ass日本风韵熟妇pics男人扒开女人屁屁桶到爽|扒开胸露出奶头亲吻视频|邻居少妇的诱惑|人人妻在线播放|日日摸夜夜摸狠狠摸婷婷|制服 丝袜 人妻|激情熟妇中文字幕|看黄色欧美特一级|日本av人妻系列|高潮对白av,丰满岳妇乱熟妇之荡,日本丰满熟妇乱又伦,日韩欧美一区二区三区在线

蘋果糖度高光譜圖像可視化預(yù)測(cè)的光強(qiáng)度校正方法
CSTR:
作者:
作者單位:

作者簡(jiǎn)介:

通訊作者:

中圖分類號(hào):

基金項(xiàng)目:

“十二五”國(guó)家科技支撐計(jì)劃資助項(xiàng)目(2014BAD21B01)和北京市自然科學(xué)基金資助項(xiàng)目(6144024)


Intensity Correction of Visualized Prediction for Sugar Content in Apple Using Hyperspectral Imaging
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:

    針對(duì)類球形水果表面曲率變化引起高光譜圖像光響應(yīng)強(qiáng)度差異較大,,難以有效預(yù)測(cè)各部位的品質(zhì)信息的問題,以富士蘋果為研究對(duì)象,,對(duì)高光譜圖像進(jìn)行黑白標(biāo)定后,,以糖度測(cè)試部位為感興趣區(qū)域提取平均光譜并建立糖度的定量預(yù)測(cè)模型,,校正集相關(guān)系數(shù)Rc為0.9305,,校正均方根誤差RMSEC為0.4331,;高光譜圖像經(jīng)構(gòu)建掩模消除樣本背景噪聲后,,提出了高光譜圖像光強(qiáng)度校正方法,,比較校正前后的高光譜圖像能量分布圖可以發(fā)現(xiàn)光強(qiáng)度得到有效補(bǔ)償,,對(duì)校正后的高光譜圖像標(biāo)記空間信息并提取對(duì)應(yīng)光譜,用已建立的蘋果糖度模型計(jì)算各像素點(diǎn)對(duì)應(yīng)的糖度值,,繪制蘋果糖度的偽彩色分布圖,。研究結(jié)果表明,高光譜圖像經(jīng)強(qiáng)度校正可以快速無損的預(yù)測(cè)蘋果的糖度及其分布,。

    Abstract:

    Hyperspectral imaging which integrating both spectroscopic and imaging techniques with higher spatial and spectral resolution, has been developed to study the physical characteristics, chemical constituents and distributions of different quality attributes. It’s difficult to further analyze because of the adverse effects produced by the curvature of spherical objects in the process of hyperspectral images acquirement. Its suitability was illustrated in a specific case of apple fruits. This study proposes a method for correcting the light intensity of radiation nonuniform on the apple fruits. Firstly, the original hyperspectral images were corrected into the reflectance hyperspectral images based on black and white reference images, resulting in reducing the influence of illumination and the dark current of the camera. Then, the mean spectra extracted from roundness region of interest (ROI) in centre area of hyperspectral image were used to develop calibration models by using partial least squares (PLS) regression. The correlation coefficient and root mean square errors of calibration were found to be 0.9305 and 0.4331, respectively. After applying the proposed correction, the spectra of the pixels in hyperspectral image were performed to calculate the sugar content of corresponding pixels. Finally, the visualization of sugar content distribution in apple was achieved by using pseudo-color mapping. The results demonstrated that the correction method was proved to be effective for eliminating the adverse effects produced by the curvature of the fruit on the intensity of the radiation. The hyperspectral imaging has a great potential to be a nondestructive and rapid tool for the quantitative measurement of sugar content distribution for apple.

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

郭志明,趙春江,黃文倩,彭彥昆,李江波,王慶艷.蘋果糖度高光譜圖像可視化預(yù)測(cè)的光強(qiáng)度校正方法[J].農(nóng)業(yè)機(jī)械學(xué)報(bào),2015,46(7):227-232. Guo Zhiming, Zhao Chunjiang, Huang Wenqian, Peng Yankun, Li Jiangbo, Wang Qingyan. Intensity Correction of Visualized Prediction for Sugar Content in Apple Using Hyperspectral Imaging[J]. Transactions of the Chinese Society for Agricultural Machinery,2015,46(7):227-232.

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:2014-09-18
  • 最后修改日期:
  • 錄用日期:
  • 在線發(fā)布日期: 2015-07-10
  • 出版日期: 2015-07-10
文章二維碼