{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-9704257","patent":{"patent_number":"US-9704257","title":"System and method for semantic segmentation using Gaussian random field network","assignee":null,"inventors":[],"filing_date":"2016-03-25T00:00:00.000Z","publication_date":"2017-07-11T00:00:00.000Z","cpc_codes":["G06T","G06F","G06N","G06N","G06N","G06T","G06V","G06V","G06T","G06T","G06T"],"num_claims":20,"abstract":"A computer-implemented method for semantic segmentation of an image determines unary energy of each pixel in an image using a first subnetwork, determines pairwise energy of at least some pairs of pixels of the image using a second subnetwork, and determines, using a third subnetwork, an inference on a Gaussian random field (GRF) minimizing an energy function including a combination of the unary energy and the pairwise energy. The GRF inference defining probabilities of semantic labels for each pixel in the image, and the method converts the image into a semantically segmented image by assigning to a pixel in the semantically segmented image a semantic label having the highest probability for a corresponding pixel in the image among the probabilities determined by the third subnetwork. The first subnetwork, the second subnetwork, and the third subnetwork are parts of a neural network."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"System and method for semantic segmentation using Gaussian random field network","description":"A computer-implemented method for semantic segmentation of an image determines unary energy of each pixel in an image using a first subnetwork, determines pairwise energy of at least some pairs of pix","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-9704257","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-9704257","citation_suggestion":"Patentable. \"System and method for semantic segmentation using Gaussian random field network\" (US-9704257). https://patentable.app/patents/US-9704257","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-9704257","json":"https://patentable.app/api/llm-context/US-9704257","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-06-06T04:09:06.729Z"}