Research Article
BibTex RIS Cite

Shape Recognition Using Histogram of Shell Chain Code

Year 2019, Volume: 7 Issue: 1, 810 - 826, 31.01.2019
https://doi.org/10.29130/dubited.490824

Abstract

Shape can be defined as perception of natural boundaries of an object in human brain. Shape recognition is
determination of class to which the object belongs by comparison of the object perceptions which are previously
encountered and stored in memory. In the computer based shape recognition, it is determination of class to
which the object belongs by comparison of the feature vectors which are obtained by contour or region-based
methods. The chain code, which is one of the contour-based feature extraction methods, is a sequence of
symbols created by following the boundary of an object. The elements of symbol set must be predefined for each
direction. The fundamental issue with chain code used for shape description is that they are not robust enough
for scaling and rotation. In other words, the length and content of chain code may change when shapes are scaled
or rotated. Therefore, in compassion process of shapes, normalized chain code histograms are preferred rather than chain codes with different lengths. Consequently, similarity calculations are performed by means of feature
vectors of which the fixed lengths are proportional with symbol types. In this study, a new chain code which is
strong for scaling and rotation has been proposed. The shell numbers where the object boundary pixels are
located has been used to generate the chain code. The rotational robustness of the proposed chain code has been
experimentally compared with outputs of Freeman 8 (FR8) chain code histogram and the obtained results have
been given.

References

  • [1] H. Freeman, “On the encoding of arbitrary geometric configurations,” IRE Transactions on Electronic Computers, vol. EC-10, no. 2, pp. 260-268, 1961.
  • [2] H. Freeman, “Computer processing of line drawing images,” ACM Computing Surveys(CSUR), vol. 6, no. 1, pp. 57-97, 1974.
  • [3] S. Papert, “Uses of technology to enhance education,” AI lab MIT, U.S.A, Technical Report 298, 1973.
  • [4] S. H. Cruz and R. M. R.Dagnino, “Compressing bi-level images by means of a 3-bit chain code,” SPIE Opt. Eng., vol. 44, no. 9, pp. 1-8, 2005.
  • [5] P. Nunes, F. Pereira, F. Marqués, “Multi-grid chain coding of binary shapes,” ICIP’97 Proceedings of the 1997 International Conference on Image Processing, DC USA, vol.3, pp. 114-117,1997.
  • [6] E. Bribiesca, “A new chain code,” Pattern Recognition, vol. 32, no. 2, pp. 235-251, 1999.
  • [7] Y.K. Lui ve B. Zalik, “An efficient chain code with Huffman coding,” Pattern Recognition, vol. 38, no. 4, pp. 553-557, 2005.
  • [8] B. Zalik, D. Mongus, Y. Liu, N. Lukač, “Unsigned Manhattan chain code,” Journal of Visual Communication and Image Representation, vol. 38, pp. 186-194, 2016.
  • [9] D. Zhang ve G. Lu, “Review of shape representation and description techniques,” Pattern Recognition, vol. 37, no. 1, pp. 1-19, 2004.
  • [10] J. Iivarinen ve A. Visa, “Shape recognition of irregular objects,” Intelligent Robots and Computer Vision XV: Algorithms, Techniques, Active Vision, and Materials Handling, vol. 2904, pp. 25-32, 1996.
  • [11] S. K. Pradhan, S. Sarker, S. K. Das, “A Character Recognition Approach using Freeman Chain Code and Approximate String Matching,” International Journal of Computer Applications, vol. 84, no. 11, pp. 38-42, 2013.
  • [12] M. Ankerst, G. Kastenmüller, H.P. Kriegel, T. Seidl, “Nearest neighbor classification in 3D protein databases,” Proceedings of the 2nd International Conference on Intelligent Systems for Molecular Biology, vol. 99, pp. 34-43, 1999.
  • [13] T.B. Sebastian, P.N. Klein, B.B. Kimia, “Recognition of shapes by editing their shock graphs,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 26, no. 5, pp. 550–571, 2004.
  • [14] H.Tuna ve R. Demirci, “Shell Chain Code,” ISMSIT 2018 Proceedings of the 2018 Symposium on Multidisciplinary Studies and Innovative Technologies, Kızılcahamam Turkey, 2018.
  • [15] D. Ballabio, F. Grisoni, R. Todeschini, “Multivariate comparison of classification performance measures,” Chemometrics and Intelligent Laboratory Systems, vol. 174, pp. 33-44, 2018.
  • [16] M. Sokolova ve G. Lapalme, “A systematic analysis of performance measures for classification tasks,” Information Processing and Management, vol. 45, no. 4, pp. 427-437, 2009.

Kabuk Zincir Kod Histogramı Kullanılarak Şekil Tanıma

Year 2019, Volume: 7 Issue: 1, 810 - 826, 31.01.2019
https://doi.org/10.29130/dubited.490824

Abstract

Şekil bir nesnenin doğal sınırlarının insan beyninde oluşturduğu algı olarak tanımlanabilir. Şekil tanıma ise
herhangi bir nesnenin ait olduğu sınıfın daha önceden karşılaşılan ve hafızaya kaydedilen algılarla
karşılaştırılarak bulunmasıdır. Bilgisayarda şekil tanıma nesnelerin sınır veya bölge tabanlı şekil temsil
yöntemleriyle elde edilen özellik vektörlerinin karşılaştırılarak sınıflarının tespitidir. Sınır tabanlı özellik çıkarma
metotlarından biri olan zincir kodu sayısal görüntüdeki bir nesnenin sınır noktaları takip edilerek üretilen sembol
dizisidir. İlgili sembol kümesinin elemanları her yön için daha önceden belirlenmelidir. Şekil temsilinde
kullanılan zincir kodlarının en temel problemi ölçekleme veya döndürme işlemlerine karşı yeterince güçlü
olmamalarıdır. Başka bir ifade ile şekiller ölçeklendiğinde ya da döndürüldüğünde zincir kodlarının
uzunluklarının ve içeriklerinin değişmesidir. Bu nedenle şekillerin benzerlik karşılaştırılmasında farklı
uzunluklardaki sembol dizisinden oluşan zincir kodları yerine, normalize edilmiş zincir kod histogramı tercih
edilmektedir. Böylece sınır bilgileri sembol çeşidi ile orantılı olan sabit uzunlukta vektörlere dönüştürülerek
benzerlik hesaplaması yapılmaktadır. Bu çalışmada nesnelerin sınır noktalarında bulunan piksellerin kabuk
numaraları kullanılarak ölçeklenme ve döndürme işlemlerine karşı dayanıklı yeni bir zincir kod histogramı
önerilmiştir. Önerilen yöntemin döndürmeye karşı duyarlılığı Freeman 8 (FR8) zincir kod histogramıyla
deneysel olarak karşılaştırılmış ve elde edilen sonuçlar verilmiştir. 

