At 81.2 million tons per year, India ranks worldwide second in the cultivation of fruit, accounting for 12.6% of global fruits production, after China (21.2%). In India as well as throughout the world, there is a much greater need and appetite for fruits. Mango, banana, papaya, guava, and pineapple are just a few of the tropical and subtropical fruits that make up a significant portion and are grown in several Indian states. Fruit production must therefore be prevented by protecting them from diseases that could compromise their quality and general condition. Fungal and bacterial pathogens are principally responsible for fruit diseases. CNN achieves a desirable exactness of 97.10 for each of the fruit image information sets. The main goal of this research is to perform a comparison of a deep learning categorization strategy within the field of fruit surveillance plus suggest an approach for classifying and detecting fruit diseases that combines deep learning (DL) and machine learning (ML). ML and DL algorithmic methods for classification are utilized on diverse fruit information sets, and different extraction and selection of features techniques are implemented.