nach oben

Tipp

Fast and Accurate Deep Learning Model for Stamps Detection for Embedded Devices

verfasst von: A. Gayer, D. Ershova, V. Arlazarov

Erschienen in: Pattern Recognition and Image Analysis | Ausgabe 4/2022

Einloggen, um Zugang zu erhalten

Abstract

The search for stamps on images is necessary to verify the authenticity of a document and extract valuable textual information contained in them. Despite the vast number of methods for detecting stamps, most of them are not universal and are limited either by the characteristics of the stamp or by the computational complexity of the approach. The last criterion is extremely relevant, since document recognition is actively transferred from server solutions to mobile devices with low computing power and limited battery life. In view of this, in this paper we propose a compact and computationally efficient neural network model for searching for stamps of any shape and color. Based on the popular neural network detector YOLO, our model contains only 128 thousand parameters. We demonstrate the effectiveness of the model in an experiment on the public dataset SPODS (scanned pseudo-official dataset), containing high-resolution scans of documents with stamps.

Vorheriger Artikel Deep Learning Algorithm for Maximizing the Spectral Efficiency of Wireless Systems

Nächster Artikel Finite Normal Mixture Models for the Ensemble Learning of Recurrent Neural Networks with Applications to Currency Pairs

Sie möchten Zugang zu diesem Inhalt erhalten? Dann informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 69.000 Bücher
über 500 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt 90 Tage mit der neuen Mini-Lizenz testen!

Jetzt informieren

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 58.000 Bücher
über 300 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt 90 Tage mit der neuen Mini-Lizenz testen!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 50.000 Bücher
über 380 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt 90 Tage mit der neuen Mini-Lizenz testen!

Jetzt informieren

M. Afifi, Ya. Ali, K. Amer, M. Shaker, and M. Elhelw, “Robust real-time pedestrian detection on embedded devices,” Proc. SPIE 11605, 1160529 (2021). https://doi.org/10.1117/12.2587097 CrossRef

S. Ahmed, F. Shafait, M. Liwicki and A. Dengel, “A generic method for stamp segmentation using part-based features,” in 12th Int. Conf. on Document Analysis and Recognition, Washington, D.C., 2013 (IEEE, 2013), pp. 708–712. https://doi.org/10.1109/ICDAR.2013.145

N. A. Andriyanov, V. E. Dementiev, and A. G. Tashlinskii, “Detection of objects in the images: from likelihood relationships towards scalable and efficient neural networks,” Komp’yut. Opt. 46, 139–159 (2022). https://doi.org/10.18287/2412-6179-CO-922 CrossRef

A. Alireza, R. P. Partha, and P. Umapada, “Logo and seal based administrative document image retrieval: A survey,” Comput. Sci. Rev. 22, 47–63 (2016). https://doi.org/10.1016/j.cosrev.2016.09.002 MathSciNetCrossRef

V. V. Arlazarov, J. S. Voysyat, D. P. Matalov, D. P. Nikolaev, and S. A. Usilin, “Evolution of the Viola–Jones object detection method: A survey,” Vestn. Yuzhno-Ural. Gos. Univ. Ser. Mat. Model. Progr. 14 (4), 5–23 (2021). https://doi.org/10.14529/mmp210401 CrossRefMATH

D. Ballard, “Generalizing the Hough transform to detect arbitrary shapes,” Pattern Recognit. 13, 111–122 (1981). https://doi.org/10.1016/0031-3203(81)90009-1 CrossRefMATH

S. Chanda, P.K. Prasad, A. Hast, A. Brun, L. Martensson, and U. Pal, “Finding logo and seal in historical document images—An object detection based approach, in Pattern Recognition. ACPR 2019, Ed. by S. Palaiahnakote, G. Sanniti di Baja, L. Wang, and W. Yan, Lecture Notes in Computer Science, Vol. 12046 (Springer, Cham, 2019), pp. 821–834. https://doi.org/10.1007/978-3-030-41404-7_58 CrossRef

S. Dey, J. Mukherjee, S. Sural, and P. Bhowmick. “Colored rubber stamp removal from document images,” in Pattern Recognition and Machine Intelligence. PReMI 2013, Ed. by P. Maji, A. Ghosh, M. N. Murty, K. Ghosh, and S. K. Pal, Lecture Notes in Computer Science, Vol. 8251 (Springer, Berlin, 2013), pp. 545–550. https://doi.org/10.1007/978-3-642-45062-4_75 CrossRef

S. Dey, J. Mukherjee, and S. Sural, “Stamp and logo detection from document images by finding outliers,” in 2015 Fifth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG), Patna, India, 2015 (IEEE, 2015), pp. 1‒4. https://doi.org/10.1109/NCVPRIPG.2015.7489947

10.

