{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11308354","patent":{"patent_number":"US-11308354","title":"Residual context refinement network architecture for optical character recognition","assignee":null,"inventors":[],"filing_date":"2020-03-30T00:00:00.000Z","publication_date":"2022-04-19T00:00:00.000Z","cpc_codes":["G06V","G06F","G06F","G06F","G06F","G06V","G06V"],"num_claims":20,"abstract":"Techniques for recognizing text in an image are described. An exemplary method may include receiving a request to recognize text in an image; extracting features from the image and generating a visual feature sequence from the extracted features; performing selective contextual refinement at least one selective contextual refinement block of a stack of selective contextual refinement blocks to generate a text prediction by: generating a contextual feature map and combining the contextual feature map with the visual feature sequence into a visual feature space, and applying a selective decoder that utilizes a two-step attention on the visual feature space to generate a text prediction, wherein the two-step attention includes performing a 1-D self-attention computation to generate attentional features and decoding the attentional features to generate the text prediction; and outputting the generated text prediction."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Residual context refinement network architecture for optical character recognition","description":"Techniques for recognizing text in an image are described. An exemplary method may include receiving a request to recognize text in an image; extracting features from the image and generating a visual","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11308354","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-11308354","citation_suggestion":"Patentable. \"Residual context refinement network architecture for optical character recognition\" (US-11308354). https://patentable.app/patents/US-11308354","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11308354","json":"https://patentable.app/api/llm-context/US-11308354","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-31T10:00:27.954Z"}