A SYSTEM FOR RECOGNITION OF DESTINATION ADDRESS IN POSTAL DOCUMENTS OF INDIA

被引:2
|
作者
Roy, Ramit Kumar [1 ]
Pal, Umapada [2 ]
Roy, Kaushik [3 ]
Kimura, Fumitaka [4 ]
机构
[1] St Xaviers Coll Autonomous, Kolkata, India
[2] ISI, CVPR Unit, Kolkata, India
[3] WBSU, Dept Comp Sc, Barasat, India
[4] Mie Univ, Grad Sch Engn, Tsu, Mie, Japan
关键词
Destination Address; Indian script recognition; Indian Pin code recognition; Document analysis; Lexicon information; CITY-NAME RECOGNITION; WRITTEN; BANGLA;
D O I
10.22452/mjcs.vol33no3.3
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Recognition of destination address is compulsory for automation of the postal system in India. Our observation found that such recognition becomes a very challenging task due to inter-mixing of three languages (Hindi, English and the official language of the particular state in which the postal document is supposed to reach).In this paper, our attempt towards development of a dynamic programming based system for city-name and pin code recognition of destination address in postal documents of India not only managed to address the difficulties related to identification of the scripts but also managed to get rid of those problems which is generated due to character touching in postal documents. For city-name recognition, lexicon information is used. However, no lexicon information is used for pin code recognition since an Indian pin code contains only 6 digits. We obtained 99.55% reliability from tri-lingual city-name recognition system where error rates are 0.20% and rejection rates are 28.11%. From our experiment on recognition of handwritten pin codes, 99.01% reliability rate, 0.83% error rate and15.27% rejection rate are obtained. Furthermore, to enhance the city-name results by distributing the lexicon size district-wise, we conducted an experiment and presented the results.
引用
收藏
页码:202 / 216
页数:15
相关论文
共 50 条
  • [21] DeepParse: A Trainable Postal Address Parser
    Abid, Nosheen
    ul Hasan, Adnan
    Shafait, Faisal
    2018 INTERNATIONAL CONFERENCE ON DIGITAL IMAGE COMPUTING: TECHNIQUES AND APPLICATIONS (DICTA), 2018, : 589 - 596
  • [22] Postal address reading in real time
    Cent for Document Analysis and, Recognition, Buffalo, NY, United States
    Int J Imaging Syst Technol, 4 (370-378):
  • [23] Postal address reading in real time
    Palumbo, PW
    Srihari, SN
    INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY, 1996, 7 (04) : 370 - 378
  • [24] A system for cursive handwritten address recognition
    Mao, JC
    Sinha, P
    Mohiuddin, K
    FOURTEENTH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOLS 1 AND 2, 1998, : 1285 - 1287
  • [25] A RURAL ADDRESS MATCHING SYSTEM USING 9 DIGIT POSTAL ZIP CODES
    HENRY, NF
    TECHNICAL PAPERS : 1989 ASPRS/ACSM ANNUAL CONVENTION, VOL 5: SURVEYING & CARTOGRAPHY, 1989, : 36 - 39
  • [26] Stages of the "Final Solution" in the Testimony of Postal Documents
    Klein, Peter
    HISTORISCHE ZEITSCHRIFT, 2022, 314 (03) : 834 - 835
  • [27] Bimodal System for Recognition of Authors of Handwritten Documents
    Gotovac, Sven
    Marusic, Zeljko
    Zelenika, Danijel
    Seremet, Zeljko
    2015 4TH MEDITERRANEAN CONFERENCE ON EMBEDDED COMPUTING (MECO), 2015, : 203 - 207
  • [28] Information extraction techniques for postal address standardization
    Abbasi, Rabeeh Ayaz
    Proceedings of the INMIC 2005: 9th International Multitopic Conference - Proceedings, 2005, : 309 - 314
  • [29] How postal address readers are made adaptive
    Schäfer, H
    Bayer, T
    Kreuzer, K
    Miletzki, U
    Schambach, MP
    Schulte-Austum, M
    READING AND LEARNING: ADAPTIVE CONTENT RECOGNITION, 2004, 2956 : 187 - 215
  • [30] EXAMININIG THE SIMILARITY OF POSTAL ADDRESS COMPONENTS IN TURKEY
    Kilic, Batuhan
    Gulgen, Fatih
    Ozturk, Ozge
    7TH INTERNATIONAL CONFERENCE ON CARTOGRAPHY AND GIS, VOLS 1 AND 2, 2018, : 401 - 407