Processing scanned documents

#The present invention generally relates to processing scanned documents, and more specifically, to improving the precision of extracting text from scanned documents.

#Currently available optical character recognition (OCR) techniques aren't always reliable and they often miss-interpret word. This is especially the case when source documents are scanned or faxed documents that include lines, shadows or other abnormalities that obscure text.

#Embodiments of the present invention are directed to processing scanned documents. A non-limiting example computer-implemented method includes obtaining an image of the scanned document and identifying a boundary of a portion of the scanned document, wherein the portion includes at least partially obscured text. The method also includes performing optical character recognition on the image of the scanned document to extract text from the document. The method further includes performing additional processing on the text extracted from inside the portion of the document.

#The specifics of the exclusive rights described herein are particularly pointed out and distinctly claimed in the claims at the conclusion of the specification. The foregoing and other features and advantages of the embodiments of the invention are apparent from the following detailed description taken in conjunction with the accompanying drawings in which:

#FIG. 1 illustrates a flow diagram of a method for processing a scanned document in accordance with one or more embodiments of the present invention;

#FIG. 2 illustrates a scanned document with suspect portions according to one or more embodiments of the present invention;

#The diagrams depicted herein are illustrative. There can be many variations to the diagrams or the operations described therein without departing from the spirit of the invention. For instance, the actions can be performed in a differing order or actions can be added, deleted or modified. Also, the term “coupled” and variations thereof describes having a communications path between two elements and does not imply a direct connection between the elements with no intervening elements/connections between them. All of these variations are considered a part of the specification.

#One or more embodiments of the present invention provide an improved method for processing a scanned document. In exemplary embodiments, image segmentation techniques are used to identify regions of a scanned document that are suspect, i.e., regions that have lines, shadows or other abnormalities that obscure text. By identifying the boundaries of the suspect regions, enhanced, i.e., more aggressive, processing techniques can be applied to the text extracted from the suspect region as compared to text from other regions of the document. As a result, the accuracy of the data that is extracted from scanned images is increased.

#Turning now to FIG. 1, a flow diagram of a method 100 for processing a scanned document in accordance with an embodiment is shown. In one or more embodiments of the present invention, the method 100 may be embodied in software that is executed by computer elements located within a network that may reside in the cloud, such as the cloud computing environment 50 described hereinabove and illustrated in FIGS. 3 and 4. In other embodiments, the computer elements may reside on a computer system or processing system, such as the processing system 300 described hereinabove and illustrated in FIG. 5, or in some other type of computing or processing environment.