USPTO Patent Grant: Neural Network Hair Modification in Digital Images

ChangeBridge: Patent Grants - AI & Computing (G06N)

Published March 24th, 2026

Detected March 25th, 2026

Summary

The USPTO has granted a patent (US12586157B2) to Ulta Salon, Cosmetics & Fragrance, Inc. for a method using generative neural networks to modify hair characteristics in digital images. The patent details a process for altering hair features while maintaining the original face and background.

View original document View source feed page

What changed

The United States Patent and Trademark Office (USPTO) has issued patent US12586157B2 to Ulta Salon, Cosmetics & Fragrance, Inc. This patent covers a computer-implemented method for modifying hair characteristics in digital images using generative neural networks. The process involves receiving an image, applying input parameters to alter hair features via a neural network, and then recombining the modified hair with the original face and background to create a composite image.

This patent grant is primarily relevant for entities involved in digital image processing, AI development, and potentially the beauty or retail sectors where virtual try-on or image manipulation technologies are employed. While this is a patent grant and not a regulatory rule imposing direct compliance obligations, it signifies intellectual property protection for specific AI applications in image modification. Companies operating in this space should be aware of this patented technology to avoid potential infringement issues.

Source document (simplified)

← USPTO Patent Grants

Methods and systems for modifying hair characteristics in a digital image

Grant US12586157B2 Kind: B2 Mar 24, 2026

Assignee

Ulta Salon, Cosmetics & Fragrance, Inc.

Inventors

Xin Chung, Bruce V. Schwartz, Giorgio Patrini, Ajinkya Indulkar, Ghassen Chaabouni, Alberto Gaona, Juan Cardelino

Abstract

An example computer-implemented image processing method includes receiving a digital image including a face area of a person and a background area, receiving an input parameter for modification of a feature of hair on the person, modifying the digital image based on the input parameter utilizing a generative neural network to create a modified digital image in which the feature of the hair on the person is modified, extracting a hair area from the modified digital image, and the face area and the background area from the digital image, and combining the face area and the background area from the digital image with the hair area from the modified digital image to create a composite modified digital image that includes data representing a modified feature of hair on the person from the modified digital image and data representing the face area and the background area from the digital image.