一种文字识别方法、装置、设备及可读存储介质

CN117671691BActive Publication Date: 2026-07-17GLODON CO LTD

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
GLODON CO LTD
Filing Date
2023-12-08
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

In existing technologies, text information in vector drawing formats (such as PDF) cannot be directly obtained, requiring users to fill it in manually, which is inefficient and cannot automatically recognize and utilize the text information in the drawings.

Method used

By acquiring the document to be recognized, determining the text style features of the sample text, identifying and grouping the text lines, and using existing text recognition algorithms to extract the text content from the vector paper.

Benefits of technology

It enables rapid and accurate recognition of text information in vector graphics, improving recognition efficiency and reducing the workload of manual input.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117671691B_ABST
    Figure CN117671691B_ABST
Patent Text Reader

Abstract

本发明公开了一种文字识别方法、装置、设备及可读存储介质,该方法包括:获取待识别文件;其中,包含在所述待识别文件中的文字由线条构成;从所述待识别文件中确定出样例文字,并计算出所述样例文字的文字样式特征信息;根据所述文字样式特征信息,从所述待识别文件的待识别区域中识别出用于构成文字的文字线条;根据所述文字样式特征信息,对得到的所有文字线条进行分组,以得到多个文字线条组;从所述文字线条组中识别出文字识别结果;本发明能够对目标文件中存在的由线条构成的文字进行快速、准确的位置定位及内容识别。
Need to check novelty before this filing date? Find Prior Art