Çeltik yanıklığı hastalığının görüntü işleme teknikleri kullanılarak tespit edilmesi

In rice plant, accurate and timely detection of diseases helps to start agricultural practices on time thus reduces economic losses significantly. For this purpose, image processing techniques were used identify classify the leaf blight disease ( Pyricularia oryzae Cav.). processing, a clustering method was for segmentation diseased part, non-diseased part background. Images taken both from ground with aid drone. Levenberg-Marquardt training algorithm preferred in artificial neural networks model. While RMS, R 2 error values test data MEITG proposed identification 0.000017, 0.9999 0.019%, respectively, they found as 0.000007, 0.002% MERITD. The MCITG MCRITD models presented classification have success rates 92.2 percent 100 percent, respectively. results obtained show feasibility effectiveness