Training a new cotton imaging system via a transfer learning approach

Muneem Shahriar, Ian Scott-Fleming, Hamed Sari-Sarraf, Eric Hequet

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

In this paper, a transfer learning case study on cotton quality evaluation is presented whereby a new prototype imaging system (target problem) is trained using knowledge transferred from a reference system (source problem). We describe the properties of both systems and explain how our problem setup is a specific case of inductive transfer learning. We then present a feature-based domain adaptation framework to reduce domain divergence, allowing data to be compared between the two systems. Finally, we discuss ways of transferring domain-specific knowledge from the reference system to the new system. We demonstrate our approach on cotton data available from the reference system, and those that we generate using our prototype system.

Original languageEnglish
Title of host publicationProceedings of the 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011
Pages767-775
Number of pages9
StatePublished - 2011
Event2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011 - Las Vegas, NV, United States
Duration: Jul 18 2011Jul 21 2011

Publication series

NameProceedings of the 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011
Volume2

Conference

Conference2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011
CountryUnited States
CityLas Vegas, NV
Period07/18/1107/21/11

Keywords

  • Non-destructive cotton evaluation
  • Transfer learning

Fingerprint Dive into the research topics of 'Training a new cotton imaging system via a transfer learning approach'. Together they form a unique fingerprint.

Cite this