Image analysis – Applications – Reading maps – graphs – drawings – or schematics
Reexamination Certificate
2000-06-30
2004-03-16
Boudreau, Leo (Department: 2621)
Image analysis
Applications
Reading maps, graphs, drawings, or schematics
C382S209000
Reexamination Certificate
active
06707932
ABSTRACT:
BACKGROUND OF THE INVENTION
Document processing and understanding is important for a variety of applications such as office automation, creation of electronic manuals, online documentation and annotation, and so forth. However, the understanding and identifying of graphical objects in large engineering drawings which often can be of the order of 10000×10000 pixels using traditional methods can be a very challenging and time consuming task due to the sheer size.
In spite of the use of electronic documents there does not appear to have been any significant decrease in the use of paper based documents. In fact, their volume appears to have increased, influenced by an apparently general preference for paper documents for reading and archiving purposes. In a similar way as newspapers remained popular even after the introduction of radio and television broadcasting, and the Web, paper documents remain in widespread use.
However, storing and analyzing paper documents and, more importantly, retrieving them, are a very cumbersome tasks. Electronic documents have the advantage that they can be easily manipulated and readily analyzed. Consequently, transformation of paper documents to electronic form has become an important goal. It is herein recognized that this is a non trivial task and it has been observed, such as in Tang et al., “Multiresolution analysis in extraction of reference lines from documents with gray level backgrounds”, IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 921-925, 1997, that it is almost impossible to develop a general system that can process all kinds of documents, such as technical reports, engineering drawings, books, journals, newspapers etc. Rather, the research community normally focuses on a specific application so that one can make best use of the inherent properties and the major characteristics of the particular type of document under consideration.
SUMMARY OF THE INVENTION
In accordance with an aspect of the invention, a method for identifying graphical objects in large engineering drawings comprises the steps of inputting an original image into a computerized system for image processing; pruning the original image to provide a pruned image; inputting a template image; processing the template image to provide a processed template image; and computing matches between the pruned image and the processed template image.
REFERENCES:
patent: 4930022 (1990-05-01), Kubota
patent: 5101443 (1992-03-01), Behrmann-Poitiers
patent: 5351095 (1994-09-01), Kerdranvat
patent: 5794257 (1998-08-01), Liu et al.
patent: 5995659 (1999-11-01), Chakraborty et al.
patent: 6154754 (2000-11-01), Hsu et al.
patent: 6272247 (2001-08-01), Manickam et al.
patent: 6373988 (2002-04-01), Thorell et al.
“Quadtree-Structured Recursive Plane Decomposition Coding of Images”, Peter Strobach, IEEE Transactions on signal processing, VOL 39, NO. 6, Jun. 1991.*
“Efficient Quadtree Coding of Images and Video”, Gary J. Sullivan, IEEE Transactions on image processing, VOl 3. No. 3, May 1994.*
Patent application Ser. No.: 09/607,886 Atty Dkt. No.: 00P7773US.
Patent application Ser. No.: 10/007,373 Atty Dkt. No.: 00P9093US01.
Patent application Ser. No.: 09/904,092 Atty Dkt. No.: 00P9094US01.
Patent application Ser. No.: 09/996,271 Atty Dkt. No.: 00P9096US01.
Boudreau Leo
Lu Tom Y.
Siemens Corporate Research Inc.
LandOfFree
Method for identifying graphical objects in large... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method for identifying graphical objects in large..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method for identifying graphical objects in large... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3272553