US 12,694,469 B2 · Generating customized arrow heads utilizing deep learning

Abstract

The present disclosure is directed toward systems, methods, and non-transitory computer readable media that provide a digital design interface for intuitively creating custom arrows that demonstrate both visual consistency and inherent directionality within vector-based design applications. In particular, in one or more implementations, the disclosed systems receive a request to create a custom arrow from a digital object and a path segment. In addition, the disclosed systems detect that the digital object is within a threshold distance of the path segment and combine the digital object with the path segment to create a custom arrow object. In particular, the disclosed systems utilize a bilateral segmentation machine-learning model to segment the digit object and a symmetry axis detection model to determine an axis of symmetry of the digital object. Moreover, the disclosed systems attach the digital object to an endpoint of the path segment at the axis of symmetry.

Claims20

Dependent claims

A method comprising:

receiving a client device interaction indicating a request to create a custom arrow object;
detecting, based on the client device interaction, that a digital object is within a threshold distance of an endpoint of a path segment;
and
generating a custom arrow object based on the digital object being within the threshold distance by:
segmenting, utilizing a bilateral segmentation machine-learning model, the digital object into a first half segment and a second half segment;
determining, utilizing a symmetry axis detection model, an axis of symmetry of the digital object based on the first half segment and the second half segment;
and
attaching the digital object to an endpoint of the path segment at the axis of symmetry.

5 more elements

A system comprising:

a memory component;
and
one or more processing devices coupled to the memory component, the one or more processing devices to perform operations comprising:
segmenting, utilizing a transformer-based neural network, a digital object into a first half segment and a second half segment by classify pixels in an image comprising the digital object as background pixels, first half pixels, or second half pixels;
determining an axis of symmetry of the digital object based on the first half segment and the second half segment;
and
generating a custom arrow by attaching the digital object to an endpoint of a path segment at the axis of symmetry.

4 more elements

Dependencies are inferred from the claim text.

Generating customized arrow heads utilizing deep learning

Life of this patent

Generating customized arrow heads utilizing deep learning

Life of this patent

Abstract

Claims20