See optical character recognition in All languages combined, or Wiktionary
{
"head_templates": [
{
"args": {
"1": "-"
},
"expansion": "optical character recognition (uncountable)",
"name": "en-noun"
}
],
"lang": "English",
"lang_code": "en",
"pos": "noun",
"senses": [
{
"categories": [
{
"kind": "other",
"name": "English entries with incorrect language header",
"parents": [
"Entries with incorrect language header",
"Entry maintenance"
],
"source": "w"
},
{
"kind": "other",
"name": "Entries with translation boxes",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Mandarin terms with redundant transliterations",
"parents": [
"Terms with redundant transliterations",
"Entry maintenance"
],
"source": "w"
},
{
"kind": "other",
"name": "Pages with 1 entry",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Pages with entries",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Terms with Czech translations",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Terms with Finnish translations",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Terms with French translations",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Terms with German translations",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Terms with Greek translations",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Terms with Kazakh translations",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Terms with Mandarin translations",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Terms with Portuguese translations",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Terms with Spanish translations",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Terms with Swedish translations",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Terms with Turkish translations",
"parents": [],
"source": "w"
},
{
"kind": "topical",
"langcode": "en",
"name": "Computing",
"orig": "en:Computing",
"parents": [
"Technology",
"All topics",
"Fundamental"
],
"source": "w"
}
],
"examples": [
{
"ref": "2018, Clarence Green, James Lambert, “Position vectors, homologous chromosomes and gamma rays: Promoting disciplinary literacy through Secondary Phrase Lists”, in English for Specific Purposes, →DOI, page 4:",
"text": "Texts were scanned, converted via optical character recognition, and part of speech tagged using CLAWS 7.",
"type": "quote"
}
],
"glosses": [
"The electronic identification and digital encoding of printed or handwritten characters by means of an optical scanner and specialized software."
],
"id": "en-optical_character_recognition-en-noun-7RKiSMmN",
"links": [
[
"computing",
"computing#Noun"
],
[
"electronic",
"electronic"
],
[
"identification",
"identification"
],
[
"digital",
"digital"
],
[
"encoding",
"encoding"
],
[
"printed",
"printed"
],
[
"handwritten",
"handwritten"
],
[
"scanner",
"scanner"
],
[
"software",
"software"
]
],
"raw_glosses": [
"(computing) The electronic identification and digital encoding of printed or handwritten characters by means of an optical scanner and specialized software."
],
"related": [
{
"word": "homoglyph"
},
{
"word": "homoglyphic"
},
{
"word": "scanno"
},
{
"word": "speech recognition"
},
{
"word": "voice recognition"
}
],
"synonyms": [
{
"word": "OCR"
}
],
"tags": [
"uncountable"
],
"topics": [
"computing",
"engineering",
"mathematics",
"natural-sciences",
"physical-sciences",
"sciences"
],
"translations": [
{
"code": "cmn",
"lang": "Chinese Mandarin",
"roman": "guāngxué zìfú shíbié",
"sense": "electronic identification and digital encoding of characters",
"word": "光學字符識別 /光学字符识别"
},
{
"code": "cs",
"lang": "Czech",
"sense": "electronic identification and digital encoding of characters",
"tags": [
"neuter"
],
"word": "optické rozpoznávání znaků"
},
{
"code": "fi",
"lang": "Finnish",
"sense": "electronic identification and digital encoding of characters",
"word": "tekstintunnistus"
},
{
"code": "fr",
"lang": "French",
"sense": "electronic identification and digital encoding of characters",
"tags": [
"feminine"
],
"word": "reconnaissance optique de caractères"
},
{
"code": "de",
"lang": "German",
"sense": "electronic identification and digital encoding of characters",
"tags": [
"feminine"
],
"word": "optische Zeichenerkennung"
},
{
"code": "de",
"lang": "German",
"sense": "electronic identification and digital encoding of characters",
"tags": [
"feminine"
],
"word": "Texterkennung"
},
{
"code": "el",
"lang": "Greek",
"roman": "optikí anagnórisi charaktíron",
"sense": "electronic identification and digital encoding of characters",
"tags": [
"feminine"
],
"word": "οπτική αναγνώριση χαρακτήρων"
},
{
"code": "kk",
"lang": "Kazakh",
"roman": "simvoldardy optikalyq tanyp bılu",
"sense": "electronic identification and digital encoding of characters",
"word": "символдарды оптикалық танып білу"
},
{
"code": "pt",
"lang": "Portuguese",
"sense": "electronic identification and digital encoding of characters",
"tags": [
"masculine"
],
"word": "reconhecimento ótico de caracteres"
},
{
"code": "es",
"lang": "Spanish",
"sense": "electronic identification and digital encoding of characters",
"tags": [
"masculine"
],
"word": "reconocimiento óptico de caracteres"
},
{
"code": "sv",
"lang": "Swedish",
"sense": "electronic identification and digital encoding of characters",
"tags": [
"common-gender"
],
"word": "teckenigenkänning"
},
{
"code": "sv",
"lang": "Swedish",
"sense": "electronic identification and digital encoding of characters",
"tags": [
"common-gender"
],
"word": "teckentolkning"
},
{
"code": "sv",
"lang": "Swedish",
"sense": "electronic identification and digital encoding of characters",
"tags": [
"common-gender"
],
"word": "textfångst"
},
{
"code": "tr",
"lang": "Turkish",
"sense": "electronic identification and digital encoding of characters",
"word": "optik karakter tanıma"
}
],
"wikipedia": [
"optical character recognition"
]
}
],
"word": "optical character recognition"
}
{
"head_templates": [
{
"args": {
"1": "-"
},
"expansion": "optical character recognition (uncountable)",
"name": "en-noun"
}
],
"lang": "English",
"lang_code": "en",
"pos": "noun",
"related": [
{
"word": "homoglyph"
},
{
"word": "homoglyphic"
},
{
"word": "scanno"
},
{
"word": "speech recognition"
},
{
"word": "voice recognition"
}
],
"senses": [
{
"categories": [
"English entries with incorrect language header",
"English lemmas",
"English multiword terms",
"English nouns",
"English terms with quotations",
"English uncountable nouns",
"Entries with translation boxes",
"Mandarin terms with redundant transliterations",
"Pages with 1 entry",
"Pages with entries",
"Terms with Czech translations",
"Terms with Finnish translations",
"Terms with French translations",
"Terms with German translations",
"Terms with Greek translations",
"Terms with Kazakh translations",
"Terms with Mandarin translations",
"Terms with Portuguese translations",
"Terms with Spanish translations",
"Terms with Swedish translations",
"Terms with Turkish translations",
"en:Computing"
],
"examples": [
{
"ref": "2018, Clarence Green, James Lambert, “Position vectors, homologous chromosomes and gamma rays: Promoting disciplinary literacy through Secondary Phrase Lists”, in English for Specific Purposes, →DOI, page 4:",
"text": "Texts were scanned, converted via optical character recognition, and part of speech tagged using CLAWS 7.",
"type": "quote"
}
],
"glosses": [
"The electronic identification and digital encoding of printed or handwritten characters by means of an optical scanner and specialized software."
],
"links": [
[
"computing",
"computing#Noun"
],
[
"electronic",
"electronic"
],
[
"identification",
"identification"
],
[
"digital",
"digital"
],
[
"encoding",
"encoding"
],
[
"printed",
"printed"
],
[
"handwritten",
"handwritten"
],
[
"scanner",
"scanner"
],
[
"software",
"software"
]
],
"raw_glosses": [
"(computing) The electronic identification and digital encoding of printed or handwritten characters by means of an optical scanner and specialized software."
],
"synonyms": [
{
"word": "OCR"
}
],
"tags": [
"uncountable"
],
"topics": [
"computing",
"engineering",
"mathematics",
"natural-sciences",
"physical-sciences",
"sciences"
],
"wikipedia": [
"optical character recognition"
]
}
],
"translations": [
{
"code": "cmn",
"lang": "Chinese Mandarin",
"roman": "guāngxué zìfú shíbié",
"sense": "electronic identification and digital encoding of characters",
"word": "光學字符識別 /光学字符识别"
},
{
"code": "cs",
"lang": "Czech",
"sense": "electronic identification and digital encoding of characters",
"tags": [
"neuter"
],
"word": "optické rozpoznávání znaků"
},
{
"code": "fi",
"lang": "Finnish",
"sense": "electronic identification and digital encoding of characters",
"word": "tekstintunnistus"
},
{
"code": "fr",
"lang": "French",
"sense": "electronic identification and digital encoding of characters",
"tags": [
"feminine"
],
"word": "reconnaissance optique de caractères"
},
{
"code": "de",
"lang": "German",
"sense": "electronic identification and digital encoding of characters",
"tags": [
"feminine"
],
"word": "optische Zeichenerkennung"
},
{
"code": "de",
"lang": "German",
"sense": "electronic identification and digital encoding of characters",
"tags": [
"feminine"
],
"word": "Texterkennung"
},
{
"code": "el",
"lang": "Greek",
"roman": "optikí anagnórisi charaktíron",
"sense": "electronic identification and digital encoding of characters",
"tags": [
"feminine"
],
"word": "οπτική αναγνώριση χαρακτήρων"
},
{
"code": "kk",
"lang": "Kazakh",
"roman": "simvoldardy optikalyq tanyp bılu",
"sense": "electronic identification and digital encoding of characters",
"word": "символдарды оптикалық танып білу"
},
{
"code": "pt",
"lang": "Portuguese",
"sense": "electronic identification and digital encoding of characters",
"tags": [
"masculine"
],
"word": "reconhecimento ótico de caracteres"
},
{
"code": "es",
"lang": "Spanish",
"sense": "electronic identification and digital encoding of characters",
"tags": [
"masculine"
],
"word": "reconocimiento óptico de caracteres"
},
{
"code": "sv",
"lang": "Swedish",
"sense": "electronic identification and digital encoding of characters",
"tags": [
"common-gender"
],
"word": "teckenigenkänning"
},
{
"code": "sv",
"lang": "Swedish",
"sense": "electronic identification and digital encoding of characters",
"tags": [
"common-gender"
],
"word": "teckentolkning"
},
{
"code": "sv",
"lang": "Swedish",
"sense": "electronic identification and digital encoding of characters",
"tags": [
"common-gender"
],
"word": "textfångst"
},
{
"code": "tr",
"lang": "Turkish",
"sense": "electronic identification and digital encoding of characters",
"word": "optik karakter tanıma"
}
],
"word": "optical character recognition"
}
Download raw JSONL data for optical character recognition meaning in English (4.6kB)
This page is a part of the kaikki.org machine-readable English dictionary. This dictionary is based on structured data extracted on 2025-01-08 from the enwiktionary dump dated 2025-01-01 using wiktextract (9a96ef4 and 4ed51a5). The data shown on this site has been post-processed and various details (e.g., extra categories) removed, some information disambiguated, and additional data merged from other sources. See the raw data download page for the unprocessed wiktextract data.
If you use this data in academic research, please cite Tatu Ylonen: Wiktextract: Wiktionary as Machine-Readable Structured Data, Proceedings of the 13th Conference on Language Resources and Evaluation (LREC), pp. 1317-1325, Marseille, 20-25 June 2022. Linking to the relevant page(s) under https://kaikki.org would also be greatly appreciated.