Knowledge-based image analysis for geophysical interpretation

Geophysical seismic interpretation is part of geophysical oil prospecting. It evaluates and analyses seismic reflection data, aiming at the detection of the position of hydrocarbon reservoirs. This paper provides a review of current efforts to automate, at least partially, seismic interpretation. As will be shown, this research area is very active and is a melting pot of various different approaches and techniques: artificial intelligence, pattern recognition, image processing, graphics, fuzzy set theory and, of course, geophysics and geology. Some methods of seismic pattern recognition (e.g. remote correlation, fuzzy seismic modeling, recognition of reservoir boundaries) and of seismic image processing (horizon following, texture analysis) are presented and some applications are shown. Expert systems used in geophysical interpretation (mainly in well log interpretation) are also briefly described. Finally, an automated system for knowledge-based image analysis for geophysical interpretation is dicussed. Its low-level vision techniques, its knowledge representation, and the control strategy for seismic pattern search are described.     

A robust recognition system for a drawing superimposed on a map

A robust and efficient drawing recognition system that is based on a representation technique using accurate shape and topological line information for an input drawing image is described. This representation supports primitive decomposition and object extraction that enable accurate automatic interpretation even for low-quality drawings. The system, which is adapted to an underground electric cable diagram, has been implemented on a workstation     

A vision system for symbolic interpretation of dynamic scenes using arsom

We describe an artificial high-level vision system for the symbolic interpretation of data coming from a video camera that acquires the image sequences of moving scenes. The system is based on ARSOM neural networks that learn to generate the perception-grounded predicates obtained by image sequences. The ARSOM neural networks also provide a three-dimensional estimation of the movements of the relevant objects in the scene. The vision system has been employed in two scenarios: the monitoring of a robotic arm suitable for space operations, and the surveillance of an electronic data processing (EDP) center.     

STRUCTURED REPRESENTATION OF FMS INTEGRATING SI-NETS AND HIGH LEVEL PETRI NETS

In this paper a structured knowledge-based approach to the representation and scheduling of flexible manufactoring systems (FMSs) is described. Our approach is based on a structured conceptual representation (a KL-ONE-like Si-net representation formalism), extended with an instant-based temporal reasoning formalism. Furthermore, the approach integrates a particular extension to high-level Petri nets (PNs), structured timed colored Petri nets (STCPNs), for the modeling and simulation of the FMS. Such a representation scheme allows us to use SI-nets' good properties related to inference (classification and inheritance), which are lacking in PNs, and at the same time provides an extension toward an explicit representation for time. The integration of Si-nets with PNs is necessary because simulation and low-level coordination of FMSs require a procedural approach that is not within the aims of Si-nets. Therefore, procedural and symbolic levels, corresponding to the different hierarchical levels of the representation and control system of the FMS, coexist in the system. Using a qualitative terminology, we may also call them analog and symbolic knowledge. We assume that such a hybrid representation system may be useful, since a procedural representation, integrated within a logic formalism, can increase the expressive power without complicating the notation or the representation itself. The paper describes both the representational aspects and the modeling of the control system of the FMS, focusing on the interaction mechanisms among the different levels of representation. In particular, we show how an STCPN-based model can be automatically derived starting from the symbolic component of the system. A particular FMS case study, regarding a class of problems of resource-constrained multiproject scheduling (where projects are sets of tasks temporally related), is discussed.     

A symbolic manipulator for automated verification of reactive systems with heterogeneous data types

In this paper, we present the design and implementation of the Composite Symbolic Library, a symbolic manipulator for model checking systems with heterogeneous data types. Our tool provides a common interface for different symbolic representations, such as BDDs, for representing Boolean logic formulas and polyhedral representations for linear arithmetic formulas. Based on this common interface, these data structures are combined using a disjunctive composite representation. We propose several heuristics for efficient manipulation of this composite representation and present experimental results that demonstrate their performance. We used an object-oriented design to implement the Composite Symbolic Library. We imported the CUDD library (a BDD library) and the Omega Library (a linear arithmetic constraint manipulator that uses polyhedral representations) to our tool by writing wrappers around them which conform to our symbolic representation interface. Our tool supports polymorphic verification procedures which dynamically select symbolic representations based on the input specification. Our symbolic representation library can be used as an interface between different symbolic libraries, model checkers, and specification languages. We expect our tool to be useful in integrating different tools and techniques for symbolic model checking, and in comparing their performance.     

