Semantic object selection

Patent metadata

Field	Value
Publication number	US-9129191-B2
Application number	US-201314107520-A
Country	US
Kind code	B2
Filing date	Dec 16, 2013
Priority date	Dec 16, 2013
Publication date	Sep 8, 2015
Grant date	Sep 8, 2015

Abstract

Techniques are disclosed herein that enable digital images to be segmented based on a user's semantic input. In other words, given an input image of a person walking a dog adjacent to a tree, a user can simply provide the semantic input “dog” and the system will segment the dog from the other elements in the image. If the user provides other semantic input, such as “person” or “tree”, the system will segment the person or the tree, respectively, from the same image. Using semantic input advantageously eliminates any need for a user to directly interact with the input image through a tedious process of painting brush strokes, tracing boundaries, clicking target points, and/or drawing bounding boxes. Thus semantic input represents an easier and more intuitive way for users to interact with an image segmentation interface, thereby enabling novice users to take advantage of advanced image segmentation techniques.

First claim

What is claimed is:

1. A non-transient computer readable medium having instructions encoded thereon that, when executed by one or more processors, causes an object proposal validation process to be carried out, the process comprising:
populating an exemplar retrieval database with exemplar images obtained by querying a text-image database based on semantic input, wherein the semantic input corresponds to target data which is to be segmented from an input image;
generating n obj…

Assignees

• Adobe Systems Inc

Inventors

• Cohen Scott
• Price Brian Lynn
• Ahmed Ejaz

Classifications

• G06V10/85

  Physics · mapped topic

• G06V10/774

  Physics · mapped topic

• G06V10/761

  Physics · mapped topic

• G06F18/214

  Physics · mapped topic

• G06F18/22

  Physics · mapped topic