A CN 202110494953A CN 113159015 A CN113159015 A CN 113159015A
- Authority
- CN
- China
- Prior art keywords
- image
- seal
- training
- original
- stamp image
- 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
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000013526 transfer learning Methods 0.000 title claims abstract description 17
- 238000012549 training Methods 0.000 claims abstract description 45
- 238000000605 extraction Methods 0.000 claims abstract description 12
- 230000007797 corrosion Effects 0.000 claims abstract description 11
- 238000005260 corrosion Methods 0.000 claims abstract description 11
- 238000012795 verification Methods 0.000 claims abstract description 10
- 238000012360 testing method Methods 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 230000008569 process Effects 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 7
- 238000013527 convolutional neural network Methods 0.000 claims description 6
- 239000003086 colorant Substances 0.000 claims description 4
- 238000005530 etching Methods 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 238000011478 gradient descent method Methods 0.000 claims description 3
- 238000011176 pooling Methods 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 abstract description 3
- 230000000694 effects Effects 0.000 abstract description 3
- 238000010276 construction Methods 0.000 abstract 1
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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
- 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
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20061—Hough transform
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Multimedia (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Evolutionary Biology (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Medical Informatics (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a seal recognition method based on transfer learning, which comprises S1 seal image collection, S2 original seal image database construction, S3 training stage and S4 recognition stage, wherein in the step S2, the preprocessing comprises an RGB color model extraction method and a binarization expansion corrosion method. The invention belongs to the technical field of seal identification methods, and particularly provides a seal identification method based on transfer learning, which can improve the accuracy of original seal image identification by performing a color model extraction method and an expansion corrosion method on a seal image with a background color, and can effectively improve the effect of deep neural network training by dividing a training set, a verification set and a test set, improve the training efficiency and increase the identification accuracy.
Description
Technical Field
The invention belongs to the technical field of seal identification methods, and particularly relates to a seal identification method based on transfer learning.
Background
With the advent of the big data age, people can more easily obtain a large amount of data. In addition, as the field of machine learning continues to develop, the problem of how to make computers have the ability to work in reverse, how to make large amounts of data work better, becomes very practical and valuable. To solve these problems, transfer learning has been proposed and increasingly receives attention.
In the identification technology of transaction bills, the identification of the seal is a relatively critical ring. For the seal authenticity identification, a pattern comparison mode is usually adopted, for example, a seal pattern folding comparison mode or an electronic pattern analysis comparison mode is adopted.
The existing seal identification method used by banks is mostly manual operation, the seal on a check is compared with an original seal image left by a client through manual angle folding, and the original comparison method has the defects of multiple artificial factors, poor accuracy, large workload and the like. In addition, the traditional folding comparison of the seal patterns and the analysis and comparison of the existing electronic patterns have error rate in a certain ratio, if the comparison requirements of the patterns are strict, the true and false seals can not pass the verification, and if the comparison requirements are loose, the true and false seals can pass the verification, so that the seal identification method is inconvenient and is not beneficial to accurately identifying the seal.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a seal recognition method based on transfer learning, which can improve the accuracy of original seal image recognition by performing a color model extraction method and an expansion corrosion method on a seal image with a background color, and can effectively improve the effect of deep neural network training by dividing a training set, a verification set and a test set, improve the training efficiency and increase the recognition accuracy.
The technical scheme adopted by the invention is as follows: the invention relates to a seal identification method based on transfer learning, which comprises the following steps:
s1 stamp image collection: collecting a seal image of a client, and scanning the seal image into a computer;
s2, constructing an original stamp image database: judging whether the stamp image in the step S1 contains a background image except the original stamp, if so, preprocessing the stamp image, then constructing the preprocessed original stamp image into an original stamp image database, and if not, directly storing the stamp image into the original stamp image database, wherein the original stamp image database contains original stamp image data;
s3 training stage: acquiring a pre-training model based on a convolutional neural network, taking an original seal image database as the input of the pre-training model, training to construct a classifier based on the convolutional neural network, and updating the classifier by using the output of the pre-training model;
s4 identification phase: and (4) carrying out seal identification by using the classifier selected in the step (S3) so as to obtain an identification result.
