Amazon Technologies, Inc.

Adarsh Natarajan

Viswanath Sankaranarayanan

Prannoy Vargis C

Sairam Reddi

Satishkumar Kothandapani Shanmugasundaram

Tony Johri

Chirag Chheda

Shataneek Guha

Srivathsan Rajagopalan

Systems, methods, and computer-readable media are disclosed for constructing fonts from scanned images. In one embodiment, a method may include receiving a scanned image with a first glyph and a second glyph that correspond to a character in the image. The method may include generating an image representative of each of the first glyph and the second glyph, determining a default positioning of the first character, determining a positional reference line indicative of an alignment of certain characters, and a third positional reference line indicative of an alignment of different characters. The method may include determining an adjustment for the first glyph by determining a distance between the default positioning and the second positional reference line. The method may include assigning an identifier to the first glyph and generating a font file to be executed by a renderer for rendering the source text.

Constructing fonts from scanned images for rendering text

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.

Adaptive editing in user interface applications

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.

Skew detection for vertical text

A method for identifying characters in scanned images of objects includes identifying a first set of characters in a scanned image of an object based on connected component analysis, identifying a second set of characters for the object based on an optical character recognition (OCR) process on the image of the object, and combining the first set of characters with the second set of characters to create a third set of characters.

Identifying characters in grid-based text

Determination of an underlying grid structure that facilitates layout of East Asian text is disclosed. The underlying grid structure includes both a size of character frames and a size of a text block frame. The East Asian text may be obtained from a scan of printed material that has the text formatted according to layout conventions established by the publisher. The text may be reformatted to appear on a display of an electronic device in a manner similar to the formatting in the original scanned document. Reformatting may include reflowing the text in order to fit a greater or lesser number of characters on a line. The reflowing may maintain character spacing from the original document and follow formatting rules against locating certain characters at the start or end of a line.

Growing community of inventors

Kerala, India

Adarsh Natarajan