The following operators can be used to better focus your queries.
( ) , AND, OR, NOT, W/#
? single char wildcard, not at start
* multi char wildcard, not at start
(Cat? OR feline) AND NOT dog?
Cat? W/5 behavior
(Cat? OR feline) AND traits
Cat AND charact*
This guide provides a more detailed description of the syntax that is supported along with examples.
This search box also supports the look-up of an IP.com Digital Signature (also referred to as Fingerprint); enter the 72-, 48-, or 32-character code to retrieve details of the associated file or submission.
Concept Search - What can I type?
For a concept search, you can enter phrases, sentences, or full paragraphs in English. For example, copy and paste the abstract of a patent application or paragraphs from an article.
Concept search eliminates the need for complex Boolean syntax to inform retrieval. Our Semantic Gist engine uses advanced cognitive semantic analysis to extract the meaning of data. This reduces the chances of missing valuable information, that may result from traditional keyword searching.
An improved segmentation method and system for optical character recognition (OCR) applications on fixed-pitch machine-printed documents is described.
English (United States)
This text was extracted from a PDF file.
This is the abbreviated version, containing approximately
66% of the total text.
Page 1 of 1
Segmentation Method for Fixed Pitch and Machine Printed Documents
An improved segmentation method and system for optical character
recognition (OCR) applications on fixed-pitch machine-printed documents is
The segmentation system utilizes the print data to find the centerline location
of each vertically projected image segment. Starting at the left end of a line of
print data, a check is made to determine whether or not there are any two
consecutive centerlines which are close to one, or a multiple of standard pitch
distance apart. A proper origin for the pitch sequence can be deduced, and
reference coordinates with such standard pitch are constructed.
The accumulative pitch deviation is measured as the distance between the
centerline of each vertically projected image segment and the corresponding
reference grid location. Incorrect data will be caused by broken and touching
characters, so such erroneous data will be rejected in the distortion analysis by
using only deviations smaller than some empirical value. The accumulative pitch
deviations are then added to the standard pitch reference as compensations. In
practice, it is preferable to use the average value of the deviation measurements
over a group of character spaces, say, 10, in order to avoid any local fluctuations.
The method can be easily implemented and incorporated into any pitch-
based segmentation system. Once the baseline is detected (by known
techniques), vertical projections on the sc...