Real Time Translation Method for Games using Machine Learning Model
OwnerShih-Pang Wang, Guan-Lin Cheninventors
Life of this patent
Estimating the term…
Abstract
A real time translation method for a game includes extracting features from video frames using computer vision and a database, performing an association process to find a machine learning model best matching the features for translation, obtaining texts in the game through optical character recognition (OCR), preprocessing the texts, translating the texts using the machine learning model to generate translated texts, and rendering the translated texts to images of the video frames for displaying the images with the translated texts on a display device.
Claims15
A real time translation method for a game, comprising:
- extracting features from video frames using computer vision and a database;
- performing an association process to find a machine learning model best matching the features for translation;
- obtaining texts in the game through optical character recognition (OCR);
- preprocessing the texts;
- translating the texts using the machine learning model to generate translated texts;
- and
- rendering the translated texts to images of the video frames for displaying the images with the translated texts on a display device.
A real time translation method for a game, comprising:
- extracting features from video frames using computer vision and a database;
- performing an association process to find weightings of N machine learning models best matching the features for translation;
- obtaining texts in the game through optical character recognition (OCR);
- preprocessing the texts;
- translating the texts using the N machine learning models with the weightings to generate translated texts;
- and
- rendering the translated texts to images of the video frames for displaying the images with the translated texts on a display device.
Dependencies are inferred from the claim text.