Fully Separable Inverse Wavelet Reconstruction. Parameters ---------- fswavedecn_result : FswavedecnResult object FswavedecnResult object from ``fswavedecn``. Returns ------- reconstructed : ndarray Array of reconstructed data. Notes ----- This
(fswavedecn_result)
| 1492 | |
| 1493 | |
| 1494 | def fswaverecn(fswavedecn_result): |
| 1495 | """Fully Separable Inverse Wavelet Reconstruction. |
| 1496 | |
| 1497 | Parameters |
| 1498 | ---------- |
| 1499 | fswavedecn_result : FswavedecnResult object |
| 1500 | FswavedecnResult object from ``fswavedecn``. |
| 1501 | |
| 1502 | Returns |
| 1503 | ------- |
| 1504 | reconstructed : ndarray |
| 1505 | Array of reconstructed data. |
| 1506 | |
| 1507 | Notes |
| 1508 | ----- |
| 1509 | This transformation has been variously referred to as the (fully) separable |
| 1510 | wavelet transform (e.g. refs [1]_, [3]_), the tensor-product wavelet |
| 1511 | ([2]_) or the hyperbolic wavelet transform ([4]_). It is well suited to |
| 1512 | data with anisotropic smoothness. |
| 1513 | |
| 1514 | In [2]_ it was demonstrated that the fully separable transform performs at |
| 1515 | least as well as the DWT for image compression. Computation time is a |
| 1516 | factor 2 larger than that for the DWT. |
| 1517 | |
| 1518 | See Also |
| 1519 | -------- |
| 1520 | fswavedecn : inverse of fswaverecn |
| 1521 | |
| 1522 | References |
| 1523 | ---------- |
| 1524 | .. [1] PH Westerink. Subband Coding of Images. Ph.D. dissertation, Dept. |
| 1525 | Elect. Eng., Inf. Theory Group, Delft Univ. Technol., Delft, The |
| 1526 | Netherlands, 1989. (see Section 2.3) |
| 1527 | http://resolver.tudelft.nl/uuid:a4d195c3-1f89-4d66-913d-db9af0969509 |
| 1528 | |
| 1529 | .. [2] CP Rosiene and TQ Nguyen. Tensor-product wavelet vs. Mallat |
| 1530 | decomposition: A comparative analysis, in Proc. IEEE Int. Symp. |
| 1531 | Circuits and Systems, Orlando, FL, Jun. 1999, pp. 431-434. |
| 1532 | |
| 1533 | .. [3] V Velisavljevic, B Beferull-Lozano, M Vetterli and PL Dragotti. |
| 1534 | Directionlets: Anisotropic Multidirectional Representation With |
| 1535 | Separable Filtering. IEEE Transactions on Image Processing, Vol. 15, |
| 1536 | No. 7, July 2006. |
| 1537 | |
| 1538 | .. [4] RA DeVore, SV Konyagin and VN Temlyakov. "Hyperbolic wavelet |
| 1539 | approximation," Constr. Approx. 14 (1998), 1-26. |
| 1540 | """ |
| 1541 | coeffs_arr = fswavedecn_result.coeffs |
| 1542 | coeff_slices = fswavedecn_result.coeff_slices |
| 1543 | axes = fswavedecn_result.axes |
| 1544 | modes = fswavedecn_result.modes |
| 1545 | wavelets = fswavedecn_result.wavelets |
| 1546 | |
| 1547 | _check_fswavedecn_axes(coeffs_arr, axes) |
| 1548 | if len(axes) != len(coeff_slices): |
| 1549 | raise ValueError("dimension mismatch") |
| 1550 | |
| 1551 | arr = coeffs_arr |
nothing calls this directly
no test coverage detected