{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:EPWFG2D7LV3UKZH5VUCUSGW7NO","short_pith_number":"pith:EPWFG2D7","schema_version":"1.0","canonical_sha256":"23ec53687f5d774564fdad05491adf6b94b9293ae32d66c4214039a0de1c2034","source":{"kind":"arxiv","id":"1505.00529","version":1},"attestation_state":"computed","paper":{"title":"Learning Document Image Binarization from Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Premkumar Natarajan, Stephen Rawls, Wael AbdAlmageed, Yue Wu","submitted_at":"2015-05-04T05:57:17Z","abstract_excerpt":"In this paper we present a fully trainable binarization solution for degraded document images. Unlike previous attempts that often used simple features with a series of pre- and post-processing, our solution encodes all heuristics about whether or not a pixel is foreground text into a high-dimensional feature vector and learns a more complicated decision function. In particular, we prepare features of three types: 1) existing features for binarization such as intensity [1], contrast [2], [3], and Laplacian [4], [5]; 2) reformulated features from existing binarization decision functions such th"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1505.00529","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-05-04T05:57:17Z","cross_cats_sorted":[],"title_canon_sha256":"3c68eedd3b67c0a2f236ebda66bfb7fbb0235d9a22e61e4554936814409e52f0","abstract_canon_sha256":"bdf10126ba152ff69c72e805695f3e00dbbdba6bf66b80a91b48ff629e2d8100"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:17:02.691612Z","signature_b64":"BuhevTk6ZkGrZVOzdP8mos1KeAgAPD0m8tzKJNyRMmDck+vzuth8fhFpXSxRd4jlyDYMdam1s1KiOHlEweFtAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23ec53687f5d774564fdad05491adf6b94b9293ae32d66c4214039a0de1c2034","last_reissued_at":"2026-05-18T02:17:02.690954Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:17:02.690954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Document Image Binarization from Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Premkumar Natarajan, Stephen Rawls, Wael AbdAlmageed, Yue Wu","submitted_at":"2015-05-04T05:57:17Z","abstract_excerpt":"In this paper we present a fully trainable binarization solution for degraded document images. Unlike previous attempts that often used simple features with a series of pre- and post-processing, our solution encodes all heuristics about whether or not a pixel is foreground text into a high-dimensional feature vector and learns a more complicated decision function. In particular, we prepare features of three types: 1) existing features for binarization such as intensity [1], contrast [2], [3], and Laplacian [4], [5]; 2) reformulated features from existing binarization decision functions such th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1505.00529","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1505.00529","created_at":"2026-05-18T02:17:02.691045+00:00"},{"alias_kind":"arxiv_version","alias_value":"1505.00529v1","created_at":"2026-05-18T02:17:02.691045+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1505.00529","created_at":"2026-05-18T02:17:02.691045+00:00"},{"alias_kind":"pith_short_12","alias_value":"EPWFG2D7LV3U","created_at":"2026-05-18T12:29:19.899920+00:00"},{"alias_kind":"pith_short_16","alias_value":"EPWFG2D7LV3UKZH5","created_at":"2026-05-18T12:29:19.899920+00:00"},{"alias_kind":"pith_short_8","alias_value":"EPWFG2D7","created_at":"2026-05-18T12:29:19.899920+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EPWFG2D7LV3UKZH5VUCUSGW7NO","json":"https://pith.science/pith/EPWFG2D7LV3UKZH5VUCUSGW7NO.json","graph_json":"https://pith.science/api/pith-number/EPWFG2D7LV3UKZH5VUCUSGW7NO/graph.json","events_json":"https://pith.science/api/pith-number/EPWFG2D7LV3UKZH5VUCUSGW7NO/events.json","paper":"https://pith.science/paper/EPWFG2D7"},"agent_actions":{"view_html":"https://pith.science/pith/EPWFG2D7LV3UKZH5VUCUSGW7NO","download_json":"https://pith.science/pith/EPWFG2D7LV3UKZH5VUCUSGW7NO.json","view_paper":"https://pith.science/paper/EPWFG2D7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1505.00529&json=true","fetch_graph":"https://pith.science/api/pith-number/EPWFG2D7LV3UKZH5VUCUSGW7NO/graph.json","fetch_events":"https://pith.science/api/pith-number/EPWFG2D7LV3UKZH5VUCUSGW7NO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EPWFG2D7LV3UKZH5VUCUSGW7NO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EPWFG2D7LV3UKZH5VUCUSGW7NO/action/storage_attestation","attest_author":"https://pith.science/pith/EPWFG2D7LV3UKZH5VUCUSGW7NO/action/author_attestation","sign_citation":"https://pith.science/pith/EPWFG2D7LV3UKZH5VUCUSGW7NO/action/citation_signature","submit_replication":"https://pith.science/pith/EPWFG2D7LV3UKZH5VUCUSGW7NO/action/replication_record"}},"created_at":"2026-05-18T02:17:02.691045+00:00","updated_at":"2026-05-18T02:17:02.691045+00:00"}