By Topic

Communications, Speech and Vision, IEE Proceedings I

Issue 1 • Date Feb. 1993

Filter Results

Displaying Results 1 - 11 of 11
  • Adaptive filter for two-dimensional Gabor transformation and its implementation

    Publication Year: 1993 , Page(s): 2 - 6
    Cited by:  Papers (1)
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (592 KB)  

    An adaptive filter that enables coefficient computation of the Gabor expansion while employing the least mean-squared algorithm for complex signals is described. A significant simplification of the filter structure and the use of FFT algorithms contribute to a fast and efficient determination of the coefficients when compared with known algorithms for Gabor computation. Based on these results, the authors propose a hardware realisation using a CORDIC processor. Computer simulations indicate that sufficient precision and a fast convergence of the coefficients can be obtained.<> View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Skeletonisation as model-based feature detection

    Publication Year: 1993 , Page(s): 7 - 11
    Cited by:  Patents (1)
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (460 KB)  

    Two closely related methods for skeletonisation via a Euclidean distance transform are presented. First from an observation on the response of the human visual system to a grey level image of the transform, convolution with the Marr-Hildreth operator is proposed. Secondly, it is suggested that skeletonisation can be performed by convolution of the distance transform with a function designed to detect the occurrence of a specific geometric model, or feature, in a way similar to that used in contemporary edge detection algorithms. Examples of the technique are shown and the results discussed.<> View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Classifying images using goal-seeking neural network architectures

    Publication Year: 1993 , Page(s): 12 - 18
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (530 KB)  

    New results, which have been achieved by using neural network architectures for two-dimensional image classification based on the goal-seeking neuron (GSN), are presented. A number of important practical issues concerning mapping topologies and the parallel implementation of GSN-based architectures are also investigated, together with a proposal for the development of a related neurally based feature extractor to be used as a front-end processor in a fully integrated Boolean network architecture.<> View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Signal-processing based method for acquiring very high resolution images with multiple cameras and its theoretical analysis

    Publication Year: 1993 , Page(s): 19 - 24
    Cited by:  Papers (2)
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (670 KB)  

    The authors describe VHD (very high definition) image media competing in spatial resolution with the familiar film media as a new digital image media concept, and discuss a problem of image acquisition as a key technology for achieving VHD image systems. Towards the development of a VHD image acquisition system, the work presents a new signal-processing based approach using multiple different cameras. The image acquisition approach, processing and integrating multiple images taken simultaneously with multiple different cameras, produces an improved spatial resolution image with sufficiently high signal-to-noise ratio. Theoretical analysis and experimental simulations show clearly the improvement in the high frequencies and details.<> View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 3-D motion estimation of human head for model-based image coding

    Publication Year: 1993 , Page(s): 26 - 35
    Cited by:  Papers (2)  |  Patents (3)
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (1137 KB)  

    Model-based image coding applied to interpersonal communication achieves very low bit-rate image transmission. To accomplish it, accurate three-dimensional (3-D) motion estimation of a speaker is necessary. A new method of 3-D motion estimation is presented, consisting of two steps. In the first, facial contours and feature points of a speaker are extracted using filtering and snake algorithms. Five feature points on a speaker's facial image are tracked between consecutive picture frames, which gives 2-D motion vectors of the feature points. Then, in the second step, the 3-D motion of a speaker's head is estimated using a three-layered neural network model, after training with many possible motion patterns of the human head using an existing 3-D general shape model. Experimental results show that the method not only achieves good results but is also more robust than existing methods.<> View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Graph-theoretical approach to colour picture segmentation and contour classification

    Publication Year: 1993 , Page(s): 36 - 45
    Cited by:  Papers (8)  |  Patents (6)
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (1028 KB)  

    The procedure aims at identifying, extracting and classifying visually important features on the image plane, such as regions of homogeneous colour and chromatic transitions. Well established principles of colour theory and graph theory are combined to obtain a unified representation of a colour picture. The picture is represented by means of a weighted graph, constructed so as to reflect the specification of the colour space employed as well as important relationships between picture elements. A spanning tree of the graph is obtained by iteratively minimising a specific picture distortion measure. Each partition comprises disjoint regions containing elements with similar attributes. Region contours defined by such partitions form a hierarchy. It is shown that, when texture is combined with colour as joint similarity attributes of regions, an improved hierarchical description of contours is possible.<> View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Distributed propagation of a-priori constraints in a Bayesian network of Markov random fields

