Logistics Information Traceability Mechanism of Fresh E-Commerce Based on Image Recognition Technology

Area of Science:

• Computer Science
• Artificial Intelligence
• Logistics and Supply Chain Management

Background:

• E-commerce logistics demand precise, real-time information for goods traceability and visibility.
• Existing tracking methods face challenges with accuracy during goods migration across various points.
• Computer vision and digital image processing offer potential for enhanced visual identification and tracking.

Purpose of the Study:

• To design an Incessant Visualized Tracking Scheme (IVTS) for identifying and tracking e-commerce logistics.
• To improve the accuracy and reduce errors in logistics tracking throughout migration points.
• To leverage computer vision for robust logistics recognition and data verification.

Main Methods:

• Developed an Incessant Visualized Tracking Scheme (IVTS) utilizing computer vision.
• Employed logistics recognition and labeled data detection for visual identification.
• Utilized deep neural networks to verify labeled logistics data based on dimensional features and regional-pixel similarity, identifying and suppressing variations due to displacement.

Main Results:

• The IVTS effectively identifies and tracks e-commerce logistics across different migration points.
• The deep neural network learning process accurately identifies dimensional variations and suppresses similarity variations.
• The scheme successfully reduces dimensional errors, improving visual accuracy and tracking maximization.

Conclusions:

• The proposed Incessant Visualized Tracking Scheme (IVTS) significantly enhances the accuracy and efficiency of e-commerce logistics tracking.
• Computer vision and deep learning integration provide a robust solution for real-time visual identification and verification of goods.
• The IVTS minimizes tracking errors by effectively handling dimensional variations and positional changes during logistics migration.