A Method of Detecting Peanut Cultivars and Quality Based on the Appearance Characteristic Recognition

The detection of peanut cultivars and quality is an important composition of peanut breeding and quality testing. In order to evaluate the feasibility of mass peanut seed detecting via appearance characteristic, firstly we get 48 varieties pictures and 6 different quality in one variety pictures with digital camera, then we use the method of principle component analysis and artificial neural network to establish a seed recognition model which is made up of 49 distinct appearance characteristic refers to shape, texture, color and optimize the model. The testing result indicates: after the model optimization, the variety recognition rate and quality recognition rate reaches 91.2% and 93.0% respectively; the color characteristic plays an impactful role in the variety and quality detection; the appearance characteristic distinguishes quality is more obvious than distinguishes varieties. The detecting method based on the machine vision possesses the cost and speed advantages, it can be used in the identification for peanut cultivars and quality.