Automatic Pill Identification from Pillbox Images

Abstract

There is a vital need for fast and accurate recognition of medicinal tablets and capsules. Efforts to date have centered on automatic segmentation, color and shape identification. Our system combines these with preprocessing before imprint recognition. Using the National Library of Medicine Pillbox database, regression analysis applied to automatic color and shape recognition allows for successful pill identification. Measured errors for the subtasks of segmentation and color recognition for this database are 1.9% and 2.2%, respectively. Imprint recognition with optical character recognition (OCR) is key to exact pill ID, but remains a challenging problem, therefore overall recognition accuracy is not yet known.

Meeting Name

8th International Conference on Computer Vision Theory and Applications (2013: Feb. 21-24, Barcelona, Spain)

Department(s)

Electrical and Computer Engineering

Second Department

Chemistry

Keywords and Phrases

Automatic Segmentations; Color Clustering; Color Space; National Library Of Medicines; Optical Character Recognition (OCR); Recognition Accuracy; Shape Identifications; Shape Recognition; Image Analysis; Image Segmentation; Regression Analysis; Color; Segmentation

International Standard Book Number (ISBN)

978-9898565471

Document Type

Article - Conference proceedings

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2013 SciTePress, All rights reserved.

Publication Date

01 Feb 2013

Link to Full Text

Share

 
COinS