EP EP4787330A1
[0001] Systems/methods provide more efficient training of ML models used to classify objects within images and videos. The systems/methods provide an augmented training dataset that crops each image and retains a portion of the image context. The image cropping may be done by manually, semi-manually, or automatically identifying a location or coordinates of an object within an image, then cropping a predefined area around the image. The cropping may be performed once for each image, or multiple crops may be performed for each image, each cropping involving a different predefined area around the image depending on the method used to identify the coordinates of the object within the image. The resulting augmented set of images is then used to train, or further train, the ML models. Such an arrangement provides ML models that have improved object disambiguation and greater classification accuracy, and are especially useful in applications involving transfer learning.
A document turning up in a search is not the same as a document that anticipates your claims. Our registered Patent Agents read the claims, not just the abstract, and tell you where you still have room.
Protect Your InventionBibliographic data via the European Patent Office's Open Patent Services (DOCDB) . Republished here for research and prior-art review. This page is not legal advice, and its presence in our index says nothing about the validity or enforceability of the document. For the Indian legal position (status, oppositions, renewals), see InPASS.