Efficient implementation of image interpolation as an inverse problem

Speaker identification is a widely used technique in several security systems. In remote access systems, speaker utterances are recoded and communicated through a communication channel to a receiver that performs the identification process. Speaker identification is based on characterizing each speaker with a set of features extracted from his or her utterance. Extracting the features from a clean speech signal guarantees the high success rate in the identification process. In real cases, a clean speech is not available for feature extraction due to channel degradations, background noise, or interfering audio signals. As a result, there is a need for speech enhancement, deconvolution, and separation algorithms to solve the problem of speaker identification in the presence of impairments. Another important issue, which deserves consideration, is how to enhance the security of a speaker identification system. This can be accomplished by watermark embedding in the clean speech signals at the transmitter. If this watermark is extracted correctly at the receiver, it can be used to ensure the correct speaker identification. Another means of security enhancement is the encryption of speech at the transmitter. Speech encryption prevents eavesdroppers from getting the speech signals that will be used for feature extraction to avoid any unauthorized access to the system by synthesis trials. Multilevels of security can be achieved by implementing both watermarking and encryption at the transmitter. The watermarking and encryption algorithms need to be robust to speech enhancement, and deconvolution algorithms to achieve the required degree of security and the highest possible speaker identification rates. This book provides for the first time a comprehensive literature review on how to improve the performance of speaker identification systems in noisy environments, by combining different feature extraction techniques with speech enhancement, deconvolution, separation, watermarking, and/or encryption.

Information Security for Automatic Speaker Identification

Edge-and-corner preserving regularization for image interpolation and reconstruction

A regularized wavelet-based image super-resolution recon- struction approach is presented. The super-resolution image reconstruc- tion problem is an ill-posed inverse problem. Several iterative solutions have been proposed, but they are time-consuming. The suggested ap- proach avoids the computational complexity limitations of existing solu- tions. It is based on breaking the problem into four consecutive steps: a registration step, a multichannel regularized restoration step, a wavelet- based image fusion and denoising step, and finally a regularized image interpolation step. The objective of the wavelet fusion step is to integrate all of the data obtained from the multichannel restoration step into a single image. The wavelet denoising is performed for the low-SNR cases to reduce the noise effect. The obtained image is then interpolated using a regularized interpolation scheme. The paper explains the implementa- tion of each of these steps. The results indicate that the proposed ap- proach has succeeded in obtaining a high-resolution image from multiple degraded observations with a high peak SNR. The performance of the proposed approach is also investigated for degraded observations with different SNRs. The proposed approach can be implemented for large- dimension low-resolution images, which is not possible in most pub- lished iterative solutions. © 2005 Society of Photo-Optical Instrumentation Engineers.

Regularized super-resolution reconstruction of images using wavelet fusion

This paper presents a wavelet-based computationally efficient implementation of the Linear Minimum Mean Square Error (LMMSE) algorithm in image super-resolution. The image super-resolution reconstruction problem is well-known to be an ill-posed inverse problem of large dimensions. The LMMSE estimator to be implemented in the image super-resolution reconstruction problem requires an inversion of a very large dimension matrix, which is practically impossible. Our suggested implementation is based on breaking the problem into four consecutive steps, a registration step, a multi-channel LMMSE restoration step, a wavelet-based image fusion step and an LMMSE image interpolation step. The objective of the wavelet fusion step is to integrate the data obtained from each observation into a single image, which is then interpolated to give a high-resolution image. The paper explains the implementation of each step. The proposed implementation has succeeded in obtaining a high-resolution image from multiple degraded observations with a high PSNR. The computation time of the suggested implementation is small when compared to traditional iterative image super-resolution algorithms.

Wavelet fusion: a tool to break the limits on lmmse image super-resolution

This paper presents a noniterative regularized inverse solution to the image interpolation problem The suggested solution is based on the segmentation of the image to be interpolated to overlapping blocks and interpolating each block separately The purpose of the overlapping of blocks is to avoid edge effects A global regularization parameter is used in interpolating each block In this suggested implementation, a single matrix inversion process of moderate dimensions is required in the whole interpolation process The suggested solution avoids the large computational complexity due to the matrices of large dimensions involved in the interpolation process The performance of this suggested image interpolation algorithm is compared to the standard iterative regularized interpolation scheme and to polynomial interpolation schemes such as the cubic spline image interpolation algorithm

M.M. Hadhoud

Papers

Sectioned implementation of regularized image interpolation