Using a novel Canny algorithm to predict rice quality and comparing its accuracy to image enhancement

Abstract

Aim:Rice is the most widely consumed food on the planet, and demand for rice is usually strong. In the rice manufacturing industry, market demand is consistently focused on rice quality. Physical parameters like length, width, and thickness play a vital part in the evaluation of rice quality. The primary objective of this review aims to be seen as the best-suited algorithm that will give us the ideal prediction.We will be comparing the accuracy with image enhancement. Materials and Methods: Novel Canny algorithms and image enhancement algorithms are implemented in this research work. Sample size is calculated using G power software and determined as 10 per group with pretest power 80%, threshold 0.05% and confidence interval 95%. Result: Canny provides a higher accuracy of 89.80% compared to the image enhancement algorithm with 70.61% in predicting Rice Quality . There is a significant difference between two groups with a significance value of 0.047 (p<0.05). Conclusion: Novel Canny Algorithm predicts Rice Quality Analysis is better than Image Enhancement.