A method for automatically locating and recognizing amount data on a document by scanning the document to first locate a particular symbol, such as a dollar sign "$", and then using the located "$" to determine the document area containing the amount data to be recognized. Elements of the "$" symbol and amount characters are extracted from a gray-level image using binary seed and mask images derived using different gray-level thresholds. Operation is such that black pixels found in the higher threshold seed image are propagated in the lower threshold mask image to form connected components which are used for character recognition.
A system, method and program product for rotating a first image in an image buffer such that the resulting, rotated image is substantially free of an aliasing error, i.e., broken lines, stair stepped edges, etc., is disclosed. An algorithm is applied to the first image that uses weighted sums of data points of the first image to create the rotated image. The weighting is based on the skew angle and data point location of the first image. The resulting rotated image also has a reduced data storage space requirement compared to rotated images created by prior art techniques.
