Showing papers on "Segmentation published in 1985"
TL;DR: A general purpose performance measurement scheme for image segmentation algorithms that function in real-time distinguish this method from previous approaches that depended on an a priori knowledge of the correct segmentation.
Abstract: This paper introduces a general purpose performance measurement scheme for image segmentation algorithms. Performance parameters that function in real-time distinguish this method from previous approaches that depended on an a priori knowledge of the correct segmentation. A low level, context independent definition of segmentation is used to obtain a set of optimization criteria for evaluating performance. Uniformity within each region and contrast between adjacent regions serve as parameters for region analysis. Contrast across lines and connectivity between them represent measures for line analysis. Texture is depicted by the introduction of focus of attention areas as groups of regions and lines. The performance parameters are then measured separately for each area. The usefulness of this approach lies in the ability to adjust the strategy of a system according to the varying characteristics of different areas. This feedback path provides the means for more efficient and error-free processing. Results from areas with dissimilar properties show a diversity in the measurements that is utilized for dynamic strategy setting.
405 citations
TL;DR: A statistic for determining the number of different textures in the image is developed and demonstrated and a theory regarding the information processing strategies in human vision motivates the development of a texture feature space.
253 citations
TL;DR: By combining a nonparametric classifier, based on a clustering algorithm, with a quad-tree representation of the image, the scheme is both simple to implement and performs well, giving satisfactory results at signal-to-noise ratios well below 1.
186 citations
TL;DR: In this paper, the authors describe how companies in basic industries are shifting to speciality products in an effort to boost growth and profits, but such moves require often unfamiliar marketing skills, especially in segmentation.
Abstract: Many companies in basic industries are shifting to speciality products in an effort to boost growth and profits. But such moves require often unfamiliar marketing skills, especially in segmentation...
178 citations
TL;DR: The algorithm described here provides an efficient code for the boundary of each region by taking advantage of certain first-order constraints related to the segmentation algorithm, the result being an asymptotic decrease in the number of bits per contour point.
157 citations
TL;DR: Three mechanisms are outlined which are sufficient to determine texture segmentation or discrimination and are compared with those proposed to occur in human visual texture discrimination.
Abstract: Three mechanisms are outlined which are sufficient to determine texture segmentation or discrimination. They are: (1) convolution of detector profiles with the input image; (2) impletion, where the perceptual 'filling in' of the input surface occurs via a nonlinear filtering operation on each detector's output (3) grouping, where areas are segregated according to their differences in detector responses after impletion occurs. These mechanisms are compared with those proposed to occur in human visual texture discrimination.
114 citations
TL;DR: In this article, the origin of formal propositions for segmenting industrial markets is presented and the industrial buying models and studies are shown to be a source of industrial market segmentation variables.
67 citations
TL;DR: In this paper, a data analysis approach and case history showing how the researcher can segment individuals into different dusters, with panelists falling into the same cluster exhibiting similar hedonic responses to stimuli.
Abstract: This paper illustrates a data analysis approach and case history showing how the researcher can segment individuals into different dusters, with panelists falling into the same cluster exhibiting similar hedonic responses to stimuli. The segmentation procedure suggests that some of the variability traditionally observed with hedonic responses may result from averaging together ratings assigned by individuals who belong in different hedonic segments.
65 citations
Patent•
30 Oct 1985TL;DR: In this paper, the various unit patterns are segmented, and each unit pattern is identified to be a partial pattern, linked pattern, etc., so that each character is recognized on a basis of total judgement, whereby ambiguity of segmentation is resolved.
Abstract: Pattern segmentation and recognition in which hand-written characters are transformed electrically into 2-dimensional image patterns, wherein if ambiguity exists in segmenting a unit pattern including a character from the image patterns, character recognition is not made compulsively, but a plurality of possible unit patterns are first established. Then, the various unit patterns are segmented, and each unit pattern is identified to be a partial pattern, linked patterns, etc., so that each character is recognized on a basis of total judgement, whereby ambiguity of segmentation is resolved.
64 citations
Book•
8 May 1985
TL;DR: In this paper, the authors present a model of market segmentation models of the communication process, measuring attitudes and images, and developing effective communications strategies to conduct attitude segmentation research.
Abstract: Premises of Market Segmentation Models of the Communication Process Measuring Attitudes and Images Constructing an Image Measurement Tool Developing Effective Communications Strategies Conducting Attitude Segmentation Research Benefit Segmentation Premises Benefit Segmentation Methodology Interpreting Segmentation Study Results Presenting Results and Beginning Follow-Through Activities Copy Research Follow-Through Media Planning and Other Forms of Follow-Through Successful Benefit Segmentation Case Histories An Overview of Attitude Segmentation Research Appendixes Author Index Subject Index.
