Parallel Processing System for Spectroscopic Understanding of Color Images by Neural network and its Application to Vegetation Monitoring

神经网络彩色图像光谱理解并行处理系统及其在植被监测中的应用

• 批准号: 10555013
• 负责人: TOYOOKA Satoru
• 金额: $ 8.51万
• 依托单位: Saitama University
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Scientific Research (B).
• 财政年份: 1998
• 资助国家: 日本
• 起止时间: 1998 至 2000
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT-10555013/
• 关键词: Neural Network; Spectroscopic image analysis; Broad band filtering system; Vegetation monitoring; 広帯域フィルク分光撮像装置; 広帯域フィルタ分光撮影装置; 植生モニタ; シラビソ

A spectral image include huge volume of data. Multi-variable analysis is usually used to extract important information in the image. On the contrary in the proposed system, important spectroscopic information in the images which we want to investigate is taken in advance in a learning phase and installed in a system as optimized filters. Filter optimization by self-organized map is discussed. Three proto-types of broad-band filtering systems to implement optimize filter functions which include liquid-crystal devises and optical components were constructed. Experimental results of spectral reconstruction from four filterer images by proposed system were compared with measured result by conventional method. A new intelligent eye which is sensitive to spectral characteristics of an object will be expected.

光谱图像包含了大量的数据。多变量分析通常用于提取图像中的重要信息。相反，在该系统中，我们想要研究的图像中的重要光谱信息在学习阶段被提前获取，并作为优化滤波器安装在系统中。讨论了基于自组织映射的滤波器优化。构建了三种实现优化滤波功能的宽带滤波系统原型，包括液晶器件和光学元件。将该系统对四幅滤波图像的光谱重建实验结果与常规方法的实测结果进行了比较。人们期待一种对物体光谱特征敏感的新型智能眼睛。

项目成果

M.Hauta-Kasari,W.Wang,S.Toyooka,J.Parkkinen,and R.Lenz: "Unsupervised Filtering of Munsell Spectra"Proceedings of the 3 ^<rd> Asian Conference on Computer Vision, (ACCV'98), Hong Kong. Vol.1. 248-255 (1998)

M.Hauta-Kasari、W.Wang、S.Toyooka、J.Parkkinen 和 R.Lenz：“孟塞尔谱的无监督过滤”第三届 ^<rd> 亚洲计算机视觉会议论文集，(ACCV98)，

M.Hauta-Kasari,K.Miyazawa,S.Toyooka,J.Parkkinen,and T.Jaaskelainen: "Spectral Vision System based on Rewritable Broad Band Color Filters"International Symposium on Multispectral Imaging and Color Reproduction for Digital Archives, Chiba. 1. 155-158 (1999)

M.Hauta-Kasari、K.Miyazawa、S.Toyooka、J.Parkkinen 和 T.Jaaskelainen：“基于可重写宽带滤色片的光谱视觉系统”数字档案多光谱成像和色彩再现国际研讨会，千叶。

S.Toyooka,K.Kurashiki,K.Miyazawa,and M.Hauta-Kasari: "Broad-band color filters with arbitrary spectral transmittance using a Liquid Crystal Tunable Filter (LCTF) "The 9^<th> Congress of International Colour Association, AIC Color 01 Rochester.

S.Toyooka、K.Kurashiki、K.Miyazawa 和 M.Hauta-Kasari：“使用液晶可调谐滤光片 (LCTF) 实现任意光谱透射率的宽带滤色片”第 9 届国际色彩协会大会

M.Hauta-Kasari, K.Miyazawa, S.Toyooka, and J.Parkkinen: "Spectral Vision System for Measuring Color Images"Journal of the Optical Society of America A. Vol.16, No.10. 2352-2362 (1999)

M.Hauta-Kasari、K.Miyazawa、S.Toyooka 和 J.Parkkinen：“用于测量彩色图像的光谱视觉系统”美国光学学会杂志 A. 第 16 卷，第 10 期。

K.Miyazawa, M.Hauta-Kasari, and S.Toyooka: "Spectral Image Analysis of a Natural Color Sample using Rewritable Transparent Broad-Band Filters"International Symposium on Multispectral Imaging and Color Reproduction for Digital Archives, MICR'99, Chiba. 110

K.Miyazawa、M.Hauta-Kasari 和 S.Toyooka：“使用可重写透明宽带滤光片对自然颜色样本进行光谱图像分析”数字档案多光谱成像和颜色再现国际研讨会，MICR99，千叶。