欢迎访问《茶叶科学》,今天是

茶叶科学 ›› 2008, Vol. 28 ›› Issue (6): 420-424.doi: 10.13305/j.cnki.jts.2008.06.001

• • 上一篇    下一篇

基于颜色和形状的茶叶计算机识别研究

汪建, 杜世平   

  1. 四川农业大学生命理学院,四川 雅安 625014
  • 收稿日期:2008-05-09 出版日期:2008-12-15 发布日期:2019-09-12
  • 作者简介:汪建(1968— ),男,四川雅安人,副教授,主要从事计算机图像处理、模式识别方面的研究。

Identification investigation of Tea Based on HSI Color Space and Figure

WANG Jian, DU Shi-ping   

  1. College of Biology and Science, Sichuan Agricultural University Yaan 625014, China
  • Received:2008-05-09 Online:2008-12-15 Published:2019-09-12

摘要: 综合利用计算机视觉、图像处理技术,增加茶叶的形状参数,改进神经网络算法,实现了茶叶品质识别的自动化。研究中通过数码相机等直接得到茶叶图像,经过对图像格式进行转换和预处理,然后基于HSI模型提取的茶叶颜色特征参数和二值化后图像提取的茶叶形状特征参数,通过遗传神经网络,最后完成对茶叶的自动识别。实验结果表明此方法能取得更好的识别效果,计算机的检测结果与人工检测结果高度吻合。

关键词: 茶叶, 颜色, 形状, 图像处理, 遗传算法, 神经网络, 识别

Abstract: The figure characteristics of tea and improved neural-network, computer vision and image processing were combined together to realize automatic identification of external quality of tea leaf. Firstly a tea-leaf image was obtained by a digital camera directly. The parameters of tea HSI model and parameters of the figure was extracted to identify tea leaf after image conversion and preprocess. Then completed automatically identify of tea-leaf through the Genetical-Neural network. The experiments reveal that the method improves the consistence between computer inspection and manual inspection.

Key words: tea, color, figure, image processing, genetical-arithmetic, neural-network, identification

中图分类号: