发明名称 Compensation for print shift in standardized forms to facilitate extraction of data therefrom
摘要 A method comprising receiving a candidate image, including a first field, a second field, a first data element, and a second data element. The processor receives a definition of first and second form zones. The processor evaluates the first data element to determine a first measure of a similarity and the second data element to determine a second measure of a similarity. The processor computes a similarity value indicative of an overall similarity, iteratively compares the overall similarity to a previous iteration, modifies the positions of the form zones, and repeats the evaluating and computing based on the modified positions until the computed similarity value meets a threshold.
申请公布号 US9411547(B1) 申请公布日期 2016.08.09
申请号 US201514811069 申请日期 2015.07.28
申请人 DST Technologies, Inc. 发明人 Bessinger Keith;Kirchmeier John
分类号 G06F3/12;H04N1/00 主分类号 G06F3/12
代理机构 Lempia Summerfield Katz LLC 代理人 Lempia Summerfield Katz LLC
主权项 1. A computer implemented method comprising: receiving, by a processor, a candidate image, wherein the candidate image contains a first field and a first data element positioned in a first position with respect thereto within the candidate image, and a second field and a second data element positioned in a second position with respect thereto within the candidate image, and storing the candidate image in a memory coupled with the processor; receiving, by the processor, a definition of first and second form zones, and storing the definition of the first and second form zones in a memory coupled with the processor, wherein the first form zone defines a third position at which the first data element is expected to be positioned with respect to the first field and the second form zone defines a fourth position at which the second data element is expected to be positioned with respect to the second field; evaluating, by the processor, the first data element with respect to the third position to determine a first measure of a similarity of the first position to the third position and the second data element with respect to the fourth position to determine a second measure of a similarity of the second position to the fourth position; computing, by the processor, a similarity value indicative of an overall similarity of the first and second positions to the third and fourth positions based on the first and second measures; and iteratively comparing, by the processor, the similarity value to a similarity value of a previous iteration, modifying, by the processor, the third and fourth positions and repeating the evaluating and computing based on the modified third and fourth positions until the computed similarity value meets a threshold.
地址 Kansas City MO US