S. Emelyanov, A. Ivanova, E. Shvets, and D. Nikolaev, “Methods of training data augmentation in the task of image classification,” Sens. Syst. J. 32, 236–245 (2018). https://doi.org/10.1134/s0235009218030058 CrossRef

11.

P. Forczmański, D. Frejlichowski (2010). “Robust stamps detection and classification by means of general shape analysis,” in Computer Vision and Graphics. ICCVG 2010, Ed. by L. Bolc, R. Tadeusiewicz, L.J. Chmielewski, and K. Wojciechowski, Lecture Notes in Computer Science, Vol. 6374 (Springer, Berlin, 2010), pp. 360–367. https://doi.org/10.1007/978-3-642-15910-7_41 CrossRef

12.

A. V. Gayer, Yu. S. Chernyshova, and A. V. Sheshkus, “Effective real-time augmentation of training dataset for the neural networks learning,” Proc. SPIE 11041, 110411I (2019). https://doi.org/10.1117/12.2522969 CrossRef

13.

R. Girshick, J. Donahue, T. Darrell, and J. Malik, “Rich feature hierarchies for accurate object detection and semantic segmentation, in Proc. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Columbus, Ohio, 2013 (IEEE, 2010), pp. 580–587. https://doi.org/10.1109/CVPR.2014.8

14.

Zh. Guangyu, S. Jaeger, and D. Doermann, “A robust stamp detection framework on degraded documents,” Proc. SPIE 6067, 60670B (2006). https://doi.org/10.1117/12.643537 CrossRef

15.

B. Jin and H. Wang, “Seal registration and identification based on SIFT,” in IEEE 9th Int. Conf. on Anti-Counterfeiting, Security, and Identification (ASID), Xiamen, China, 2015 (IEEE, 2015), pp. 97–100. https://doi.org/10.1109/ICASID.2015.7405669

16.

D. P. Matalov, S. A. Usilin, and V. V. Arlazarov, “About Viola–Jones image classifier structure in the problem of stamp detection in document images,” Proc. SPIE 11605, 116050V (2021). https://doi.org/10.1117/12.2586842 CrossRef

17.

V. Mazzia, A. Khaliq, F. Salvetti and M. Chiaberge, “Real-time apple detection system using embedded systems with hardware accelerators: An edge AI application,” IEEE Access 8, 9102–9114 (2020). https://doi.org/10.1109/ACCESS.2020.2964608 CrossRef

18.

R. A. McLaughlin, “Randomized Hough transform: Improved ellipse detection with comparison,” Pattern Recognit. Lett. 19, 299–305 (1998). https://doi.org/10.1016/S0167-8655(98)00010-5 CrossRefMATH

19.

B. Micenkova and J. van Beusekom, “Stamp detection in color document images,” in Int. Conf. on Document Analysis and Recognition, Beijing, 2011 (IEEE, 2011), pp. 1125–1129. https://doi.org/10.1109/ICDAR.2011.227

20.

A. V. Nandedkar, J. Mukherjee, and S. Sural, “SPODS: A Dataset of color-official documents and detection of logo, stamp, and signature,” in Computer Vision, Graphics, and Image Processing. ICVGIP 2016, Ed. by S. Mukherjee, S. Mukherjee, D. P. Mukherjee, J. Sivaswamy, S. Awate, S. Setlur, A. M. Namboodiri, and S. Chaudhury, Lecture Notes in Computer Science, Vol. 10481 (Springer, Cham, 2017), pp. 219–230. https://doi.org/10.1007/978-3-319-68124-5_19 CrossRef

21.

P. P. Roy, U. Pal, and J. Lladós, “Document seal detection using GHT and character proximity graphs,” Pattern Recognit. 44, 1282–1295 (2011). https://doi.org/10.1016/j.patcog.2010.12.004 CrossRef

22.

