一种基于图像识别的包装箱外观检测系统
By using an image recognition-based packaging box appearance inspection system, which utilizes a dual-stream convolutional neural network and a semantic ambiguity index to dynamically adjust the detection strategy, the system solves the problems of false alarm rate and false negative rate of traditional detection technology under complex working conditions, and achieves high accuracy and efficient logistics sorting.
CN121811141BActive Publication Date: 2026-07-17ANHUI YONGSHENG PRINTING TECH CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ANHUI YONGSHENG PRINTING TECH CO LTD
- Filing Date
- 2025-12-30
- Publication Date
- 2026-07-17
Smart Images
Figure CN121811141B_ABST
Abstract
本发明涉及智能物流装备与工业机器视觉检测技术领域，具体为一种基于图像识别的包装箱外观检测系统，包括：视觉数据采集模块，生成待检测目标图像序列；特征解耦提取模块，构建纹理表征特征图与拓扑结构骨架图；语义模糊度量化模块，生成数值化的视觉‑物理语义模糊度指数；推断模式仲裁模块，生成自适应检测策略指令；结构完整性判定模块，生成包装箱适航性验证结果；物流分拣控制模块，生成针对包装箱的传输路径导向信号，用于驱动分拣执行机构动作；本发明有效解决了传统算法难以区分表面污渍、旧胶带与真实物理裂缝的难题，阻断了非结构性表面干扰，显著提升了在复杂工况下对包装箱实质损伤的识别准确度。
Need to check novelty before this filing date? Find Prior Art