Measuring efficiency of crop cleaners by image analysis

The purity of product from agricultural cleaners(such as chile,cotton,bean,wheat and other crop cleaners)is needed to be measured under various conditions in order to adjust and optimize the machine at the design and improvement stages.The traditional weight-based method of measuring purity is time consuming,and requires much labor.In this study,we used image analysis to measure percent crop cover for the product output to infer the purity.Chile cleaner was used as one example machine to compare between Photoshop©and Arcview©software for the analysis of fresh and dry harvest pictures.The data collection process is more reproducible and less labor and time consuming than the traditional technique.Both software packages provided accurate estimations of purity for both fresh and dry harvest pictures.Photoshop©had better accuracy than Arcview©(mean error ratio of 0.016 vs.0.081 for fresh harvest;and 0.035 vs.0.114 for dry harvest).