Hypothesis integration in image understanding systems
Computer Vision Graphics and Image ProcessingPublished 1 November 1986
Vincent Hwang, Larry S. Davis, Takashi Matsuyama
Citations46
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
An image understanding system, SIGMA, is constructed based on a general framework based on the integration of “related” hypotheses and its performance on an aerial image of a suburban housing development is demonstrated.
Abstract
The goal of this research is to develop a robust control strategy for constructing image understanding systems (IUS). This paper proposes a general framework based on the integration of related hypotheses. Hypotheses are regarded as predictions of the occurrences of objects in the image. Related hypotheses are clustered together. A composite hypothesis is computed for each cluster. The goal of the IUS is to verify the hypotheses. We constructed an image understanding system, SIGMA, based on this framework and demonstrated its performance on an aerial image of a suburban housing development.
Keywords
Computer Science
Elsevier eBooksA FRAMEWORK FOR REPRESENTING KNOWLEDGE
4,545 Citations1988Marvin Minsky
The enormous problem of the volume of background common sense knowledge required to understand even very simple natural language texts is discussed and it is suggested that networks of frames are a reasonable approach to represent such knowledge.
HAL (Le Centre pour la Communication Scientifique Directe)Smalltalk-80: The Language and its Implementation
3,896 Citations1983Adele Goldberg, D. Robson
This book is the first detailed account of the Smalltalk-80 system and is divided into four major parts: an overview of the concepts and syntax of the programming language, a specification of the system's functionality, and an example of the design and implementation of a moderate-size application.
Principles of Artificial Intelligence
3,336 Citations1982Nils J. Nilsson
This classic introduction to artificial intelligence describes fundamental AI ideas that underlie applications such as natural language processing, automatic programming, robotics, machine vision, automatic theorem proving, and intelligent data retrieval.
IEEE Transactions on Pattern Analysis and Machine IntelligenceComputer Image Processing and Recognition
546 Citations1981
Elsevier eBooksFRAME REPRESENTATIONS AND THE DECLARATIVE/PROCEDURAL CONTROVERSY
477 Citations1975Terry Winograd
This chapter presents some criteria for evaluating ideas for representation and presents a rough sketch of a particular version of a frame representation, and discusses the ways in which it can deal with the issues raised.
An Overview of Production Systems
427 Citations1975Randall Davis, Jonathan J. King
This paper is an attempt to provide an analysis and overview of recurrent themes in production systems, as well as a conceptual framework by which many of the seemingly disparate efforts can be viewed, both in relation to each other, and to other methodologies.
Elsevier eBooksREASONING ABOUT KNOWLEDGE AND ACTION
372 Citations1981Robert C. Moore
The importance of having systems that understand the concept of knowledge, and how knowledge is related to action, and a logic of knowledge based on the idea of possible worlds is presented.
The International Journal of Robotics ResearchSurvey of Model-Based Image Analysis Systems
347 Citations1982Thomas O. Binford
A survey and critique of the state of the art in model-based image analysis systems is presented and principles of design of general vision systems are described.
A Structural Analysis of Complex Aerial Photographs
329 Citations1980Makoto Nagao, Takashi Matsuyama
A new system for the structural analysis of complex aerial photographs is presented, which has the ability of focussing its attention of the analysis on the limited local areas where objects are highly supposed to exist.
IEEE Transactions on Pattern Analysis and Machine IntelligenceRule-Based Interpretation of Aerial Imagery
328 Citations1985David M. McKeown, Wilson A. Harvey +1 more
The organization of a rule-based system, SPAM, that uses map and domain-specific knowledge to interpret airport scenes is described, characterized by the labeling of individual regions in the image and the collection of these regions into consistent interpretations of the major components of an airport model.
IEEE Transactions on Pattern Analysis and Machine IntelligenceLow Level Image Segmentation: An Expert System
320 Citations1984Ahmed M. Nazif, Martin D. Levine
A new solution to the image segmentation problem that is based on the design of a rule-based expert system that dynamically alters the processing strategy is presented.
Elsevier eBooksENCODING KNOWLEDGE IN PARTITIONED NETWORKS
167 Citations1979Gary G. Hendrix
This chapter discusses network notations for encoding a number of different kinds of knowledge, including taxonomic information; general statements involving quantification; information about processes and procedures; the delineation of local contexts, beliefs, and wishes; and the relationships between syntactic units and their interpretations.
DSpace@MIT (Massachusetts Institute of Technology)Flavors: Message Passing in the Lisp Machine.
70 Citations1980Daniel Weinreb, David A. Moon
This chapter attempts to explain what programming the objects and with message passing means, the various means of implementing these in Lisp Machine Lisp, and when you should use them.
Lecture notes in computer scienceComputer Vision Systems
64 Citations2001Schiele, Bernt, Sagerer, Gerhard
Defense Technical Information Center (DTIC)MSYS: A System for Reasoning About Scenes.
63 Citations1975Jay M. Tenenbaum, Barrow,H G
MSYS is a system for reasoning with uncertain information and inexact rules of inference that contributes to the interpretation of visual features in scene analysis by repeatedly applying rules until a consistent set of likelihood values is attained.
Distributed Problem Solving: The Contract Net Approach
50 Citations1978Reid G. Smith, Randall Davis
This paper proposes a model of a distributed problem solver which consists of a collection of processors connected with communications and control mechanisms that enable them to operate concurrently, and enabling them to cooperate in solving complex problems.
UR Research (University of Rochester)Reasoning about success and failure in aerial image understanding
46 Citations1982Peter G. Selfridge
A more general conclusion is that adaptive techniques are required if high-level knowledge is to appropriately interact with computations at all levels of an Image Understanding system.
Evidence Accumulation for Spatial Reasoning in Aerial Image Understanding.
25 Citations1983Vincent Hwang, Takashi Matsuyama +2 more
A general conclusion from this work is that by accumulating relevant evidence, one can realize a flexible process which performs both top-down picture processing and bottom-up verification of consistent spatial relations among objects.
DSpace@MIT (Massachusetts Institute of Technology)Reasoning Modeled As A Society Of Communicating Experts
21 Citations1979Luc Steels
Verification vision within a programmable assembly system
15 Citations1976Robert C. Bolles
This thesis concentrates on a subclass of visual information processing referred to as verification vision (abbreviated VV), which uses a model of a scene to locate objects of interest in a picture of the scene.