Modelling uncertainty in agricultural image analysis

Christine M. Onyango, John A. Marchant, Reyer Zwiggelaar

Research output: Contribution to journalArticlepeer-review

3 Citations (SciVal)


No absolute certainty can be given for information derived from images. In most cases image analysis uses single algorithms, or multiple single algorithms' results which are combined in an ad hoc manner, to derive certain information (e.g. edges and textures) to segment images into various regions of interest. However, more robust methods of data fusion can be developed which are based on mathematical foundations of probability theory. One such method combines results from single algorithms using a Bayesian network. This should improve the confidence in the derived image segmentation and gives a direct measure of the probability of each region to be classified correctly. Specific agricultural examples using a Bayesian data fusion approach are given.
Original languageEnglish
Pages (from-to)295-305
Number of pages11
JournalComputers and Electronics in Agriculture
Issue number3
Publication statusPublished - Jun 1997


  • Bayesian networks
  • Uncertainty
  • Image analysis
  • Algorithm fusion


Dive into the research topics of 'Modelling uncertainty in agricultural image analysis'. Together they form a unique fingerprint.

Cite this