https://libeldoc.bsuir.by/handle/123456789/41659| Title: | Image enhancement by 2D non-separable quaternionic filter bank-based thresholding neural network |
| Authors: | Avramov, V. V. Rybenkov, E. V. Petrovsky, N. A. |
| Keywords: | публикации ученых;image enhancement;thresholding neural network |
| Issue Date: | 2019 |
| Publisher: | Springer |
| Citation: | Avramov, V. V. Image enhancement by 2D non-separable quaternionic filter bank-based thresholding neural network / V. V. Avramov, E. V. Rybenkov, N. A. Petrovsky // Pattern Recognition and Information Processing : 14th International conference, Minsk, 21–23 may 2019 / Springer. – Minsk, 2019. – P. 207–212. |
| Abstract: | The thresholding neural network with a 2-D non-separable paraunitary filter bank based on quaternion multipliers (2-D NSQ-PUFB) for image enhancement is proposed. Due to the high characteristics of the multi-bands 2-D NSQ-PUFB (structure 64in-64out, CG2D =17,15 dB, prototype filter bank (8x24) Q-PUFB), which forms the basis of the TNN, the results of noise editing in comparison with the approaches based on the two-channel wavelet transform in terms of PSNR are 1 1.5 dB higher. |
| URI: | https://libeldoc.bsuir.by/handle/123456789/41659 |
| Appears in Collections: | Публикации в зарубежных изданиях |
| File | Description | Size | Format | |
|---|---|---|---|---|
| Avramov_Image.pdf | 177.36 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.