Julius T. Tou

Dynoc—A dynamic optimal cluster-seeking technique

A new technique for automatic clustering of multivariate data is proposed. In this approach a performance index for determining optimal clusters is introduced. This performance index is expressed in terms of the ratio of the minimum interset distance to maximum intraset distance. The optimal clusters are found when the performance index reaches a global maximum. If there are alternative groupings with equal number of clusters, the one with the largest performance index is chosen.

Design of expert systems for integrated production automation

Abstract An approach to the design of expert systems for integrated production automation is presented. The major components in an integrated manufacturing system consist of corporate planning, marketing planning, research and development, engineering design, production planning, manufacturing, warehousing, and product distribution. These components are linked by management information flow, technology information flow, as well as materials flow. An intelligent computer is used to integrate information flow and to control materials flow. This paper discusses characteristics of the future factory, elements of knowledge based systems, and the design of computer based expert systems for production planning, for engineering design, and for integrated manufacturing.

Recognition of Handwritten Characters by Topological Feature Extraction and Multilevel Categorization

A handwritten character recognition system has been designed by making use of topological feature extraction and multilevel decision making. By properly specifying a set of easily detectable topological features, it is possible to convert automatically the handwritten characters into stylized forms and to classify them into primary classes with similar topological configurations. Final recognition is accomplished by a secondary stage that performs local analysis on the characters in each primary category. The recognition system consists of two stages: global recognition, followed by local recognition. Automatic character stylization results in pattern clustering which simplifies the classification tasks considerably, while allowing a high degree of generality in the acceptable writing format. Simulation of this scheme on a digital computer has shown only 6 percent misrecognition.

Feature extraction in pattern recognition

Abstract Sensing, feature extraction, optimum decision, parameter estimation, adaptation and learning are the major problems in the design of pattern recognition systems. This paper discusses the selection of mathematical features on the basis of entropy minimization and introduces the concept of extracting statistical features by the method of kernel approximation.

A solder joint inspection system for automated printed circuit board manufacturing

The design of a solder joint inspection system which will be used as an integral part of the PCB/AID (automated inspection and diagnosis for PC board manufacturing) system is presented. The inspection system utilizes four frames of solder joint images, extracts 15 features from the images to categorize the most important seven classes of solder joint defects, and provides two forms of inspection results according to their applications (touch-up of defects and fault diagnosis for online process control). The system has been tested for several PC boards provided by electronics firms, and experimental results have shown that it has exceptional promise.<<ETX>>

A clique-detection algorithm based on neighborhoods in graphs

The notion of cliques is the logical starting point for a broad class of clustering problems. Algorithms for the identification of the cliques of a graph are of great importance in automatic classification by computer. This paper presents an approach which proceeds recursively from the given graph downward through a chain of subgraphs. The proposed approach permits the removal of more than a single point in the progression from one subgraph to the next, thus reducing the number of iterations required for completion.

Knowledge engineering revisited

About six years ago a paper on Knowledge Engineering was published in this Journal. This paper attempts to extend and elaborate on the ideas and concepts discussed earlier. Four major problems are addressed: Preservation of knowledge, proliferation of knowledge, dissemination of knowledge, and application of knowledge. The design principles for both rule-based expert systems and pattern-directed expert systems are discussed and compared.

Pictorial feature extraction and recognition via image modeling

Publisher Summary This chapter reviews the image modeling approaches for pictorial feature extraction and recognition. Research activities in computer-based picture processing have been centered around picture enhancement, interpretation, recognition, generation, and editing. Quantitative study of a picture is often concerned with four types of parameters that are of fundamental importance. They are contrast, color, shape, and texture. The contents of a picture may be categorized into three general types: (1) identifiable objects with well-defined structural patterns, (2) identifiable objects with fuzzy or diffused patterns, and, (3) non-identifiable objects. To process a picture with identifiable objects, the objects must be localized and their contrast, color, and shape for recognition must be studied. In the case of objects with fuzzy structures, identification of objects may require texture analysis. When pictures are processed with non-identifiable objects such as wood grain or forests, the study of the textures in the picture becomes indispensable. Under this circumstance, textural information provides important features for interpretation and recognition. Texture information thus is very useful in automatic photointerpretation, earth resources exploration, and biomedical image processing. Textures may be regarded as repetitive arrangements of a unit sub-pattern, as inhomogeneities in the gray scale, or as global properties of a picture or scene in a statistical sense.

Engineering Principles of Pattern Recognition

In recent years our very complex and technically oriented society has created a situation in which more people and organizations have become concerned with handling information and fewer with handling materials. The need for improved information systems has become more conspicuous, since the world is generating more information in its various forms and information is an essential element in decision making. One of the major problems in the design of modern information systems is automatic pattern recognition. This has been the subject of investigation by many diverse groups, including research workers dealing with electronic computers, automatic controls, information theory, applied physics, statistics, psychology, biology, physiology, medicine, and linguistics. Each group emphasizes certain aspects of the problem. This chapter attempts to discuss some engineering principles for the design of pattern recognition systems.

Application of Error-Correcting Codes in Computer Reliability Studies

The use of error-correcting codes as one of the important techniques to increase computer system reliability is introduced. The different codes used in the central processing unit (CPU) are described. Since the CPU usually contains the data path, logic, and arithmetic units, the codes used in this area are error-detecting codes, such as parity check codes and residue codes. The codes used or suggested for the memory system are discussed, emphasis being placed on parity check codes, two-dimensional codes, Hamming codes and other recently developed codes. The various codes used in the input/output system are presented. The input/output area of the computer system is relatively unreliable as compared with CPU or memory; therefore, error-correcting codes used in this area usually are much more powerful than single parity check codes. These include codes for the magnetic tape, disk, and drum units. The error coding techniques are compared with other techniques for increasing computer system reliability. The future trend of using error-correcting codes in a computer system is also discussed.