Determination of Maize Seed Purity Based on Multi-Step Clustering

Abstract

Abstract. Electrophoresis has been widely used to determine maize seed purity; however, the associated time and complexity hinder its application for maize seeds. Equipment to estimate seed purity was designed to improve the efficiency of identification of circulating maize seeds, and a multi-step clustering method was created for the determination of seed purity. The main components included a host computer, a black box, a seed transmission belt with grooves, a binocular vision system, and an under-controller. First, image information of the crown and the non-embryo side of every maize seed was collected using the binocular vision system while seeds underwent intermittent movement on the transmission belt. Second, multi-area color characteristics, which included red, green, and blue (RGB), hue, saturation, intensity (HSI), and lightness-a-b (Lab) color model parameters of maize seeds were extracted and optimized to generate 25-dimensional purity identification vectors. Finally, a multi-step clustering model was used to determine seed purity. The original center of K-mean clustering was established based on the results of self-organizing map (SOM) clustering; subsequently, maize seed purity parameters were obtained by combining the results of the second and the first clustering analyses. A result was achieved by testing three groups of samples, including 'ZHENGDAN 958' mixed with 'XIANYU 335', 'XIANYU 335' mixed with its male parent, and 'XIANYU 335' mixed with its female parent. The result showed that the correct recognition rate of 'XIANYU 335' mixed with 'ZHENGDAN 958' that had no genetic relationship could reach 100% under the condition of the experimental sample, and the accuracy of identification between 'XIANYU 335' and their respective male and female parents was 96.7% and 88.7%. This recognition rate met with the technical requirements of field inspection and provided a reliable scientific basis for the rapid determination of maize seed purity. Keywords: Identification, Maize seed, Multi-step clustering, Purity, Rapid.