Abstract
The evaluation of finished (i.e., chemically treated) goat/sheep leather can be highly subjective, resulting in disagreements that can eventually lead to the interruption of production programs in the tannery and leather industry. As a result, much research has been carried out in the leather industry aiming at developing an automated system to evaluate goat/sheep leather. In this paper, a computational vision system is proposed in order to classify the quality of the leather automatically. Initially, three filtering steps are used to segment the region of interest (ROI). After highlighting the ROI, the Haralick texture obtained from the gray level co-occurrence matrix is extracted. Some descriptions (e.g., Haralick) are used in this work, namely energy, homogeneity, contrast, cluster tendency, cluster shade, correlation, information measures of correlation, and maximal correlation coefficient. After that, the performances of machine learning algorithms, such as the Naive Bayes classifier, classifier optimum-path forest and support vector machines are compared. The hit rate of the results to automatically classify goat leather quality was similar to other approaches in the literature. However, the proposed system used ten attributes, six less than the best approach found in the literature and in shorter processing time. In summary, the proposed methodology was considered reliable to automatically classify goat leather quality, as it had an accuracy of 93.22% and total processing time was 3.78 s.
Similar content being viewed by others
Notes
Notation
p(i, j): (i, j) entry in a normalized gray-tone spatial-dependence matrix, \(= P(i,j)/R\).
\(p_{x}(i)\): ith entry in the marginal-probability matrix obtained by summing the rows of p(i, j), = \(\sum _{j=1}^{N_g}P(i,j)\).
\(N_g\): number of distinct gray levels in the quantized image.
\(p_y(j)\): jth entry in the marginal-probability matrix obtained by summing the lines of p(i, j), = \(\sum _{i=1}^{N_g}P(i,j)\).
References
M. Alves, E. Clua, F. Leta, Evaluation of surface roughness standards applying Haralick parameters and artificial neural networks, in 2012 19th International Conference on Systems, Signals and Image Processing (IWSSIP), pp. 452–455 (2012)
W.P. Amorim, H. Pistori, M.C. Pereira, M.A.C. Jacinto, Attributes reduction applied to leather defects classification, in Proceedings of the 2010 Conference on Graphics, Patterns and Images (SIBGRAPI)’10, pp. 353–359 (2010)
P. Anand, T. Ajitha, M. Priyadharshini, M. Vaishali, Content based image retrieval CBIR using multiple features for texture images by using SVM classifier. Int. J. Comput. Sci. Commun. Netw. 2(2), 33–42 (2014)
S. Beura, B. Majhi, R. Dash, Mammogram classification using two dimensional discrete wavelet transform and gray-level co-occurrence matrix for detection of breast cancer. Neurocomputing 154, 1–14 (2015). https://doi.org/10.1016/j.neucom.2014.12.032
C. Burges, A tutorial on support vector machines for pattern recognition. Data Min. Knowl. Discov. 2(2), 121–167 (1998). https://doi.org/10.1023/A:1009715923555
J. Canny, A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell. 8, 679–698 (1986)
C.C. Chang, C.J. Lin, LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2(3), 27:1–27:27 (2011). https://doi.org/10.1145/1961189.1961199
S. Chu, L. Hong, C. Liu, J. Chen, A new regional shape index for classification of high resolution remote sensing images, in 2014 3rd International Workshop on Earth Observation and Remote Sensing Applications (EORSA), pp. 156–160 (2014). https://doi.org/10.1109/EORSA.2014.6927869
C. Cortes, V. Vapnik, Support vector networks. Mach. Learn. 20(3), 273–297 (1995)
R.O. Duda, P.E. Hart, D.G. Stork, Pattern Classification, 2nd edn. (Wiley, Hoboken, 2006)
A.X. Falcão, J. Stolfi, R.A. Lotufo, The image foresting transform theory, algorithms, and applications. IEEE Trans. Pattern Anal. Mach. Intell. 26(1), 19–29 (2004)
Z.G. Feng, K.F.C. Yiu, K.L. Mak, Feature extraction of the deformed patterned textile, in 2011 2nd International Conference on Intelligent Control and Information Processing (ICICIP), vol. 1, pp. 264–266 (2011). https://doi.org/10.1109/ICICIP.2011.6008245
R.C. Gonzalez, R.E. Woods, S.I. Eddins, Digital Image Processing, 3rd edn. (Gatesmark Publishing, Knoxville, 2009)
R. Haralick, K. Shanmugam, I. Dinstein, Textural features for image classification. IEEE Trans. Syst. Man Cybern. SMC–3(6), 610–621 (1973). https://doi.org/10.1109/TSMC.1973.4309314
