Koninklijke Philips has developed a system for annotating image data, allowing users to iteratively label images. The system combines a label propagation algorithm and a machine-learned classifier to generate and correct labels based on user input. The classifier is retrained using user-verified labels for improved accuracy. GlobalData’s report on Koninklijke Philips gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
Discover B2B Marketing That Performs
Combine business intelligence and editorial excellence to reach engaged professionals across 36 leading media platforms.
According to GlobalData’s company profile on Koninklijke Philips, Treatment progress monitoring was a key innovation area identified from patents. Koninklijke Philips's grant share as of January 2024 was 57%. Grant share is based on the ratio of number of grants to total number of patents.
Image data annotation system with iterative user verification
A recently granted patent (Publication Number: US11886543B2) describes a system for annotating image data using a combination of label propagation algorithms and machine-learned classifiers. The system includes an input interface to access the image data, a user interface subsystem for user interaction, and a processor to establish a user interface enabling iterative annotation. During each iteration, the processor generates labels for a current image data part based on user-verified labels from the previous part, allowing users to verify and correct these labels. The system combines outputs from a label propagation algorithm and a machine-learned classifier, with the classifier being retrained using user-verified labels and image data to improve accuracy.
Furthermore, the patent details a method for annotating image data and a computer-readable medium storing instructions for the same process. The method involves accessing image data, enabling users to iteratively annotate the data, and generating labels based on previous user-verified labels. The labels are created by combining outputs from a label propagation algorithm and a machine-learned classifier, with the classifier being retrained using current user-verified labels and image data. The weighting between the two outputs can be adjusted based on an annotation accuracy metric, with the system allowing for fine-tuning of the weighting during the annotation process. This innovative system aims to enhance the efficiency and accuracy of image data annotation, particularly in fields requiring detailed labeling for analysis and processing.
To know more about GlobalData’s detailed insights on Koninklijke Philips, 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.
