Neural networks and low-cost optical filters for plant segmentation

In this paper, we describe a low-cost system for image segmentation in agricultural applications. In applications such as weed detection and classification, plants must be segmented from the image. Our novel approach combines low-cost NIR filters used on a standard camera with neural networks to achieve a significantly higher accuracy as compared to classic threshold techniques. © 2010 IADIS.

ISBN:9789728939229

Jaar van publicatie:2010

Toegankelijkheid:Closed