亚洲一区欧美在线,日韩欧美视频免费观看,色戒的三场床戏分别是在几段,欧美日韩国产在线人成

基于多光譜圖像及組合特征分析的茶葉等級(jí)區(qū)
作者:
作者單位:

作者簡介:

通訊作者:

中圖分類號(hào):

基金項(xiàng)目:


of Tea Grades by Multi-spectral Images and Combined Features
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 圖/表
  • |
  • 訪問統(tǒng)計(jì)
  • |
  • 參考文獻(xiàn)
  • |
  • 相似文獻(xiàn)
  • |
  • 引證文獻(xiàn)
  • |
  • 資源附件
  • |
  • 文章評(píng)論
    摘要:

    提出了一種采用多光譜成像的機(jī)器視覺技術(shù)對(duì)4個(gè)等級(jí)的西湖龍井茶進(jìn)行區(qū)分的方法。首先采用3CCD多光譜攝像機(jī)同時(shí)獲取茶葉在540、670和800nm波譜處的波長圖像,然后對(duì)預(yù)處理后的圖像進(jìn)行圖像特征提取,選取了18個(gè)形狀特征和15個(gè)紋理特征?;谶@2組特征分別對(duì)4個(gè)等級(jí)的茶葉進(jìn)行主成分聚類分析,得到的兩幅主成分空間的聚類圖都不能對(duì)4個(gè)等級(jí)茶葉進(jìn)行有效的區(qū)分。為了得到高效的區(qū)分模型,本研究對(duì)形狀特征和紋理特征進(jìn)行組合,聚類分析的結(jié)果優(yōu)于原先的分析結(jié)果。隨后,采用多類逐步判別分析法對(duì)形狀特征、紋理特征和組合特征(形狀+紋理)這3組特征分別進(jìn)行特征優(yōu)化,并建立了對(duì)應(yīng)各組特征的等級(jí)區(qū)分模型,經(jīng)過比較發(fā)現(xiàn)基于組合特征的區(qū)分模型的效果仍為最佳,對(duì)于預(yù)測集樣本的區(qū)分正確率為85%。本研究還發(fā)現(xiàn)對(duì)于等級(jí)區(qū)分最重要的兩個(gè)特征依次為波長800nm通道圖像的相關(guān)性、波長800nm通道圖像的二階角矩。

    Abstract:

    A method for classification of Xi-hu-long-jing tea in four grades was introduced based on machine vision of multi-spectral imaging technique. Firstly, three monochrome images at 540,670 and 800 nm wavelengths were simultaneously obtained based on 3CCD multi-spectral camera, then image features including 18 shape features and 15 texture features were extracted based on image processing technology. These two groups of features were adopted for cluster analysis with principal component analysis of the four grades tea. However the result was not satisfactory. In order to obtain a more effective separation model, the two groups of features were combined, and the cluster analysis was conducted again based on the combined features. The result was better than the former. After optimization of these three groups of features, three classification models were developed by means of multiple stepwise discriminant analysis (MSDA). It was found that model based on the combined features had the best performance with accuracy of 85% for prediction of unknown samples. The most important two features for classification were correlation and energy of 800 nm wavelength monochrome image.

    參考文獻(xiàn)
    相似文獻(xiàn)
    引證文獻(xiàn)
引用本文

李曉麗,何勇.基于多光譜圖像及組合特征分析的茶葉等級(jí)區(qū)[J].農(nóng)業(yè)機(jī)械學(xué)報(bào),2009,40(Z1):113-118. of Tea Grades by Multi-spectral Images and Combined Features[J]. Transactions of the Chinese Society for Agricultural Machinery,2009,40(Z1):113-118.

復(fù)制
分享
文章指標(biāo)
  • 點(diǎn)擊次數(shù):
  • 下載次數(shù):
  • HTML閱讀次數(shù):
  • 引用次數(shù):
歷史
  • 收稿日期:
  • 最后修改日期:
  • 錄用日期:
  • 在線發(fā)布日期:
  • 出版日期: