IEE Proceedings - Vision, Image and Signal Processing

The authors review the notion of multiwavelets and describe the use of the discrete multiwavelet transform (DMWT) in image fusion processing. Multiwavelets are extensions from scalar wavelets, and have several advantages in comparison with scalar wavelets. Multiwavelet analysis can offer more precise image analysis than wavelet multiresolution analysis. A novel fusion algorithm is presented for mu... View full abstract»

The design of a two-channel nonuniform-division filter (NDF) bank with infinite impulse response (IIR) analysis/synthesis filters and low group delay in the sense of L1 error criteria is considered. The problem formulation results in a nonlinear optimisation problem. Based on a variant of Karmarkar's algorithm, the optimisation problem is solved through a frequency sampling and iterativ... View full abstract»

In the traditional approach of block transform image coding, a large number of bits are allocated to the DC coefficients. A technique called DC coefficient restoration (DCCR) has been proposed to further improve the compression ability of block transform image coding by not transmitting the DC coefficients but estimating them from the transmitted AC coefficients. Images thus generated, however, ha... View full abstract»

The problem of phase image denoising through nonlinear (NL) filtering is addressed. There are various imaging systems in which the phase information is utilised to generate useful imaging data. However, the presence of noise makes difficult to obtain the appropriate phase image. The authors apply NL vector filtering techniques to denoise the complex data from which the phase image is extracted. A ... View full abstract»

When designing boundary filters for multiwavelets, perfect reconstruction and moment conditions are two of the most important criteria to be considered. Since the filter coefficients of multiwavelets are expressed in the form of matrices, the moment conditions for multiwavelets do not relate to the filter coefficients in a simple way as for scalar wavelets. The authors first formulate the moment c... View full abstract»

An eigenfilter approach is presented for designing 1-D and 2-D variable fractional delay FIR and all-pass filters. First, the coefficients of filters are expressed as a polynomial of the fractional delay parameter. Then, the optimal polynomial coefficients are obtained from the elements of the eigenvector corresponding to the minimum eigenvalue of a real, symmetric and positive definite matrix. Fi... View full abstract»

A new technique is presented for instantaneous blind signal separation from nonlinear mixtures using a general neural network based demixer scheme. The nonlinear demixer model follows directly from the general mixer model. A general mixer model is described which includes linear mixtures as a special case. In the second part the general framework for a demixer based on a feedforward multilayer per... View full abstract»

Texture analysis techniques are used to segment rough surfaces into regions of homogeneous texture. The performance of three rough surface classifiers was assessed and compared. The classifiers differ in their discrimination as well as in their input and computational requirements. Simulation and experiment were used to identify the limitations of the classifiers and to identify which classifier i... View full abstract»