Further, in step S1, the stamp image is photographed or scanned by a camera or a scanner, so as to obtain stamp image data.
Further, the preprocessing in step S2 includes an RGB color model extraction method and a binarization expansion etching method, where the RGB color model extraction method is used to process a red stamp image, and the binarization expansion etching method is used to process a blue stamp image.
Further, the specific step of step S3 includes:
(1) firstly, dividing an original seal image data set into a training set, a verification set and a test set, inputting pictures of the training set into a pre-training model, obtaining a plurality of characteristic graphs after each picture passes through each convolution layer and each pooling layer in the pre-training model, and obtaining a prediction result after the characteristic graphs pass through each full-connection layer;
(2) then, evaluating the difference between the prediction result and the true value by using a cross entropy function, repeating the steps for each picture in the training set, in the process, optimizing and updating one or more full link layer parameters of the model by using a gradient descent method each time, and inputting all training picture samples into the network to update the network once;
(3) after each network updating, calculating the accuracy by using the verification set, and selecting the model with the highest accuracy to obtain a classifier;
(4) and obtaining a plurality of classifiers through multiple steps, verifying the accuracy of each classifier by using the test set, and selecting the classifier with the highest accuracy.
Further, the RGB color model extraction method includes the steps of:
(1) extracting a seal image; if Red in the pixel values of the stamp image is more than 100, and the differences between the pixel values Red and Blue and the differences between Red and Green are both more than 45, the pixel point is considered as an effective stamp color, namely Red; if the sum of the three component values is larger than 540, the pixel point is considered as a normal background color; except for the two situations, the pixel points are background interference colors;
(2) and removing noise information on the stamp image by using Hough change and median filtering to obtain the original stamp image.
Further, the binarization expansion corrosion method comprises the following steps:
(1) after the seal image is subjected to binarization processing, calculating background identification discrete points in the seal image, acquiring an image frame of the background identification discrete points, and repeatedly expanding the image frame of the background identification discrete points to obtain an image with continuous edges;
(2) performing multiple corrosion on the image subjected to repeated expansion; and removing the background of the corroded image, and marking a target of a closed edge to obtain an original seal image.
The beneficial effects obtained by adopting the scheme are as follows: according to the seal recognition method based on transfer learning, the accuracy of original seal image recognition can be improved through a color model extraction method and an expansion corrosion method for the seal image with the background color, the effect of deep neural network training can be effectively improved, the training efficiency is improved, and the recognition accuracy is improved.
Drawings
Fig. 1 is a diagram of a process flow for organizing a seal identification method based on transfer learning according to the present invention.
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments; all other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention relates to a seal identification method based on transfer learning, which comprises the following steps:
s1 stamp image collection: collecting a seal image of a client, and scanning the seal image into a computer;
s2, constructing an original stamp image database: judging whether the stamp image in the step S1 contains a background image except the original stamp, if so, preprocessing the stamp image, then constructing the preprocessed original stamp image into an original stamp image database, and if not, directly storing the stamp image into the original stamp image database, wherein the original stamp image database contains original stamp image data;
s3 training stage: acquiring a pre-training model based on a convolutional neural network, taking an original seal image database as the input of the pre-training model, training to construct a classifier based on the convolutional neural network, and updating the classifier by using the output of the pre-training model;
s4 identification phase: and (4) carrying out seal identification by using the classifier selected in the step (S3) so as to obtain an identification result.
In step S1, the stamp image is photographed or scanned by a camera or a scanner to obtain stamp image data.
The preprocessing in the step S2 includes an RGB color model extraction method for processing a red stamp image and a binarization expansion etching method for processing a blue stamp image.
