A criterion based on Fourier transform for segmentation of connected digits View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2000-08

AUTHORS

Xiaoyan Zhu, Yu Hao, Yifan Shi, Song Wang

ABSTRACT

. Segmentation is the most difficult problem in handwritten character recognition systems and often causes major errors in performance. To reach a balance between speed and accuracy, a filter distinguishing connected images from isolated images for multiple stage segmentation is required. The Fourier spectrum is a promising approach to this problem, although it suffers from the heavy influence of stroke width. Therefore, we introduce SFS (SFS) to eliminate the stroke-width effect. Based on the SFS, a set of features and a fine-tuned criterion are presented to classify connected/isolated images. Theoretical analysis demonstrates their soundness, while experimental results demonstrate that this criterion is better than other methods. More... »

PAGES

27-33

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/pl00013550

DOI

http://dx.doi.org/10.1007/pl00013550

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1008830704


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

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/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Artificial Intelligence and Image Processing", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "State Key Laboratory of Intelligent Technology and Systems, Department of Computer Science and Technology, Tsinghua University, Beijing, China; e-mail: zxy-dcs@mail.tsinghua.edu.cn, CN", 
          "id": "http://www.grid.ac/institutes/grid.12527.33", 
          "name": [
            "State Key Laboratory of Intelligent Technology and Systems, Department of Computer Science and Technology, Tsinghua University, Beijing, China; e-mail: zxy-dcs@mail.tsinghua.edu.cn, CN"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Zhu", 
        "givenName": "Xiaoyan", 
        "id": "sg:person.013176254423.92", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013176254423.92"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "State Key Laboratory of Intelligent Technology and Systems, Department of Computer Science and Technology, Tsinghua University, Beijing, China; e-mail: zxy-dcs@mail.tsinghua.edu.cn, CN", 
          "id": "http://www.grid.ac/institutes/grid.12527.33", 
          "name": [
            "State Key Laboratory of Intelligent Technology and Systems, Department of Computer Science and Technology, Tsinghua University, Beijing, China; e-mail: zxy-dcs@mail.tsinghua.edu.cn, CN"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Hao", 
        "givenName": "Yu", 
        "id": "sg:person.014270173173.47", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014270173173.47"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "State Key Laboratory of Intelligent Technology and Systems, Department of Computer Science and Technology, Tsinghua University, Beijing, China; e-mail: zxy-dcs@mail.tsinghua.edu.cn, CN", 
          "id": "http://www.grid.ac/institutes/grid.12527.33", 
          "name": [
            "State Key Laboratory of Intelligent Technology and Systems, Department of Computer Science and Technology, Tsinghua University, Beijing, China; e-mail: zxy-dcs@mail.tsinghua.edu.cn, CN"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Shi", 
        "givenName": "Yifan", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "State Key Laboratory of Intelligent Technology and Systems, Department of Computer Science and Technology, Tsinghua University, Beijing, China; e-mail: zxy-dcs@mail.tsinghua.edu.cn, CN", 
          "id": "http://www.grid.ac/institutes/grid.12527.33", 
          "name": [
            "State Key Laboratory of Intelligent Technology and Systems, Department of Computer Science and Technology, Tsinghua University, Beijing, China; e-mail: zxy-dcs@mail.tsinghua.edu.cn, CN"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Wang", 
        "givenName": "Song", 
        "type": "Person"
      }
    ], 
    "datePublished": "2000-08", 
    "datePublishedReg": "2000-08-01", 
    "description": "Abstract. Segmentation is the most difficult problem in handwritten character recognition systems and often causes major errors in performance. To reach a balance between speed and accuracy, a filter distinguishing connected images from isolated images for multiple stage segmentation is required. The Fourier spectrum is a promising approach to this problem, although it suffers from the heavy influence of stroke width. Therefore, we introduce SFS (SFS) to eliminate the stroke-width effect. Based on the SFS, a set of features and a fine-tuned criterion are presented to classify connected/isolated images. Theoretical analysis demonstrates their soundness, while experimental results demonstrate that this criterion is better than other methods.", 
    "genre": "article", 
    "id": "sg:pub.10.1007/pl00013550", 
    "inLanguage": "en", 
    "isAccessibleForFree": false, 
    "isPartOf": [
      {
        "id": "sg:journal.1038042", 
        "issn": [
          "1433-2833", 
          "1433-2825"
        ], 
        "name": "International Journal on Document Analysis and Recognition (IJDAR)", 
        "publisher": "Springer Nature", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "1", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "3"
      }
    ], 
    "keywords": [
      "handwritten character recognition system", 
      "character recognition system", 
      "set of features", 
      "recognition system", 
      "stroke width", 
      "stage segmentation", 
      "connected images", 
      "segmentation", 
      "difficult problem", 
      "experimental results", 
      "images", 
      "promising approach", 
      "theoretical analysis", 
      "SFS", 
      "heavy influence", 
      "soundness", 
      "accuracy", 
      "set", 
      "performance", 
      "system", 
      "error", 
      "features", 
      "transform", 
      "speed", 
      "Fourier spectrum", 
      "digits", 
      "method", 
      "major errors", 
      "criteria", 
      "results", 
      "Fourier transform", 
      "analysis", 
      "balance", 
      "spectra", 
      "problem", 
      "influence", 
      "width", 
      "approach", 
      "effect"
    ], 
    "name": "A criterion based on Fourier transform for segmentation of connected digits", 
    "pagination": "27-33", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1008830704"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/pl00013550"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/pl00013550", 
      "https://app.dimensions.ai/details/publication/pub.1008830704"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2022-06-01T22:02", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20220601/entities/gbq_results/article/article_343.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://doi.org/10.1007/pl00013550"
  }
]
 

