Farsi document image recognition system using word layout signature

Cem ERGÜN, (Doğu Akdeniz Üniversitesi, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü, Kıbrıs)
Sajedeh NOROZPOUR (Yakın Doğu Üniversitesi, Fen Edebiyat Fakültesi, Matematik Bölümü, Kıbrıs)
Turkish Journal of Electrical Engineering and Computer Sciences
2 0
Yıl: 2019 Cilt: 27 Sayı: 2 Sayfa Aralığı: 1477 - 1488 Metin Dili: İngilizce DOI: 10.3906/elk-1804-92 İndeks Tarihi: 15-05-2020

Farsi document image recognition system using word layout signature

Öz:
In this paper, a new representation of Farsi words is proposed to present the keyword spotting problems inFarsi document image retrieval. In this regard, we define a signature for each Farsi word based on the word connectedcomponent layout. The mentioned signature is shown as boxes, and then, by sketching vertical and horizontal lines, weconstruct a grid of each word to provide a new descriptor. One of the advantages of this method is that it can be usedfor both handwritten and machine-printed texts. Finally, to evaluate the performance of our system in comparison toother methods, a database that contains 19,582 printed Farsi words is examined, and after applying this approach, arecall rate of 98.1% and a precision rate of 94.3% are obtained.
Anahtar Kelime:

