Semi supervised target recognition in video

US11823453B2 · kind B2 · utility

Assignee

• MICROSOFT TECHNOLOGY LICENSING, LLC · US

Inventors

• Oron Nir · Herzliya, IL
• Maria Zontak · Seattle, US
• Tucker Cunningham Burns · Issaquah, US
• Apar Singhal · Seattle, US
• Lei Zhang · Beijing, CN
• Irit Ofer · Kfar Sava, IL
• Avner Levi · Kiryat Ono, IL
• Haim Sabo · Netanya, IL
• Ika Bar-Menachem · Tel Aviv-Yafo, IL
• Eylon Ami · Givatayim, IL
• Ella BEN TOV · Tel Aviv-Yafo, IL

Key dates

• Filing date: Feb 1, 2022
• Grant date: Nov 21, 2023
• Expiry date: Feb 1, 2042

Classification

• Technology area (CPC G): Physics
• CPC primary: G06V20/47
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

The technology described herein is directed to a media indexer framework including a character recognition engine that automatically detects and groups instances (or occurrences) of characters in a multi-frame animated media file. More specifically, the character recognition engine automatically detects and groups the instances (or occurrences) of the characters in the multi-frame animated media file such that each group contains images associated with a single character. The character groups are then labeled and used to train an image classification model. Once trained, the image classification model can be applied to subsequent multi-frame animated media files to automatically classifying the animated characters included therein.