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

A method and system for intelligent detection of form picture text

A technology of intelligent detection and text detection, applied in the field of artificial intelligence, can solve problems such as missed detection or false detection, and achieve the effect of improving detection accuracy

Active Publication Date: 2022-04-15
ZHEJIANG LAB
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This type of detection method is usually able to automatically detect the text position, but it may cause missed detection or false detection

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
  • A method and system for intelligent detection of form picture text
  • A method and system for intelligent detection of form picture text
  • A method and system for intelligent detection of form picture text

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] Specific embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings. It should be understood that the specific embodiments described here are only used to illustrate and explain the present invention, and are not intended to limit the present invention.

[0040] A method for intelligent detection of table picture text, specifically including a text automatic detection module, a position transformation matrix module and a position weighting module, such as figure 1 Shown:

[0041] 1. The text automatic detection module is used to detect all possible texts in the target table image, which is realized by the following sub-steps, such as figure 2 Shown:

[0042] (1.1) Obtain table image data. Table images usually contain multiple text objects, and here it is assumed that there are K objects. This method adopts the method of deep learning training for model training. A model requires a portion of labeled data fo...

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 discloses a method and a system for intelligently detecting texts in tables and pictures. The system includes an automatic text detection module, a position transformation matrix module and a position weighting module. The method includes: S1, detecting all possible texts in the target table image; S2, automatically generating a transformation matrix of relative positional relationship; S3, calculating the final detection result by position weighting. The present invention adopts the method of deep learning training for the table picture text, and combines the general automatic text detection method with the relative position between the table text, not only depends on the position of the text object itself, but also depends on the relative position relationship between the texts, Finally, it is expressed in the form of a position transformation matrix, and the specific position of each target is confirmed by weighting the target detection results, thereby improving the detection accuracy of the table image text.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a method and system for intelligent detection of form picture text. Background technique [0002] Text intelligent detection and recognition technology has been widely used in application scenarios such as license plate recognition. The premise of text recognition is to detect text, and the target usually exists in text data and image data. The present invention is mainly aimed at the intelligent detection of text in form picture data. The difference between image data and text data is that it contains a lot of background information, so the premise of using image text is to correctly detect the location of the text. At present, image text detection mainly includes methods such as character detection, word detection and line text detection. This type of detection method can usually detect the text position automatically, but it may cause missed detectio...

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): G06V30/413G06V30/14G06V30/19G06K9/62G06N3/08
CPCG06N3/08G06F18/214
Inventor 叶汇贤徐晓刚王军何鹏飞朱亚光曹卫强
Owner ZHEJIANG LAB