MediScan AI: Medical Expiry Scanner

Medicines may lose effectiveness after their labelled expiry date, making accurate expiry-date checking an important part of safe medicine management. However, expiry information is often printed in small characters, on curved containers, or on reflective foil, which can make manual reading difficult. This paper presents MediScan AI, a mobile-first, image-based system that identifies expiry dates from photographs of medicine strips, bottles, and boxes. The proposed workflow combines image capture, image pre-processing, deep-learning-based optical character recognition (OCR), date extraction, expiry-status classification, and a medicine inventory with reminder notifications. Pre-processing operations include grayscale conversion, denoising, adaptive thresholding, and skew correction. OCR output is examined using expiry-related keywords and date-pattern rules to distinguish expiry information from manufacturing dates and other printed numbers. The extracted date is normalized and compared with the current date to classify a medicine as Safe, Expiring Soon, or Expired. In a prototype evaluation on a self-collected set of 300 medicine-package images captured under varied lighting and packaging conditions, the system reached an exact-match extraction accuracy of 91.7% with an average processing time of 2.3 seconds per image. These values come from a self-collected test set and have not been independently verified. MediScan AI is designed as a decision-support aid; it does not provide medical advice, verify medicine authenticity, or assess storage conditions.Keywords—Medicine expiry detection, optical character recognition, image processing, date extraction, medicine inventory, expiry alerts.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-19
DOI
https://doi.org/10.5281/zenodo.24362511
Primary Topic
Handwritten Text Recognition Techniques
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

MediScan AI: Medical Expiry Scanner

Poornima Pandit Andewadi
Zenodo (CERN European Organization for Nuclear Research)
Handwritten Text Recognition Techniques
preprint

MediScan AI: Medical Expiry Scanner

Poornima Pandit Andewadi
preprint en

Abstract

Medicines may lose effectiveness after their labelled expiry date, making accurate expiry-date checking an important part of safe medicine management. However, expiry information is often printed in small characters, on curved containers, or on reflective foil, which can make manual reading difficult. This paper presents MediScan AI, a mobile-first, image-based system that identifies expiry dates from photographs of medicine strips, bottles, and boxes. The proposed workflow combines image capture, image pre-processing, deep-learning-based optical character recognition (OCR), date extraction, expiry-status classification, and a medicine inventory with reminder notifications. Pre-processing operations include grayscale conversion, denoising, adaptive thresholding, and skew correction. OCR output is examined using expiry-related keywords and date-pattern rules to distinguish expiry information from manufacturing dates and other printed numbers. The extracted date is normalized and compared with the current date to classify a medicine as Safe, Expiring Soon, or Expired. In a prototype evaluation on a self-collected set of 300 medicine-package images captured under varied lighting and packaging conditions, the system reached an exact-match extraction accuracy of 91.7% with an average processing time of 2.3 seconds per image. These values come from a self-collected test set and have not been independently verified. MediScan AI is designed as a decision-support aid; it does not provide medical advice, verify medicine authenticity, or assess storage conditions.Keywords—Medicine expiry detection, optical character recognition, image processing, date extraction, medicine inventory, expiry alerts.

Zenodo (CERN European Organization for Nuclear Research)
Handwritten Text Recognition Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon