By Topic

Industrial Applications of Machine Intelligence and Vision, 1989., International Workshop on

Date 10-12 April 1989

Filter Results

Displaying Results 1 - 25 of 66
  • MIV-89 Proceedings of the International Workshop on Industrial Applications of Machine Intelligence and Vision (Seiken Symposium) (Cat. No.89TH0250-1)

    Publication Year: 1989
    Save to Project icon | Request Permissions | PDF file iconPDF (152 KB)  
    Freely Available from IEEE
  • Intelligent operator guidance systems beyond the prototype

    Publication Year: 1989 , Page(s): 249 - 252
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (412 KB)  

    The authors present the method used to enable a certain class of expert system, the intelligent operator guidance system, to progress from prototype to production system. They discuss the prototype system, prototype review, data-driven system development, the SHERPA (system for heuristic real-time process assistance), and knowledge-base maintenance.<> View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Connectionist approach to associative recall of 3D objects

    Publication Year: 1989 , Page(s): 229 - 234
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (280 KB)  

    A connectionist model that can store a sequence of various views of a three-dimensional object is presented. The model consists of four components, each of which is realized as a network or neuronlike elements. The model can store several 3-D objects in the same network in an overlapped manner. If the model is shown one view of a stored 3-D object, then a sequence of other views is recalled one by one. Since the storage is based on an associative matrix, the recall is possible even from an incomplete view. Instead of raw image data, a set of extracted features is stored for efficient storage View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • EXPERT ESSENCE: a new expert shell with automatic rule relaxation

    Publication Year: 1989 , Page(s): 199 - 204
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (364 KB)  

    An expert shell designed to meet practical design tradeoff problems is described. Unlike conventional production system approaches, the proposed system can automatically relax firing conditions of rules during the reasoning process. Metarules are introduced to represent the design expert's knowledge on how to relax the conditions. Moreover, an automatic knowledge-base refinement mechanism is proposed. From a given set of expert designer's reasoning examples, the system generates improved metarules. It makes possible automatic knowledge-base refinements from examples at reasonable cost. The proposed expert shell has been in experimental use for designing LSI logic View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • CSES: an approach to integrating graphic, music and voice information into a user-friendly interface

    Publication Year: 1989 , Page(s): 349 - 354
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (496 KB)  

    CSES/V1 (Customer Service Expert System Version 1) is an easy-to-use consultation system with an integrated multimedia user interface. CSES/V1 advises naive users which electric appliances are suitable for their daily life. To develop CSES/V1, the authors adopt frame-based knowledge representations, rule-based inference mechanisms, and the analytic hierarchy process, a non-Bayesian decision method. These mechanisms are implemented in OPS83 and the C language. The system combines (1) graphic information in NAPLPS codes to illustrate the pictures of electric appliances, (2) music in MIDI codes to attract users, and (3) voice explanation to advise users. These techniques make CSES/V1 a user-friendly and flexible system run on an MS/DOS-based microcomputer. The authors describe the design principles and the architecture of CSES/V1, focusing on the user interface View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new robust algorithm for estimating 3-D motion parameters over three frames of stereo images

    Publication Year: 1989 , Page(s): 235 - 238
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (272 KB)  

    In many industrial applications, it is very important to determine 3-D motion and the location of rigid objects in an environment. To meet the demands of practical use, a robust algorithm is proposed. By using three frames of stereo images, the algorithm avoids solving some nonlinear equations and involves simple linear computation. Both rotation parameters and translation parameters are obtained by the algorithm and a posteriori criterion for rejecting outliers in a set of triples is applied in order to make the estimates more robust and precise. Experiments with noisy synthetic data have shown that the results are quite good View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Rule based procedures for diagnosis and error recovery

    Publication Year: 1989 , Page(s): 88 - 93
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (248 KB)  

    A description is given of a knowledge-based approach to the error recovery problem, applied to real cases. Practical results are presented and discussed. The error recovery system was implemented in OPS5/VMS on a VAX 750 and tested for two cases. The first one is an electrical signaling relay subassembly; the second one is a weapon subassembly. The average duration for each operation of the recovery task is about 10 s. The generic expertise is the same for these two different applications View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new method of document structure extraction using generic layout knowledge

    Publication Year: 1989 , Page(s): 282 - 287
    Cited by:  Papers (8)  |  Patents (8)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (472 KB)  

    A method of document structure extraction using generic layout knowledge is described. With this method, it is possible to translate images of multimedia documents, i.e. documents that include pictures, graphics, and color information, to hypertext. Hypertext consists of decomposed elements linked with each other through some logical relationship. The principal components of the method are extraction of logical structure elements using a rectangular set operation and generation of hierarchical links of the logical structure between the extracted document elements. It is shown experimentally that the logical structure of a technical paper can be extracted View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Scene retrieval method for video database applications using temporal condition changes

    Publication Year: 1989 , Page(s): 355 - 359
    Cited by:  Papers (2)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (284 KB)  

