Machine vision techniques are now widely used to detect the quality of fruits. Image processing is usually the first step in detecting the quality of fruits. The process starts by capturing the image of the fruits using raspberry pi. Then, the image is transmitted to the processing stage where it can extract the features of the fruit like shape, size, and color. These processes are done using image processing. It helps to identify and compare the fruit shape, size, and color with the trained datasets. This is done during the training and testing stage. A diversity of methods for automatic separation of fruits is developed. Artificial Neural Network is the one that helps to segregate the fruits based on the quality such as good, moderate and rotten fruit. The existing system can only separate the fruits into good and rotten one with an accuracy of 87.4% but our proposed system is capable of separating the fruits into good, moderate and rotten one with an accuracy of 94.12%.