    Publication Year: 1993 , Page(s): 46 - 55
    Cited by:  Papers (4)  |  Patents (2)
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (940 KB)  

    Bayesian networks of Markov random fields (BN-MRFs) are proposed as a technique for representing and applying a-priori knowledge at different abstraction levels inside a distributed image processing framework. It is shown that this approach, thanks to the common probabilistic basis of the two techniques, is able to combine in a natural way causal inference properties at different abstraction levels as provided by Bayesian networks with optimisation criteria usually applied to find the best configuration for an MRF. Examples of two-level BN-MRFs are given, where each node uses a coupled Markov random field which has to solve a coupled restoration and segmentation problem. Experiments are concerned with expert-driven registered segmentation and tracking of regions from image sequences.<> View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fast lattice-based gain-shape vector quantisation for image-sequence coding

    Publication Year: 1993 , Page(s): 56 - 66
    Cited by:  Papers (4)  |  Patents (4)
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (1493 KB)  

    A fast lattice-based gain/shape vector-quantisation method (FLGSVQ) is presented. The proposed technique combines the basic ideas of gain/shape vector quantisation (GSVQ) with lattice codes to offer an encoding process which is extremely fast compared with the conventional GSVQ. A simple single-/two-stage coding system based on lattice quantisation is tested for interframe predictive coding of image sequences. Simulation results are provided to compare the performance of the proposed method with the conventional LBG-designed vector quantisation. These results, along with subjective evaluations, clearly demonstrate that lattice quantisation can be competitive with vector quantisation in terms of signal-to-noise performance, only at a very small fraction (4%) of the vector-quantiser complexity.<> View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Theory and design of multidimensional QMF sub-band filters from 1-D filters and polynomials using transforms

    Publication Year: 1993 , Page(s): 67 - 71
    Cited by:  Papers (1)
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (388 KB)  

    The general theory of designing multidimensional quadrature mirror filters (QMF) for use in sub-band coding systems using the McClellan transform is presented. It was recently shown that the McClellan transform could be used to generate 2-D diamond-shape QMF filters (de Lameillieure et al. 1991). The proofs of the diamond-shape case are formalised and generalised to other shapes, sampling rasters and dimensions. It is possible and even more convenient to design QMF filter banks by performing transformations on a class of real-valued polynomials. Examples are given of two-dimensional diamond and fan-shape filters and three-dimensional tetrad filters designed using this transformation technique.<> View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recognition of polyhedral objects using triangle pair features

    Publication Year: 1993 , Page(s): 72 - 85
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (1555 KB)  

    The authors consider the problem of model-based recognition of polyhedral objects from a single perspective view. A hypothesise-verify paradigm based on the use of high level knowledge constraints derived from local shape properties is presented. In the recognition system, two high level features, namely triangle pair and quadrilateral are employed as key features for model invocation and hypothesis generation. A verification process for performing a detailed check on the model to scene correspondences is developed. Two geometrical constraints, namely distance and angle constraints are employed. A list of closed polygons and C-triple pairs extracted from a 2D intensity image by means of edge and intermediate feature detection process is used as an input to the matching system. The intermediate feature grouping process starts by identifying junctions and forming triples which are then scanned by a procedure which connects them into meaningful geometric structures. Extensive experimental results are reported.<> View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • New technique for 3D artery modelling by noninvasive ultrasound

    Publication Year: 1993 , Page(s): 86 - 94
    Cited by:  Papers (1)
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (1362 KB)  

    The approach aims to improve visualisation of the artery under consideration for later use in monitoring disease within it. The technique is based on analysing a series of transverse noninvasive ultrasound scans. Noninvasive transverse scanning allows a circle to be used as an appropriate model to determine the arterial wall data in each slice. This circle is extracted from the edge magnitude information provided by a version of the Canny edge-detection operator and is then located using an implementation of the Hough transform tailored to determine the contour which best fits the arterial data. The deviation from the circle provides the arterial wall template except where data is absent when the approximation itself is used. By extracting the template from successive ultrasound images in in vivo studies 3D pictures of vessels, initially of the carotid artery and the bifurcation, have been developed. The model's accuracy has been validated by a test object study.<> View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.