Table 2.

Accuracy assessment of pixel-based classification method for plant and soil classification

	Reference data			User accuracy (%)
	Soil	Plant	Row total
Predicted data
Soil	469	31	500	93.8
Plant	13	487	500	97.4
Column total	482	518	1000
Producer accuracy (%)	97.3	94.0
Overall accuracy (%) = 95.6

One thousand random points were generated and placed on the orthomosaiced image using the equalized random sampling method. The predicted data was generated from k-means clustering and the reference data was manually created using visual observations of the images. Accuracy assessment results were generated using ERDAS IMAGINE software. An overall classification of 95.6% was achieved

The diagonal elements are italicized to highlight the number of correctly classified pixels in terms of plant or soil classifications