17988377. Image-Based Searches for Templates simplified abstract (ADOBE INC.)

Image-Based Searches for Templates

Organization Name

ADOBE INC.

Inventor(s)

Brian Eriksson of San Jose CA (US)

Wei-ting Hsu of San Jose CA (US)

Santiago Pombo of San Francisco CA (US)

Sandilya Bhamidipati of Mountain View CA (US)

Rida Khan of Saratoga CA (US)

Ravali Devarapalli of San Jose CA (US)

Maya Christmas Davis of San Francisco CA (US)

Lam Wing Chan of Sunnyvale CA (US)

Konstantin Blank of Seattle WA (US)

Jason Omid Kafil of Los Angeles CA (US)

Di Ni of San Jose CA (US)

Image-Based Searches for Templates - A simplified explanation of the abstract

This abstract first appeared for US patent application 17988377 titled 'Image-Based Searches for Templates

Simplified Explanation

The abstract describes a patent application related to image-based searches for templates using a machine learning model to generate embedding vectors and identify templates for replacement of candidate digital images.

• The patent application involves a computing device implementing a search system for image-based searches.
• The search system uses a machine learning model to generate embedding vectors representing digital images.
• Templates containing candidate digital images are identified based on distances between embedding vectors.
• A template is selected based on the distance between the embedding vector of the candidate digital image and the input digital image.
• The search system outputs a digital image with the candidate digital image replaced by the input digital image.

Potential Applications

This technology can be applied in various fields such as e-commerce, graphic design, and content creation to automate the process of replacing images in templates.

Problems Solved

This technology streamlines the process of replacing images in templates, saving time and effort for users who frequently work with digital images.

Benefits

The technology offers a more efficient and accurate way to customize templates with different images, enhancing the overall user experience and productivity.

Potential Commercial Applications

One potential commercial application of this technology is in online design platforms where users can easily customize templates with their own images.

Possible Prior Art

Prior art in this field may include image recognition and replacement technologies used in graphic design software and online editing tools.

What is the impact of this technology on user experience in graphic design software?

This technology significantly improves user experience in graphic design software by simplifying the process of replacing images in templates, making it more efficient and user-friendly.

How does this technology contribute to the automation of content creation processes?

By automating the process of replacing images in templates, this technology helps streamline content creation processes, saving time and effort for users who need to customize templates with different images.

Original Abstract Submitted

In implementations of image-based searches for templates, a computing device implements a search system to generate an embedding vector that represents an input digital image using a machine learning model. The search system identifies templates that include a candidate digital image to be replaced by the input digital image based on distances between embedding vector representations of the templates and the embedding vector that represents the input digital image. A template of the templates is determined based on a distance between an embedding vector representation of the candidate digital image included in the template and the embedding vector that represents the input digital image. The search system generates an output digital image for display in a user interface that depicts the template with the candidate digital image replaced by the input digital image.