J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 2016 (IEEE, 2016), pp. 779–788. https://doi.org/10.1109/CVPR.2016.91

23.

J. Redmon and A. Farhadi, “YOLOv3: An incremental improvement,” (2018). arXiv:1804.02767 [cs.CV]

24.

P. Singh, B. Raman, and P. Roy, “Detection of seal and signature entities with hierarchical recovery based on watermark self embedding in tampered digital documents,” Displays 54, 47–59 (2018). https://doi.org/10.1016/j.displa.2018.09.004 CrossRef

25.

S. Tsuji and F. Matsumoto, “Detection of ellipses by a modified Hough transformation,” IEEE Trans. Comput. 27, 777–781 (1978). https://doi.org/10.1109/TC.1978.1675191 CrossRef

26.

K. Ueda, T. Mutoh, and K. Matsuo, “Automatic verification system for seal imprints on Japanese bankchecks,” Proc. Fourteenth Int. Conf. on Pattern Recognition, Brisbane, Australia, 1998 (IEEE, 1998), Vol. 1, pp. 629–632. https://doi.org/10.1109/ICPR.1998.711222

27.

S. Volkova, “Analysis of the training parameters of cascade classifier to find elements of a face,” Inf. Tekhnol. Vychislit. Sist. 4, 78–85 (2015).

28.

K. L. Wiggers, A. S. Britto, L. Heutte, A. L. Koerich, and L. S. Oliveira, “Image retrieval and pattern spotting using Siamese neural network,” in Int. Joint Conf. on Neural Networks (IJCNN), Budapest, 2019 (IEEE, 2019), pp. 1–8. https://doi.org/10.1109/IJCNN.2019.8852197

29.

J. Younas, M. Z. Afzal, M. I. Malik, F. Shafait, P. Lukowicz, and S. Ahmed, “D-StaR: A generic method for stamp segmentation from document images,” in 14th IAPR Int. Conf. on Document Analysis and Recognition (ICDAR), Kyoto, Japan, 2017 (IEEE, 2017), pp. 248–253. https://doi.org/10.1109/ICDAR.2017.49

30.

Lv Zhaohao, Li Huiyan, and L. Yeming, “Garbage detection and classification method based on YoloV5 algorithm,” Proc. SPIE 12084, 1208403 (2022). https://doi.org/10.1117/12.2622439 CrossRef

Titel: Fast and Accurate Deep Learning Model for Stamps Detection for Embedded Devices
verfasst von: A. Gayer
D. Ershova
V. Arlazarov
Publikationsdatum: 01.12.2022
Verlag: Pleiades Publishing
Erschienen in: Pattern Recognition and Image Analysis / Ausgabe 4/2022
Print ISSN: 1054-6618
Elektronische ISSN: 1555-6212
DOI: https://doi.org/10.1134/S1054661822040046

Springer Professional

Tipp

Weitere Artikel dieser Ausgabe durch Wischen aufrufen

Fast and Accurate Deep Learning Model for Stamps Detection for Embedded Devices

Abstract

Sie möchten Zugang zu diesem Inhalt erhalten? Dann informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Wirtschaft"

Springer Professional "Technik"

Premium Partner

Springer Professional

Tipp

Weitere Artikel dieser Ausgabe durch Wischen aufrufen

Abstract

Bitte loggen Sie sich ein, um Zugang zu diesem Inhalt zu erhalten

Sie möchten Zugang zu diesem Inhalt erhalten? Dann informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Wirtschaft"

Springer Professional "Technik"

Weitere Artikel der Ausgabe 4/2022

Reduction of Video Data at Translation of a Registered Object Relative to Video Sensors Based on the Eigenbasis of Interpretation Model

Finite Normal Mixture Models for the Ensemble Learning of Recurrent Neural Networks with Applications to Currency Pairs

ATM Cash Flow Prediction Using Local and Global Model Approaches in Cash Management Optimization

Subjective Restoration of Omissions in the Measurement Data of an Object of Study and Its Mathematical Model

Hough Encoder for Machine Readable Zone Localization

Deep Learning Algorithm for Maximizing the Spectral Efficiency of Wireless Systems

Premium Partner