.png){kind=icon}
.png){kind=icon}
Return
Bank check processing system
.png){kind=icon}
PRE
AI
DOI：10.1002/(SICI)1098-1098(199624)7:4<392::AID-IMA14>3.0.CO;2-Y.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This article describes a system being developed to process bank checks. To interpret the various items of information contained in the image of a check, many modules are required. These begin with the implementation of image-processing techniques to isolate and identify each category of handwritten information. The relevant recognizers are then used to read the numeric and legal amounts, as well as the date on the check. The recognizers must be able to process digits (in isolated or connected form), handwritten cursive words, and a mixture of numerals and words, the last of which is necessary for the recognition of the date written on checks. While these recognizers have different functions, they can also share certain components. We describe the algorithms used in the implementation of each module, their experimental results, and some connections among the modules. (C) 1996 John Wiley & Sons, Inc.
Keywords:
HANDWRITTEN
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
2.5
Papers:
2.1K
Citations:
2.3K
Organization
No organization information available