塑料瓶分类识别方法、分选机、电子设备及可读存储介质
By acquiring near-infrared spectral images in multiple bands, bottleneck areas can be identified and located, solving the problem of low accuracy in plastic bottle identification in existing technologies and achieving efficient sorting of PET plastic bottles.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING HONEST TECHNOLOGY CO LTD
- Filing Date
- 2024-08-19
- Publication Date
- 2026-07-17
AI Technical Summary
Existing near-infrared plastic sorting systems are easily interfered with by factors such as labels, caps, and reflected light spots on the plastic surface when identifying PET plastic bottles, resulting in low accuracy of feature extraction and material identification, and low sorting efficiency.
By acquiring near-infrared spectral images in multiple different bands, the bottleneck region is identified and located. The stable characteristics of the bottleneck region are used to eliminate interference factors, and the category of plastic bottle is determined by combining gray-scale mean analysis.
It improves the accuracy of feature extraction and material identification in the plastic bottle recognition process, enhances sorting efficiency, adapts to plastic bottles of different sizes and shapes, and has high practicality and versatility.
Smart Images
Figure CN121589047B_ABST