Space-Frecuency Descriptors for Automatic Identification of Texture Patterns Using Supervised Learning
Abstract
This article presents an evaluation of frequency-space descriptors and texture analysis techniques for textile classification. The work methodology consists of three fundamental stages: characterization, classification and validation. The characterization stage uses descriptors such as wavelet transform, Fourier transform, a state-of-the-art texture characterization method such as segmentation-based fractal texture analysis (SFTA) and the adaptation of the short-space Fourier transform. The classification stage analyzes the use of three state-ofthe-art methods such as Artificial Neural Networks (ANN), Support Vector Machines (SVM) and the Gaussian Process (GP); linear, Gaussian and polynomial kernels were included in SVM and GP. To validate the method, an annotated database is built with ten types of fabrics and 1,000 photos, to which the characterization and classification process is applied by means of a Monte Carlo experiment. At this stage, random training (70 %) and testing (30 %) configurations are generated, finding the performance of each classification model. Finally, the confusion matrix is obtained, and the success percentages of each experiment are determined. Additionally, a time analysis is carried out for each algorithm, both at the descriptor and classifier levels, in order to determine the configuration that offers better features and its computational cost.
Downloads
References
Control de calidad textil. [En línea]. Disponible en: http://www.detextiles.com/files/CONTROL%20DE%20CALIDAD%20TEXTIL.pdf
C. Spinola et al., "Image processing for surface quality control in stainless steel production lines," 2010 IEEE International Conference on Imaging Systems and Techniques, Thessaloniki, 2010, pp. 192-197. https://doi.org/10.1109/IST.2010.5548466
M. Sharifzadeh, S. Alirezaee, R. Amirfattahi and S. Sadri, "Detection of steel defect using the image processing algorithms," 2008 IEEE International Multitopic Conference, Karachi, 2008, pp. 125-127. https://doi.org/10.1109/INMIC.2008.4777721
P. L. Mazzeo, L. Giove, G. M. Moramarco, P. Spagnolo and M. Leo, "HSV and RGB color histograms comparing for objects tracking among non overlapping FOVs, using CBTF," 2011 8th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), Klagenfurt, 2011, pp. 498-503. https://doi.org/10.1109/AVSS.2011.6027383
Arias, N., & Ortiz, A. (2016). ANÁLISIS COMPARATIVO DE DESCRIPTORES PARA LA CLASIFICACIÓN DE TELAS UTILIZANDO IMÁGENES. Universidad Tecnológica de Pereira, Pereira, Colombia.
A. Luna, M. Angel, "Análisis del Clúster Textil en el Perú". [En línea]. Disponible en: http://sisbib.unmsm.edu.pe/bibvirtualdata/Tesis/Ingenie/angulo_lm/cap2.PDF
COATS, "Todo Sobre Fibras Textiles". [En línea]. Disponible en: http://www.coatsindustrial.com/es/images/Know_About_Textile_Fibres_tcm62-9073.pdf
ZHANG, Dengsheng; LU, Guojun. Shape-based image retrieval using generic Fourier descriptor. Signal Processing: Image Communication, 2002, vol. 17, no 10, p. 825-848. https://doi.org/10.1016/S0923-5965(02)00084-X
DENG, Yining, et al. An efficient color representation for image retrieval. IEEE Transactions on image processing, 2001, vol. 10, no 1, p. 140-147. https://doi.org/10.1109/83.892450
VEERARAGHAVAN, Ashok, et al. Dappled photography: Mask enhanced cameras for heterodyned light fields and coded aperture refocusing. ACM Trans. Graph., 2007, vol. 26, no 3, p. 69. https://doi.org/10.1145/1276377.1276463
PERNER-NOCHTA, Iris; POSTEN, Clemens. Simulations of light intensity variation in photobioreactors. Journal of Biotechnology, 2007, vol. 131, no 3, p. 276-285. https://doi.org/10.1016/j.jbiotec.2007.05.024
Obagi, Elementos de teoría de probabilidad para ingenieros. Bogotá (Colombia): Pontificia Universidad Javeriana, 2003.
