FIELD: physics.
SUBSTANCE: method of determining the orientation of text content lines includes: obtaining a document image by the processing device; transforming the image into a binarized image by executing a binarization operation with respect to this image; identifying a fragment of the binary image that includes one or more lines of the text content; determining a plurality of horizontal white pixel series in one or more text content lines in a given binary image fragment, and a plurality of vertical white pixel series in one or more text content lines in a given binary image fragment; creating the first histogram for the plurality of horizontal series of white pixels and the second histogram for the plurality of vertical series of white pixels; and determining by the device the orientation processing of one or more text content lines in the image based on the first histogram and the second histogram.
EFFECT: increasing the effectiveness of determining the orientation of text content lines in the document image.
45 cl, 14 dwg
Authors
Dates
2017-10-11—Published
2016-06-15—Filed