Systems and methods for generating typographical images or videos
AssigneeAdobe Inc.
InventorIonut Mironica
Life of this patent
Estimating the term…
Abstract
This disclosure involves automatically generating a typographical image using an image and a text document. Aspects of the present disclosure include detecting a region of interest from the image and generating an object template from the detected region of interest. The object template defines the areas of the image, in which words of the text document are inserted. A text rendering protocol is executed to iteratively insert the words of the text document into the available locations of the object template. The typographical image is generated by rendering each word of the text document onto the available location assigned to the word.
Claims20
A computer-implemented method comprising:
- receiving an image including an object;
- receiving text data;
- detecting a region of interest within the image using a trained neural network, the region of interest including the object;
- generating an object template from the region of interest, the object template defining an area of the object, in which the text data is to be inserted;
- and
- inserting the text data into the object template to visually form a contour of the object of the image.
A system, comprising:
- one or more processors;
- and
- a non-transitory computer-readable storage medium containing instructions which, when executed on the one or more processors, cause the one or more processors to perform operations including:
- receiving a video feed including a plurality of image frames;
- receiving text data;
- detecting, using a neural network, a region of interest within an image frame of the plurality of image frames of the video feed;
- generating a template from the region of interest, the template defining an area of the image frame, in which the text data is to be inserted;
- and
- inserting the text data into the template, the text data visually forming an object of a typographical image.
A computer-program product tangibly embodied in a non-transitory machine-readable storage medium, including instructions configured to cause a processing apparatus to perform operations including:
- receiving an image including one or more edges;
- receiving text data;
- detecting a region of interest within the image using a trained neural network, the region of interest including the one or more edges;
- generating an edge template from the region of interest, the edge template defining an area of the image, in which the text data is to be inserted;
- and
- inserting the text data into the edge template creating a typographical image that visually presents the text data as the one or more edges of the image.
Dependencies are inferred from the claim text.