Browse Prior Art Database

Dynamic Photo Cropping / Mashup Based on Cognitive Evaluation Disclosure Number: IPCOM000246656D
Publication Date: 2016-Jun-24
Document File: 1 page(s) / 20K

Publishing Venue

The Prior Art Database


Disclosed is a method and system for dynamic image generation based on entity analysis, existing images, audience context, and confidence of a cohesive image.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 59% of the total text.

Page 01 of 1

Dynamic Photo Cropping / Mashup Based on Cognitive Evaluation

Current methods for cropping and merging elements of two or more photographs to form one image are manual, extremely labor and time intensive. Many examples of entity extraction exist that provide means for analyzing a photograph and determining the entities within it.

An improved method is needed for using information from two or more images to generate an entirely new image.

The novel contribution is a system that can consider a variety of images and generate a cohesive and relevant photo mashup based on input entities. The system considers the input entities, input audience, and context. It then scans through a database or search engine of photos, selects 1-n photos based on confidence, removes non-relevant entities in the images, and generates a new image utilizing tooling to make the image more cohesive and natural.

The system applies to both people and objects as photograph subjects, and can mashup the subject with text such as for advertising purposes, show people, the product, and the text in the image. The system can look at and adjust the hue/brightness/tone of an image according to the other images in the mashup to make a cohesive photo.

The system associates a level of confidence with the cohesiveness of a photo, which can dictate the images used such as two photos of different entities might have extremely high confidence and relevance, but together do not make sense. The system can add s...