The specific steps of step S3 include:
(1) firstly, dividing an original seal image data set into a training set, a verification set and a test set, inputting pictures of the training set into a pre-training model, obtaining a plurality of characteristic graphs after each picture passes through each convolution layer and each pooling layer in the pre-training model, and obtaining a prediction result after the characteristic graphs pass through each full-connection layer;
(2) then, evaluating the difference between the prediction result and the true value by using a cross entropy function, repeating the steps for each picture in the training set, in the process, optimizing and updating one or more full link layer parameters of the model by using a gradient descent method each time, and inputting all training picture samples into the network to update the network once;
(3) after each network updating, calculating the accuracy by using the verification set, and selecting the model with the highest accuracy to obtain a classifier;
(4) and obtaining a plurality of classifiers through multiple steps, verifying the accuracy of each classifier by using the test set, and selecting the classifier with the highest accuracy.
The RGB color model extraction method comprises the following steps:
(1) extracting a seal image; if Red in the pixel values of the stamp image is more than 100, and the differences between the pixel values Red and Blue and the differences between Red and Green are both more than 45, the pixel point is considered as an effective stamp color, namely Red; if the sum of the three component values is larger than 540, the pixel point is considered as a normal background color; except for the two situations, the pixel points are background interference colors;
(2) and removing noise information on the stamp image by using Hough change and median filtering to obtain the original stamp image.
The binarization expansion corrosion method comprises the following steps:
(1) after the seal image is subjected to binarization processing, calculating background identification discrete points in the seal image, acquiring an image frame of the background identification discrete points, and repeatedly expanding the image frame of the background identification discrete points to obtain an image with continuous edges;
(2) performing multiple corrosion on the image subjected to repeated expansion; and removing the background of the corroded image, and marking a target of a closed edge to obtain an original seal image.
In the training stage, the training time can be greatly shortened, corresponding training can be completed within 250-300 s, the classifier is well represented in recognition, the accuracy rate reaches more than 85%, and the accuracy of original official seal recognition is improved by respectively using a color model extraction method and an expansion corrosion method through different image characteristics represented by official seals with different colors.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by the present specification, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (6)
1. A seal identification method based on transfer learning is characterized by comprising the following steps:
s1 stamp image collection: collecting a seal image of a client, and scanning the seal image into a computer;
s2, constructing an original stamp image database: judging whether the stamp image in the step S1 contains a background image except the original stamp, if so, preprocessing the stamp image, then constructing the preprocessed original stamp image into an original stamp image database, and if not, directly storing the stamp image into the original stamp image database, wherein the original stamp image database contains original stamp image data;
s3 training stage: acquiring a pre-training model based on a convolutional neural network, taking an original seal image database as the input of the pre-training model, training to construct a classifier based on the convolutional neural network, and updating the classifier by using the output of the pre-training model;
s4 identification phase: and (4) carrying out seal identification by using the classifier selected in the step (S3) so as to obtain an identification result.
2. The seal recognition method based on transfer learning according to claim 1, characterized in that: in the step S1, the stamp image is photographed or scanned by a camera or a scanner to obtain stamp image data.
3. The seal recognition method based on transfer learning according to claim 1, characterized in that: the preprocessing in the step S2 includes an RGB color model extraction method for processing a red stamp image and a binarization expansion etching method for processing a blue stamp image.
4. The method for identifying a seal based on transfer learning according to claim 1, wherein the specific step of step S3 includes:
(1) firstly, dividing an original seal image data set into a training set, a verification set and a test set, inputting pictures of the training set into a pre-training model, obtaining a plurality of characteristic graphs after each picture passes through each convolution layer and each pooling layer in the pre-training model, and obtaining a prediction result after the characteristic graphs pass through each full-connection layer;
(2) then, evaluating the difference between the prediction result and the true value by using a cross entropy function, repeating the steps for each picture in the training set, in the process, optimizing and updating one or more full link layer parameters of the model by using a gradient descent method each time, and inputting all training picture samples into the network to update the network once;
(3) after each network updating, calculating the accuracy by using the verification set, and selecting the model with the highest accuracy to obtain a classifier;
(4) and obtaining a plurality of classifiers through multiple steps, verifying the accuracy of each classifier by using the test set, and selecting the classifier with the highest accuracy.
