eBay has filed a patent for a search system that uses morphed images to perform item searches. The system generates morphed images by combining visual characteristics of objects from input images. Users can select a morphed image for searching, and the system identifies visually similar items from a database. The search results are then presented to the user. GlobalData’s report on eBay gives a 360-degree view of the company including its patenting strategy. Buy the report here.

Smarter leaders trust GlobalData

Data Insights eBay Inc - Company Profile

Buy the

Data Insights

The gold standard of business intelligence.

Find out more

According to GlobalData’s company profile on eBay, dynamic premium pricing was a key innovation area identified from patents. eBay's grant share as of September 2023 was 55%. Grant share is based on the ratio of number of grants to total number of patents.

Morphed image search system for identifying visually similar items

Source: United States Patent and Trademark Office (USPTO). Credit: eBay Inc

A recently filed patent (Publication Number: US20230315797A1) describes a computer-implemented method for generating and searching morphed images of objects. The method involves receiving two or more images of objects and using a generative model to create one or more morphed images that combine visual characteristics from the received images. These morphed images are then presented to the user. The user can select a morphed image, which is used as search input to perform a search on an item database. The search results are presented to the user, who can then select a search result. Using the selected morphed image and the corresponding search result, a further morphed image is generated using the generative model. Another search is performed using this further morphed image as search input, and the further search results are presented to the user.

The generative model used in this method is a generative adversarial network trained on images of objects of the same type as the received images. This model generates multiple morphed images, with each morphed image having a visual similarity closer to one of the received images. The search on the item database can be performed using additional search parameters such as text input, filter selection, and user preference.

The patent also describes computer storage media and a computer system that implement the same method. The computer storage media store the computer-useable instructions for performing the method, while the computer system includes a processor and the computer storage medium.

Overall, this patent presents a computer-implemented method for generating and searching morphed images of objects. By combining visual characteristics from multiple images, the method allows users to explore and search for objects in a more visually intuitive manner. The use of a generative model trained on images of the same type of object enhances the accuracy and relevance of the generated morphed images.

To know more about GlobalData’s detailed insights on eBay, 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

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.