Screen had 27 patents in artificial intelligence during Q2 2024. Screen Holdings Co Ltd filed patents related to image processing, print control, and cell counting methods. The image processing apparatus estimates region types in an image using a feature extractor and an identifier. The print control device recommends print parameter values based on print result logs from multiple inkjet printing apparatuses. The cell counting method involves generating heat maps from images of cell masses at different depths, detecting peaks, and counting cells using a machine learning model trained on teacher images and ground truth images. GlobalData’s report on Screen gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
Access deeper industry intelligence
Experience unmatched clarity with a single platform that combines unique data, AI, and human expertise.
Screen had no grants in artificial intelligence as a theme in Q2 2024.
Recent Patents
Application: Image processing apparatus, learning method of feature extractor, updating method of identifier, and image processing method (Patent ID: US20240193907A1)
The patent filed by Screen Holdings Co Ltd describes an image processing apparatus that estimates the region type of each pixel in an image using a feature extractor and an identifier. The feature extractor outputs a feature vector for each pixel, while the identifier estimates the region type based on the feature vector. The apparatus can differentiate between different types of regions, such as defect regions in captured images, by adjusting the feature extractor and identifier to improve estimation accuracy.
The claims of the patent detail the components and methods of the image processing apparatus, including the use of a three-dimensional feature space, machine learning models, and nearest neighbor identifiers. The learning method for the feature extractor involves adjusting parameters to separate feature vectors of different region types in the feature space. Additionally, the patent describes a user feedback mechanism for relearning the feature extractor based on user input. The updating method for the identifier involves redefining known regions in the image to improve estimation accuracy. Overall, the patent outlines a comprehensive approach to estimating region types in images using a combination of feature extraction and identification techniques.
To know more about GlobalData’s detailed insights on Screen, 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.
