Image Processing for Data Capture
Original Publication Date: 1982-Nov-01
Included in the Prior Art Database: 2005-Nov-11
Software Patent Institute
Yoshiaki Shirai: AUTHOR [+3]
AbstractAs hardware costs decrease, we will see the implementation of increasingly complex image processing techniques, including several methods for recovering 3-D geometry from 2-D images.
THIS DOCUMENT IS AN APPROXIMATE REPRESENTATION OF THE ORIGINAL.
This record contains textual material that is copyright ©; 1982 by the Institute of Electrical and Electronics Engineers, Inc. All rights reserved. Contact the IEEE Computer Society http://www.computer.org/ (714-821-8380) for copies of the complete work that was the source of this textual material and for all use beyond that as a record from the SPI Database.
Image Processing for Data Capture
Electrotechnical Laboratory, Japan
As hardware costs decrease, we will see the implementation of increasingly complex image processing techniques, including several methods for recovering 3-D geometry from 2-D images.
In recent years a number of image processing systems have been developed for automatic manufacturing applicatipnsi~4 such as bonding of IC chips and inspection of printed circuit boards. Most of these systems employ simple image processing techniques developed several years ago. Their success is due mainly to the decreasing cost of hardware over the past few years, both for input devices and processors. Since this trend is expected to continue, it will be possible to apply more complex techniques to industry.
Recently, data capturing systems have been proposed in various fields, including the recognition of handwritten circuit designs and data capturing for three-dimensional objects. Some of these systems are already undergoing feasibility tests.
The role of image processing in human-computer interaction includes input of handwritten drawings, checks on the consistency of input data, and direct capture of data from real scenes. This article describes some of the image processing methods designed to accomplish these tasks.
Recognition and interpretation of line drawings
Recognition of handwritten designs.
Recognition of figures in books or documents has been studied intensively in the context of CAD or of rice automation. The objects of recognition are figures that have already been drawn by humans for humans, and figures to be drawn in the future for both humans and computers. Recognition of the first type is beyond today's technology; recognition of the second is easier because appropriate restrictions can be imposed on the drawings. This approach (off-line recognition) is often compared to conventional interac tive methods using light pens or data tablets (on-line recognition). The main features of off-line recognition are that
figures of good quality can be drawn on large pieces of paper with high resolution,
figures can be drawn without any special devices, and
the cost of an off-line recognition machine is less than that of many on-line interactive devices.
One of the early experimental systems is the line drawing editors developed at the Bell Laboratory. This system employs a computer-controlled TV camera as an input device and obtains an image with 512x512 picture elements. It recognizes handwritten logic circuit
IEEE Computer Society, Nov 01...