52 citations
Patent•
24 Apr 1985TL;DR: In this paper, a coarse or rough segmentation apparatus is developed for use in a sensor system for analyzing half-tone images, which is based on the pipeline principle, where edges of an object are represented in the form of a sequence of high contrast as compared with the surroundings.
Abstract: A coarse or rough segmentation apparatus has been developed for use in a sensor system for analyzing half-tone images. In contrast with previously employed methods, the apparatus is based on the pipeline principle. In the image picked up by the camera, edges of an object are represented in the form of a sequence of points of high contrast as compared with the surroundings. These edges are initially sought out and tracked by so-called edge tracking. Subsequently, in a rough or coarse segmentation, this line is divided into as large as possible contiguous pieces or sections of equal curvature and pieces or sections with a strong directional change.
Patent•
16 Jan 1985TL;DR: In this paper, a real-time digital image enhancement system for performing the image enhancement segmentation processing required for a real time automated system for detecting and classifying surface imperfections in hot steel slabs.
Abstract: The disclosure relates to a real time digital image enhancement system for performing the image enhancement segmentation processing required for a real time automated system for detecting and classifying surface imperfections in hot steel slabs. The system provides for simultaneous execution of edge detection processing and intensity threshold processing in parallel on the same image data produced by a sensor device such as a scanning camera. The results of each process are utilized to validate the results of the other process and a resulting image is generated that contains only corresponding segmentation that is produced by both processes.
TL;DR: Two segmentation methods for segmenting stacked seismic data into zones of common signal character based on texture analysis are described and their performance is demonstrated on a line of seismic data from the Gulf of Mexico that had been manually segmented.
TL;DR: A software package for analysis of liver tissue images has been developed by combining some newly developed algorithms with other techniques, including the converging squares algorithm for location of cell nuclei, and the wedge filter technique for nuclei segmentation.
Abstract: Image analysis techniques are described for the automatic detection, segmentation, feature description, and classification of tissue components, in liver tissue images. The result of the analysis is a quantitative description of the tissue, based on statistics of the components. A software package for analysis of these images has been developed by combining some newly developed algorithms with other techniques. The newly developed algorithms include the converging squares algorithm for location of cell nuclei, and the wedge filter technique for nuclei segmentation.
TL;DR: A phenomenological model for the representation of clinical EEGs is proposed and an algorithm for automatic EEG evaluation is described that consists of two steps, a segmentation process which isolates the elementary patterns, and a clustering procedure which groups similar patterns with each other.
TL;DR: The paper stresses the importance, for segmentation, of data integration from several sensors and data integration over time, particularly the use of motion, and of stating clearly the assumptions before developing or using a particular image segmentation algorithm.
TL;DR: A method of image segmentation known as pyramid linking was developed several years ago for segmenting images into gray level subpopulations and is applied here to the segmentation of optical flow fields.
5 Apr 1985
TL;DR: This report concentrates on textured-image segmentation using local texture-energy measures and user delimited training regions to identify regions that are similar to a target texture and dissimilar to other textures.
Abstract: The SLICE segmentation system identifies image regions that differ in gray-level distribution, color, spatial texture, or some other local property. This report concentrates on textured-image segmentation using local texture-energy measures and user delimited training regions. Knowledge of target textures or signatures is combined with knowledge of background textures by using histogram-similarity transforms to identify regions that are similar to a target texture and dissimilar to other textures.
TL;DR: In this paper, the authors expose common pitfalls in the practice of segmenting industrial markets and show how previous industrial segmentation research has been of limited managerial value, and present an operational approach to conducting industrial market segmentation.
Abstract: This article exposes common pitfalls in the practice of segmenting industrial markets and shows how previous industrial segmentation research has been of limited managerial value. An operational approach to conducting industrial market segmentation is presented and explained.
TL;DR: In this paper, individual variety seeking is shown to be a more meaningful partitioning criterion than simple aggregate brand switching, and the consumer's way of partitioning the market is suggested as a useful criterion for segmentation.
1 Jan 1985
TL;DR: This chapter is devoted to the presentation and, in some cases, the comparison, of some segmentation algorithms for nonstationary digital signals; the common feature of all these algorithms is real time (or quasi-real time) processing.
