DE-NOISING OF TOMATO FRUIT IMAGE USING SPIRAL SEED FILTER

Abstract

Fruit disease causes more economic losses in agricultural industry. In prediction of disease image pre-processing plays an important role. Fruits may appear healthy and fresh to human eye but its quality is known by customer after eating the fruits. Images are used to forecast quality of the fruits and vegetables, but accuracy of grading will be affected by distortion. Various noise affect the quality of the image and it can be denoised by various filters. The preservative edges, background information and contrast of images are the challenging issues in exiting filtering methods. This research proposed Spiral Seed Filter (SSF) to increase the quality of the tomato fruit image by extracting the luma variance and by applying the row wise and column wise 3x3 cross correlation. The result shows that the proposed filter increases the PSNR (Peak Signal to Noise ratio) and reduces MSE (Mean Square Error) metric values and yield good results. It gives highest PSNR value such as 94.68. It gives 0.0001 as MSE value for proposed method.