http:^^www.cs.washington.edu^homes^shapiro^wtc.html
来自「This data set contains WWW-pages collect」· HTML 代码 · 共 73 行
HTML
73 行
Date: Tue, 10 Dec 1996 14:58:03 GMTServer: NCSA/1.4.2Content-type: text/htmlLast-modified: Tue, 13 Feb 1996 23:42:37 GMTContent-length: 2450<html><head><title>From Technical Diagrams to Electronic Documents</title></head> <body background="./wood.gif"><address> Department of Electrical Engineering<br> University of Washington </address><h1>From Technical Diagrams to Electronic Documents</h1><b><h2>Sponsors</b></h2><ul><em><li> The Washington Technology Center <li> Infoaccess Inc.<li> The Boeing Company</em></ul><a href= "lam.gif">Example of a Technical Diagram</a><em>. Warning: this image is BIG!!</em><p><b><h2>Problem Statement and Objectives</h2></b> InfoAccess is a small Washington State company whose main product line isGuide, a collection of software modules that allow the semi-automaticconversion of technical manuals to interactive electronic documents.The manuals are typically technical documents such as installation,operations and maintenance manuals, which contain large numbers ofcomplex diagrams. Diagrams are converted to images with ``hot spots,''which are regions in which the user can click a mouse and receiveadditional information or help. The hot spots are located where thereare ``callouts'' in the original diagram; these are numbers or textidentifying a portion of the diagram and usually adjacent to a straightline or arrow pointing to this portion. Currently the callouts must belocated and identified by hand; this is slow and tedious. InfoAccesswould like an image analysis system that can automatically find thecallouts, read the numbers or text, and send an ASCII character stringplus the image coordinates of the callout to the appropriate GUIDEpackage.<p>The problem to be solved in this work is the development ofautomatic methods for locating and recognizing patterns in complex technical document images. InfoAccess is currently most interested inthe callouts, which are usually numbers or text, sometimessurrounded by circles or boxes, since automatic calloutdetection software would be of immediate use in theircurrent product. However, developing a general approach will allow them to produce more powerful future products. Our objective for this workis to develop an approach to document patternmatching that is specifically applicable to the automaticcallout recognition problem, that is easily extendable torecognition of more advanced patterns such as parts andsubassemblies, that can be trained to recognize new patterns,and that is efficient and easy to use.⌨️ 快捷键说明
复制代码Ctrl + C
搜索代码Ctrl + F
全屏模式F11
增大字号Ctrl + =
减小字号Ctrl + -
显示快捷键?