An automatic recognition method of handwritten test data based on CNN and RNN model

A test data, automatic recognition technology, applied in character and pattern recognition, biological neural network models, instruments, etc., can solve the problems of cumbersome and lengthy data processing process, inability to effectively distinguish numbers and digital handwritten consecutive decimal points, etc., to increase the diversity and enhance the effect of anti-interference

Inactive Publication Date: 2019-01-25
GUANGDONG POWER GRID CO LTD DONGGUAN POWER SUPPLY BUREAU +1
View PDF8 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a method for automatic recognition of handwritten test data based on C...

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • An automatic recognition method of handwritten test data based on CNN and RNN model
  • An automatic recognition method of handwritten test data based on CNN and RNN model
  • An automatic recognition method of handwritten test data based on CNN and RNN model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0054] As a preferred embodiment of the present invention, S2 specifically includes the following steps:

[0055] S21. Perform multi-angle rotation and storage of the picture data acquired in step S1;

[0056] S22, adding noise points to the data image processed in step S21, and saving it;

[0057] S23. Perform elastic distortion processing on the data image processed in step S22, and save it.

[0058] In step S21, the picture data acquired in step S1 is stored at 15°, 30° and 45° rotations, the noise points in step S22 are black spots like snowflakes, and the elastic distortion in step S23 is processed to imitate the random shaking of hand muscles The data image is distorted. After the above measures, the original data volume is expanded by 3 times. The diversity of data is increased, and the anti-interference ability of the model is also strengthened, that is, the stability.

[0059] As a preferred embodiment of the present invention, step S3 specifically includes the fol...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

An automatic recognition method of handwritten test data based on CNN and RNN model comprises the following steps: S1, extracting historical data related to handwritten test digital recognition; obtaining data pictures of various test forms through establishing data interface with test data reporting system; S2, expanding the data: expanding the data picture in step 1; 3, training the CNN + RNN model of handwritten test digit recognition; S4, recognizing handwritten test digits: recognizing the digits in the new handwritten test digit picture according to the CNN + RNN model of the handwrittentest digits obtained in step 3; S5, performing on-site verification: after the on-site personnel check, feeding back whether the test number identified by feedback is consistent with the input number. The invention recognizes the handwritten numerals on the test form through the picture processing and the model training, can directly recognize the data string, including the decimal point in the data string, and can realize the automatic recording of the field operation terminal account and the form.

Description

technical field [0001] The invention relates to the field of automatic recognition of handwritten test data, in particular to a method for automatic recognition of handwritten test data based on CNN and RNN models. Background technique [0002] The automatic recognition of handwritten numbers based on computer vision technology has a long history and was first used in the postal industry to automatically recognize the handwritten numbers of postal codes on envelopes and automatically sort mail. In this method, first segment into a single number, identify the category of a single number, and then concatenate the recognition results. This method of dividing into parts is the general method of optical character recognition in the decades before the emergence of deep learning. [0003] This method has the following problems: 1. Segmentation errors will affect recognition performance; 2. Word recognition fails to consider contextual information. In order to make up for these tw...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06K9/34G06K9/62G06N3/04
CPCG06V30/153G06N3/045G06F18/21
Inventor 廖肇毅薛峰张伟平李汉钊刘丽荣张熙李通张雅洁张广伟孔蓓蓓邓琨温启良赵国杰许德成张渊渊
Owner GUANGDONG POWER GRID CO LTD DONGGUAN POWER SUPPLY BUREAU
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap