Amgen had 16 patents in artificial intelligence during Q1 2024. Amgen Inc has filed patents for various techniques including developing an image library for training AVI models, monitoring biopharmaceutical processes using spectral data, diagnosing equipment performance, regulating cell culture treatment based on imaging, and predicting mixing quality in tanks using a surrogate machine learning model based on CFD. GlobalData’s report on Amgen gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
Amgen grant share with artificial intelligence as a theme is 43% in Q1 2024. Grant share is based on the ratio of number of grants to total number of patents.
Recent Patents
Application: Image augmentation techniques for automated visual inspection (Patent ID: US20240095983A1)
The patent filed by Amgen Inc. describes techniques for developing an image library to train and validate an automated visual inspection (AVI) model, such as an AVI neural network for image classification. One aspect involves using an arithmetic transposition algorithm to generate synthetic images from original images by transposing features like defects onto the original images with pixel-level realism. Additionally, digital inpainting techniques are utilized to create realistic synthetic images by adding, removing, or modifying defects or other features depicted in the original images. Quality control techniques are also employed to evaluate the suitability of image libraries for training AVI models and to determine if individual images are appropriate for inclusion in such libraries.
The patent further details a method for generating synthetic images by transferring features onto original images, involving steps such as receiving or generating feature and surrogate area matrices, normalizing the feature matrix, and generating the synthetic image based on these matrices. The system described in the patent includes processors and computer-readable media storing instructions to receive feature and surrogate area matrices, normalize the feature matrix, and generate synthetic images. These synthetic images can be used to train a neural network for automated visual inspection, enhancing the efficiency and accuracy of image classification processes. Additionally, the system includes techniques for normalizing feature matrices on a per-row or per-column basis, generating histograms, and determining desired rotations based on the position of the area to which the feature will be transferred, all aimed at improving the quality and realism of the synthetic images generated for training AVI models.
To know more about GlobalData’s detailed insights on Amgen, 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.