Mallat, S. "A theory for multiresolution signal decomposition: the wavelet representation," IEEE Pattern Anal. and Machine Intell., vol. 11, no. 7, pp. 674-693. https://doi.org/10.1109/34.192463
Meyer, Y. Ondelettes et opérateurs, Tome 1, Hermann Ed. (English translation: Wavelets and operators, Cambridge Univ. Press. 1993.) https://doi.org/10.1017/CBO9780511623820
J. Núnez, J.C. Carvajal, L.A. Bautista, "El TLC con estados unidos y su impacto en el sector agropecuario colombiano: Entre esperanzas e incertidumbres", Revista Electrónica de la facultad de Derecho, 1 (1), 118-133, 2004.
V.A. Contreras, C. Gutiérrez, M.E. León, Y. Cadena, F.E. León, "Iso 9001-2: un compromiso posible en la era del TLC," Revista Teoría Y Praxis Investigativa, 3 (2), 52-60, 2008.
A. Bejarano & A. F. Calvo, (2012) Escáner 3d para control de calidad de piezas metalúrgicas. Tesis de pre-grado, Universidad Tecnológica de Pereira.
N. Florez, L.P. Sánchez, F.G. Ramírez, (2011) Visión Artificial Para Detección Automática de Fallas Estructurales en Botellas de Vidrio. Tesis de Maestría, Instituto politécnico nacional.
J.M. Prats, (2005) Control Estadístico de Procesos Mediante Análisis Multivariante de Imágenes. Tesis de Doctorado, Universidad Politécnica de Valencia.
C.G. Spinola, J.M. Cañero-Nieto, M.J. Martin, J.M. Bonelo, F. Garcia, G. Moreno, S. Espejo, G. Hylander, & J. Vizoso. (2010, Julio). Image Processing for Surface Quality Control in Stainless Steel Production Lines. Presentado en Imaging Systems and Techniques (IST), 2010 IEEE International Conference on. [En línea] Disponible: http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=5548466. https://doi.org/10.1109/IST.2010.5548466
C.G. Spinola, J. Canero, G. Moreno, J.M. Bonelo, & M. Martin. (2011, Mayo). Real-time Image Processing for Edge Inspection and Defect Detection in Stainless Steel Production Lines. Presentado en Imaging Systems and Techniques (IST), 2011 IEEE International Conference on. [En línea] Disponible: http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=5962196. https://doi.org/10.1109/IST.2011.5962196
A. Bejarano Martínez, A. F. Calvo and C. A. Henao, "Supervised learning models for control quality by using color descriptors: A study case," 2016 XXI Symposium on Signal Processing, Images and Artificial Vision (STSIVA), Bucaramanga, 2016, pp. 1-7. doi: 10.1109/STSIVA.2016.7743368 http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7743368&isnumber=7743290 https://doi.org/10.1109/STSIVA.2016.7743368
B. Shabari Shedthi, Surendra Shetty y M. Siddappa. Implementation and comparison of K-means and fuzzy C-means algorithms for agricultural data. Inventive Communication and Computational Technologies (ICICCT), 2017 International Conference on. Disponible en: http://ieeexplore.ieee.org/document/7975168/ https://doi.org/10.1109/ICICCT.2017.7975168
Duber Martínez Torres y Sergio Orjuela. Máquina de Vectores de soporte para la detección de defectos textiles empleando características espaciales de textura. Revista Colombiana de Tecnologías de Avanzada. ISSN: 1692-7257, Vol 2, No 14, 2009
Chi-Ho Chan and G. K. H. Pang, "Fabric defect detection by Fourier analysis," in IEEE Transactions on Industry Applications, vol. 36, no. 5, pp. 1267-1276, Sep/Oct 2000. doi: https://doi.org/10.1109/28.871274
Sungshin Kim, Man Hung Lee and Kwang-Bang Woo, "Wavelet analysis to fabric defects detection in weaving processes," Industrial Electronics, 1999. ISIE '99. Proceedings of the IEEE International Symposium on, Bled, 1999, pp. 1406-1409 vol.3. doi: 10.1109/ISIE.1999.796918. https://doi.org/10.1109/ISIE.1999.796918
A. F. Costa, G. Humpire-Mamani and A. J. M. Traina, "An Efficient Algorithm for Fractal Analysis of Textures," 2012 25th SIBGRAPI Conference on Graphics, Patterns and Images, Ouro Preto, 2012, pp. 39-46. doi: https://doi.org/10.1109/SIBGRAPI.2012.15
A. Bejarano Martínez, A. F. Calvo and C. A. Henao "Identificación automática de productos textiles utilizando caracterización espacio frecuencia y aprendizaje supervisado". Congreso Internacional de Multimedia 2017.