Machine learning for map interpretation: An intelligent tool for environmental planning

The design of a user interface integrating instruments for visual and textual representation and image interpretation is a relevant problem when developing an advisory system for environmental planning. Indeed, the user of the system needs a support to the interpretation of maps, that is, a tool that segments maps and automatically associates geometric regions on a map with those semantic labels useful for applying hints and advices suggested by the environmental planning system. In the article, we present the application of symbolic machine learning techniques to the interpretation of maps. Two inductive learning systems, namely, INDUBI/CSL and ATRE, have been used to complete the knowledge base of an expert system for environmental planning. The application described concerns the recognition of four environmental concepts that are relevant for environmental protection. The positive results obtained in two different experiments prove the strength of the adopted approach for the interpretation task.     

SMIRP-A Systems Approach to Laboratory Automation

SMIRP (Standard Modular Integrated Research Protocols), a web-based laboratory management system, will be described. SMIRP uses a protocol-experiment-parameter data representation system for all components of laboratory operations, including knowledge acquisition, laboratory data generation and analysis, and document production. Data tractability is inherent to the use of the system, permitting rapid browser-based navigation through linked information. The implementation of SMIRP in an academic research environment is discussed.     

VISTA: visual interpretation system for technical applications-architecture and use

The present state of the construction of a vision system for the fast interpretation of complicated industrial scenes is reported. The system is being built at the Fraunhofer Institute for Information and Data Process in Karlsruhe, West Germany. The scenes for which the system is intended are also presented. They form the basis for specifying the requirements for the system called VISTA. Its principal architecture as a bus-oriented multiprocessor system is discussed. Some special hardware modules of VISTA are described in more detail, and its basic software concept is introduced. As an application, detection and classification of defects that appear in automatic visual inspection of hard wood are reviewed. Using special modules for the iconic and the symbolic stage, VISTA is capable of real-time processing and evaluation of endless images, image sequences, images of various formats, and multisensorial data     

Coding, analysis, interpretation, and recognition of facialexpressions

We describe a computer vision system for observing facial motion by using an optimal estimation optical flow method coupled with geometric, physical and motion-based dynamic models describing the facial structure. Our method produces a reliable parametric representation of the face's independent muscle action groups, as well as an accurate estimate of facial motion. Previous efforts at analysis of facial expression have been based on the facial action coding system (FACS), a representation developed in order to allow human psychologists to code expression from static pictures. To avoid use of this heuristic coding scheme, we have used our computer vision system to probabilistically characterize facial motion and muscle activation in an experimental population, thus deriving a new, more accurate, representation of human facial expressions that we call FACS+. Finally, we show how this method can be used for coding, analysis, interpretation, and recognition of facial expressions     

Modelling timed reactive systems from natural-language requirements

At the very beginning of system development, typically only natural-language requirements are documented. As an informal source of information, however, natural-language specifications may be ambiguous and incomplete; this can be hard to detect by means of manual inspection. In this work, we present a formal model, named data-flow reactive system (DFRS), which can be automatically obtained from natural-language requirements that describe functional, reactive and temporal properties. A DFRS can also be used to assess whether the requirements are consistent and complete. We define two variations of DFRS: a symbolic and an expanded version. A symbolic DFRS (s-DFRS) is a concise representation that inherently avoids an explicit representation of (possibly infinite) sets of states and, thus, the state space-explosion problem. We use s-DFRS as part of a technique for test-case generation from natural-language requirements. In our approach, an expanded DFRS (e-DFRS) is built dynamically from a symbolic one, possibly limited to some bound; in this way, bounded analysis (e.g., reachability, determinism, completeness) can be performed. We adopt the s-DFRS as an intermediary representation from which models, for instance, SCR and CSP, are obtained for the purpose of test generation. An e-DFRS can also be viewed as the semantics of the s-DFRS from which it is generated. In order to connect such a semantic representation to established ones in the literature, we show that an e-DFRS can be encoded as a TIOTS: an alternative timed model based on the widely used IOLTS and ioco. To validate our overall approach, we consider two toy examples and two examples from the aerospace and automotive industry. Test cases are independently created and we verify that they are all compatible with the corresponding e-DFRS models generated from symbolic ones. This verification is performed mechanically with the aid of the NAT2TEST tool, which supports the manipulation of such models.     

