Amazon Technologies, Inc.

Vasanth Elancheralathan

Lokesh Joshi

Ramya Dass

Rajasekaran Nagarajan

Hemanthkumar S

Medhini Gajapathy

Senthilkumar Ponnappan

Vignesh Jayaraman

Sanjay Singh

Kaushik Ramachandran

Gajendran Mani

Prasanna Somasundaram

Gowtham Chandrasekar

Hemant Kumar Agrawal

Palanisamy Chinnusamy

Nishanth Madichetti

Aaishwarya Ramalingam

Systems and methods for determining semantic relationships in digital content are provided. Digital content may be processed to detect and extract one or more entities present in at least a subset of the digital content. The entities may include at least one image and at least one body of text. One or more aspects of the entities may be analyzed to filter out a subset of the entities based on a determined importance of the entities to the subset of the digital content. An anchor entity may be determined from one or more remaining entities after the filtering. Relationships between the one or more remaining entities and the anchor entity may be determined, and a presentation pattern for presenting the related entities may be determined. The presentation pattern may be stored to a repository and used as training data to detect future relationships within digital content.

Semantic detection and rendering in digital content

Images in e-book and other electronic media content can be automatically enhanced for viewing on client devices, using various image categories, attributes, and expected qualities. Should systems and methods determine, based on the categories and attributes, that a given media object does not satisfy at least one rule for optimized presentation of the content on a particular client device, an updated presentation of the content can be generated, possibly in accordance with a predetermined specification. The updating may be in the form of image enhancement through adjustment of the size of the images in the media object. Machine learning schema can assist in recognizing images by category, importance and readability scoring, and in adjusting the images for optimal viewing.

Automated optimization of displayed electronic content imagery

Systems and methods for digital content editing and assessment are described. Software tools may perform heuristic processing of the digital content, producing computer-generated edits to the digital content. In addition, a user may accept, reject, or modify these computer-generated edits, and/or make additional edits to other portions of the digital content. The digital content may be subjected to additional processing steps prior to completion or publication. Various metrics associated with the editing of the digital content may be stored and analyzed to evaluate the performance of the digital content editing. This evaluation may be used to make changes to the editing process, such as to refine the detection heuristics for automated editing or modify other processes of the editing workflow.

Digital content editing and publication tools

Systems and methods for analyzing letters in an image of text are described. For each letter, a number of properties are determined and the letters are classified into letterform classes. The properties may include independent letter properties based on only the letter itself, such as a slanted bounding box encompassing the letter. The properties may also include dependent letter properties that are based, in part, on other letters, such as adjacent letters or letters in the same word or line.

Optical character recognition

Embodiments of methods, systems and storage media associated with enhancing glyphs in a scanned image are disclosed herein. Based on properties of a glyph, one or more stroke kernels representing the glyph may be identified or generated. The stroke kernels may be compared to both the glyph and one another, and one or more preferred stroke kernels may be identified. The preferred stroke kernels may be stored and applied to the glyph to enhance the glyph.

Image glyph enhancement

Growing community of inventors

Puducherry, India

Vasanth Elancheralathan