Intelligent computer vision system for vegetables and fruits quality inspection using soft computing techniques

The quality of food products is essential for human health. The large population and the increased requirements of food products make it challenging to arrive at the desired class. The quality inspection and sorting tons of fruits and vegetables manually are slow, costly, and an inaccurate process. In this research, vision-based quality inspection and sorting system are developed, to increase the quality of food products. The quality inspection and sorting process depends on capturing the image of the fruits/vegetables, analyzing the captured image to discard defected products to identify the good or bad. Four different systems for different food products have been developed namely, Orange, Lemon, Sweet Lime, and Tomato. A dataset of 1200 images is used to train and test the vision systems (300 images for each). The obtained accuracy ranges from 85.00% to 95.00% for Orange, Lemon, Sweet Lime and Tomato used soft-computing techniques such as Backpropagation neural network and Probabilistic neural network.