References

  • [1] H. Freeman, “On the encoding of arbitrary geometric configurations,” IRE Transactions on Electronic Computers, vol. EC-10, no. 2, pp. 260-268, 1961.
  • [2] H. Freeman, “Computer processing of line drawing images,” ACM Computing Surveys(CSUR), vol. 6, no. 1, pp. 57-97, 1974.
  • [3] S. Papert, “Uses of technology to enhance education,” AI lab MIT, U.S.A, Technical Report 298, 1973.
  • [4] S. H. Cruz and R. M. R.Dagnino, “Compressing bi-level images by means of a 3-bit chain code,” SPIE Opt. Eng., vol. 44, no. 9, pp. 1-8, 2005.
  • [5] P. Nunes, F. Pereira, F. Marqués, “Multi-grid chain coding of binary shapes,” ICIP’97 Proceedings of the 1997 International Conference on Image Processing, DC USA, vol.3, pp. 114-117,1997.
  • [6] E. Bribiesca, “A new chain code,” Pattern Recognition, vol. 32, no. 2, pp. 235-251, 1999.
  • [7] Y.K. Lui ve B. Zalik, “An efficient chain code with Huffman coding,” Pattern Recognition, vol. 38, no. 4, pp. 553-557, 2005.
  • [8] B. Zalik, D. Mongus, Y. Liu, N. Lukač, “Unsigned Manhattan chain code,” Journal of Visual Communication and Image Representation, vol. 38, pp. 186-194, 2016.
  • [9] D. Zhang ve G. Lu, “Review of shape representation and description techniques,” Pattern Recognition, vol. 37, no. 1, pp. 1-19, 2004.
  • [10] J. Iivarinen ve A. Visa, “Shape recognition of irregular objects,” Intelligent Robots and Computer Vision XV: Algorithms, Techniques, Active Vision, and Materials Handling, vol. 2904, pp. 25-32, 1996.
  • [11] S. K. Pradhan, S. Sarker, S. K. Das, “A Character Recognition Approach using Freeman Chain Code and Approximate String Matching,” International Journal of Computer Applications, vol. 84, no. 11, pp. 38-42, 2013.
  • [12] M. Ankerst, G. Kastenmüller, H.P. Kriegel, T. Seidl, “Nearest neighbor classification in 3D protein databases,” Proceedings of the 2nd International Conference on Intelligent Systems for Molecular Biology, vol. 99, pp. 34-43, 1999.
  • [13] T.B. Sebastian, P.N. Klein, B.B. Kimia, “Recognition of shapes by editing their shock graphs,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 26, no. 5, pp. 550–571, 2004.
  • [14] H.Tuna ve R. Demirci, “Shell Chain Code,” ISMSIT 2018 Proceedings of the 2018 Symposium on Multidisciplinary Studies and Innovative Technologies, Kızılcahamam Turkey, 2018.
  • [15] D. Ballabio, F. Grisoni, R. Todeschini, “Multivariate comparison of classification performance measures,” Chemometrics and Intelligent Laboratory Systems, vol. 174, pp. 33-44, 2018.
  • [16] M. Sokolova ve G. Lapalme, “A systematic analysis of performance measures for classification tasks,” Information Processing and Management, vol. 45, no. 4, pp. 427-437, 2009.
There are 16 citations in total.

Details

Primary Language Turkish
Subjects Engineering
Journal Section Articles
Authors

Haydar Tuna 0000-0003-2388-653X

Recep Demirci 0000-0002-3278-0078

Publication Date January 31, 2019
Published in Issue Year 2019 Volume: 7 Issue: 1

Cite

APA Tuna, H., & Demirci, R. (2019). Kabuk Zincir Kod Histogramı Kullanılarak Şekil Tanıma. Duzce University Journal of Science and Technology, 7(1), 810-826. https://doi.org/10.29130/dubited.490824
AMA Tuna H, Demirci R. Kabuk Zincir Kod Histogramı Kullanılarak Şekil Tanıma. DUBİTED. January 2019;7(1):810-826. doi:10.29130/dubited.490824
Chicago Tuna, Haydar, and Recep Demirci. “Kabuk Zincir Kod Histogramı Kullanılarak Şekil Tanıma”. Duzce University Journal of Science and Technology 7, no. 1 (January 2019): 810-26. https://doi.org/10.29130/dubited.490824.
EndNote Tuna H, Demirci R (January 1, 2019) Kabuk Zincir Kod Histogramı Kullanılarak Şekil Tanıma. Duzce University Journal of Science and Technology 7 1 810–826.
IEEE H. Tuna and R. Demirci, “Kabuk Zincir Kod Histogramı Kullanılarak Şekil Tanıma”, DUBİTED, vol. 7, no. 1, pp. 810–826, 2019, doi: 10.29130/dubited.490824.
ISNAD Tuna, Haydar - Demirci, Recep. “Kabuk Zincir Kod Histogramı Kullanılarak Şekil Tanıma”. Duzce University Journal of Science and Technology 7/1 (January 2019), 810-826. https://doi.org/10.29130/dubited.490824.
JAMA Tuna H, Demirci R. Kabuk Zincir Kod Histogramı Kullanılarak Şekil Tanıma. DUBİTED. 2019;7:810–826.
MLA Tuna, Haydar and Recep Demirci. “Kabuk Zincir Kod Histogramı Kullanılarak Şekil Tanıma”. Duzce University Journal of Science and Technology, vol. 7, no. 1, 2019, pp. 810-26, doi:10.29130/dubited.490824.
Vancouver Tuna H, Demirci R. Kabuk Zincir Kod Histogramı Kullanılarak Şekil Tanıma. DUBİTED. 2019;7(1):810-26.