Color image segmentation with genetic algorithm for in-field weed sensing

This study was undertaken to develop machine vision-based weed detection te chnology for outdoor natural lighting conditions. Supervised color image se gmentation using a binary-coded genetic algorithm (GA) identifying a region in Hue-Saturation-Intensity (HSI) color space (GAHSI) for outdoor field we ed sensing was successfully implemented. Images from two extreme intensity lighting conditions, those under sunny and cloudy sky conditions, were mosa icked to explore the possibility of using GAHSI to locate a plant region in color space when these two extremes were presented simultaneously. The GAH SI result provided evidence for the existence and separability of such a re gion. In the experiment, GAHSI performance was measured by comparing the GA HSI-segmented image with a corresponding hand-segmented reference image. Wh en compared with cluster analysis-based segmentation results, the GAHSI ach ieved equivalent performance.