The combination of low-level image processing algorithms with CCD/CMOS based VLSI electronics makes possible the realization of a smart image sensor, which is capable of carrying out 2D feature detection on the image plane. The device presented is a low-cost, fast and small solution for real-time, low-level image processing problems.

We present a new approach to segmentation of 3-D shapes that initializes and then optimizes a 3-D surface model given only the data and a very small number of 3-D seed points and corresponding surface normals. This is a valuable capability for medical, robotic and cartographic applications where such seed points can be naturally supplied. In effect, the surface model is clamped onto the object boundary in manner reminiscent of a Velcro being closed. We develop the method's mathematic framework and show preliminary results using volumetric medical data.>

Moment invariants are important shape descriptors in computer vision. In this paper rules are presented to form complete sets of rotational invariants of arbitrary order given complex Zernike moments. The relevance of the pseudoinvariants is shown by inverting the rotational invariants to reconstruct the normalized image pattern.>

We propose a snake-based approach that lets a user specify only the distant end points of the curve he wishes to delineate without having to supply an almost complete polygonal approximation. We achieve much better convergence properties than those of traditional snakes by using the image information around these end points to provide boundary conditions and by introducing an optimization schedule that allows the snake to take image information into account first only near its extremities and then, progressively, towards its center. These snakes could be used to alleviate the often repetitive task practitioners have to face when segmenting images by abolishing the need to sketch a feature of interest in its entirety, that is, to perform a painstaking, almost complete, manual segmentation.>

In this paper, we present a new snake-based method to delineate contours where the user has to specify only the two distant end points without having to supply an almost complete polygonal approximation. We achieve much better convergence properties than those of traditional snakes by propagating the image information along the curve from both end points towards its center. We use our new method to outline curved object boundaries and for interactive road delineation.

Length estimation of three dimensional digitized curves is considered. The three dimensional chain code representation is assumed. It is shown that previously suggested length estimators are biased, and alternative simple estimators that possess desired optimality properties are developed. To support optimal design of three dimensional length estimators, useful statistical properties of three dimensional chain encoded digital straight lines are derived. Although this paper focuses on simple estimators, the suggested approach can be used to design more complicated three dimensional length estimators.>

In contrast to acquisition-based noise reduction methods a postprocess based on anisotropic diffusion is proposed. Extensions of this technique support 3-D and multiecho magnetic resonance imaging (MRI), incorporating higher spatial and spectral dimensions. The procedure overcomes the major drawbacks of conventional filter methods, namely the blurring of object boundaries and the suppression of fine structural details. The simplicity of the filter algorithm permits an efficient implementation, even on small workstations. The efficient noise reduction and sharpening of object boundaries are demonstrated by applying this image processing technique to 2-D and 3-D spin echo and gradient echo MR data. The potential advantages for MRI, diagnosis, and computerized analysis are discussed in detail.

An algorithm is presented for the segmentation of volume data acquired in medicine by computer tomography (CT) or magnetic resonance (MR) imaging. The algorithm is based on edge detection by a 3-D implementation of the difference of Gaussians or the Laplace of Gaussians operator followed by an object refinement procedure. This consists of matched filters and/or a decision strategy which is included in a 3-D connected-component labelling procedure. Results from the analysis of segmented CT and MR data are presented utilizing an advanced display facility and quantitative 3-D analysis techniques.>