Unlock instant, AI-driven research and patent intelligence for your innovation.

Signature feature recognition method, system, device and storage medium based on mask pre-training model

A pre-training and model technology, applied in the direction of character and pattern recognition, character recognition, neural learning methods, etc., can solve the problems of single consideration of writing features, large amount of model calculation, poor transferability, etc., to achieve cost reduction, good effect, and reduce The effect of training time

Active Publication Date: 2022-07-01
CHONGQING AOXIONG INFORMATION TECH
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention proposes an online handwritten signature recognition based on mask pre-training in view of the shortcomings of the prior art, such as large amount of model calculation, poor mobility, single consideration of writing features, poor versatility and lack of pre-training technology in the electronic signature recognition method method and system

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
  • Signature feature recognition method, system, device and storage medium based on mask pre-training model
  • Signature feature recognition method, system, device and storage medium based on mask pre-training model
  • Signature feature recognition method, system, device and storage medium based on mask pre-training model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] The implementation of the present invention will be further described in detail below with reference to the accompanying drawings and specific examples.

[0019] like figure 1 Shown is a schematic diagram of the handwritten data signature system based on the mask pre-training model of the present invention. The system includes: a data acquisition part, a data pre-processing module, and a pre-training module. The data acquisition module extracts all feature information generated by writing on terminal devices that can realize handwriting input, including mobile phones, tablets, signature pads, etc., such as the abscissa X, ordinate Y, time feature T of the text on the terminal device during the signature writing process , pressure feature P, pen-lifting state S and other writing feature information, the features collected by the collection board exist as time-varying sequence information, and make full use of the continuous process of the signer's writing to convert the ...

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

The present invention claims to protect a handwritten data signature recognition method based on a mask pre-training model, which relates to the technical field of data recognition processing. Multiple feature data sequences of fixed length; masking and masking some feature values ​​in the feature data sequence; converting multiple feature data sequences with some feature values ​​masked into feature vectors of corresponding features, superimposing all feature vectors and performing layer normalization The feature sequence corresponding to the masked part is extracted, and the mean square error function is determined in combination with the pre-defined target value, the network weight of the prediction model is updated through the mean square error function, and the prediction model is constructed to identify the handwriting features. The invention can be widely used in electronic signature recognition.

Description

technical field [0001] The invention relates to a recognition technology for handwritten signature data, in particular to a handwritten online signature data recognition technology based on a pre-training model. Background technique [0002] Since the advent of the digital age, handwritten online signatures have been used as evidence of electronic data in government, business, and financial neighborhoods, enhancing the certifiability of electronic data. Online signature data has the characteristics of real-time authentication. As long as the user signs his name, the system can recognize it. However, different models need to be trained for different tasks, which increases the cost and reduces the production efficiency. This paper proposes a mask-based pre-training model that can perform transfer learning on similar tasks, reducing industrial costs and improving production efficiency. [0003] The mask pre-training model for handwritten signatures comes from the mask-based na...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06V10/774G06V10/82G06V30/10G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/214
Inventor 吴乐琴覃勋辉曾川刘科
Owner CHONGQING AOXIONG INFORMATION TECH