Search

One objective in precision agriculture is to minimise the volume of herbicides that are applied to the fields through the use of site-specific weed management systems. An automatic computer vision system for the detection and differential spraying of weeds in crop fields is discussed. The system involves an image segmentation approach and a decision maker. The first is designed as a sequence of image processing techniques and the second is a decision maker based on the Hebbian learning paradigm under the self-organising criterion. The combination of both and the use of the second are the main findings. The method is compared favourably with other existing strategies achieving a suitable performance.

A new automatic hybrid classifier for natural images by combining two base classifiers through the fuzzy cognitive maps (FCMs) approach is presented in this study. The base classifiers used are fuzzy clustering (FC) and the parametric Bayesian (BP) method. During the training phase, different partitions are established until a valid partition is found. Partitioning and validation are two automatic processes based on validation measurements. From a valid partition, the parameters of both classifiers are estimated. During the classification phase, FC provides for each pixel the supports (membership degrees) that determine which cluster the pixel belongs to. These supports are punished or rewarded based on the supports (probabilities) provided by BP. This is achieved through the FCM approach, which combines the different supports. The automatic strategy and the combined strategy under the FCM framework make up the main findings of this study. The analysis of the results shows that the performance of the proposed method is superior to other hybrid methods and more accurate than the single usage of existing base classifiers.