GRADING AND QUALITY TESTING OF FOOD GRAINS USING NEURAL NETWORK

Abstract

The quality of food grains is referred to the every aspect of the profit of supply and marketing. The varietals purity is one of the factors whose inspection is more difficult and more complic ated than that of other factors. In the present gra in-handling system, grain type and quality are rapidly assessed by visual inspecti on. This evaluation process is, however, tedious an d time consuming. The decisionmaking capabilities of a grain inspector can be ser iously affected by his/her physical condition such as fatigue and eyesight, mental state caused by biases and work pressure, and worki ng conditions such as improper lighting, climate, e tc. The farmers are affected by this manual activity. Hence, these tasks require au tomation and develop imaging systems that can be he lpful to identify quality of grain images. A model of quality grade testing and identification is built which is based on appearanc e features such as the morphological and colour with technology of compute r image processing and neural network. The morpholo gical and colour features are presented to the neural network for training pu rposes. The trained network is then used to identif y the unknown grain types, impurities and its quality .