Pictorial knowledge representation using pictorial semantic networks

Lee, Edward T.

doi:10.1017/s0263574700003970

Cited by 14 publications

(9 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this approach, color clusters, color codebooks, an unsupervised learning algorithm, and a nearest‐neighbor classifier are thoroughly studied (Wu, 1986). Furthermore, the relationships among pictorial data compression techniques, pictorial databases (Lee, 1980b, 1984), pictorial knowledge (Lee, 1987, 1988a, b; Lee et al , 1987a, 1989b) and pictorial information systems (Chang, 1989; Chang and Fu, 1980) are also carefully investigated.…”

Section: Proposed Research Topicsmentioning

confidence: 99%

“…More specifically, given a simple picture, how to find an array grammar which has the capability of generating this picture is the main subject of this task. In addition,the problem of array production minimization,time and space complexity analyses,pictorial knowledge (Lee, 1988a; Lee et al , 1989b),entity‐relationship (ER) model (Lee, 1988b; Lee et al , 1987a),the size and shape of the array, andoctree (Lee and Harjardi, 1989)are also investigated with illustrative examples.…”

Section: Proposed Research Topicsmentioning

confidence: 99%

See 1 more Smart Citation

Research topics in pictorial databases

Lee¹

2004

Kybernetes

Self Cite

View full text Add to dashboard Cite

Pictures are natural and effective means of communication among people, computers, and robotics. A pictorial database is a collection of sharable pictorial data encoded in various formats. During the past several years, pictorial databases have attracted growing attention as an important component in building pictorial information systems as well as intelligent information systems. Eight research tasks are presented. They are comparing the numerical and the linguistic variable approaches, examining new linguistic hedges, studying the similarity of various similarity measures, investigating pictorial data compression techniques, performing pictorial data compression using array grammars, applying the entity‐relationship (ER) model to picture description; further investigating the relationship hierarchy for picture representation using ER diagrams, and extracting pictorial knowledge from pictorial databases. The research results may have a major impact on the development of object‐oriented pictorial databases.

show abstract

Section: Proposed Research Topicsmentioning

confidence: 99%

Section: Proposed Research Topicsmentioning

confidence: 99%

Research topics in pictorial databases

Lee¹

2004

Kybernetes

Self Cite

View full text Add to dashboard Cite

show abstract

“…As we know, semantic networks are widely used in knowledge representation and pictorial knowledge representation. 3…”

Section: Semantic Networkmentioning

confidence: 99%

“…Theorem 1: If a convex 3D object has only planar faces, then the 3D object can be represented by the intersections of a set of planes. 3 Example 1: A cube may be represented as the intersections of the six planes denoted as…”

Section: Intersection Of Planesmentioning

confidence: 99%

Algorithms for simple object reconstruction using the largest possible object approach

Lee

1992

Robotica

Self Cite

View full text Add to dashboard Cite

SUMMARYRecently, three-dimensional motion analysis and shape recovery have attracted growing attention as promising avenues of approach to image understanding, object reconstruction as well as computer vision for robotic Systems. The image generation problem and the model generation problem are presented. More specifically, the inputs to the image generator are an old image, object model, motion specification, and hidden line and hidden surface algorithms. The output is a new image. Since the object model is given, the top-down approach is usually used. On the other hand, for the model generation problem, the input is an image sequence while the output is an object model. Since the object model is not given, and bottom-up approach is usually used.In this paper, the largest possible object approach is proposed and the advantages of this approach are stated. They are:1. This approach may be applicable to objects with planar surfaces as well as nonplanar surfaces.2. This approach may be applicable to the case that there are more than one face change per frame.3. This approach may be applicable when the camera is moving.4. This approach may be applicable when the object is measured by several measuring stations.By using this approach, algorithms for simple object reconstruction given a sequence of pictures are presented together with illustrative examples. The relevance and importance of this work are discussed.The results of this paper may have useful applications in object reconstruction, pictorial data reduction and computer vision for robotic Systems.

show abstract

“…The intelligent manufacturing movement in the context of factory automation [1] is accelerated by the advent of programmable controllers [2,3], microprocessors, process control computers, industrial logic control systems, pictorial knowledge-based systems [4][5][6][7], and artificial intelligence technologies [8,9], which are now enjoying even more acceptance and application in manufacturing automation than are industrial robots. All of these devices may be viewed as members of a family of flexible automation tools that is changing the way in which products are manufactured.…”

Section: Introductionmentioning

confidence: 99%