An integrated approach to document decomposition and structural analysis

A document image is a visual representation of a paper document, such as a journal article page, a cover page of facsimile transmission, office correspondence, an application form, etc. Document image understanding as a research endeavor consists of developing processes for taking a document through various representations, from scanned image to semantic representation. This article describes document decomposition and structural analysis, which constitutes one of the major processes involved in document image understanding. The current state of the art and future directions in the areas of document segmentation, layout analysis, and logical block grouping are indicated. A system that performs decomposition and structural analysis (including logical grouping and read-order determination) on complex multiarticled documents is presented. This system uses bottom-up segmentation techniques to identify the block structure of a document, and layout rules to classify and group these blocks into logical units that represent meaningful subdivisions of the document. Experimental results showing the efficiency of this approach are presented and discussed. © 1996 John Wiley & Sons, Inc.     

Offline Chinese handwriting recognition: an assessment of current technology

Offline Chinese handwriting recognition (OCHR) is a typically difficult pattern recognition problem. Many authors have presented various approaches to recognizing its different aspects. We present a survey and an assessment of relevant papers appearing in recent publications of relevant conferences and journals, including those appearing in ICDAR, SDIUT, IWFHR, ICPR, PAMI, PR, PRL, SPIEDRR, and IJDAR. The methods are assessed in the sense that we document their technical approaches, strengths, and weaknesses, as well as the data sets on which they were reportedly tested and on which results were generated. We also identify a list of technology gaps with respect to Chinese handwriting recognition and identify technical approaches that show promise in these areas as well as identify the leading researchers for the applicable topics, discussing difficulties associated with any given approach.     

Macro-capp: A prototype capp system for an FMS

This paper deals with the role, advantages, problems and solution techniques for the implementation of dynamic Computer Aided Process Planning (CAPP) systems in a Felxible Manufacturing system (FMS). A large variety of part features for both rotational and prismatic parts are considered. A custom group technology coding technique is designed and implemented to describe part profile to system software concisely and comprehensively. The part profile code is assimilated by the system interactively. A prototype CAPP system was designed for a pseudo FMS containing multiple machining centres. The system described develops process plans that consider both alternative routes and methods to manufacture a part. Heuristic knowledge was implemented to choose between alternatives with flowtime minimization as the objective function. The system was tested and its outputs validated with respect to both prismatic and rotational parts.     

Optimisation of the Substrate Preheat Temperature for the Encapsulation of Flip Chip Devices

This research addressed the feasibility of using a substrate preheat temperature which is higher than the manufacturer’s recommendation in order to reduce the cycle time of the encapsulation process while still ensuring package reliability. temperature are discussed and evaluated. A statistical model was generated to help determine the optimal substrate preheat temperature for given chip dimensions, standoff height, surface texture, etc. Using the substrate preheat temperature determined by the model, the flow time of the encapsulant could be reduced by more than a factor of two while still ensuring a 6s quality level.     

An architecture for handwritten text recognition systems

This paper presents an end-to-end system for reading handwritten page images. Five functional modules included in the system are introduced in this paper: (i) pre-processing, which concerns introducing an image representation for easy manipulation of large page images and image handling procedures using the image representation; (ii) line separation, concerning text line detection and extracting images of lines of text from a page image; (iii) word segmentation, which concerns locating word gaps and isolating words from a line of text image obtained efficiently and in an intelligent manner; (iv) word recognition, concerning handwritten word recognition algorithms; and (v) linguistic post-pro- cessing, which concerns the use of linguistic constraints to intelligently parse and recognize text. Key ideas employed in each functional module, which have been developed for dealing with the diversity of handwriting in its various aspects with a goal of system reliability and robustness, are described in this paper. Preliminary experiments show promising results in terms of speed and accuracy. Received October 30, 1998 / Revised January 15, 1999     

Constitutive Behavior of Commercial Grade ZEK100 Magnesium Alloy Sheet over a Wide Range of Strain Rates

The constitutive behavior of a rare-earth magnesium alloy ZEK100 rolled sheet is studied at room temperature over a wide range of strain rates. This alloy displays a weakened basal texture compared to conventional AZ31B sheet which leads to increased ductility; however, a strong orientation dependency persists. An interesting feature of the ZEK100 behavior is twinning at first yield under transverse direction (TD) tensile loading that is not seen in AZ31B. The subsequent work hardening behavior is shown to be stronger in the TD when compared to the rolling and 45 deg directions. One particularly striking feature of this alloy is a significant dependency of the strain rate sensitivity on orientation. The yield strength under compressive loading in all directions and under tensile loading in the TD direction is controlled by twinning and is rate insensitive. In contrast, the yield strength under rolling direction tensile loading is controlled by non-basal slip and is strongly rate sensitive. The cause of the in-plane anisotropy in terms of both strength and strain rate sensitivity is attributed to the initial crystallographic texture and operative deformation mechanisms as confirmed by measurements of deformed texture. Rate-sensitive constitutive fits are provided of the tensile stress–strain curves to the Zerilli–Armstrong[1] hcp material model and of the compressive response to a new constitutive equation due to Kurukuri et al.[2]     

Automated knowledge acquisition for the surface-mount PWB assembly domain

The development of knowledge-based (or expert) systems for the surface-mount printed wiring board (PWB) assembly domain requires the understanding and regulation of several complex tasks. While the knowledge base in an expert system serves as a storehouse of knowledge primitives, its design and development is a bottleneck in the expert system development life-cycle. Therefore the development of an automated knowledge acquisition (KA) facility (or KA tool) would facilitate the implementation of expert systems for any domain. This paper describes an automated KA tool that helps to elicit and store information in domain-specific knowledge bases for surface-mount PWB assembly. A salient feature of this research is the acquisition of uncertain information.     

A numerical study of the thermal performance of an impingement heat sink-fin shape optimization

This paper presents the results of a numerical analysis of the performance of an impingement heat sink designed for use with a specific blower as a single unit. These self-contained heat sink/blower units, which cause impingement type flow on the heat sink fins, are now commonly used for desktop microprocessors. One of the objectives of this study is to examine the effect of the shape of the heat sink fins, particularly near the center of the heat sink, on the thermal performance of the package. The pressure gradient at the center of the heat sink, near the base, tends to be high. It significantly reduces the airflow, and hence, transport in that region. Different fin shapes and airflow rates have been studied with the objective of searching for an optimal heat sink design that would improve the thermal performance without increasing the pressure drop across the heat sink. Parallel plate fins have been studied by removing fin material from the region near the center of the heat sink along the length and height of the fins. Seventeen different designs have been compared, and an "optimum" heat sink shape is reported that results in a lower operating temperature and pressure drop. It is found that removal of fin material from the central region of the heat sink enhances the thermal as well as hydraulic performance of the heat sink.     

Expert system based placement sequence identification for surface mount PCB assembly

Component placement is a critical and time consuming task in the assembly of surface mount printed circuit boards (PCBs). The past decade has witnessed the need for high speed, accurate, and repeatable placement procedures in the PCB assembly domain. At the same time, manufacturing engineers are faced with demands to reduce flow-time and increase throughput rates in order to increase productivity. A consequence of these trends has been the need to identify acceptable (possibly optimal) placement sequences during surface mount PCB assembly.The focus of this research was the identification of near optimal solutions for the placement sequence identification problem while considering machine and process constraints in a manufacturing environment. Expert (or knowledge-based) systems were used as the solution method for this problem. PROLOG, a popular language for artificial intelligence applications, was used in this research. The prototype knowledge-based system developed in this research identifies solutions in (almost) real-time.