发明名称 Efficient verification or disambiguation of character recognition results
摘要 Machines, systems and methods for character recognition disambiguation are provided. The method comprises selecting a first set of characters that match a first visual profile based on results of a character recognition process applied to target content; selecting a subset of the first set based on criteria associated with at least one of confidence level with which characters grouped in the subset are recognized or fragmentation associated with the characters grouped in the subset; and disambiguating recognition results for the characters grouped in the subset by displaying the characters along with context information, wherein reviewing two or more of the characters on a display screen along with context information associated with said two or more characters allows a human operator to select one or more suspect characters from among the two or more characters.
申请公布号 US9008428(B2) 申请公布日期 2015.04.14
申请号 US201313751176 申请日期 2013.01.28
申请人 International Business Machines Corporation 发明人 Barkan Ella;Toshinari Itoko;Tzadok Asaf
分类号 G06K9/34;G06K9/46;G06K9/03;G06K9/68 主分类号 G06K9/34
代理机构 代理人 Gooshaw Isaac J.;Sosa Jason H.
主权项 1. A method for character recognition disambiguation, the method comprising: selecting, by one or more processors, a first set of characters that match a first visual profile based on results of a character recognition process applied to target content; selecting, by the one or more processors, a subset of the first set based on criteria associated with at least one of confidence level with which characters grouped in the subset are recognized or fragmentation associated with the characters grouped in the subset; and disambiguating, by the one or more processors, recognition results for the characters grouped in the subset by displaying the characters along with context information, wherein reviewing two or more of the characters on a display screen along with the context information associated with said two or more characters allows a human operator to select one or more suspect characters from among the two or more characters and wherein the context information includes one or more neighboring characters of the target content.
地址 Armonk NY US