一种标签识别方法、装置、设备及存储介质
By acquiring label images from the surface of a laptop, determining the label category, and selecting regions with character differences, semantic segmentation and character recognition are performed. This solves the problem of identifying labels of the same category and achieves highly accurate label recognition and classification.
CN115731196BActive Publication Date: 2026-07-17LCFC HEFEI ELECTRONICS TECH
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- LCFC HEFEI ELECTRONICS TECH
- Filing Date
- 2022-11-23
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
Existing technologies struggle to accurately identify labels of the same type on the surface of laptops, especially those with similar backgrounds but different characters, making it difficult to detect mislabeling.
Method used
By acquiring the image of the label to be identified, determining the label category, selecting the character difference region, performing semantic segmentation and character recognition, and finally comparing it with the template string multiple times, the label recognition result is determined.
Benefits of technology
It improves the stability and accuracy of label recognition, and can accurately classify labels of the same category that are too similar, reducing the risk of mislabeling.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN115731196B_ABST
Abstract
本公开提供了一种标签识别方法、装置、设备及存储介质，所述方法包括：获取待识别标签图像；确定所述待识别标签图像的标签类别，基于所述标签类别对所述待识别标签图像进行截选，得到字符差异区域；对所述字符差异区域进行分割和识别，得到待识别字符串；将所述待识别字符串与模板字符串进行对比，获得所述字符比对结果；基于所述字符比对结果确定所述待识别标签对应的标签识别结果。本方法首先确定字符差异区域，针对字符差异区域进行分割和识别，提高了标签识别的稳定性，可以准确的识别出待识别标签中的待识别字符，进而实现对相似度过高的同类别标签进行精准分类。
Need to check novelty before this filing date? Find Prior Art