Konular: Mühendislik, Elektrik ve Elektronik Bilgisayar Bilimleri, Yazılım Mühendisliği Bilgisayar Bilimleri, Sibernitik Bilgisayar Bilimleri, Bilgi Sistemleri Bilgisayar Bilimleri, Donanım ve Mimari Bilgisayar Bilimleri, Teori ve Metotlar Bilgisayar Bilimleri, Yapay Zeka
Belge Türü: Makale Makale Türü: Araştırma Makalesi Erişim Türü: Erişime Açık
  • [1] Kameshiro T, Hirano T, Okada Y, Yoda F. A document image retrieval method tolerating recognition and segmentation errors of optical character recognition using shape feature and multiple candidates. In: IEEE 1999 International Conference on Document Analysis and Recognition; Bangalore, India; 1999. pp. 681–684. doi: 10.1109/ICDAR.1999.791879
  • [2] Mehran R, Pirsiavash H, Razzazi F. A front-end optical character recognition for omni-font Persian/Arabic cursive printed documents. In: IEEE 2005 Digital Image Computing, Techniques and Applications; Queensland, Australia; 2005. pp. 385–392. doi: 10.1109/DICTA.2005.3
  • [3] Mozaffari S, Faez K, Margner V, El-Abed H. Lexicon reduction using dots for off-line Farsi/Arabic handwritten word recognition. Pattern Recognition Letters 2008; 29 (6): 724-734. doi: 10.1016/j.patrec.2007.11.009
  • [4] Doermann D. Indexing and retrieval of document images: a survey. Computer Vision and Image Understanding 1998; 70 (3): 287–298. doi: 10.1006/cviu.1998.0692
  • [5] Myers CS, Rabiner LR, Rosenberg AE. On the use of dynamic time warping for word spotting and connected word recognition. Bell Lab System Technical Journal 1981; 60 (3): 303–325. doi: 10.1002/j.1538-7305.1981.tb00243.x
  • [6] Rose RC, Paul DB. A hidden Markov model based keyword recognition system. In: IEEE 1990 International Conference on Acoustics, Speech and Signal Processing; Albuquerque, NM, USA; 1990. pp. 129–132. doi: 10.1109/ICASSP.1990.115555
  • [7] Knill KM, Young SJ. Speaker dependent keyword spotting for accessing stored speech. Cambridge, UK: Cambridge University Engineering Department, 1994.
  • [8] Kuo SS, Agazzi OE. Keyword spotting in poorly printed documents using pseudo 2-D hidden markov models. IEEE Transactions on Pattern Analysis Machine Intelligence 1994; 16 (8): 842–848. doi: 10.1109/34.308482
  • [9] Cho BJ, Kim JH. Print keyword spotting with dynamically synthesized pseudo 2D HMMs. Pattern Recognition Letter 2004; 25 (9): 999–1011. doi: 10.1016/j.patrec.2004.02.014
  • [10] Chen FR, Wilcox LD, Bloomberg DS. Word spotting in scanned images using hidden markov models. In: IEEE 1993 International Conference on Acoustics, Speech and Signal Processing; Minneapolis, MN, USA; 1993. pp. 1–4. doi: 10.1109/ICASSP.1993.319732
  • [11] Murugappan A, Ramachandran B, Dhavachelvan P. A survey of keyword spotting techniques for printed document images. Artificial Intelligence Review 2011; 35 (2): 119-136. doi: 10.1007/s10462-010-9187-5
  • [12] Giotis AP, Sfikas G, Gatos B, Nikou C. A survey of document image word spotting techniques. Pattern Recognition 2017; 68: 310-332. doi: 10.1016/j.patcog.2017.02.023
  • [13] Kim SH, Park SC, Jeong CB, Kim JS, Park HR et al. Keyword spotting on Korean document images by matching the keyword image. In: ICADL 2005 International Conference on Asian Digital Libraries, Implementing Strategies and Sharing Experiences; Bangkok, Thailand; 2005. pp. 158–166.
  • [14] Lu Y, Tan CL. Chinese word searching in imaged documents. International Journal of Pattern Recognition and Artificial Intelligence 2004; 18 (2): 229–246. doi: 10.1142/S0218001404003137
  • [15] Srihari SN, Srinivasan H, Huang C, Shetty S. Spotting words in Latin, Devanagari and Arabic scripts. Indian Journal of Artificial Intelligence 2006; 16: 2–9.
  • [16] Srihari SN, Srinivasan H, Babu P, Bhole C. Spotting words in handwritten Arabic documents. In: SPIE 6067 Document Recognition and Retrieval XIII; San Jose, CA, USA; 2006. pp. 606702-1–606702-12. doi:10.1117/12.643107
  • [17] Srihari SN, Srinivasan H, Babu P, Bhole C. Handwritten Arabic word spotting using the CEDARABIC document analysis system. In: SDIUT 2005 Proceedings of Symposium on Document Image Understanding Technology; Collage Park, MD, USA; 2005. pp. 123–132.
  • [18] Pourasad Y, Hassibi H, Ghorbani A. Farsi word spotting and font size recognition. Procedia Technology 2012; 1: 372–377. doi: 10.1016/j.protcy.2012.02.077
  • [19] Pourasad Y, Hassibi H, Ghorbani A. A word spotting method for Farsi machine-printed document images. Turkish Journal of Electrical Engineering and Computer Sciences 2013; 21 (3): 734-746. doi: 10.3906/elk-1107-26
  • [20] Pourasad Y, Hassibi H, Ghorbani A. A Farsi/Arabic word spotting approach for printed document images. International Journal of Natural and Engineering Sciences 2012; 6 (1): 15-18.
  • [21] Ebrahimi A, Kabir E. A pictorial dictionary for printed Farsi sub words. Pattern Recognition Letters 2008; 29 (5): 656-663. doi: 10.1016/j.patrec.2007.11.008
  • [22] Akbari M, Azmi R. Document image database indexing with pictorial dictionary. In: SPIE 7546 International Conference on Digital Image Processing, International Society for Optics and Photonics; Singapore, Singapore 2010. p. 75462R. doi: 10.1117/12.856302
