Comparison of Image Preprocessing Techniques for Fruit Grading

Image analysis is one of the important approaches in fruit grading. Since manual grading is more popular, if it done manually, the process is slow, labor expensive and grading is done by visual inspection that could be error prone. So automatic fruit grading is needed. Preprocessing in fruit image is a crucial initial step before image analysis is performed. Many preprocessing methods are available in the literature. Datasets are limited by laboratory constraints so that the need is for guidelines on quality and robustness of fruit, to proceed experimentation mango image is taken. In this paper, the performance of four preprocessing methods is compared namely contrast adjustment, Removing noise, Histogram equalization, and Binarization. The performances of these methods are evaluated using Peak Signal to Noise Ratio (PSNR) and Mean Square Error (MSE).