An improved method based on twIst and dual-camera design for hyperspectral image reconstruction

2021 ◽  
Author(s):  
Xinyu Liu ◽  
Chenning Tao ◽  
Qin Xie ◽  
Yan Sun ◽  
Jinlei Zhang ◽  
...  
Keyword(s):  
Image Reconstruction ◽  
Hyperspectral Image ◽  
Improved Method ◽  
Camera Design

scholarly journals Hyperspectral Image Reconstruction via Block Low-Rank and Three-Dimension Weighted Total Variation Constraint

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 47698-47713 ◽  
Author(s):  
Zongrui Wu ◽  
Xi Chen ◽  
Wenxuan Shi ◽  
Liqiong Chen ◽  
Shiyong Hu
Keyword(s):  
Image Reconstruction ◽  
Total Variation ◽  
Hyperspectral Image ◽  
Low Rank ◽  
Three Dimension ◽  
Weighted Total Variation

scholarly journals Deep Learning in Hyperspectral Image Reconstruction from Single RGB images—A Case Study on Tomato Quality Parameters

2020 ◽  
Vol 12 (19) ◽  
pp. 3258
Author(s):  
Jiangsan Zhao ◽  
Dmitry Kechasov ◽  
Boris Rewald ◽  
Gernot Bodner ◽  
Michel Verheul ◽  
...  
Keyword(s):  
Image Reconstruction ◽  
Hyperspectral Image ◽  
Absolute Error ◽  
Solid Content ◽  
Image Resolution ◽  
Soluble Solid Content ◽  
Quality Properties ◽  
Tomato Quality ◽  
Rgb Images

Hyperspectral imaging has many applications. However, the high device costs and low hyperspectral image resolution are major obstacles limiting its wider application in agriculture and other fields. Hyperspectral image reconstruction from a single RGB image fully addresses these two problems. The robust HSCNN-R model with mean relative absolute error loss function and evaluated by the Mean Relative Absolute Error metric was selected through permutation tests from models with combinations of loss functions and evaluation metrics, using tomato as a case study. Hyperspectral images were subsequently reconstructed from single tomato RGB images taken by a smartphone camera. The reconstructed images were used to predict tomato quality properties such as the ratio of soluble solid content to total titratable acidity and normalized anthocyanin index. Both predicted parameters showed very good agreement with corresponding “ground truth” values and high significance in an F test. This study showed the suitability of hyperspectral image reconstruction from single RGB images for fruit quality control purposes, underpinning the potential of the technology—recovering hyperspectral properties in high resolution—for real-world, real time monitoring applications in agriculture any beyond.

Improved Method of Medical Image Reconstruction Based on MC Algorithm

2011 ◽  
Vol 135-136 ◽  
pp. 592-596
Author(s):  
Xue Mei Huang ◽  
Wei Hong Liu ◽  
Hong Quan Wang
Keyword(s):  
Data Structure ◽  
Image Reconstruction ◽  
Medical Image ◽  
Normal Vector ◽  
Reconstruction Method ◽  
Segmentation Result ◽  
Improved Method ◽  
Image Reconstruction Method ◽  
Medical Image Reconstruction ◽  
Reconstructed Model

Some improvements were put forward to modify the medical image reconstruction method based on MC algorithm. Computing redundancy, bad expansibility and “scalelike effect” lie in standard MC algorithm now. To solve the repeating calculation redundant problem, a suitable data structure was applied to seek cubes; by making segmentation result as the input of MC algorithm, the author eliminated the limitation of expansibility; by smoothing the normal vector of isosurfaces, this paper improved the image displaying effect. Finally, a special storage data structure was designed to save the non-manifold triangle model obtained from MC algorithm. The modification mentioned above has been realized in 3D reconstructing software-MedLG which was developed by authors’ institute and applied successfully in customized prostheses designing already. Moreover, The reconstructed model can also be used in biomechanics researching.

Parallel hyperspectral image reconstruction using random projections

2016 ◽  
Author(s):  
Jorge Sevilla ◽  
Gabriel Martín ◽  
José M. P. Nascimento
Keyword(s):  
Image Reconstruction ◽  
Hyperspectral Image ◽  
Random Projections

scholarly journals Coded Aperture Hyperspectral Image Reconstruction

Sensors ◽  
2021 ◽  
Vol 21 (19) ◽  
pp. 6551
Author(s):  
Ignacio García-Sánchez ◽  
Óscar Fresnedo ◽  
José P. González-Coma ◽  
Luis Castedo
Keyword(s):  
Image Reconstruction ◽  
Hyperspectral Image ◽  
Computational Cost ◽  
Hyperspectral Images ◽  
Coded Aperture ◽  
Block Model ◽  
Reconstruction Procedure ◽  
Estimation Algorithms ◽  
Efficient Mechanisms

In this work, we study and analyze the reconstruction of hyperspectral images that are sampled with a CASSI device. The sensing procedure was modeled with the help of the CS theory, which enabled efficient mechanisms for the reconstruction of the hyperspectral images from their compressive measurements. In particular, we considered and compared four different type of estimation algorithms: OMP, GPSR, LASSO, and IST. Furthermore, the large dimensions of hyperspectral images required the implementation of a practical block CASSI model to reconstruct the images with an acceptable delay and affordable computational cost. In order to consider the particularities of the block model and the dispersive effects in the CASSI-like sensing procedure, the problem was reformulated, as well as the construction of the variables involved. For this practical CASSI setup, we evaluated the performance of the overall system by considering the aforementioned algorithms and the different factors that impacted the reconstruction procedure. Finally, the obtained results were analyzed and discussed from a practical perspective.

Sign in / Sign up

Export Citation Format

Share Document