Methods and systems for enhancing image quality for documents with highlighted content

A method comprising:

• receiving an input;
• automatically detecting a highlighted content from the received input and marking the remaining content as a non-highlighted content;
• automatically segmenting the highlighted content into a text layer and further segmenting the non-highlighted content into an image layer and a text layer;
• assigning a resolution value to the text layer corresponding to the highlighted content and a resolution value each to the image layer and the text layer corresponding to the non-highlighted content, wherein the resolution value assigned to the highlighted content is greater than the respective resolution value for the image layer and the text layer, to improve quality of the highlighted content;
• compressing the text layer corresponding to the highlighted content using JBIG2 compression and further compressing the image layer using JPEG compression and the text layer using JBIG2 compression;
• and
• integrating the text layer corresponding to the highlighted content and the image layer and the text layer corresponding to the non-highlighted content to generate an image data in an MRC file format.

An image processing system comprising:

• a processor;
• a content identification unit coupled to the processor, the content identification unit:
• to detect a highlighted portion from a received document;
• and
• to automatically segment the highlighted portion as a text layer and further segment the remaining portion as a separate text layer and an image layer;
• a document generation unit coupled to the processor, the document generation unit to:
• assign a resolution to the highlighted portion, wherein the resolution assigned to the highlighted portion is greater than a resolution for the remaining portion, to improve quality of the highlighted portion;
• and
• integrate the text layer corresponding to the highlighted portion and the separate text layer and the image layer to generate a scanned document in a Mixed Raster Content (MRC) file format.