6533b823fe1ef96bd127e002

RESEARCH PRODUCT

Colour image segmentation and labeling through multiedit-condensing

Francisco FerriEnrique Vidal

subject

Colour imageComputer scienceColor imagebusiness.industryObject (computer science)Task (project management)Artificial IntelligenceSignal ProcessingPattern recognition (psychology)SegmentationComputer visionComputer Vision and Pattern RecognitionArtificial intelligencebusinessSoftware

description

Abstract A new method is proposed for detecting and locating objects of interest within a colour scene under very strong variabilities in lighting conditions, object shape and pigmentation. The method is based on Nearest Neighbour classification and Multiedit-Condensing techniques and is applied to implement the vision subsystem of a robotic citric harvesting device. Experiments and results are reported showing the effectiveness of the method and illustrating its appropriateness to the proposed task.

yearjournalcountryeditionlanguage
1992-08-01Pattern Recognition Letters
https://doi.org/10.1016/0167-8655(92)90091-d