    An algorithm is proposed to retrieve desired scenes from video sequences in a video database. The functions expressing the user's query, which describes a temporal condition change of object images, are used as search keys for retrieval. Retrieval is performed using primitive characteristic data (PCD) extracted from video images as database management data and a condition description factor generated from the user's query. A simple experiment confirms the effectiveness of the proposed method. Object locations generate the PCD values, whereas interpreted object motions are the retrieval keys. This method is effective for video database applications such as video libraries or video editing systems in which retrieval of a desired scene, specified by the user's query, is needed View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning with nonstatic paradigms in neural networks

    Publication Year: 1989 , Page(s): 72 - 75
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (272 KB)  

    Schemata, concepts, or any kind of knowledge contained in a neural network is usually represented in the interconnections of the constituent units. Learning in neural networks is regarded as modifying the strength of these interconnections. The authors define higher structured learning as not only modifying the weights but also the overall topology of the net, which implies that knowledge in a neural network is also represented in the architecture of the net. In the static paradigm, the definition of a neural network is similar to a variable declaration in a block-oriented language. The overall topology of the network is defined before learning takes place and is not altered during the learning phase. During learning only the values of the weights change. In a nonstatic paradigm units can be created at any time and can be connected arbitrarily with other units of the net. The authors demonstrate that using a nonstatic approach can improve learning View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Two interfaces in image database systems

    Publication Year: 1989 , Page(s): 22 - 27
    Cited by:  Papers (2)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (452 KB)  

    Two interfaces, called the data interface and the human interface, are used in image database systems to use effectively visual data such as images, graphics, documents, and drawings. The data interface is related to database capture (input) techniques. Data conversion efficiency, man-machine cooperative conversion, knowledge-based understanding, and flexible internal database model generation are emphasized. Several promising approaches towards the effective human interface are also suggested in combination with input technical level View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hitech chess: from master to senior master with no hardware change

    Publication Year: 1989 , Page(s): 12 - 21
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (744 KB)  

    Hitech is a chess computer program that has been the dominant force in computer chess from September 1985 to July 1988. During this time it has continued to use the same hardware and yet has improved its standing in the US chess community from being initially in the top 2% to its present top 0.5%. The author explains how this has been achieved, using better management of the resources that have been available View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A methodological approach to visual reasoning

    Publication Year: 1989 , Page(s): 50 - 55
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (492 KB)  

    The lack of a structured and theoretical approach to reasoning with visual information is a major obstacle for designing and implementing vision systems. The authors provide a four-step methodological approach to this problem: (1) visual reasoning problems are classified into several categories by their characteristics; (2) a particular class of problems, namely two-dimensional object recognition, is examined, and a system model for describing it is formally extracted; (3) several probability-related inference mechanisms are examined, and the one that is most appropriate for reasoning with the above model is chosen; and (4) a hybrid inference mechanism, the outcome of the above comparative study, is applied to a visual reasoning problem. They show how this approach can be used to overcome the difficulties in designing visual reasoning systems. The implications of this work are discussed View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Qualitative judgement of structural integrity

    Publication Year: 1989 , Page(s): 245 - 248
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (192 KB)  

    Fuzzy logic is used to distinguish one type of body (a plate) from others (rods and bars). Topologies are expressed using B-reps, and they are written in Prolog. To computerize the process, an examination of the relation of two bodies is carried out on the basis of length ratio View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Volume intersection algorithm with changing directions of views

    Publication Year: 1989 , Page(s): 309 - 314
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (424 KB)  

    An algorithm is proposed for reconstructing a three-dimensional object from multiple silhouettes. The silhouettes are represented as binary arrays, and the three-dimensional object is represented as a linear octree. The silhouettes are taken in any viewing direction lying on one of the three coordinate planes with reference to the front face of the object. The authors propose a method of choosing automatically a direction of view using the information from the current reconstruction. Thus, the proposed method is more advantageous than earlier approaches where the silhouettes are obtained for a set of prespecified directions independent of the objects. The authors gradually generate the geometrical properties of the object during the reconstruction and, hence, determine a direction so as to get a better reconstruction. A method to quantify the degree of accuracy is proposed View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • About 3D-reconstruction from technical drawings

    Publication Year: 1989 , Page(s): 46 - 49
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (256 KB)  

    The problem in document analysis of the conversion of technical drawings into descriptions that are appropriate to be manipulated by CAD systems is addressed. Ideas are presented for the construction of 3-D-geometric models from noisy and inaccurate images of simple workpiece drawings. The main ideas are the search for instances of primitive solids in the image, the incremental construction of partial descriptions based on these primitives, and their manipulation to achieve consistency with the image data. The implementation of the method is described, limitations are discussed, and the possible future development of the approach is outlined View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic animation control method influenced by spatial relationships

    Publication Year: 1989 , Page(s): 343 - 348
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (376 KB)  

    A description is given of an intelligent animation control method and an experimental three-dimensional animation system, AVA (Active Video Animation). The control method is driven by the user's commands and proceeds in two stages: (1) it automatically selects a motion goal based on the attributes of the object(s), and (2) it creates realistic motion control using the spatial relationship of the objects(s) to the simulated human. AVA is an advanced animation system that integrates the animation control method with a powerful command language. It frees the user from having to input low-level commands and creates realistic animation in near real time. Although AVA has yet to be fully developed, the authors present initial experimental results which indicate its potential View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A curve analysis approach to surface feature extraction from range image

