Authors:
K. Sanjana, G. Pragati Amba, K. Shruthi, R. Angeline, Aishwarya Kamanaluri

Addresses:
Department of Computer Science and Engineering with Specialisation in Artificial Intelligence and Machine Learning, SRM Institute of Science and Technology, Ramapuram, Chennai, Tamil Nadu, India. Department of Business Analytics, University of Birmingham, Birmingham, England, United Kingdom.

Abstract:

The e-commerce platform has grown rapidly since COVID, with contactless delivery becoming prevalent.  Every day millions of parcels are shipped across the globe. Today, many Proof-of-Delivery (POD) systems result in damaged items, incorrect deliveries or no proof of where packages were delivered. Static images and OTP confirmation cannot verify parcel damage, location and drop-off positioning at the intended destination. Logi-Track’s smart courier verification software solves these problems. The system and method are well described in Logi-Track. However, its influence may increase through quantitative metrics such as latency, predicted accuracy and performance improvements. The device camera does Optical Character Recognition (OCR) to read and interpret the package label while the package label is mapped to the delivery agent's position. Distance verification compares the delivery coordinates with a geo-tag to verify that the photo was taken within a specified radius and declines deliveries outside of it. Failure of any condition results in non-acknowledgement of delivery. The technical stack includes: React Native or Flutter for cross-platform interoperability, EfficientNet-Lite for package damage detection, Google Maps API for location accuracy, and Tesseract for OCR. These elements develop reliable, efficient delivery records. AI-augmented validation takes the place of OTP and photo confirmation, building a scalable, efficient foundation for operational transparency and consumer satisfaction.

Keywords: Proof-of-Delivery; Optical Character Recognition (OCR); Haversine Formula and Efficientnet-Lite; Package Damage Detection; Geospatial Distance Validation; Google Maps.

Received on: 11/05/2025, Revised on: 28/07/2025, Accepted on: 27/08/2025, Published on: 29/06/2026

DOI: 10.69888/FTSCL.2026.000701

FMDB Transactions on Sustainable Computer Letters, 2026 Vol. 4 No. 2, Pages: 107-118

• Views : 37
• Downloads : 7

Download PDF