一种基于中文字符图像识别的位置获取系统和方法

By combining segmentation algorithms and deep learning technology, the Chinese character image recognition system has solved the problem of traditional monitoring equipment recognizing Chinese characters, enabling accurate location positioning of employees in industrial parks and improving the effectiveness of park security management.

CN116343207BActive Publication Date: 2026-07-17YUNNAN KUNGANG ELECTRONICS INFORMATION TECH CO LTD

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
YUNNAN KUNGANG ELECTRONICS INFORMATION TECH CO LTD
Filing Date
2023-02-02
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

In industrial parks, traditional monitoring equipment struggles to recognize employees' Chinese character information, especially when employees are wearing masks, leading to difficulties in safety management. Existing technologies cannot effectively identify employee locations and thus fail to achieve the goal of park safety management.

Method used

A location acquisition system based on Chinese character image recognition is adopted. Combining cutting algorithms and deep learning technology, the system collects Chinese character information on employees' work clothes through image acquisition equipment, uses a deep learning network model for object detection and character recognition, and combines character spacing detection and edge computing modules to achieve accurate cutting and recognition of Chinese characters. The recognition results are then bound to the location information of the monitoring equipment.

Benefits of technology

It enables accurate location tracking of employees within industrial parks, improving the efficiency and accuracy of park safety management, solving the problem of difficult employee location tracking, and enhancing safety management capabilities.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116343207B_ABST
    Figure CN116343207B_ABST
Patent Text Reader

Abstract

本发明涉及一种基于中文字符图像识别的位置获取系统和方法,该方法是采集员工佩戴的卡牌上被识别的中文图像字符;提取采集的中文字符图像信息;使用深度学习网络模型进行对象检测;利用切割中文字符的位置坐标信息得出的中文字符间距及二值化下图像极值,判断文字边缘,做出切割和识别动作终止的决定;将识别结果与图像采集设备位置信息绑定并记录。本发明利用中文字符间距及图像字符切割算法,将偏旁部首的中文字准确有效的进行逐个切割,切割出的字符传输到识别模型并输出识别结果。
Need to check novelty before this filing date? Find Prior Art