scispace - formally typeset
Search or ask a question

Showing papers on "Contextual image classification published in 1986"


Journal ArticleDOI
TL;DR: A set of computer simulation results shows that the Foley-Sammon transform provides good classification performance and that a proper number of training images is essential to ensure a low error rate of classification.
Abstract: Application of the Foley-Sammon transform to image classification is discussed. The computing procedures of the transform are presented for the case in which the total number of training images (M) is smaller than the dimension of the images to be classified (N). A set of computer simulation results shows that the Foley-Sammon transform provides good classification performance and that a proper number of training images is essential to ensure a low error rate of classification.

94 citations


Book ChapterDOI
01 Sep 1986
TL;DR: This chapter shows how the MRF’s are used as texture image models, region geometry models, as well as edge models, and how they have been successfully used for image classification, surface inspection, image restoration, and image segmentation.
Abstract: This chapter deals with the problem of image modelling through the use of 2D Markov Random Field (MRF). The MRF’s are parametric models with a noncausal structure where the various dependencies over the plane is described in all directions. We first show how the MRF’s are used as texture image models, region geometry models, as well as edge models.Then we show how they have been successfully used for image classification, surface inspection, image restoration, and image segmentation.

33 citations


Journal ArticleDOI
TL;DR: In this article, the classification decision is formed on the basis of the cross correlation between a photon-limited input image and a reference function stored in computer memory, and expressions for the statistical parameters of the low-light-level correlation signal are given and verified experimentally.
Abstract: An imaging photon-counting detector is used to achieve automatic sorting of two image classes. The classification decision is formed on the basis of the cross correlation between a photon-limited input image and a reference function stored in computer memory. Expressions for the statistical parameters of the low-light-level correlation signal are given and are verified experimentally. To obtain a correlation-based system for two-class sorting, it is necessary to construct a reference function that produces useful information for class discrimination. An expression for such a reference function is derived using maximum-likelihood decision theory. Theoretically predicted results are used to compare on the basis of performance the maximum-likelihood reference function with Fukunaga–Koontz basis vectors and average filters. For each method, good class discrimination is found to result in milliseconds from a sparse sampling of the input image.

22 citations


Proceedings ArticleDOI
15 Oct 1986
TL;DR: A new shape classification scheme is proposed which uses the image processing formalism of associative memory mappings and this scalar transform technique is applied to two-dimensional images, applicable to both full- and partial-view recognition problems.
Abstract: In this paper a new shape classification scheme is proposed which uses the image processing formalism of associative memory mappings. This scalar transform technique is applied to two-dimensional (2D) images. The shape description is the centroidal profile which is the radius as a function of arc length parametrization of the boundary. Other one-dimensional (1D) representations are also discussed. The scheme is applicable to both full- and partial-view recognition problems. The restoration of degraded images, either due to occlusion or other forms of information loss, is optimal in the least squares sense.

8 citations


Proceedings ArticleDOI
21 Apr 1986
TL;DR: An algorithm for texture characterization based upon curvilinear integration of grey tone signal along some predefined directions is presented, and good classification performances are obtained on quite different pictures.
Abstract: We present an algorithm for texture characterization based upon curvilinear integration of grey tone signal along some predefined directions.In the context of image segmentation, we compare the performances of this very simple technique with two other ones : texture features by second-order cooccurrence probabilities, and texture features by local one dimensional histograms. Good classification performances are obtained on quite different pictures.© (1986) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

6 citations


Proceedings ArticleDOI
21 Apr 1986
TL;DR: The potential of a circular sampling technique that may replace the pattern recognition process with one processing step and one comparison step is examined.
Abstract: Attempts to automate zooplankton measurement dates back to [1]. More recently, image processing and feature extraction techniques have been used as part of a pattern recognition process implemented with multicomputer systems. This paper examines the potential of a circular sampling technique that may replace the pattern recognition process with one processing step and one comparison step. Circular sampling is approximated by rearranging pixels to form a one dimensional sequence and is used for comparison with base images. The properties of these sequences are examined, using images from six major zooplankton categories, and their classification accuracy is investigated.

4 citations


Proceedings ArticleDOI
15 Oct 1986
TL;DR: A novel method for two-dimensional pattern recognition and feature extraction, applicable to microprocessor-based vision systems, is presented which employs fractal geometric analysis, supported by experimental verification of a ship silhouette recognition algorithm.
Abstract: A novel method for two-dimensional pattern recognition and feature extraction, applicable to microprocessor-based vision systems, is presented which employs fractal geometric analysis. Fractal contour transformation and transform correlation techniques are discussed in relation to their effectiveness in classifying rotationally deformed images over a wide resolution range. vractal geometric analysis exhibits several attributes: 1. position-, size-, and rotation-invariance is preserved in the absence of image coordinate transformation, 2. invariance to out-of-plane rotation is exhibited over the range ±60° of broadside, and 3. out-of-plane rotation can be computed from imagery and quantified in terms of the fractal dimension. This work is supported by experimental verification of a ship silhouette recognition algorithm. Results are presented in terms of recognition ratio and computational load.