    Publication Year: 1989 , Page(s): 223 - 228
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (528 KB)  

    A curve analysis approach to extracting surface curvature features from a range image is presented. The aim is to cope with the problem of the sensitivity of the derivative estimation to the noise and the conflict between the smoothness of the image required by the feature extraction procedures and the preservation of the local structure of the original image. It is based on the analysis of a one-dimensional image profile, because the surface curvature such as mean curvature and Gaussian curvature can be computed from the partial derivatives in the two axis directions. These derivatives should be estimated using only coherent data. This is achieved by curve fitting after curve segmentation. A measure is presented for postprocessing of segmentation that takes into account the pixel value in relation to a threshold and its neighboring context. The use of this measure significantly improves the quality of image segmentation View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Use of meta-knowledge in an expert system: a real case application

    Publication Year: 1989 , Page(s): 176 - 180
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (400 KB)  

    A description is given of a system, called M-EXPAIR, that makes use of meta-knowledge for generalizing and improving expert system efficiency. M-EXPAIR is the follow-up of a preliminary version of an expert system designed for diagnostic applications in the domain of radar equipment. This system uses a knowledge base containing both a physical and a functional description of the equipment and the history concerning the past diagnosis. M-EXPAIR is a variant of a structured production system such that the rules in the fired rule classes are dynamically updated during diagnosis. An example for a radar display device is described to illustrate the actual implementation of M-EXPAIR View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image pattern recognition by quad string array approach

    Publication Year: 1989 , Page(s): 292 - 297
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (388 KB)  

    Image processing using pixel recursion is proposed as the simplest and fastest approach to shape recognition. The pixel recursion image can be achieved by scanning, and the image after size and orientation normalization can be recognized by the quad-string-array approach. Size normalization can be achieved by the scanning device, and the orientation normalization can be handled by the circular-layer-string method. In orientation normalization, the principle axis of unknown image is achieved by rotation and compared with the standard patterns, which are pre-estimated. The unknown image can be divided into several subimages, and each subimage is coded by the vertical string array, which allows the shape of the unknown object to be described precisely. Experimental results for the vertical string array, random walk, and Gauss-Markov-R-process are discussed View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A computational model for perceptual grouping

    Publication Year: 1989 , Page(s): 315 - 320
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (384 KB)  

    A computational model for perceptual grouping is described, based on a single-instruction multiple-data (SIMD) machine, embedding a cellular automaton. The author shows that extraction of information and combination of perceptual features into higher-level grouping can be performed by SIMD computations. A description is given of a labeling procedure for the cellular automaton, based on the Huffman-Clowes system, where the labels are the states of the automation and the label combination rules its local transition rules View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Integrated architecture of an expert system for configuring distributed control systems

    Publication Year: 1989 , Page(s): 193 - 198
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (432 KB)  

    An application of knowledge-based systems to the field of engineering is described. NETCON is an expert system for configuring distributed control systems. It is integrated within the company information system and deployed by automation systems engineers. An illustration is presented of its architecture, design, and implementation criteria as well as the system integration in an overall automated engineering system. Knowledge and data structures are also described View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 3D recovery of polyhedra by rectangularity heuristics

    Publication Year: 1989 , Page(s): 210 - 215
    Cited by:  Papers (70)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (512 KB)  

    The three-dimensional shape of a polyhedron is reconstructed from its perspectively projected image by finding rectangular corners. If a corner is known to be rectangular, its three-dimensional configuration is analytically computed, and hence the surface gradients of the faces incident to it are also determined. In order to decide which corners are rectangular, the rectangularity heuristics are introduced, i.e. corners are assumed to be rectangular as long as no inconsistency arises as a result. An optimization technique is presented in order to cope with the problem of insufficiency of information and inconsistency due to error and noise View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning a visual model and an image processing strategy from a series of silhouette images on MIRACLE-IV

    Publication Year: 1989 , Page(s): 56 - 61
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (740 KB)  

    MIRACLE-IV is capable of obtaining the internal structure of an object from a series of silhouette images with no initial explicit models about the object. The images are derived from only one object, but the form is varied. The system is composed of two subsystems: a model acquisition part (the modeler) and an image-processing strategy part (the strategist). On the assumption that the object consists of hinges, slides and solids, the modeler learns the number of these in the object and the relationship among them. The strategist binds the functional features as hinges or slides with visual features in the actual image data. The image-processing sequence for the extraction of the visual feature is not given previously but is learned automatically through trial and error View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A flexible semi-automatic program generator for dynamic vision systems

    Publication Year: 1989 , Page(s): 100 - 105
    Cited by:  Papers (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (396 KB)  

    A program generator that facilitates the development of programs for low- and intermediate-level dynamic vision is described. It accepts inputs from the user in a two-dimensional graphic way and converts these into an extremely efficient executable code for both a conventional microprocessor and a special pipeline processor designed for dynamic vision. Programs produced by this system have been used in robot vision, including the guidance of a fast autonomous road vehicle View full abstract»

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