Safran had 17 patents in artificial intelligence during Q4 2023.Safran SA’s patents filed in Q4 2023 focus on using neural networks to generate mattes for portraits on identity documents and identifying document types through neural network processing of document images. The first patent involves training a matting neural network with standardized images depicting human faces, while the second patent involves matching features from document images with reference features to determine the type of document. GlobalData’s report on Safran gives a 360-degreee view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
Safran grant share with artificial intelligence as a theme is 47% in Q4 2023. Grant share is based on the ratio of number of grants to total number of patents.
Recent Patents
Application: Method and system for training matting neural network, and method and device for generating portrait to be used on identity document (Patent ID: US20230409896A1)
Safran SA has filed a patent for a computer-implemented method and system to train a matting neural network for generating mattes to create portraits for identity documents. The method involves obtaining standardized images conforming to a template that requires each image to depict a human face. These standardized images are generated by adjusting input images to meet specific size and distance criteria outlined in the template. The system includes a computing device that executes instructions to adjust input images, train the matting neural network, generate mattes, and create portraits based on the mattes, ensuring compliance with the template requirements.
The patent claims detail the steps involved in training the matting neural network, adjusting input images to meet template specifications, and generating standardized images for creating portraits. The method includes scoring input images to select the major view, determining dimensions based on distance between target points, and resizing images to standard sizes. The system also involves extracting foreground images, combining them with background images, and adjusting the composite image to meet identity document requirements. Additionally, the template specifies that standardized images should feature a frontal view of the full human face, with the method ensuring that the generated portraits adhere to these guidelines. The computing device is designed to streamline the process of creating portraits for identity documents by utilizing a trained matting neural network and standardized images that meet specific criteria outlined in the template.
To know more about GlobalData’s detailed insights on Safran, buy the report here.
Data 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, 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.
