Sketch recognition system


Ontology type: sgo:Patent     


Patent Info

DATE

N/A

AUTHORS

Tom Yu Ouyang , Randall Davis

ABSTRACT

Handwriting interpretation tools, such as optical character recognition (OCR), have improved over the years such that OCR is a common tool in business for interpreting typed text and sometimes handwritten text. OCR does not apply well to non-text-only diagrams, such as chemical structure diagrams. A method according to an embodiment of the present invention of interpreting a human-drawn sketch includes determining a local metric indicating whether a candidate symbol belongs to a certain classification based on a set of features. The set of features includes, as a feature, scores generated from feature images of the candidate symbol. Also included is determining a joint metric of multiple candidate symbols based on their respective classifications and interpreting the sketch as a function of the local and joint metrics. Sketches can be chemical composition, biological composition, electrical schematic, mechanical, or any other science- or engineering-based diagrams for which human-drawn symbols have well-known counterparts. More... »

Related SciGraph Publications

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/2790", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "name": "Tom Yu Ouyang", 
        "type": "Person"
      }, 
      {
        "name": "Randall Davis", 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1016/j.cag.2008.05.008", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1012830428"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf01589116", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1022481421", 
          "https://doi.org/10.1007/bf01589116"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/1015706.1015741", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1026967310"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.cag.2005.05.007", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1043207870"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0142-694x(95)00006-d", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1048166911"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "description": "

Handwriting interpretation tools, such as optical character recognition (OCR), have improved over the years such that OCR is a common tool in business for interpreting typed text and sometimes handwritten text. OCR does not apply well to non-text-only diagrams, such as chemical structure diagrams. A method according to an embodiment of the present invention of interpreting a human-drawn sketch includes determining a local metric indicating whether a candidate symbol belongs to a certain classification based on a set of features. The set of features includes, as a feature, scores generated from feature images of the candidate symbol. Also included is determining a joint metric of multiple candidate symbols based on their respective classifications and interpreting the sketch as a function of the local and joint metrics. Sketches can be chemical composition, biological composition, electrical schematic, mechanical, or any other science- or engineering-based diagrams for which human-drawn symbols have well-known counterparts.

", "id": "sg:patent.US-9064147-B2", "keywords": [ "recognition system", "interpretation", "optical character recognition", "common tool", "Commerce", "interpreting", "text", "diagram", "chemical structure", "method", "embodiment", "invention", "sketch", "symbol", "classification", "feature", "score", "joint", "chemical composition", "composition", "Engineering", "counterpart" ], "name": "Sketch recognition system", "recipient": [ { "id": "https://www.grid.ac/institutes/grid.116068.8", "type": "Organization" } ], "sameAs": [ "https://app.dimensions.ai/details/patent/US-9064147-B2" ], "sdDataset": "patents", "sdDatePublished": "2019-03-07T15:29", "sdLicense": "https://scigraph.springernature.com/explorer/license/", "sdPublisher": { "name": "Springer Nature - SN SciGraph project", "type": "Organization" }, "sdSource": "s3://com.uberresearch.data.dev.patents-pipeline/full_run_10/sn-export/5eb3e5a348d7f117b22cc85fb0b02730/0000100128-0000348334/json_export_03300925.jsonl", "type": "Patent" } ]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/patent.US-9064147-B2'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/patent.US-9064147-B2'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/patent.US-9064147-B2'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/patent.US-9064147-B2'


 

This table displays all metadata directly associated to this object as RDF triples.

