{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11514720","patent":{"patent_number":"US-11514720","title":"Geometrically constrained, unsupervised training of convolutional autoencoders for extraction of eye landmarks","assignee":null,"inventors":[],"filing_date":"2020-01-02T00:00:00.000Z","publication_date":"2022-11-29T00:00:00.000Z","cpc_codes":["G06N","G06F","G06N","G06N","G06N","G06T","G06V","G06V","G06V","G06V","G06V","G06V","G06N","G06T","G06T","G06T"],"num_claims":11,"abstract":"The disclosure relates to systems, methods and programs for geometrically constrained, unsupervised training of convolutional autoencoders on unlabeled images for extracting eye landmarks. Disclosed systems for unsupervised deep learning of gaze estimation in eyes' image data are implementable in a computerized system. Disclosed methods include capturing an unlabeled image comprising the eye region of a user; and training a plurality of convolutional autoencoders on the unlabeled image comprising the eye region of a user using an initial geometrically regularized loss function to determine a plurality of eye landmarks."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Geometrically constrained, unsupervised training of convolutional autoencoders for extraction of eye landmarks","description":"The disclosure relates to systems, methods and programs for geometrically constrained, unsupervised training of convolutional autoencoders on unlabeled images for extracting eye landmarks. Disclosed s","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11514720","license":"CC-BY-4.0-like","license_terms":"AI-generated analysis on this page (summary, layman_explanation, technical_analysis, business_analysis, faqs) may be reused with attribution and a visible link back to the canonical URL above. Patent abstracts, claims, and bibliographic data are USPTO public domain.","required_link":"https://patentable.app/patents/US-11514720","citation_suggestion":"Patentable. \"Geometrically constrained, unsupervised training of convolutional autoencoders for extraction of eye landmarks\" (US-11514720). https://patentable.app/patents/US-11514720","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11514720","json":"https://patentable.app/api/llm-context/US-11514720","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-31T03:57:00.260Z"}