3 citations


Proceedings ArticleDOI
21 Apr 1986
TL;DR: This paper presents an application of textural analysis to high resolution SPOT satellite images to improve classification results, i.e. image segmentation in remote sensing.
Abstract: Textural analysis is now a commonly used technique in digital image processing. In this paper, we present an application of textural analysis to high resolution SPOT satellite images. The purpose of the methodology is to improve classification results, i.e. image segmentation in remote sensing. Remote sensing techniques, based on high resolution satellite data offer good perspectives for the cartography of littoral environment. Textural information contained in the pan-chromatic channel of ten meters resolution is introduced in order to separate different types of structures. The technique we used is based on statistical pattern recognition models and operates in two steps. A first step, features extraction, is derived by using a stepwise algorithm. Segmentation is then performed by cluster analysis using these extracted. features. The texture features are computed over the immediate neighborhood of the pixel using two methods : the cooccurence matrices method and the grey level difference statistics method. Image segmentation based only on texture features is then performed by pixel classification and finally discussed. In a future paper, we intend to compare the results with aerial data in view of the management of the littoral resources.

2 citations


Proceedings ArticleDOI
26 Mar 1986
TL;DR: A scheme is presented for segmenting textured images using a filter design approach and classification accuracies of more than 90% are achieved using a set of four textures from Brodatzl album of textures.
Abstract: A scheme is presented for segmenting textured images using a filter design approach. The discrete Fourier transform (DFT) of each texture in the training set is computed. Using the DFT information, an empirical method for evaluating the texel size (in pixels) for the training set of textures is given. A separable filter template of a particular texel size is designed for each texture based on the DFT. Each textured image is then convolved with these sets of filter templates. A training feature vector is stored in the classifier for each texture by summing the outputs of the filtered images. For texture classification or segmentation, a texture mosaic consisting of one or more textures in the data set is convolved with the same set of filter templates applied in the training procedure. Each filtered image output is summed within image blocks of a particular texel size. A feature vector is computed for each block and fed into a minimum distance classifier. Classification accuracies of more than 90% are achieved using a set of four textures from Brodatzl album of textures.

1 citations


Proceedings ArticleDOI
15 Oct 1986
TL;DR: A new approach based on the Hough method of line detection is introduced,based on the relative orientation and location of the lines within the texture, which classifies periodic textures that consist of mostly straight lines.
Abstract: Texture is one of the important image characteristics and is used to identify objects or regions of interest The problem of texture classification has been widely studied Some texture classification approaches use Fourier power-spectrum features, while others are based on first and second-order statistics of gray level differences Periodic textures that consist of mostly straight lines are of particular interest In this paper, a new approach based on the Hough method of line detection is introduced This classification is based on the relative orientation and location of the lines within the texture Experimental results will also be presented

Proceedings ArticleDOI
26 Mar 1986
TL;DR: Flexible template matching as mentioned in this paper automatically brings the unknown target image and each one, in turn of a set of class-defining template images (one per class) into mutual registration, without requiring any prior knowledge of the differences of view that may exist between them.
Abstract: The target recognition problem is complicated by the fact that target is doubly "unknown". The sensed image is obviously a function of target class: a fundamental problem of target recognition has been that the form of the sensed image is also a strong function of target "geometry". The differences of class, upon which classification necessarily depends, may therefore be com-pletely swamped by the irrelevant differences of view. Human recognition of targets is generally unaffected by this problem. A new method of Automatic Target Recognition, called Flexible Template Matching, is described. It eliminates "geometry" from the recognition problem, by means of a new registration algorithm. This automatically brings the unknown target image and each one, in turn, of a set of class-defining template images (one per class) into mutual registration, without requiring any prior knowledge of the differences of view that may exist between them. The elimination of all irrelevant differences of view (scale, position, rotation, aspect, etc) allows for an optimum match-decision to identify the one true template, based upon computation (using Bayes Formula) of the probability, for each template, that the observed match differences are a typical sample of the match-differences known to occur in a (registered) true match of the target and its template. Since the range and aspect of the target are provided as a by-product of the registration action, the match-error statistics used can be selected according to the observed position and orientation of the target.

Proceedings ArticleDOI
21 Apr 1986
TL;DR: Two groups of approaches based on orthogonal transforms, namely power spectral methods and methods using correlation masks, are considered and compared to show the close correspondence between the two groups of methods.
Abstract: In the domain of digital processing of textures orthogonal transforms are applicable to the characterization of structural properties and to texture discrimination and synthesis. Two groups of approaches based on orthogonal transforms, namely power spectral methods and methods using correlation masks, are considered and compared. The latter propose to match orthogonal basis vectors with the image structure. The degree of match expresses itself in the variance found at the output of the correlation masks for a limited image region. It is one of the aims of this paper to show the close correspondence between the two groups of methods. Common aspects comprise the use of orthogonal transforms, of windows of certain sizes and of quadrature and averaging in the process of feature extraction. The main difference with respect to attainable resolution and representation of structural detail is due to the recommended dimensions of the windows which has consequences for the interpretation of the features as well as for the domain of applicability. The power spectral methods produce features which are appropriate to characterize textures which humans tend to qualify as periodic, striped, grainy etc. The correlation methods are not tuned to extract all of these features but, due to the smaller primary window size, are able to find texture boundaries. The good classification results obtained with the use of the correlation masks suggests, because of the close relationship between the two concepts, a reappraisal of the suitability of spectral methods for texture analysis problems. On the basis of the comparison it is tried to further a deeper understanding of spectral analysis and to show how to better apply it for texture classification.