ADOBE had 14 patents in cybersecurity during Q4 2023. ADOBE Inc filed patents for face anonymization techniques and privacy preserving document analysis systems. The face anonymization techniques involve generating an anonymized face by using machine learning to mix target and reference face encodings. The privacy preserving document analysis systems derive insights from digital documents without accessing the content, by capturing visual or contextual features and creating stamp representations based on machine learning-generated stamp encoding models. These techniques allow for determining document similarity without accessing the actual content. GlobalData’s report on ADOBE gives a 360-degreee view of the company including its patenting strategy. Buy the report here.

ADOBE grant share with cybersecurity as a theme is 85% in Q4 2023. Grant share is based on the ratio of number of grants to total number of patents.

Recent Patents

Application: Face anonymization in digital images (Patent ID: US20230360299A1)

The patent filed by ADOBE Inc. describes face anonymization techniques that utilize a digital object editing system to generate an anonymized face by combining features from a target face and a reference face. The system employs machine learning to extract encodings of the target and reference faces, generate a mixed encoding, and then use this mixed encoding to create a mixed face that replaces the target face in the digital image. The method involves selecting a reference face based on similarity to the target face, extracting encodings, and using linear interpolation to mix the encodings for face generation.

The system described in the patent includes a processing device coupled to a memory component that performs operations such as receiving a target digital image, generating a search query for a reference object, executing a search of digital images, automatically selecting the reference digital image based on similarity scores, and generating a mixed object based on the target and reference objects. The system utilizes machine learning models to select the reference image, extract encodings, and mix them to create the mixed object. The patent also covers a non-transitory computer-readable storage medium storing executable instructions for performing similar operations related to face anonymization using a target face, a reference face, and machine learning techniques for generating a mixed face.

To know more about GlobalData’s detailed insights on ADOBE, buy the report here.

Premium Insights

From

The gold standard of business intelligence.

Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.

GlobalData

GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.

GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.