R.M. Haralick, Statistical and structural approaches to texture. Proc. IEEE 67(5), 786–804 (1979)
R.P.R. Hassanzadeh, K. Faez, S. Aslanzadeh, Feature extraction of scale pattern in animal textile fibers, in Proceedings of 12-th in Central Europe on Computer Graphics, Visualization and Computer Vision (WSCG), Plzen, Czech Republic, February 2–6, pp. 53–56 (2004)
F.Q. He, W. Wang, Z.C. Chen, Automatic visual inspection for leather manufacture. Key Eng. Mat. 326–328, 469–472 (2006)
IBGE, Censo Agropecuário 2017, resultados preliminares (MPOG, Rio de Janeiro, 2018)
P.A. Jadhav, M.S. Biradar, An approach for feature extraction of fabric using wavelet transform and defect detection using genetic algorithm. Int. J. Recent Innov. Trends Comput. Commun. 2(7), 1799–1802 (2014)
M. Jawahar, N.C. Babu, M.M. Ismail, K. Vani, Compression of leather images for automatic leather grading system using multiwavelet, in 2016 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC) (IEEE, 2016), pp. 1–7
W. Keqi, B. Jingfeng, M. Hong, K. Xianglin, C. Kebing, Feature extraction of defects on wood surface. J. For. Res. 9(1), 54–56 (1993). https://doi.org/10.1007/BF02856457
J. Lampinen, S. Smolander, Self-organizing feature extraction in recognition of wood surface defects and color images. Int. J. Pattern Recognit. Artif. Intell. 10, 97–113 (1996)
Mathworks: Image Processing Toolbox: User’s Guide (r2011a). Retrived 22 Feb 2016 from www.mathworks.com (2011)
A. McAndrew, Introduction Do Digital Image Processing with Matlab (Thomson Learning, London, 2004)
E.C. Neto, S.L. Gomes, P.P.R. Filho, V.H.C. de Albuquerque, Brazilian vehicle identification using a new embedded plate recognition system. Measurement 70, 36–46 (2015)
J.P. Papa, A.X. Falcão, C.T.N. Suzuki, Supervised pattern classification based on optimum-path forest. Int. J. Imaging Syst. Technol. 19(2), 120–131 (2009)
J.P. Papa, C.T.N. Suzuki, A.X. Falcão, LibOPF: library for the design of optimum-path forest classifiers. IEEE Trans. Power Syst. 26 (2009)
R.F. Pereira, C.M.S. Medeiros, P.P.R. Filho, Goat leather quality classification using computer vision and machine learning, in Proceedings of International Joint Conference on Neural Networks (IJCNN), Rio de Janeiro, Brazil, July 8–13 (2018). https://doi.org/10.1109/ijcnn.2018.8489265
Prasetiyo, M. Khalid, R. Yusof, F. Meriaudeau, A comparative study of feature extraction methods for wood texture classification, in 2010 Sixth International Conference on Signal-Image Technology and Internet-Based Systems (SITIS), pp. 23–29 (2010)
J.E. Ruppental, Prospects of the Leather Sector of the Rio Grande do Sul State. Master Thesis in Production Engineering, Federal University of Santa Catarina (2001) (in Portuguese)
E.Q. Santos Filho, G.A. Barreto, Evaluation of feature extraction methods for classification of goat leather quality (in Portuguese), in Proceedings of the 11th Brazilian Congress on Computational Intelligence (CBIC’2013), pp. 1–6, Porto de Galinhas, Brazil (2013). https://doi.org/10.21528/CBIC2013-220
B. Schölkopf, A.J. Smola, Learning with Kernels (MIT Press, Cambridge, 2002)
S. Theodoridis, Pattern Recognition (Academic Press, Cambridge, 2009)
V.N. Vapnik, An overview of statistical learning theory. IEEE Trans. Neural Netw. 10(5), 988–999 (1999)
L. Wang, Z. Deng, X. Wang, Application of wavelet transform method for textile material feature extraction. Wavelet Transforms Recent Appl. Biol. Geosci. (2012). https://doi.org/10.5772/38793
S. Winiarti, A. Prahara, D.P.I. Murinto, Pre-trained convolutional neural network for classification of tanning leather image. Int. J. Adv. Comput. Sci. Appl. 9(1), 1–6 (2018). https://doi.org/10.14569/IJACSA.2018.090129
Acknowledgements
This work was supported in part by Brazilian National Council for Research and Development (CNPq) via the Grant Nos. 301928/2014-2, 309335/2017-5, 309451/2015-9, 304315/2017-6 and 430274/2018-1; by the Federal Institute of Education, Science and Technology of Ceara via grants PROINFRA/2017 and PROINFRA PPG/2017; and by the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior—Brasil (CAPES)—Finance Code 001.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Santos Filho, E.Q., de Sousa, P.H.F., Rebouças Filho, P.P. et al. Evaluation of Goat Leather Quality Based on Computational Vision Techniques. Circuits Syst Signal Process 39, 651–673 (2020). https://doi.org/10.1007/s00034-019-01180-4
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00034-019-01180-4