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/pub.10.1007/pl00013550'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/pl00013550'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/pl00013550'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/pl00013550'


 

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

116 TRIPLES      21 PREDICATES      65 URIs      57 LITERALS      6 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/pl00013550 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author Na878eee8d7bf493b9ce1c517b3e89353
4 schema:datePublished 2000-08
5 schema:datePublishedReg 2000-08-01
6 schema:description Abstract. Segmentation is the most difficult problem in handwritten character recognition systems and often causes major errors in performance. To reach a balance between speed and accuracy, a filter distinguishing connected images from isolated images for multiple stage segmentation is required. The Fourier spectrum is a promising approach to this problem, although it suffers from the heavy influence of stroke width. Therefore, we introduce SFS (SFS) to eliminate the stroke-width effect. Based on the SFS, a set of features and a fine-tuned criterion are presented to classify connected/isolated images. Theoretical analysis demonstrates their soundness, while experimental results demonstrate that this criterion is better than other methods.
7 schema:genre article
8 schema:inLanguage en
9 schema:isAccessibleForFree false
10 schema:isPartOf N6064d95d58744c6ab808fc771611bb0b
11 Ne5863ebfac9e486c895757e42e8fcf79
12 sg:journal.1038042
13 schema:keywords Fourier spectrum
14 Fourier transform
15 SFS
16 accuracy
17 analysis
18 approach
19 balance
20 character recognition system
21 connected images
22 criteria
23 difficult problem
24 digits
25 effect
26 error
27 experimental results
28 features
29 handwritten character recognition system
30 heavy influence
31 images
32 influence
33 major errors
34 method
35 performance
36 problem
37 promising approach
38 recognition system
39 results
40 segmentation
41 set
42 set of features
43 soundness
44 spectra
45 speed
46 stage segmentation
47 stroke width
48 system
49 theoretical analysis
50 transform
51 width
52 schema:name A criterion based on Fourier transform for segmentation of connected digits
53 schema:pagination 27-33
54 schema:productId N45fd9ed2716b4d5782c3199db21034ea
55 N67a9b84f74e24987899eee338c47a3a6
56 schema:sameAs https://app.dimensions.ai/details/publication/pub.1008830704
57 https://doi.org/10.1007/pl00013550
58 schema:sdDatePublished 2022-06-01T22:02
59 schema:sdLicense https://scigraph.springernature.com/explorer/license/
60 schema:sdPublisher N6775b09f6e8c4b0aa94ca9fb05823cb3
61 schema:url https://doi.org/10.1007/pl00013550
62 sgo:license sg:explorer/license/
63 sgo:sdDataset articles
64 rdf:type schema:ScholarlyArticle
