Using Image Processing Techniques to Compare Accuracy with the Canny Algorithm for Predicting Rice Quality Analysis

The most popular food consumed worldwide is rice, and there is typically a high demand for it. Within the rice manufacturing sector, there is a constant focus on market demand for rice quality. Physical characteristics such as thickness, width, and length are important in determining rice quality. This review's main goal is to identify the optimal method that will provide the best prediction. We'll be contrasting the accuracy with image processing-based methods.In this research project, Canny's Algorithm and image processing techniques are used. Using the <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathrm{G}$</tex> - power software, the sample size was determined to be 10 per group with pretest <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathrm{G}$</tex> - power <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\text{8 0 \%}$</tex>, threshold <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\text{0. 0 5 \%}$</tex>, and confidence interval 95 %. When estimating rice quality, Canny Algorithm yields a greater prediction of 85.60 % than image processing techniques, which predict 80.00 %. With an insignificance score of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\text{1. 0 0 0}(p&gt;0.05)$</tex>, there is a substantial difference between the two groups. An program known as Clever forecasts rice quality assessments more accurately than image processing methods.