63 TRIPLES      14 PREDICATES      40 URIs      29 LITERALS      2 BLANK NODES

Subject Predicate Object
1 sg:patent.US-9064147-B2 schema:about anzsrc-for:2790
2 schema:author N0f11f4a253fe4ddbb65bb0e54a60f1b1
3 schema:citation sg:pub.10.1007/bf01589116
4 https://doi.org/10.1016/0142-694x(95)00006-d
5 https://doi.org/10.1016/j.cag.2005.05.007
6 https://doi.org/10.1016/j.cag.2008.05.008
7 https://doi.org/10.1145/1015706.1015741
8 schema:description <p id="p-0001" num="0000">Handwriting interpretation tools, such as optical character recognition (OCR), have improved over the years such that OCR is a common tool in business for interpreting typed text and sometimes handwritten text. OCR does not apply well to non-text-only diagrams, such as chemical structure diagrams. A method according to an embodiment of the present invention of interpreting a human-drawn sketch includes determining a local metric indicating whether a candidate symbol belongs to a certain classification based on a set of features. The set of features includes, as a feature, scores generated from feature images of the candidate symbol. Also included is determining a joint metric of multiple candidate symbols based on their respective classifications and interpreting the sketch as a function of the local and joint metrics. Sketches can be chemical composition, biological composition, electrical schematic, mechanical, or any other science- or engineering-based diagrams for which human-drawn symbols have well-known counterparts.</p>
9 schema:keywords Commerce
10 Engineering
11 chemical composition
12 chemical structure
13 classification
14 common tool
15 composition
16 counterpart
17 diagram
18 embodiment
19 feature
20 interpretation
21 interpreting
22 invention
23 joint
24 method
25 optical character recognition
26 recognition system
27 score
28 sketch
29 symbol
30 text
31 schema:name Sketch recognition system
32 schema:recipient https://www.grid.ac/institutes/grid.116068.8
33 schema:sameAs https://app.dimensions.ai/details/patent/US-9064147-B2
34 schema:sdDatePublished 2019-03-07T15:29
35 schema:sdLicense https://scigraph.springernature.com/explorer/license/
36 schema:sdPublisher Na11d941487dd443db867b09798a39b1d
37 sgo:license sg:explorer/license/
38 sgo:sdDataset patents
39 rdf:type sgo:Patent
40 N0f11f4a253fe4ddbb65bb0e54a60f1b1 rdf:first N496d5880a6664529b0eb21707dc568ec
41 rdf:rest N5d967784c575478781fc8c357dd77bb0
42 N496d5880a6664529b0eb21707dc568ec schema:name Tom Yu Ouyang
43 rdf:type schema:Person
44 N5d967784c575478781fc8c357dd77bb0 rdf:first N7b173774791f4a00baf8b81d76e06c8e
45 rdf:rest rdf:nil
46 N7b173774791f4a00baf8b81d76e06c8e schema:name Randall Davis
47 rdf:type schema:Person
48 Na11d941487dd443db867b09798a39b1d schema:name Springer Nature - SN SciGraph project
49 rdf:type schema:Organization
50 anzsrc-for:2790 schema:inDefinedTermSet anzsrc-for:
51 rdf:type schema:DefinedTerm
52 sg:pub.10.1007/bf01589116 schema:sameAs https://app.dimensions.ai/details/publication/pub.1022481421
53 https://doi.org/10.1007/bf01589116
54 rdf:type schema:CreativeWork
55 https://doi.org/10.1016/0142-694x(95)00006-d schema:sameAs https://app.dimensions.ai/details/publication/pub.1048166911
56 rdf:type schema:CreativeWork
57 https://doi.org/10.1016/j.cag.2005.05.007 schema:sameAs https://app.dimensions.ai/details/publication/pub.1043207870
58 rdf:type schema:CreativeWork
59 https://doi.org/10.1016/j.cag.2008.05.008 schema:sameAs https://app.dimensions.ai/details/publication/pub.1012830428
60 rdf:type schema:CreativeWork
61 https://doi.org/10.1145/1015706.1015741 schema:sameAs https://app.dimensions.ai/details/publication/pub.1026967310
62 rdf:type schema:CreativeWork
63 https://www.grid.ac/institutes/grid.116068.8 schema:Organization
 




Preview window. Press ESC to close (or click here)


...