Clarivate has been granted a patent for a method that involves searching an image database by receiving an adulterated image with object annotations, applying neural networks for correlation with a reference database, and selecting matching images above a threshold value. The method also includes a masking process for object recognition and generating a contour mask. GlobalData’s report on Clarivate gives a 360-degree view of the company including its patenting strategy. Buy the report here.

According to GlobalData’s company profile on Clarivate, was a key innovation area identified from patents. Clarivate's grant share as of April 2024 was 64%. Grant share is based on the ratio of number of grants to total number of patents.

Image database search method using neural networks and object recognition

Source: United States Patent and Trademark Office (USPTO). Credit: Clarivate Plc

A recently granted patent (Publication Number: US11908053B2) discloses a method for searching an image database using advanced neural network technology. The method involves receiving an adulterated image of an object with annotations, applying a neural network to edit the image, correlating the edited image with a reference database, and selecting matching images based on correlation values above a threshold. Additionally, a masking process is applied to the adulterated image, involving object recognition, computer vision for callout features, and generating a contour mask of the object. The neural network used is a convolutional neural network for pixel-level classification, and object segmentation is applied to generate the contour mask.

Furthermore, the patent includes claims for a non-transitory computer-readable storage medium and an apparatus implementing the method for searching an image database. The computer-readable storage medium stores instructions for receiving an adulterated image, applying neural networks, correlating with a reference database, and selecting matching images. The apparatus includes processing circuitry for performing the method steps, including applying neural networks, correlating images, and generating contour masks. The processing circuitry is configured to edit images by removing annotations, based on the results of neural network applications and masking processes, and generate contour masks through object segmentation. Overall, the patent highlights a sophisticated approach to image searching using neural networks and advanced computer vision techniques for improved accuracy and efficiency in image retrieval processes.

To know more about GlobalData’s detailed insights on Clarivate, buy the report here.

Premium 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

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.