基于图像处理技术的小麦萌芽率测试研究

Research on Wheat Germination Rate Test Based on Image Processing Technology

本研究选择了‘郑麦618’、‘西农511’、‘中麦875’、‘豫麦58号’、‘山农27号’、‘冀麦38号’6种小麦种子作为研究对象,通过扫描仪获得了小麦种子的图像后,再对图像进行灰度化、中值滤波和图像分割等处理后,提取了3个颜色特征(R,G,B),4个形状特征(边界长度,面积,圆形度,伸长度)和4个纹理特征(熵,对比度,局部平稳性,相关性),通过人工神经网络对这11个特征进行分类识别,检测了6种小麦种子的萌芽率,准确率分别为92.97%、91.87%、91.67%、90.57%、90.9%、91.75%,每种小麦种子的预测准确率均大于90%,且图像处理效率较高。综合来看,利用计算机图像处理技术对小麦种子的检测具有速度快且准确率高的优点,在种子的育种和质量检测方面具有可观的实际应用价值。

In this study,six wheat seeds,’Zhengmai618’,’Xinong511’,’Zhongmai875’,’Yumai58’,’Shannong27’,and’Jimai38’are selected as the research objects.After obtaining the image of wheat seeds through the scanner,after processing the image by graying,median filtering and image segmentation,3 color features(R,G,B)and 4 shape features(boundaries length,area,roundness,elongation length)and 4 texture features(entropy,contrast,local stability,correlation).These 11 features are classified and identified by artificial neural network,and the germination of 6 kinds of wheat seeds are detected.The accuracy rates are respectively 92.97%,91.87%,91.67%,90.57%,90.9%,91.75%.The prediction accuracy rate of each wheat seed is>90%,and the image processing efficiency is high.In general,the use of computer image processing technology has the advantages of fast speed and high accuracy in the detection of wheat seeds,and has considerable practical application value in seed breeding and quality detection.