en
Conference presentation
Open access
English

PharmaPack: mobile fine-grained recognition of pharma packages

Presented at25th European Signal Processing Conference (EUSIPCO), Kos (Greece), 28 August - 2 September, p. 5
Publication date2017
Abstract

We consider the problem of fine-grained physical object recognition and introduce a dataset PharmaPack con- taining 1000 unique pharma packages enrolled in a controlled environment using consumer mobile phones as well as several recognition sets representing various scenarios. For perfor- mance evaluation, we extract two types of recently proposed local feature descriptors and aggregate them using popular tools. All enrolled raw and pre-processed images, extracted and aggregated descriptors are made public to promote re- producible research. To evaluate the baseline performance, we compare the methods based on aggregation of local descriptors with methods based on geometrical matching.

Keywords
  • Fine-grained recognition
  • Dataset
  • Advanced local descriptors
Citation (ISO format)
TARAN, Olga et al. PharmaPack: mobile fine-grained recognition of pharma packages. In: 25th European Signal Processing Conference (EUSIPCO). Kos (Greece). 2017. 5 p.
Main files (1)
Presentation
Identifiers
  • PID : unige:97444
420views
588downloads

Technical informations

Creation10/06/2017 12:22:00 PM
First validation10/06/2017 12:22:00 PM
Update time03/15/2023 2:06:34 AM
Status update03/15/2023 2:06:34 AM
Last indexation01/17/2024 12:52:02 AM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack