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

Single-template workflow optimization method

An optimization method and workflow technology, applied in the field of deep learning and image text recognition, can solve problems such as text recognition errors, improve usability, ensure extraction effect, and improve accuracy.

Pending Publication Date: 2021-06-22
SHANDONG LANGCHAO YUNTOU INFORMATION TECH CO LTD
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The extraction of text information from pictures is mainly based on Optical Character Recognition (OCR) technology. The optimized OCR technology can correctly recognize most of the text content, but there are still some recognition errors that resemble text.

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
  • Single-template workflow optimization method
  • Single-template workflow optimization method
  • Single-template workflow optimization method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] In order to enable those skilled in the art to better understand the solutions of the present invention, the present invention will be further described in detail below in conjunction with specific embodiments. Apparently, the described embodiments are only some of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts fall within the protection scope of the present invention.

[0032] A preferred embodiment is given below:

[0033] Such as figure 1 As shown, a single-template workflow optimization method in this embodiment has the following steps:

[0034] S1. Build an N-Gram knowledge base in the field of template images:

[0035] First of all, BiGram segmentation is performed on the collected template picture domain text set, the word collocation in the domain text set is analyzed and counted, the templa...

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 invention relates to the field of deep learning and image character recognition, and particularly provides a single-template workflow optimization method which comprises the following steps: S1, constructing an N-Gram knowledge base in the field of template pictures; S2, preprocessing the OCR error correction text into a sequence to be subjected to error correction; S3, recognizing suspected wrong characters; S4, constructing a correct candidate word list based on an error rule reasoning model; and S5, comprehensive weight generation is carried out by using a candidate word screening algorithm, weights are sorted, and the word with the highest weight is the correct word of the wrong word in the current text to be corrected. Compared with the prior art, the text availability of the image after OCR conversion in the single-template workflow is improved, and the method is applied to frame selection of a reference field, frame selection of a recognition area and an evaluation application stage, so that the precision of a single-template workflow character recognition model is improved, and the extraction effect of structured information is ensured.

Description

technical field [0001] The invention relates to the fields of deep learning and image character recognition, and specifically provides a single-template workflow optimization method. Background technique [0002] The single-template workflow can independently build a text recognition template, recognize the text in the template image, provide a high-precision text recognition model, and ensure the accuracy of structured information extraction. The availability of image OCR text recognition is the single-template workflow in the frame selection reference field , frame the identification area and evaluate the key indicators in the application stage, such as Figure 4 shown. [0003] The extraction of text information from pictures is mainly based on Optical Character Recognition (OCR) technology. The optimized OCR technology can correctly recognize most of the text content, but there are still some recognition errors that resemble text. [0004] The problem of text error corr...

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): G06K9/03G06K9/34G06K9/62G06N5/04G06F40/216G06F40/284G06F16/36
CPCG06F40/284G06F40/216G06F16/367G06N5/04G06V10/98G06V30/153G06V30/10G06F18/22
Inventor 玄洪升李明明潘心冰郭保荣冷静
Owner SHANDONG LANGCHAO YUNTOU INFORMATION TECH CO LTD