MARCO: MAp retrieval by COntent

A system named MARCO (denoting map retrieval by content) that is used for the acquisition, storage, indexing, and retrieval of map images is presented. The input to MARCO are raster images of separate map layers and raster images of map composites. A legend-driven map interpretation system converts map layer images from their physical representation to their logical representation. This logical representation is then used to automatically index both the composite and the layer images. Methods for incorporating logical and physical layer images as well as composite images into the framework of a relational database management system are described. Indices are constructed on both the contextual and the spatial data thereby enabling efficient retrieval of layer and composite images based on contextual as well as spatial specifications. Example queries and query processing strategies using these indices are described. The user interface is demonstrated via the execution of an example query. Results of an experimental study on a large amount of data are presented. The system is evaluated in terms of accuracy and in terms of query execution time     

Knowledge-based segmentation of sonar data

Work is described that forms part of a project the aim of which is to develop a fully automated knowledge-based system capable of interpreting passive sonar data. In particular, the task of transforming (raw) signal data to symbolic data has been approached from the viewpoint of developing a knowledge-based vision system that mimics the performance of operators when analysing noisy ‘chart’ recordings for significant events.     

Qlisp: parallel processing in Lisp

The authors describe a version of Common Lisp for multiprocessing, called Qlisp. It supports medium-grained parallelism for artificial-intelligence and symbolic programs. Qlisp supports the futures data type. It also introduces partially, multiply invoked functions that let program components be synchronized. An implementation of Qlisp on an Alliant FX/8, based on Lucid Common Lisp, a commercial system, is described     

Scientific workflows: Past,present and future

This special issue and our editorial celebrate 10 years of progress with data-intensive or scientific workflows. There have been very substantial advances in the representation of workflows and in the engineering of workflow management systems (WMS). The creation and refinement stages are now well supported, with a significant improvement in usability. Improved abstraction supports cross-fertilisation between different workflow communities and consistent interpretation as WMS evolve. Through such re-engineering the WMS deliver much improved performance, significantly increased scale and sophisticated reliability mechanisms. Further improvement is anticipated from substantial advances in optimisation. We invited papers from those who have delivered these advances and selected 14 to represent today’s achievements and representative plans for future progress. This editorial introduces those contributions with an overview and categorisation of the papers. Furthermore, it elucidates responses from a survey of major workflow systems, which provides evidence of substantial progress and a structured index of related papers. We conclude with suggestions on areas where further research and development is needed and offer a vision of future research directions.     

Iconic representation of visual data and models

Knowledge based image analysis is a combination of digital signal processing and symbolic reasoning. In this paper, we will look at some problems connected to the symbolic reasoning approach to image interpretation and see how an iconic representation can help to solve some of them. We will show that many of the features and problems connected with both symbolic and iconic representation are complementary.     

Novel moment invariants for improved classification performance in computer vision applications

A novel set of moment invariants based on the Krawtchouk moments are introduced in this paper. These moment invariants are computed over a finite number of image intensity slices, extracted by applying an innovative image representation scheme, the image slice representation (ISR) method. Based on this technique an image is decomposed to a several non-overlapped intensity slices, which can be considered as binary slices of certain intensity. This image representation gives the advantage to accelerate the computation of image's moments since the image can be described in a number of homogenous rectangular blocks, which permits the simplification of the computation formulas. The moments computed over the extracted slices seem to be more efficient than the corresponding moments of the same order that describe the whole image, in recognizing the pattern under processing. The proposed moment invariants are exhaustively tested in several well known computer vision datasets, regarding their rotation, scaling and translation (RST) invariant recognition performance, by resulting to remarkable outcomes.     

The learning organization information system (LOIS): looking for the next generation

This paper explores the notion that the next generation of information systems will focus on supporting organizational learning. The paper suggests that the increasingly successful automation of procedural work will lead to pressure on organizations to improve performance through enhanced support for knowledge work. A set of outline requirements for the learning organization information system (LOIS) is then proposed using recent research findings from computer supported co‐operative working and organizational learning. The computerized on‐line journal from this research is described. This journal provides transparent capture of episodes of work and it is argued that the general principles established could support LOIS by helping to provide a richly defined organizational memory. The journal supports collaborative working through the use of groupware, which manages the sharing of, and learning from, journal contents. This can facilitate the retention of not only data and information, but also the inquiry process that produced them. The paper concludes that LOIS will be a self‐organizing system, focussing on knowledge work, learning and using advanced technologies drawn from ubiquitous computing. A view of a system that moves towards this aim is presented. Future topics for research are identified, and a natural language approach to knowledge asset management is discussed briefly. In closing, it is argued that LOIS is an important future vision for organizations operating in the information age.