-
公开(公告)号:US09141877B2
公开(公告)日:2015-09-22
申请号:US13573899
申请日:2012-12-17
申请人: Richard Linderman , Oinru Qiu , Qing Wu
发明人: Richard Linderman , Oinru Qiu , Qing Wu
CPC分类号: G06K9/62 , G06K9/64 , G06K9/723 , G06K2209/01
摘要: A method for context-aware text recognition employing two neuromorphic computing models, auto-associative neural network and cogent confabulation. The neural network model performs the character recognition from input image and produces one or more candidates for each character in the text image input. The confabulation models perform the context-aware text extraction and completion, based on the character recognition outputs and the word and sentence knowledge bases.
摘要翻译: 一种使用两个神经形态计算模型,自动关联神经网络和有力闭塞的语境识别文本识别的方法。 神经网络模型从输入图像执行字符识别,并为文本图像输入中的每个字符产生一个或多个候选。 混合模型基于字符识别输出和单词和句子知识库,执行上下文感知文本提取和完成。