Abstract: Systems and methods for improving automated processing of electronic media items are disclosed. In one embodiment, a computer system identifies a first set of regions of a page of an electronic media item, and a respective region type for at least one region of the first set, where the identification of the respective region type is based on one or more typographical features, historical data, and, optionally, the position and/or dimensions of the region. The computer system receives an identification by a user of a second set of regions of the page and a respective region type for at least one region of the second set, and then modifies the historical data when there is a difference between the regions and respective region types of the first set, and the regions and respective region types of the second set.

Abstract: A method for detecting and correcting skew in scanned vertical text includes identifying an image of vertically oriented characters, and identifying a plurality of vertical lines corresponding to character positions of the vertically oriented characters in the image. The method further includes generating an average slope of a subset of the plurality of lines, and causing the image to be deskewed based on the average slope.