5. The seal recognition method based on transfer learning of claim 3, wherein the RGB color model extraction method comprises the following steps:
(1) extracting a seal image; if Red in the pixel values of the stamp image is more than 100, and the differences between the pixel values Red and Blue and the differences between Red and Green are both more than 45, the pixel point is considered as an effective stamp color, namely Red; if the sum of the three component values is larger than 540, the pixel point is considered as a normal background color; except for the two situations, the pixel points are background interference colors;
(2) and removing noise information on the stamp image by using Hough change and median filtering to obtain the original stamp image.
6. The seal recognition method based on transfer learning according to claim 3, characterized in that: the binarization expansion corrosion method comprises the following steps:
(1) after the seal image is subjected to binarization processing, calculating background identification discrete points in the seal image, acquiring an image frame of the background identification discrete points, and repeatedly expanding the image frame of the background identification discrete points to obtain an image with continuous edges;
(2) performing multiple corrosion on the image subjected to repeated expansion; and removing the background of the corroded image, and marking a target of a closed edge to obtain an original seal image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110494953.8A CN113159015A (en) | 2021-05-07 | 2021-05-07 | Seal identification method based on transfer learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110494953.8A CN113159015A (en) | 2021-05-07 | 2021-05-07 | Seal identification method based on transfer learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113159015A true CN113159015A (en) | 2021-07-23 |
Family
ID=76873896
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110494953.8A Pending CN113159015A (en) | 2021-05-07 | 2021-05-07 | Seal identification method based on transfer learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113159015A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113954360A (en) * | 2021-10-25 | 2022-01-21 | 华南理工大学 | 3D printing product anti-counterfeiting method based on embedded identification code multi-process application |
-
2021
- 2021-05-07 CN CN202110494953.8A patent/CN113159015A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113954360A (en) * | 2021-10-25 | 2022-01-21 | 华南理工大学 | 3D printing product anti-counterfeiting method based on embedded identification code multi-process application |
| WO2023071159A1 (en) * | 2021-10-25 | 2023-05-04 | 华南理工大学 | 3d printed product counterfeiting prevention method based on embedded identification code and applicable to multiple processes |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111539316B (en) | High-resolution remote sensing image change detection method based on dual-attention twin network | |
| CN110427990B (en) | Artistic image classification method based on convolutional neural network | |
| CN111428781A (en) | Remote sensing image ground object classification method and system | |
| CN110349136A (en) | A kind of tampered image detection method based on deep learning | |
| CN109615604B (en) | Part appearance flaw detection method based on image reconstruction convolutional neural network | |
| CN109145766A (en) | Model training method, device, recognition methods, electronic equipment and storage medium | |
| CN106203454B (en) | The method and device of certificate format analysis | |
| CN111680690B (en) | Character recognition method and device | |
| CN106548169A (en) | Fuzzy literal Enhancement Method and device based on deep neural network | |
| CN109978871B (en) | Fiber bundle screening method integrating probability type and determination type fiber bundle tracking | |
| CN108334955A (en) | Copy of ID Card detection method based on Faster-RCNN | |
| CN110738216A (en) | Medicine identification method based on improved SURF algorithm | |
| CN111209858A (en) | Real-time license plate detection method based on deep convolutional neural network | |
| Zhang et al. | Improved Fully Convolutional Network for Digital Image Region Forgery Detection. | |
| CN110457996B (en) | Video moving object tampering evidence obtaining method based on VGG-11 convolutional neural network | |
| CN109815923B (en) | Needle mushroom head sorting and identifying method based on LBP (local binary pattern) features and deep learning | |
| CN108710893A (en) | A kind of digital image cameras source model sorting technique of feature based fusion | |
| KR20180092455A (en) | Card number recognition method using deep learnig | |
| CN106709916A (en) | Image quality assessment method and device | |
| CN111461101A (en) | Method, device and equipment for identifying work clothes mark and storage medium | |
| CN110991434B (en) | Self-service terminal certificate identification method and device | |
| CN112651333A (en) | Silence living body detection method and device, terminal equipment and storage medium | |
| CN115497010A (en) | Deep learning-based geographic information identification method and system | |
| CN111046838A (en) | Method and device for identifying wetland remote sensing information | |
| CN113159015A (en) | Seal identification method based on transfer learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |