Hyper Spectral Image compression using Higher Order Orthogonal Iteration Tucker decomposition

Hyper spectral images need more memory to store, process, and transmit due to the large amount of information they carry. One of the most effective way to compress hyper spectral images is to represent them as a three-dimensional tensor. Tensors are multi-dimensional Structures. Tensors have a wide...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Annual IEEE India Conference s. 1 - 7
Hlavní autori: Sucharitha, B., Anitha Sheela, K.
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 24.11.2022
Predmet:
ALS
HOOI
HOSVD
Hyper spectral Image
Image coding
Memory management
PSNR
Simulation
SSIM
Tensor
Tensors
Termination of employment
Three-dimensional displays
Transforms
ISSN:2325-9418
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Hyper spectral images need more memory to store, process, and transmit due to the large amount of information they carry. One of the most effective way to compress hyper spectral images is to represent them as a three-dimensional tensor. Tensors are multi-dimensional Structures. Tensors have a wide range of applications in numerical linear algebra, chemometrics, data mining, signal processing, statics, data mining, and machine learning. For dimensional reduction of tensors, many tensor decomposition methods have been developed, which we can adapt to Hyper spectral image compression. The proposed method uses Discrete Wavelet Transform and Higher-Order Orthogonal Iteration Tucker Decomposition method to compress the Hyper spectral Image. The simulation results were compared with 3 more tensor decomposition techniques. Four real hyper spectral images were used in the experimentation: Pavia University (610 X 340 X 103), Indian Pines adjusted (145 x 145 x 200), Salinas image (512 x 217 x 224), and Abu-beach (150 X 150 X 102). After processing, the perceptional quality of the Hyper spectral images is evaluated using PSNR and SSIM. When compared to the other three methods, the proposed method offers good PSNR and SSIM with High Compression.
ISSN:2325-9418
DOI:10.1109/INDICON56171.2022.10040093