Multiple image input for optical character recognition processing systems and methods
作者： Donald B. Curtis , Shawn Reid
DOI:
关键词: Computer science 、 Image (mathematics) 、 Multiple image 、 Computer vision 、 Process (computing) 、 Optical character recognition 、 Artificial intelligence
摘要: A method of processing an image includes receiving a digital version the image, through at least two binarization processes to thereby create first and second binarization, optical character recognition process OCR output file. Processing compiling metrics associated with The also using metrics, in part, select final file from among files.
lens.org 参考文章(41)
Celine Thillou, Bernard Gosselin, None, SEGMENTATION-BASED BINARIZATION FOR COLOR DEGRADED IMAGES ICCVG. pp. 808- 813 ,(2006) , 10.1007/1-4020-4179-9_117
Joerg Wuertz, Markus Graulich, Method and system for interleaving OCR and ABL for automated mail sorting ,(2000)
Richard S. Andel, Robert S. Lunt, Detection and identification of postal metermarks ,(2006)
Edward Ovando, Richard Andel, Segmenting touching characters in an optical character recognition system to provide multiple segmentations ,(2003)
Carstan Steger, System and method for object recognition ,(2001)
Yoko Fujiwara, Image recognition apparatus, method and program product ,(2001)
Tomoyuki Shimmura, Hitoshi Hayama, Takanobu Kameda, Kenji Watanabe, Apparatus and method for processing character information ,(1997)
Gregory K. Myers, Hrishikesh Aradhye, Method and apparatus for recognition of symbols in images of three-dimensional scenes ,(2004)
Satoshi Naoi, Katsuhito Fujimoto, Atsuko Ohara, Apparatus for extracting ruled line from multiple-valued image ,(2004)