By Topic

IEE Proceedings - Vision, Image and Signal Processing

Issue 4 • Aug 1994

Filter Results

Displaying Results 1 - 9 of 9
  • Some investigations on neural processing of scattered light in water quality assessment

    Publication Year: 1994, Page(s):261 - 266
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (396 KB)

    Applications of artificial neural networks to in situ assessment of water quality are considered by means of an online optical scatter nephelometer. Light scattered by suspensions of oil in water is investigated for three different oils in the concentration range 0-100 parts per million by volume. An artificial neural network is designed to recognise the oil species and output its concentration to... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Partitioned mixture distribution: an adaptive Bayesian network for low-level image processing

    Publication Year: 1994, Page(s):251 - 260
    Cited by:  Papers (3)  |  Patents (3)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (680 KB)

    Bayesian methods are used to analyse the problem of training a model to make predictions about the probability distribution of data that has yet to be received. Mixture distributions emerge naturally from this framework, but are not ideally matched to the density estimation problems that arise in image processing. An extension, called a partitioned mixture distribution is presented, which is essen... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Supervised and unsupervised learning in radial basis function classifiers

    Publication Year: 1994, Page(s):210 - 216
    Cited by:  Papers (19)  |  Patents (3)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (560 KB)

    The paper considers a number of strategies for training radial basis function (RBF) classifiers. A benchmark problem is constructed using ten-dimensional input patterns which have to be classified into one of three classes. The RBF networks are trained using a two-phase approach (unsupervised clustering for the first layer followed by supervised learning for the second layer), error backpropagatio... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Original approach for the localisation of objects in images

    Publication Year: 1994, Page(s):245 - 250
    Cited by:  Papers (39)  |  Patents (2)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (432 KB)

    An original approach is presented for the localisation of objects in an image which approach is neuronal and has two steps. In the first step, a rough localisation is performed by presenting each pixel with its neighbourhood to a neural net which is able to indicate whether this pixel and its neighbourhood are the image of the search object. This first filter does not discriminate for position. Fr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Two original weight pruning methods based on statistical tests and rounding techniques

    Publication Year: 1994, Page(s):230 - 237
    Cited by:  Papers (1)  |  Patents (2)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (556 KB)

    The authors focus on the use of neural networks to approximate continuous decision functions. In this context, the parameters to be estimated are the synaptic weights of the network. The number of such parameters and the quantity of data (information) available for training greatly influence the quality of the solution obtained. A previous study analysed the influence and interaction of these two ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robot path planning using VLSI resistive grids

    Publication Year: 1994, Page(s):267 - 272
    Cited by:  Papers (9)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (448 KB)

    The resistive grid algorithm for mobile robot path planning is described. A major advantage of the method is that it is capable of a fine-grained parallel analogue VLSI implementation, which offers a fast, low-power solution to the problem of mobile robot navigation. The results from a small-scale test chip are presented, together with their implications for scaling up to a full-sized path-plannin... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Novelty detection and neural network validation

    Publication Year: 1994, Page(s):217 - 222
    Cited by:  Papers (67)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (460 KB)

    One of the key factors which limits the use of neural networks in many industrial applications has been the difficulty of demonstrating that a trained network will continue to generate reliable outputs once it is in routine use. An important potential source of errors is novel input data; that is, input data which differ significantly from the data used to train the network. The author investigate... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Contextual image labelling with a neural network

    Publication Year: 1994, Page(s):238 - 244
    Cited by:  Papers (2)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (472 KB)

    A neural network with a multilayer perceptron architecture is shown to be capable of labelling the visible objects in colour images of urban and rural outdoor scenes. The two problems of segmentation and recognition are separated by using `ideal' segmentations, allowing the performance of the recognition method to be studied independently of the effects of using an imperfect real segmentation proc... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Decision-theoretic approach to visual inspection using neural networks

    Publication Year: 1994, Page(s):223 - 229
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (488 KB)

    The Bayesian real-time network (BARTIN) is applied to solving a visual-inspection problem requiring translation, rotation and scale (TRS) invariance. The system is capable of classifying n-fold symmetric engineering parts from near-axial views which may contain more than one part. It is evaluated and compared with other approaches using real visual-inspection data. A novel TRS-invariant preprocess... View full abstract»

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