65 N084d1d19492d45d9b5e4d17139b40f6b rdf:first sg:person.014270173173.47
66 rdf:rest Nfbe05af2951d485b9e201367ecd73e69
67 N45fd9ed2716b4d5782c3199db21034ea schema:name doi
68 schema:value 10.1007/pl00013550
69 rdf:type schema:PropertyValue
70 N6064d95d58744c6ab808fc771611bb0b schema:volumeNumber 3
71 rdf:type schema:PublicationVolume
72 N6775b09f6e8c4b0aa94ca9fb05823cb3 schema:name Springer Nature - SN SciGraph project
73 rdf:type schema:Organization
74 N67a9b84f74e24987899eee338c47a3a6 schema:name dimensions_id
75 schema:value pub.1008830704
76 rdf:type schema:PropertyValue
77 N9c23d891f7de46c6bcad13fe3d342dc1 schema:affiliation grid-institutes:grid.12527.33
78 schema:familyName Shi
79 schema:givenName Yifan
80 rdf:type schema:Person
81 Na878eee8d7bf493b9ce1c517b3e89353 rdf:first sg:person.013176254423.92
82 rdf:rest N084d1d19492d45d9b5e4d17139b40f6b
83 Nc48f35672b5f4b20a8901054478ad82f schema:affiliation grid-institutes:grid.12527.33
84 schema:familyName Wang
85 schema:givenName Song
86 rdf:type schema:Person
87 Ndf59dcda3ba24b50ac4a6d6f3ee93650 rdf:first Nc48f35672b5f4b20a8901054478ad82f
88 rdf:rest rdf:nil
89 Ne5863ebfac9e486c895757e42e8fcf79 schema:issueNumber 1
90 rdf:type schema:PublicationIssue
91 Nfbe05af2951d485b9e201367ecd73e69 rdf:first N9c23d891f7de46c6bcad13fe3d342dc1
92 rdf:rest Ndf59dcda3ba24b50ac4a6d6f3ee93650
93 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
94 schema:name Information and Computing Sciences
95 rdf:type schema:DefinedTerm
96 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
97 schema:name Artificial Intelligence and Image Processing
98 rdf:type schema:DefinedTerm
99 sg:journal.1038042 schema:issn 1433-2825
100 1433-2833
101 schema:name International Journal on Document Analysis and Recognition (IJDAR)
102 schema:publisher Springer Nature
103 rdf:type schema:Periodical
104 sg:person.013176254423.92 schema:affiliation grid-institutes:grid.12527.33
105 schema:familyName Zhu
106 schema:givenName Xiaoyan
107 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013176254423.92
108 rdf:type schema:Person
109 sg:person.014270173173.47 schema:affiliation grid-institutes:grid.12527.33
110 schema:familyName Hao
111 schema:givenName Yu
112 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014270173173.47
113 rdf:type schema:Person
114 grid-institutes:grid.12527.33 schema:alternateName State Key Laboratory of Intelligent Technology and Systems, Department of Computer Science and Technology, Tsinghua University, Beijing, China; e-mail: zxy-dcs@mail.tsinghua.edu.cn, CN
115 schema:name State Key Laboratory of Intelligent Technology and Systems, Department of Computer Science and Technology, Tsinghua University, Beijing, China; e-mail: zxy-dcs@mail.tsinghua.edu.cn, CN
116 rdf:type schema:Organization
 




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


...