| 摘要 |
A valuable document identification method and system are provided. The method comprises, detecting features in different space ranges of a valuable document, and obtaining multi-source information ©={X i ,X j ,...,X n }, wherein X i ˆ©X j ‰ Õ, or X i ˆ©X j ‰ Õ and X i < = > X j ; labeling the space position of X j with X i according to semantic constraints of X i and X j , and obtaining position constraints ¨ ij (x, y); extracting a characteristic value f i from X i , and extracting a characteristic value f j from X j according to the position constrains ¨ ij (x, y); determining whether f i , f j meet the characteristic criteria of the valuable document, if yes, then receiving the valuable document, or else, rejecting the valuable document. The method enables improved reliability and robustness of the valuable document identification system. |