Abstract: This chapter is devoted to the presentation and, in some cases, the comparison, of some segmentation algorithms for nonstationary digital signals; the common feature of all these algorithms is real time (or quasi-real time) processing.
TL;DR: A technique incorporating a rotating neighbourhood is introduced and utilized for image enhancement and texture derivation and a threshold which adapts itself to an unknown noise level and image segmentation into individual objects is presented.
11 Jul 1985
TL;DR: A sequence of algorithms used to perform segmentation of aerial images of natural terrain for the purpose of extracting features pertinent to cartographic applications are described.
Abstract: The paper describes a sequence of algorithms used to perform segmentation of aerial images of natural terrain for the purpose of extracting features pertinent to cartographic applications. Topics include image filtering, labeling, automated editing and refinement of the segmentation within a resolution pyramid. These techniques are considered to be preprocessing activities which will, in general, require some editing by trained cartographers. The objective of this work is to minimize the tedium of feature extraction using algorithms that do not require excessive computational overhead.
IBM1
TL;DR: In this paper, the problem of detecting and segmenting objects in textured dark-field digital images for automated visual-inspection applications is addressed by correcting optical shading effects in conventional dark field microscopy.
Abstract: In this paper we deal with the problem of detecting and segmenting objects in textured dark-field digital imagery for automated visual-inspection applications. We first present a technique for correcting optical shading effects in conventional dark-field microscopy. After compensating for possible imperfections in the optical setting we address the problem of segmenting objects (defects) in textured dark-field images. The technique that we will follow is based on a sequential application of local operators, which serves the purpose of clustering the object and the background gray levels. This procedure can be considered an extension of average-thresholding-type techniques. Both algorithms for shading correction and object segmentation have fast implementations in general-purpose image-processing pipeline architectures, and therefore they are appealing to real-time computer vision applications. Computational examples showing the appropriateness of the shading-correction procedure as well as the effectiveness of the segmentation wil be discussed.
TL;DR: In this paper, image segmentation and object recognition using syntactic methods are investigated and the segmentation process is embedded in the parsing algorithm.
1 Apr 1985
TL;DR: It is shown that for segmentation problems the optimal Bayesian estimator is the maximizer of the posterior marginals, while for reconstruction tasks, the threshold posterior mean has the best possible performance.
Abstract: A very fruitful approach to the solution of image segmentation and surface reconstruction tasks is their formulation as estimation problems via the use of Markov random field models and Bayes theory. However, the Maximuma Posteriori (MAP) estimate, which is the one most frequently used, is suboptimal in these cases. We show that for segmentation problems the optimal Bayesian estimator is the maximizer of the posterior marginals, while for reconstruction tasks, the threshold posterior mean has the best possible performance. We present efficient distributed algorithms for approximating these estimates in the general case. Based on these results, we develop a maximum likelihood that leads to a parameter-free distributed algorithm for restoring piecewise constant images. To illustrate these ideas, the reconstruction of binary patterns is discussed in detail.
TL;DR: It is shown how the segmentation problem encountered in the interpretation of visual motion may be formulated as an ill-posed problem using the notion of maximum likelihood to provide a general framework and guide the choice of regularizing constraints.
TL;DR: In this article, a bank will only maintain its competitive edge if all customers are considered within the same perspective; if a segment is justifiable in its uniqueness and profitabilitty then it achieves viability.
Abstract: Market segmentation is a powerful and discriminating method of grouping customers categorically so that their needs may be properly addressed. Segmentation can be devised on a geographic, demographic, sociographic or psychographic basis, but a bank will only maintain its competitive edge if all customers are considered within the same perspective. Segments must be evenly balanced so as not to systematically create a vacuum in one market area; if a segment is justifiable in its uniqueness and profitabilitty then it achieves viability. Service benefits must be considered from the customer's perspective as well as the bank's own and, segmentation being a dynamic tool, it must be well thought out and executed with care.
TL;DR: A flexible automatic method for segmentation of meteorological satellite data using a multidimensional clustering procedure and its application to cloud data from the METEOSAT-1 satellite is described.
Abstract: The techniques of pattern recognition can provide unique information on cloud structures for cloud climatology programmes. We present a flexible automatic method for segmentation of meteorological satellite data using a multidimensional clustering procedure. The algorithm developed is described, together with its application to cloud data from the METEOSAT-1 satellite. If the data are transformed prior to segmentation by use of the Principal Components Transformation, the results compare favourably with those of alternative methods.
TL;DR: It is shown that by extracting event portions of the transient waveform through segmentation, a low order autoregressive model can provide an effective feature set for cluster analysis and event classification.