An image fusion algorithm based on multiscale analysis along arbitrary orientations is presented. After a steerable dyadic wavelet transform decomposition of multi-sensor images is carried out, the maximum local oriented energy is determined at each level of scale and spatial position. Maximum local oriented energy and local dominant orientation are used to combine transform coefficients obtained from the analysis of each input image. Reconstruction is accomplished from the modified coefficients, resulting in a fused image. Examples of multi-sensor fusion and fusion using different settings of a single sensor are demonstrated.

The aim of the paper is to introduce a new pattern recognition method of multiresolution representation and analysis of ECG waveforms. The multiresolution representation is based on filtering the curvature of the curve with continuum of Gaussian filters where Gaussian standard deviation increases, and on extracting of extrema points in filtered versions of the curvature (scale-space filtering). The original curve is then segmented at each scale into linear parts with regard to the extracted extrema points. After segmentation and linking segments between scales, shape is represented qualitatively in a hierarchical tree form holding information on coarser and finer details of shape. Different methods of tree form analysis can be applied to data compression, classification of heart beats or tine structure analysis We introduce a method of multiresolution representation. The fast computation scheme and transformation into hierarchical structure are described. In addition to the method of representation data compression method is proposed. Comparision to the AZTEC data compression method is also given. 0276-6574/91/0000/0547$01 .OO 0 1991 IEEE

We present a n i n teractive s c heme for processing of digital mammograms relying upon a steerable dyadic wavelet transform. Coe cients of the translation and rotationinvariant transform are interactively processed before an inverse transform is applied. Analysis is carried out at dyadic scales and along arbitrary orientations. Local orientation is computed at each level of scale and spatial position and formulated into criteria for including or excluding speci c orientations for contrast enhancement and enhancing locally radiating structures. Transform coe cients that were selected for contrast enhancement are modi ed by a piecewise linear enhancement function. The presented scheme is exible enough to enable e cient position, scale, and orientation based interactive processing and analysis.

This paper describes two approaches for accomplishing interactive feature analysis by overcomplete multiresolution representations. We show quantitatively that transform coefficients, modified by an adaptive non-linear operator, can make more obvious unseen or barely seen features of mammography without requiring additional radiation. Our results are compared with traditional image enhancement techniques by measuring the local contrast of known mammographic features. We design a filter bank representing a steerable dyadic wavelet transform that can be used for multiresolution analysis along arbitrary orientations. Digital mammograms are enhanced by orientation analysis performed by a steerable dyadic wavelet transform. Arbitrary regions of interest (ROT) are enhanced by Deslauriers-Dubuc interpolation representations on an interval. We demonstrate that our methods can provide radiologists with an interactive capability to support localized processing of selected (suspicious) areas (lesions). Features extracted from multiscale representations can provide an adaptive mechanism for accomplishing local contrast enhancement. By improving the visualization of breast pathology we can improve chances of early detection while requiring less time to evaluate mammograms for most patients.

Robust and reliable edge detection is an important step for accomplishing automatic detection of heart wall boundaries in echocardiograms. We present a n e d g e detection algorithm that makes use of both spatial and temporal information. Our algorithm is comprised of (1) a 3-D discrete dyadic wavelet transform carried out on a sequence of images, (2) edge detection that is carried out by maxima detection and a search strategy for maxima curves within the transform space. Using detected edges and \a priori" knowledge of cardiographic features we demonstrate the performance of fully automatic detection of epicardial and endocardial boundaries along the posterior and anterior walls in 2-D short-axis echocardiographic image sequences.