PURWARUPA SISTEM PREDIKSI LUAS DAN HASIL PANEN PADI SUATU WILAYAH MENGGUNAKAN PENGOLAHAN CITRA DIGITAL DENGAN METODE SOBEL DAN OTSU; PROTOTYPE OF AREA AND PADDY CROP YIELD PREDICTION SYSTEM OF AN AREA USING DIGITAL IMAGE PROCESSING BY SOBEL’S AND OTSU’S METHOD

Putri, Ardya Yunita, Sumiharto

2015 | Skripsi | FMIPA UGM

Area and paddy crop yield prediction system of an area using digital image processing by Sobel’s and Otsu’s method is one of the system that utilize digital image processing as a detector when the color of paddy is yellowing, which is ready-to-harvest and measuring the area and prediction of its crop yield. This system is an early stage in paddy field measurements of an area by using image processing that utilize aerial photographs. Methods used in this system are Otsu’s and Sobel’s method. The Otsu’s method is used to maximize thresholding process by optimizing threshold values. The Sobel’s method is used to detect paddy field’s edges that will calculate its area. After thresholding process is done, the generated images still have noises that need filters, so when in the scanning process, the calculated white pixels only exists in the desired area. After the amount of white pixel(s) is obtained, their amount is multiplied with the scale that obtained from calibration process and crop yield prediction (kg/m2). The detection of yellow paddy color that ready-to-harvest is successfully performed by processing color of RGB image to HSV, which is then detected by thresholding HSV. HSV value used is the minimum of 16.6 for the value H, 106.4 for a minimum value of S, and 70 for the V minimum. Then the maximum value for the range is 29.6 to H maximum, 227.8 for the maximum value of S, and 183 V for maximum value. At the time of testing with variety data of paddy color, the detected paddy color is the paddy color that ready-to-harvest, which is brownish yellow that represented by white pixels, and will be used then to predict its area and crop yield. Thereafter, accuracy calculation test resulting in different error levels in different paddy fields. Error in testing of this system are 3,1 %, 8,7%, 4,9% dan 248%. The highest error value is caused by excessive exposure of light, with the result that the green color on paddy is detected by the system as yellow. The other errors is caused by some areas are covered by trees that, thereby reducing the paddy fields area calculation. From the results of paddy fields area calculation and the yellowing paddies, the paddy crop yield prediction is obtained.

Kata Kunci : aerial photographs; color detection; thresholding; edge detection; area calculation.