The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.
The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.
Patent No.:
Date of Patent:
Jul. 05, 2016
Filed:
Jan. 29, 2015
Konica Minolta Laboratory U.s.a., Inc., San Mateo, CA (US);
Wei Ming, Cupertino, CA (US);
KONICA MINOLTA LABORATORY U.S.A., INC., San Mateo, CA (US);
Abstract
A word segmentation method uses a recursive technique to segment a text line image into word segments. Spacing segments of the line are obtained; an initial word segmentation is performed to classify the spacing segments based on their lengths into candidate character spacing segments and candidate word spacing segments. The initial segmentation result is evaluated to determine whether the candidate character spacing segments still have a bimodal or multi-modal distribution or a large spread in the distribution, or whether the line contains long words and too few words. If the conditions indicate that the initial segmentation is inadequate, another classification step is performed for the candidate character spacing segments to further classify them into new candidate character spacing segments and new candidate word spacing segments. The process is repeated until the word segmentation is deemed adequate based on the evaluation.