Maturity Detection in Peanuts (Arachis Hypogaea L.) Using Machine Vision

The flavor of shelled peanuts (Arachis hypogaea L.) is dependent on several factors including variety, growing conditions, post harvest operations, and maturity of the crop at harvest. At harvest, the peanut crop will have kernels in different stages of development due to the plant’s indeterminate fruiting nature. The maturity of individual peanut kernels can be determined by surface texture characteristics. However, at present, there is no automated method for separating peanut kernels by maturity. To facilitate development of a method, peanuts were hand classified into three maturity groupings (mature, mid-mature, and immature). A machine vision algorithm was developed to find useful surface texture descriptors for detecting each peanut maturity group. A descriptor derived from the gradient image of a peanut was found to be most useful in identifying peanuts of the mid-mature and immature groups in three market size classifications (jumbo, medium, and No. 1) when either white background or black background and red filter conditions were used. The gray level histogram characterization of peanut provided some information but additional experimentation will be necessary to derive texture descriptors useful for maturity sorting. Vision analysis of the gradient image appears as a promising technique for the development of an automated peanut maturity detection system.