Show simple item record

dc.contributor.authorWang, Y.
dc.contributor.authorRibera, J.
dc.contributor.authorLiu, C.
dc.contributor.authorYarlagadda, Sri Kalyan
dc.contributor.authorZhu, Maggie
dc.identifier.citationWang, Y. and Ribera, J. and Liu, C. and Yarlagadda, S.K. and Zhu, M. 2017. Pill Recognition Using Minimal Labeled Data, 2017 IEEE Third International Conference on Multimedia Big Data, pp. 346-353.

© 2017 IEEE. Inappropriate medication use such as wrong drug or wrong dose intake can be harmful to patients. In this work we present a method to automatically identify a pill from a single image using Convolutional Neural Network (CNN). We first localize the pill in the image by detecting the region with the highest concentration of edges. To overcome the challenge of minimal labeled training data and domain shift from the training images taken under the controlled lab environment to the consumer images taken under natural living conditions, several data augmentation techniques are applied on the Region of Interest to generate synthetic pill images for training the CNN. We adopted GoogLeNet Inception Network as our main classifier. Three GoogLeNet models with different specialties on color, shape and feature are trained on the augmented dataset. We evaluate our proposed method with a publicly available dataset provided by National Institute of Health that contains 1000 different pill classes.

dc.titlePill Recognition Using Minimal Labeled Data
dc.typeConference Paper
dcterms.source.titleProceedings - 2017 IEEE 3rd International Conference on Multimedia Big Data, BigMM 2017
dcterms.source.seriesProceedings - 2017 IEEE 3rd International Conference on Multimedia Big Data, BigMM 2017
dcterms.source.conference2017 IEEE Third International Conference on Multimedia Big Data
curtin.departmentSchool of Public Health
curtin.accessStatusFulltext not available

Files in this item


There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record