  • [23] Erlandson EJ, Trenkle JM, Vogt RC. Word-level recognition of multifont Arabic text using a feature-vector matching approach. In: SPIE 2660 Proceedings of the International Society for Optical Engineers; San Jose, SFO, USA; 1996. p. 2660-08. doi: 10.1117/12.234725
  • [24] Miri E, Razavi SM, Mehrshad N. Search space reduction in printed Persian sub word recognition by a heretical method. Indian Journal of Science and Technology 2017; 10 (9): 17485. doi: 10.17485/ijst/2017/v10i9/110158
  • [25] Lu S, Li L, Tan CL. Document image retrieval through word shape coding. IEEE Transactions on Pattern Analysis and Machine Intelligence 2008; 30 (11): 1913-1918. doi: 10.1109/TPAMI.2008.89
  • [26] Zagoris K, Ergina K, Papamarkos N. A document image retrieval system. Engineering Applications of Artificial Intelligence 2010; 23 (6): 872-879. doi: 10.1016/j.engappai.2010.03.002
  • [27] Keyvanpour M, Tavoli R. Feature weighting for improving document image retrieval system performance. International Journal of Computer Science Issues 2012; 9 (3): 125-130.
  • [28] Naveen, Guru DS. Retrieval of document images based on page layout similarity. Lect Notes Comp Sci 2007; 4398: 136-148. doi: 10.1007/978-3-540-71545-0_11
  • [29] Liu J, Jain AK. Image-based form document retrieval. In: IEEE 1998 International Conference on Pattern Recognition; Brisbane, Australia; 1998. pp. 503-513. doi: 10.1109/ICPR.1998.711221
  • [30] Das AK, Chanda B. A fast algorithm for skew detection of document images using morphology. International Journal on Document Analysis and Recognition 2001; 4 (2): 109-114. doi: 10.1007/PL00010902
  • [31] Guru DS, Punitha P, Mahesh S. Skew estimation in digitized documents: a novel approach. In: ICVGIP 2004 Indian Conference on Computer Vision, Graphics and Image Processing; Kolkata, India; 2004. pp. 314-319.
  • [32] Das AK, Saha SK, Chanda B. An empirical measure of the performance of a document image segmentation algorithm. International Journal on Document Analysis and Recognition 2002; 4 (3): 183-190. doi: 10.1007/s100320100
  • [33] Jain AK, Yu B. Document representation and its application to page decomposition. IEEE Transactions on Pattern Analysis and Machine Intelligence 1998; 20 (3): 294-308. doi: 10.1109/34.667886
  • [34] Isapour S, Homayounpour M, Bijabkhan M. The prediction of Ezafe construction in Persian by using probabilistic context free grammar. In: CSICC 2008 International Conference of Computer Society of Iran; Kish Island, Iran; 2008. p. ACCSI13-100.
APA ERGÜN C, Norozpour S (2019). Farsi document image recognition system using word layout signature. , 1477 - 1488. 10.3906/elk-1804-92
Chicago ERGÜN Cem,Norozpour Sajedeh Farsi document image recognition system using word layout signature. (2019): 1477 - 1488. 10.3906/elk-1804-92
MLA ERGÜN Cem,Norozpour Sajedeh Farsi document image recognition system using word layout signature. , 2019, ss.1477 - 1488. 10.3906/elk-1804-92
AMA ERGÜN C,Norozpour S Farsi document image recognition system using word layout signature. . 2019; 1477 - 1488. 10.3906/elk-1804-92
Vancouver ERGÜN C,Norozpour S Farsi document image recognition system using word layout signature. . 2019; 1477 - 1488. 10.3906/elk-1804-92
IEEE ERGÜN C,Norozpour S "Farsi document image recognition system using word layout signature." , ss.1477 - 1488, 2019. 10.3906/elk-1804-92
ISNAD ERGÜN, Cem - Norozpour, Sajedeh. "Farsi document image recognition system using word layout signature". (2019), 1477-1488. https://doi.org/10.3906/elk-1804-92
APA ERGÜN C, Norozpour S (2019). Farsi document image recognition system using word layout signature. Turkish Journal of Electrical Engineering and Computer Sciences, 27(2), 1477 - 1488. 10.3906/elk-1804-92
Chicago ERGÜN Cem,Norozpour Sajedeh Farsi document image recognition system using word layout signature. Turkish Journal of Electrical Engineering and Computer Sciences 27, no.2 (2019): 1477 - 1488. 10.3906/elk-1804-92
MLA ERGÜN Cem,Norozpour Sajedeh Farsi document image recognition system using word layout signature. Turkish Journal of Electrical Engineering and Computer Sciences, vol.27, no.2, 2019, ss.1477 - 1488. 10.3906/elk-1804-92
AMA ERGÜN C,Norozpour S Farsi document image recognition system using word layout signature. Turkish Journal of Electrical Engineering and Computer Sciences. 2019; 27(2): 1477 - 1488. 10.3906/elk-1804-92
Vancouver ERGÜN C,Norozpour S Farsi document image recognition system using word layout signature. Turkish Journal of Electrical Engineering and Computer Sciences. 2019; 27(2): 1477 - 1488. 10.3906/elk-1804-92
IEEE ERGÜN C,Norozpour S "Farsi document image recognition system using word layout signature." Turkish Journal of Electrical Engineering and Computer Sciences, 27, ss.1477 - 1488, 2019. 10.3906/elk-1804-92
ISNAD ERGÜN, Cem - Norozpour, Sajedeh. "Farsi document image recognition system using word layout signature". Turkish Journal of Electrical Engineering and Computer Sciences 27/2 (2019), 1477-1488. https://doi.org/10.3906/elk-1804-92
Sayfa Oluşturulma Tarihi
23-04-2024 11:40

İLETİŞİM

TÜBİTAK ULAKBİM TR Dizin

Yüzüncüyıl, İşçi Blokları Mahallesi

Muhsin Yazıcıoğlu Caddesi No:51/C

06530 Çankaya / ANKARA +90 (312) 298 92 00

trdizin@tubitak.gov.tr

TÜBİTAK ULAKBİM Ulusal Akademik Ağ ve Bilgi Merkezi Cahit Arf Bilgi Merkezi © Tüm Hakları Saklıdır. Gizlilik Politikası Kullanım Şartları