TY  - JOUR
T1  - GPU Accelerated Intuitionistic Fuzzy and Otsu Algorithms for Foreign Leaf Detection in Cotton
TT  - Pamuktaki Yabancı Elyafların GPU ile Hızlandırılmış Sezgisel Bulanık Mantık ve Otsu Algoritmaları ile Tesbiti
AU  - Yalçın, Eyüp
AU  - Güneş, Mahit
PY  - 2019
DA  - November
DO  - 10.17780/ksujes.598920
JF  - Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi
JO  - KSU J. Eng. Sci.
PB  - Kahramanmaras Sutcu Imam University
WT  - DergiPark
SN  - 1309-1751
SP  - 95
EP  - 108
VL  - 22
LA  - en
AB  - The foreignsubstances, arising during the production and shaping of wool and cotton rawmaterials that are used in textile and cotton gin factories or coming from theoutside, decrease considerably the quality of the obtained fabric or yarn.Nowadays, a different methods are used to separate foreign substances in thetextile sector, most of these methods are not efficient in terms of speed andquality. Computerized vision systems play a vital role in the field of textilesas in other fields. In this study, Intuitionistic Fuzzy Algorithm is used todefine the foreign substances in the images that obtained from a camera. CPU(Central Processing Unit) based applications have speed problems due to thestructure of the algorithm. For this reason, GPU (Graphics Processing Unit)technology was used to overcome the speed problem. The otsu algorithm generatesa dynamic threshold from the numerical values of the image obtained using theIntuitionistic fuzzy algorithm. By this means, the threshold value of eachframe obtained from the camera was calculated on real time and implemented onthe image timely. These algorithms were accelerated maximum 262 times usingNVIDIA GTX 480 GPU supported display card.
KW  - GPU Programming
KW  - Intuitionistic Fuzzy
KW  - Otsu
KW  - CUDA
KW  - Foreign Fiber Detection
N2  - Tekstil,pamuk ve çırçır fabrikalarında kullanılan veya dışarıdan gelen yün ve pamuk hammaddelerinin üretimi ve şekillendirilmesinde ortaya çıkan yabancı maddeler,elde edilen kumaş veya ipliğin kalitesini önemli ölçüde azaltır. Günümüzdetekstil sektöründeki yabancı maddeleri ayırmak için farklı yöntemlerkullanılmaktadır, ancak bu yöntemlerinçoğu hız ve kalite açısından verimli değildir. Bilgisayarlı görme sistemleri,diğer alanlarda olduğu gibi tekstil alanında da hayati bir rol oynamaktadır. Buçalışmada, kameradan elde edilen görüntülerdeki yabancı maddeleri tanımlamakiçin Sezgisel Bulanık Mantık kullanılmıştır. CPU tabanlı uygulamalar ilgilialgoritmanın yapısı gereği hız problemlerine yol açmaktadır. Bu hız probleminigidermek için ise GPU teknolojisi kullanılmıştır. Otsu algoritması kullanarakSezgisel bulanık mantık algoritmasıyla elde edilen görüntüler için dinamik bireşik değeri hesaplanmıştır. Bu sayede, kameradan elde edilen her karenin eşikdeğeri gerçek zamanlı olarak hesaplanmış ve görüntüye aynı anda uygulanmıştır.Bu algoritmalar, NVIDIA GTX 480 GPU destekli ekran kartı kullanılarak maksimum262 kez hızlandırılmıştır.
CR  - Alam, I. J. (2013). Detecting Edge in an Image with the Help of Fuzzy Parameters. 11th International Conference on Frontiers of Information Technology, (pp. 19-24). Islamabad, Pakistan.Atanossov, K. (1986). Intuitionistic Fuzzy Sets. Fuzzy Sets and Systems, 20, 87-96.Bahri, H. S. (2017). Image feature extraction algorithm based on CUDA architecture: case study GFD and GCFD. IET Computers & Digital Techniques, 11(4), 125-132.Chaira, T. R. (2008). A new measure using intuitionistic fuzzy set theory and its application to edge detection. Applied Soft Computing, 8(2), 919–927.Chen, Z. X. (2010). A New High-Speed Foreign Fiber Detection System with Machine Vision. Mathematical Problems in Engineering, Article ID 398364, 15 pages.Fan, J. X. (1999). Distance measure and induced fuzzy entropy. Fuzzy Sets and Systems, 104, 305-314.Faujdar, N. G. (2017). A practical approach of GPU bubble sort with CUDA hardware. 7th International Conference on Cloud Computing (pp. 7-12). Noida: Data Science & Engineering.Gunes, M. B. (2016). Detecting Direction of Pepper Stem by Using CUDA-Based Accelerated Hybrid Intuitionistic Fuzzy Edge Detection and ANN. Journal of Sensors, 11 pages.Ji, R. L. (2010). Classification and Identification of Foreign Fibers in Cotton on the Basis of a Support Vector Machine. Mathematical and Computer Modelling, 51, 1433-1437.Kaushik, R. B. (2015). On Intuitionistic Fuzzy Divergence Measure with Application to Edge Detection. Procedia Computer Science, 70, 2-8.Liberman, M. A. (1998). Determining gravimetric bark content in cotton with machine vision. Textile Research Journal, 68(2), 94-104.Millman, M. P. (2001). Computer vision for textured yarn interlace (nip) measurements at high speeds. Mechatronics, 11(8), 1025-1038.NVIDIA, C. (2019). CUDA C Programming GUIDE. Retrieved from 9th Edition: https://docs.nvidia.com/cuda/cuda-c-programming-guide/Otsu, N. A. (1979). Threshold Selection Method from Gray-level Histograms. IEEE Transactions on Systems, Man and Cybernetic, 9(1), 62-66.Pal, N. R. (1992). Some Properties of the Exponential Entropy. Inform. Sci., 66, 119-137.Tastaswadi, P. V. (1999). Machine vision for automated visual inspection of cotton quality in textile industries using color isodiscrimination contour. Computer Industrial Engineering, 37(1-2), 347-350.Wang, X. Y. (2015). A fast image segmentation algorithm for detection of pseudo-foreign fibers in lint cotton. Comput. Electr. Eng., 46, 500-510.Xuecheng, L. (1992). Entropy, distance measure and similarity measure of fuzzy sets and their relations. Fuzzy Sets and Systems, 52, 305-318.Yang, W. Z. (2009). A new approach for image processing in foreign fiber detection. Computers and Electronics in Agriculture, 68(1), 68-77.Zadeh, L. A. (1965). Fuzzy sets. Information and Control, 8(3), 338–353.Zhang, H. L. (2014). Applications of computer vision techniques to cotton foreign matter inspection: A review. Computers and Electronics in Agriculture, 109, 59-70.Zhang, X. L. (2011). A fast Segmentation Method for High-Resulation Color Images of Foreign Fibers in Cotton. Computers and Electronics in Agriculture, 78, 71-79.
UR  - https://doi.org/10.17780/ksujes.598920
L1  - https://dergipark.org.tr/en/download/article-file/858057
ER  -