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.
This method enables to dsitinct between similar
English (United States)
This text was extracted from a PDF file.
100% of the total text.
Page 1 of 1
The method of distinction of similar characters by making dynamic difference masks of templates
When we use optical character reader (OCR), OCR sometimes fails to distinguish between similar characters (e.g. 0 and 8). Especially when we use normalized correlation for perception of characters, the possibility of failure increases. The reason is that the method of normalized correlation processes all of area. This means that if the similar portion is larger than different one, the result might be failed. Therefore we proposed new procedure for it. I list below. 1 Compare a template to a character to read. 2 Repeat 1 until all templates compared. 3 If there are two candidates, select two templates indicating high score (T1, T2). 4 Search the center of TI by using normalized correlation. 5 Fit the center of both of templates and make exclusive new template (NT1). 6 Search the center of T2 by using normalized correlation. 7 Fit the center of both of templates and make exclusive new template (NT2). 8 Compare the character to NT1 and NT2. Decide the most similar pattern by using normalized correlation.
Disclosed by International Business Machines Corporation